OpenClaw Official Changelog

Source: github.com/openclaw/openclaw ↗, auto-synced hourly

v2026.5.272026-05-28

openclaw 2026.5.27

GitHub ↗

Highlights

·Stronger security and content boundaries: group prompt text is kept out of the system prompt, repeated-dot hostnames are normalized, side-effecting command wrappers and unsafe Node runtime env overrides are blocked, no-auth Tailscale exposure is rejected, and node/device-role approvals now require admin authority. (#87144, #87305, #87292, #87308, #87146)
·More reliable Codex app-server runs: Codex runtime models resolve first, workspace memory is routed through tools, shared app-server clients survive startup and spawned-helper failures, native hook relay generations survive restarts and rotate on fresh fallbacks, and false runtime live switches are avoided. (#87383, #87403, #87375, #72574, #87428)
·Faster Gateway and reply paths: session reads, plugin metadata fingerprints, auth env snapshots, auto-enabled plugin config, tool-search catalogs, and stable metadata caches do less hot-path rediscovery while visible replies no longer inherit hidden cleanup timeouts. (#86439, #87044)
·Better provider and model coverage: OpenAI-compatible embedding providers are core, DeepInfra catalog browsing loads the full credential-aware model set, Pixverse adds video generation and API region selection, VLLM thinking params are wired, Claude CLI OAuth overlays load for PI auth profiles, and bare direct Anthropic model ids work. (#85269, #84549, #87167)
·Channel delivery is steadier: Telegram `sendMessage` actions use durable outbound delivery, iMessage suppresses duplicate native exec approval prompts and sends, Slack keeps delivered final replies during late cleanup, Matrix mention previews/finals are stricter, QQBot fallback approval buttons honor slash-command auth, Discord guild requester checks are tighter, recovered Discord tool-warning artifacts stay out of successful replies, and Google Chat stops thread sends in DMs. (#87261, #87154)
·Release, package, and CI proof paths are harder to wedge: npm/package inventory honors dist exclusions, shrinkwrap override pins merge correctly, Docker runtime workspace templates are packaged and smoked, release postpublish checks are stricter, beta smoke rejects empty runs, and E2E log/probe waits are bounded.

Changes

·Memory: add a core OpenAI-compatible embedding provider for local and hosted OpenAI-style endpoints, with config, doctor, and docs support. (#85269)
·Plugin SDK: mark memory-specific embedding provider registration as deprecated compatibility and surface non-bundled usage in plugin compatibility diagnostics. (#85072)
·Providers: add the Pixverse video generation provider, API region selection, docs, and external plugin packaging support.
·DeepInfra: load the full model catalog when users browse models during onboarding, preserve configured API-key catalogs, refresh media/video defaults, and keep pricing/default model metadata aligned. (#84549)
·Plugin SDK: expose plugin approval action metadata and stop exporting Vitest test helpers from the public SDK surface. (#87120)
·Channel SDK: move channel message compatibility into core, remove old channel turn runtime aliases, and preserve runtime catalog markdown metadata for plugins.
·ClawHub: add plugin display metadata so catalog/package listings use cleaner names. (#87354)
·Agents: split the heartbeat runtime template out of docs assets and add compatibility repair for legacy heartbeat template content. (#85416)

Fixes

·Security/content boundaries: route untrusted group prompt metadata outside system prompts, normalize repeated trailing hostname dots, block side-effecting command wrappers, reject unsafe Node runtime env overrides, reject no-auth Tailscale exposure, block untrusted Microsoft Teams service URLs, enforce `/allowlist configWrites` origin policy, gate QQBot fallback approval buttons, and require admin for node/device-role approvals. (#87144, #87305, #87292, #87308, #87146, #87154, #87334)
·Codex: resolve Codex runtime models before generic routing, route workspace memory through tools, preserve shared app-server clients after startup and spawned-helper failures, preserve native hook relay generations across restarts and fresh fallbacks, keep raw reasoning/source-reply guards intact, report quarantined dynamic tools, keep the attempt watchdog armed for queued terminal turns, and route Codex OAuth compaction through OpenAI-Codex. (#87383, #87403, #87375, #72574, #87428)
·Agents/runtime: avoid session event queue self-waits, bound compaction wake and steering retries, preserve grace for pending error diagnostics, avoid false Codex runtime live switches, avoid stale restart continuation reuse, preserve session fallback errors, suppress duplicate Claude CLI skill prompts, keep runtime context before active user turns, strip stale Anthropic thinking, quarantine unsupported tool schemas, recover completed write timeouts safely, release retained session write locks on timeout abort, and validate forced plugin harness support before pinning. (#86123, #55424, #86855, #74341, #87278)
·Reply/session delivery: keep visible turn admission unbounded, keep visible fallback delivery on latest targets, preserve bridge hook context, classify direct fallback targets by channel grammar, report approval resolutions in bridge mode, and avoid stale source-reply artifacts. (#87044)
·Channels: make Telegram `sendMessage` action replies durable and preserve SecretRef prompt config, suppress duplicate iMessage native exec approval prompts and sends, keep iMessage approval polling alive after denied reactions, keep Slack delivered final replies during late cleanup, keep Matrix mention previews/finals mention-inert and normally delivered, ignore filename-embedded Matrix IDs, suppress recovered Discord tool-warning artifacts from successful replies, suppress Google Chat thread sends in DMs, and harden Discord guild requester checks. (#87261, #87452)
·Memory: salvage QMD search JSON after nonzero exits and keep workspace memory routing through the Codex tool path where possible. (#87225, #87383, #87403)
·Providers/models: forward cached token usage in OpenAI-compatible chat completions, load Claude CLI OAuth overlays for PI auth profiles, send bare direct Anthropic model ids, wire configured VLLM thinking params, honor OpenAI-compatible cache retention, normalize OpenAI Responses replay tool ids, resolve OpenAI `gpt-5.5` without a cached catalog, preserve `retry-after` fallback handling, bound GitHub Copilot auth requests, and load DeepInfra custom/live catalogs consistently. (#82062, #87167, #84549)
·Gateway/performance: borrow read-only session metadata and active session working stores, cache current/stable plugin metadata fingerprints, cache auto-enabled plugin config, slim metadata identity caches, trust current metadata lifecycle caches, stabilize isolated cron prompt-cache affinity, persist model auth profile suffixes, drain probe client closes, expire browser tokens after auth rotation, and keep default status fast paths bounded.
·CLI/help/config: reject loose or malformed numeric options for gateway timeouts, model limits, directory limits, message options, webhooks, and partial values; respect subcommand version options; route generated/root/plugin help targets correctly; keep skills JSON output flushing naturally; and keep plugin descriptor loading quiet in root help. (#87398)
·Plugin state/tool search: evict the current namespace when plugin rows hit caps, reuse unchanged tool-search catalogs, align the release catalog reuse wrapper, and keep fallback tool warnings mention-inert.
·Install/package/release: match npm globstar exclusions, honor dist package exclusions in inventory, omit unpacked test helpers, skip Homebrew until macOS packages need it, package Docker runtime workspace templates, smoke Docker runtime templates during full validation, merge nested shrinkwrap override pins, preserve forked shrinkwrap pins, pin aged `lru-cache`, harden postpublish verification, accept main full-validation proof, and reject empty beta smoke runs.
·E2E/QA/Crabbox: bound Telegram, Open WebUI, ClawHub, Matrix, Tool Search, MCP, gateway network, bundled runtime, kitchen-sink, codex media, config reload, and agent-turn assertion waits; prefer Azure for Windows targets; reinitialize invalid changed-gate git dirs; full-sync sparse container runs; and fail empty explicit test requests. (#87186)

Release verification

·npm package: https://www.npmjs.com/package/openclaw/v/2026.5.27
·registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.5.27.tgz
·integrity: `sha512-2N93zhdAo88KAbHt6T7KvYXf4s7XIkYXBgv1npYpn7e1Y9FvrtgtpsA38my9rtFW+70uXEojRPX5/OqnuDqJPw==`
·full release CI report: https://github.com/openclaw/releases/blob/main/evidence/2026.5.27/release-evidence.md
·release publish: https://github.com/openclaw/openclaw/actions/runs/26571393853
·npm preflight: https://github.com/openclaw/openclaw/actions/runs/26569630056
·full release validation: https://github.com/openclaw/openclaw/actions/runs/26569544553
·release checks: https://github.com/openclaw/openclaw/actions/runs/26569853272
·product performance: https://github.com/openclaw/openclaw/actions/runs/26569541556
·plugin npm publish: https://github.com/openclaw/openclaw/actions/runs/26571646739
·plugin ClawHub publish: https://github.com/openclaw/openclaw/actions/runs/26571650967
·OpenClaw npm publish: https://github.com/openclaw/openclaw/actions/runs/26572175549
·macOS preflight/sign/notarize: https://github.com/openclaw/releases/actions/runs/26572630696
·macOS validation: https://github.com/openclaw/releases/actions/runs/26573954998
·macOS publish/appcast: https://github.com/openclaw/releases/actions/runs/26574441406
·appcast: https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml
·macOS zip: https://github.com/openclaw/openclaw/releases/download/v2026.5.27/OpenClaw-2026.5.27.zip
·macOS dmg: https://github.com/openclaw/openclaw/releases/download/v2026.5.27/OpenClaw-2026.5.27.dmg
·macOS dSYM: https://github.com/openclaw/openclaw/releases/download/v2026.5.27/OpenClaw-2026.5.27.dSYM.zip

v2026.5.27-beta.1pre-release2026-05-28

openclaw 2026.5.27-beta.1

GitHub ↗

Highlights

·Stronger security and content boundaries: group prompt text is kept out of the system prompt, repeated-dot hostnames are normalized, side-effecting command wrappers and unsafe Node runtime env overrides are blocked, no-auth Tailscale exposure is rejected, and node/device-role approvals now require admin authority. (#87144, #87305, #87292, #87308, #87146)
·More reliable Codex app-server runs: Codex runtime models resolve first, workspace memory is routed through tools, shared app-server clients survive startup and spawned-helper failures, native hook relay generations survive restarts and rotate on fresh fallbacks, and false runtime live switches are avoided. (#87383, #87403, #87375, #72574, #87428)
·Faster Gateway and reply paths: session reads, plugin metadata fingerprints, auth env snapshots, auto-enabled plugin config, tool-search catalogs, and stable metadata caches do less hot-path rediscovery while visible replies no longer inherit hidden cleanup timeouts. (#86439, #87044)
·Better provider and model coverage: OpenAI-compatible embedding providers are core, DeepInfra catalog browsing loads the full credential-aware model set, Pixverse adds video generation and API region selection, VLLM thinking params are wired, Claude CLI OAuth overlays load for PI auth profiles, and bare direct Anthropic model ids work. (#85269, #84549, #87167)
·Channel delivery is steadier: Telegram `sendMessage` actions use durable outbound delivery, iMessage suppresses duplicate native exec approval prompts and sends, Slack keeps delivered final replies during late cleanup, Matrix mention previews/finals are stricter, QQBot fallback approval buttons honor slash-command auth, Discord guild requester checks are tighter, recovered Discord tool-warning artifacts stay out of successful replies, and Google Chat stops thread sends in DMs. (#87261, #87154)
·Release, package, and CI proof paths are harder to wedge: npm/package inventory honors dist exclusions, shrinkwrap override pins merge correctly, Docker runtime workspace templates are packaged and smoked, release postpublish checks are stricter, beta smoke rejects empty runs, and E2E log/probe waits are bounded.

Changes

·Memory: add a core OpenAI-compatible embedding provider for local and hosted OpenAI-style endpoints, with config, doctor, and docs support. (#85269)
·Plugin SDK: mark memory-specific embedding provider registration as deprecated compatibility and surface non-bundled usage in plugin compatibility diagnostics. (#85072)
·Providers: add the Pixverse video generation provider, API region selection, docs, and external plugin packaging support.
·DeepInfra: load the full model catalog when users browse models during onboarding, preserve configured API-key catalogs, refresh media/video defaults, and keep pricing/default model metadata aligned. (#84549)
·Plugin SDK: expose plugin approval action metadata and stop exporting Vitest test helpers from the public SDK surface. (#87120)
·Channel SDK: move channel message compatibility into core, remove old channel turn runtime aliases, and preserve runtime catalog markdown metadata for plugins.
·ClawHub: add plugin display metadata so catalog/package listings use cleaner names. (#87354)
·Agents: split the heartbeat runtime template out of docs assets and add compatibility repair for legacy heartbeat template content. (#85416)

Fixes

·Security/content boundaries: route untrusted group prompt metadata outside system prompts, normalize repeated trailing hostname dots, block side-effecting command wrappers, reject unsafe Node runtime env overrides, reject no-auth Tailscale exposure, block untrusted Microsoft Teams service URLs, enforce `/allowlist configWrites` origin policy, gate QQBot fallback approval buttons, and require admin for node/device-role approvals. (#87144, #87305, #87292, #87308, #87146, #87154, #87334)
·Codex: resolve Codex runtime models before generic routing, route workspace memory through tools, preserve shared app-server clients after startup and spawned-helper failures, preserve native hook relay generations across restarts and fresh fallbacks, keep raw reasoning/source-reply guards intact, report quarantined dynamic tools, keep the attempt watchdog armed for queued terminal turns, and route Codex OAuth compaction through OpenAI-Codex. (#87383, #87403, #87375, #72574, #87428)
·Agents/runtime: avoid session event queue self-waits, bound compaction wake and steering retries, preserve grace for pending error diagnostics, avoid false Codex runtime live switches, avoid stale restart continuation reuse, preserve session fallback errors, suppress duplicate Claude CLI skill prompts, keep runtime context before active user turns, strip stale Anthropic thinking, quarantine unsupported tool schemas, recover completed write timeouts safely, release retained session write locks on timeout abort, and validate forced plugin harness support before pinning. (#86123, #55424, #86855, #74341, #87278)
·Reply/session delivery: keep visible turn admission unbounded, keep visible fallback delivery on latest targets, preserve bridge hook context, classify direct fallback targets by channel grammar, report approval resolutions in bridge mode, and avoid stale source-reply artifacts. (#87044)
·Channels: make Telegram `sendMessage` action replies durable and preserve SecretRef prompt config, suppress duplicate iMessage native exec approval prompts and sends, keep iMessage approval polling alive after denied reactions, keep Slack delivered final replies during late cleanup, keep Matrix mention previews/finals mention-inert and normally delivered, ignore filename-embedded Matrix IDs, suppress recovered Discord tool-warning artifacts from successful replies, suppress Google Chat thread sends in DMs, and harden Discord guild requester checks. (#87261, #87452)
·Memory: salvage QMD search JSON after nonzero exits and keep workspace memory routing through the Codex tool path where possible. (#87225, #87383, #87403)
·Providers/models: forward cached token usage in OpenAI-compatible chat completions, load Claude CLI OAuth overlays for PI auth profiles, send bare direct Anthropic model ids, wire configured VLLM thinking params, honor OpenAI-compatible cache retention, normalize OpenAI Responses replay tool ids, resolve OpenAI `gpt-5.5` without a cached catalog, preserve `retry-after` fallback handling, bound GitHub Copilot auth requests, and load DeepInfra custom/live catalogs consistently. (#82062, #87167, #84549)
·Gateway/performance: borrow read-only session metadata and active session working stores, cache current/stable plugin metadata fingerprints, cache auto-enabled plugin config, slim metadata identity caches, trust current metadata lifecycle caches, stabilize isolated cron prompt-cache affinity, persist model auth profile suffixes, drain probe client closes, expire browser tokens after auth rotation, and keep default status fast paths bounded.
·CLI/help/config: reject loose or malformed numeric options for gateway timeouts, model limits, directory limits, message options, webhooks, and partial values; respect subcommand version options; route generated/root/plugin help targets correctly; keep skills JSON output flushing naturally; and keep plugin descriptor loading quiet in root help. (#87398)
·Plugin state/tool search: evict the current namespace when plugin rows hit caps, reuse unchanged tool-search catalogs, align the release catalog reuse wrapper, and keep fallback tool warnings mention-inert.
·Install/package/release: match npm globstar exclusions, honor dist package exclusions in inventory, omit unpacked test helpers, skip Homebrew until macOS packages need it, package Docker runtime workspace templates, smoke Docker runtime templates during full validation, merge nested shrinkwrap override pins, preserve forked shrinkwrap pins, pin aged `lru-cache`, harden postpublish verification, accept main full-validation proof, and reject empty beta smoke runs.
·E2E/QA/Crabbox: bound Telegram, Open WebUI, ClawHub, Matrix, Tool Search, MCP, gateway network, bundled runtime, kitchen-sink, codex media, config reload, and agent-turn assertion waits; prefer Azure for Windows targets; reinitialize invalid changed-gate git dirs; full-sync sparse container runs; and fail empty explicit test requests. (#87186)

Release verification

·npm package: https://www.npmjs.com/package/openclaw/v/2026.5.27-beta.1
·registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.5.27-beta.1.tgz
·integrity: `sha512-Bwc1x2bsmmjgc/zfKrZZTUCVKSwc29WJ96RxKb6xvR/3/ISvBjmMGa1goJuJi2Po+oqrD3IJ8zdbxcGSY7Woww==`
·full release validation: https://github.com/openclaw/openclaw/actions/runs/26555534701
·npm preflight: https://github.com/openclaw/openclaw/actions/runs/26555537448
·release publish parent: https://github.com/openclaw/openclaw/actions/runs/26556941655
·OpenClaw npm publish: https://github.com/openclaw/openclaw/actions/runs/26557350528
·plugin npm publish: https://github.com/openclaw/openclaw/actions/runs/26557065983 published all plugins except @openclaw/pixverse-provider in Actions; @openclaw/pixverse-provider was recovered manually via npm maintainer auth.
·plugin ClawHub publish: https://github.com/openclaw/openclaw/actions/runs/26557068673 published all workflow candidates except @openclaw/pixverse-provider in Actions; @openclaw/pixverse-provider was recovered manually on ClawHub after package-row bootstrap.
·postpublish verifier: `fnm exec --using 24.15.0 -- node --import tsx scripts/openclaw-npm-postpublish-verify.ts 2026.5.27-beta.1` passed.
·beta release verifier: `fnm exec --using 24.15.0 -- pnpm release:verify-beta -- 2026.5.27-beta.1 ... --skip-clawhub --plugins <all publishable except @openclaw/pixverse-provider>` passed for core npm, GitHub release, 30 plugin npm packages, full validation, and OpenClaw npm publish.
·@openclaw/pixverse-provider recovery verifier: `node --import tsx scripts/release-verify-beta.ts 2026.5.27-beta.1 --plugins @openclaw/pixverse-provider --skip-postpublish` passed for GitHub release, core npm, plugin npm, and ClawHub.
·beta smoke: blocked locally because Parallels VM `Ubuntu 26.04` is missing on this host.
·@openclaw/pixverse-provider: https://www.npmjs.com/package/@openclaw/pixverse-provider/v/2026.5.27-beta.1
·@openclaw/pixverse-provider tarball: https://registry.npmjs.org/@openclaw/pixverse-provider/-/pixverse-provider-2026.5.27-beta.1.tgz
·@openclaw/pixverse-provider integrity: `sha512-9rfWZ4GcKSd9sFrdfI9jncRKWvdtGLjNVWZdbJ+6ztd3WRyxSJTFfj/i9Py8Qj0gr3mDCiQqQXceFA0l7DW2Rg==`
·@openclaw/pixverse-provider ClawHub: https://clawhub.ai/plugins/%40openclaw%2Fpixverse-provider
·@openclaw/pixverse-provider ClawHub API: https://clawhub.ai/api/v1/packages/%40openclaw%2Fpixverse-provider/versions/2026.5.27-beta.1

v2026.5.262026-05-27

openclaw 2026.5.26

GitHub ↗

Highlights

·Faster Gateway and replies: startup avoids repeated plugin, channel, session, usage-cost, warning, scheduled-service, and filesystem scans; visible replies separate user-facing sends from slower follow-up work; Gateway runtime/session caches churn less under load.
·Transcripts are core: transcript-backed meeting summaries, source-provider chunks, cleaned user turns, media provenance, Codex mirrors, WebChat replies, and CLI/TUI replay now use one more reliable transcript path.
·More channels are production-ready: Telegram keeps typing/progress context and forum topics, iMessage handles attachment roots, remote media staging, and duplicate local Messages sources, WhatsApp restores group/media behavior, Discord improves voice playback and model picking, and Signal/iMessage/WhatsApp get reaction approvals.
·Better voice and Talk: realtime Talk runs can be inspected, steered, cancelled, or followed up from Web UI and Discord voice; wake-name handling is more tolerant without letting ambient speech trigger agents.
·Safer content boundaries: Browser snapshot reads honor SSRF policy, system-event text cannot spoof nested prompt markers, fetched file text is wrapped as external content, ClickClack inbound sender allowlists run before agent dispatch, stale device tokens are rejected, and serialized tool-call text is scrubbed from replies.
·Providers, Codex, and local models are steadier: named auth profiles, OpenAI sampling params, Codex app-server resume/timeout/usage-limit recovery, dynamic tool-schema guards, xAI usage-limit surfacing, Ollama top-p normalization, and local approval resolution reduce provider-specific dead ends.
·More reliable install/update/release paths: Alpine installs, trusted runtime fallback roots, stable update channels, Docker/package timeouts, Windows Scheduled Tasks, Windows/macOS proof lanes, Testbox/Crabbox delegation, plugin publish checks, and macOS runner bootstraps all got hardened.
·Better observability: Activity tab, gateway secret-prep traces, tool/model stream progress, explicit fast-mode status, systemd Gateway hygiene, OpenTelemetry LLM spans, release performance evidence, and richer telemetry signals make failures easier to inspect.

Changes

·Transcripts: add core transcript capture and source-provider support for transcript-backed meeting summaries, including the renamed Transcripts docs, CLI surface, source-provider chunks, and cleaned user-turn persistence.
·Auth: add named model login profiles and supported credential migration for Hermes, OpenCode, and Codex auth profiles, with explicit opt-out and non-interactive controls. (#85667)
·Diagnostics: trace gateway secret preparation, classify skill/tool usage, surface model stream progress, add OpenTelemetry LLM content spans, and expose alertable telemetry for blocked tools, failover, stale sessions, liveness, oversized payloads, and webhook ingress. (#83019, #80370, #86191)
·Channels: add Signal reaction approvals, iMessage thumb approval reactions, and WhatsApp thumb approval reaction support so mobile approval flows work without textual `/approve` commands. (#85894, #85952, #85477)
·Agents/API: forward OpenAI sampling params through the Gateway and expose estimated context-budget status for active agent runs. (#84094)
·TUI/status: queue prompts submitted while an agent is busy and show explicit fast-mode state plus richer systemd Gateway hygiene in status output. (#86722, #87115, #86976)
·Exec approvals: hide durable approval actions that are unavailable for the current prompt and keep approval runtime tokens local-only so stale prompts cannot offer misleading controls. (#86270, #86359)
·Plugin SDK: add reaction approval helpers and keep diagnostic event root exports discoverable across function-name and alias-bound module graphs. (#86735, #87084)
·Android/iOS: add the Android pair-new-gateway action and improve mobile Talk mode surfaces, including iOS realtime Talk mode and Android offline voice/gateway recovery. (#86798, #86355)
·Performance: cache plugin metadata snapshots, package realpaths, stable gateway metadata, model cost indexes, channel resolution, usage-cost indexes, and session/auth hot-path facts so common Gateway and reply paths do less rediscovery. (#84649, #85843, #86517, #86678)
·Voice: expose shared realtime turn-context tracking through the realtime voice SDK and reuse it for Discord speaker attribution and wake-name context recovery.
·Voice: reuse shared realtime output activity tracking in Google Meet command and node audio bridges, including recent-output checks for local barge-in detection.
·Voice: expose shared realtime output activity tracking through the realtime voice SDK and reuse it for Discord playback activity and barge-in decisions.
·Voice: expose shared realtime consult question matching, speakable-result extraction, and alias-aware forced-consult coordination through the realtime voice SDK, then reuse it in Gateway Talk, Voice Call, and Discord voice paths.
·Voice: share activation-name matching and consult-transcript screening through the realtime voice SDK so Discord, browser voice, and meeting surfaces can reuse one implementation.
·Cron: default `cron.maxConcurrentRuns` to 8 so scheduled automations and their isolated agent turns can make progress in parallel without explicit configuration.
·QA-Lab: add `qa coverage --match <query>` so focused proof selection can discover matching scenarios from existing metadata before running live or remote lanes.
·Discord/model picker: surface an alpha-bucket select (e.g. `A–G (12) · H–N (18) · O–Z (5)`) when the provider list or a provider's model list exceeds 25 items, so configs with `provider/*` wildcards stay one click from the right page instead of paginating through prev/next; falls back to numeric chunks when every item shares the same first letter. (#86181)
·Control UI: add an ephemeral Activity tab for sanitized live tool activity summaries without persisting raw telemetry. Fixes #12831.
·Build: include `ui:build` in the `full` and `ciArtifacts` profiles of `scripts/build-all.mjs` so `pnpm build` always rebuilds `dist/control-ui` after `tsdown` cleans `dist`, removing the second-command requirement and the missing-asset failure mode for source/runtime installs and CI artifact uploads. (#85206)
·iOS: improve Talk mode with direct realtime voice sessions, compact toolbar status, and responsive voice waveform feedback. (#86355)
·Media: replace the Sharp image backend with Rastermill for metadata, resizing, EXIF orientation, and PNG alpha-preserving optimization so OpenClaw no longer installs Sharp or the WhatsApp Jimp fallback for image processing. (#86437)
·Codex: update the bundled Codex CLI to 0.134.0 and keep native compaction disabled for budget-triggered app-server turns so OpenClaw owns the recovery boundary. (#86772)

Fixes

·Memory/security: reject prompt-like text submitted through the explicit `memory_store` tool before embedding or storage, matching the existing auto-capture prompt-injection filter. (#87142)
·Gateway/security: enable the default auth rate limiter for remote non-browser and HTTP gateway auth failures when `gateway.auth.rateLimit` is unset, while preserving the loopback exemption. (#87148)
·Security/content boundaries: validate Browser snapshot tab URLs against SSRF policy before ChromeMCP or direct CDP reads, sanitize queued system-event text so untrusted plugin/channel labels cannot spoof nested prompt markers, wrap fetched file text and metadata as external content, apply ClickClack `allowFrom` sender allowlists before agent dispatch, reject RPCs from invalidated device-token clients during rotation, require staged sandbox media refs, and scrub serialized tool-call text from replies. (#78526, #87094, #87062, #83741, #70707, #86924)
·Transcripts/user turns: persist CLI, WebChat, media, follow-up, hook, and Codex-mirror user turns to the admitted session target; keep cleaned transcript text, inline image routing, provenance metadata, replay hooks, and fallback paths idempotent when runtimes fail or restart.
·TUI/status/onboarding/UI: queue busy TUI prompts instead of dropping them, preserve the configured default model during onboarding, show failed tool results as errors, show config-open failures in Control UI, keep status JSON plugin scans healthy, preserve xAI usage-limit errors locally, and expose explicit fast-mode/systemd state. (#86722, #87000, #85786, #87108, #87001, #86614, #87115, #86976)
·Plugin commands/SDK: preserve plugin LLM command auth, bind native plugin command dispatch to the host agent's LLM auth, keep `onDiagnosticEvent` exports discoverable through `Function.name`, stabilize diagnostic event root aliases, correlate pathless read diagnostics, suppress transient runner failures in channel command paths, and repair local approval resolution. (#85936, #87084, #86977, #87069, #86771)
·Codex/providers: keep WebChat delivery hints out of user prompts, avoid false queued-terminal idle timeouts, share the native hook relay registry, quarantine unsupported dynamic tool schemas, preserve Claude resumed-session system prompts, normalize greedy Ollama `top_p`, preserve per-agent thinking defaults for ingress runs, and avoid native compaction takeover on budget-triggered Codex turns. (#87096, #73950, #87049, #86689, #86772)
·Gateway/perf/release: reuse startup-warning metadata and prepared auth stores, avoid cloning live-switch and lifecycle session caches on read paths, defer warning and scheduled-service fallback imports, trim Gateway session/startup/runtime CPU churn, skip duplicate turn session touches, stop chat timeout fallback cascades, drop stale subagent announce history, bound benchmark/watch/kitchen-sink teardown waits, bound macOS/package/onboarding/plugin smoke commands, bound install finalization probes, resolve Parallels npm-update commands from guest `PATH`, and bootstrap raw AWS macOS Node/pnpm commands through `/usr/bin/env`. (#86997)
·Reply/perf: reduce visible reply delivery latency by preserving Telegram typing/progress context, lazy-loading slash-command startup metadata, avoiding hot-path model hydration, flag-gating Codex profiler timing, deferring context compaction maintenance, and tracking delivery timing. (#86989, #86990, #86991, #86992, #86993, #86994)
·Reply/source delivery: keep TUI, Control UI, media, TTS, transcript, and Codex source-reply finals live without duplicate terminal events or stale replay artifacts.
·Agents/replay: repair legacy tool results before replay, preserve `sessions_spawn` transcript payloads, restore current guard checks, stage sandboxed workspace media, and keep duplicate transcripts tool display metadata from reappearing. (#82203, #86934, #87025)
·Agents/sessions: handle active-fallback failures in `sessions_send` so fallback routing reports the real failure and does not leave callers with an ambiguous dropped send. (#86638)
·Agents/hooks/subagents: enforce default hook agent allowlists, recover failed subagent lifecycle completions, and keep node task lifecycle cleanup from closing the Gateway listener. (#86101)
·Codex: project newer OpenClaw chat history into resumed app-server threads and keep Codex turn timeouts inside the Codex runtime boundary so timeouts do not poison shared app-server clients or fall through to unrelated provider fallback. (#86677, #86476)
·Config/doctor/update: narrow profiled tool-section doctor repair, keep runtime-injected legacy web-search provider config out of user-authored config validation, and keep prerelease tags excluded from stable updater resolution. (#87030, #86818, #86559)
·CLI/Windows: add a Windows-only stack-size respawn for stack-heavy startup paths, default CLI logs to local timestamps, and validate timeout/banner TTY state more strictly. (#87031, #85387)
·Locking/security: require owner identity proof before stale plugin lock removal, memoize session lock owner arguments, and avoid writing default exec approval stores unless policy state actually changed. (#86814, #86964)
·Install/release: bound Docker package build, inventory, pack, and tarball preparation with process-group timeouts; pin shrinkwrap patch drift to the pnpm lock; harden macOS restart and dSYM packaging; and run release Docker/live timeout wrappers in the foreground so child processes cannot wedge gates.
·Telegram/network: treat `ENETDOWN` as a transient pre-connect network failure so Telegram sends, gateway unhandled-rejection handling, and cron network retries follow the same recovery path as sibling network outages. (#86762)
·Telegram: preserve inbound text entities, overlapping DM replies, account topic cache sidecars, outbound reply context, targeted bot-command mentions, durable group retry targets, forum topic names, and native progress callbacks. (#83873, #85361, #85555, #85656, #85709, #86299, #86553)
·iMessage: read image attachments from local Messages attachment roots, dedupe duplicate local Messages-source accounts, seed direct DM history, fix image/group media attachment commands, advance catchup cursors after live handling, and keep slash-command acknowledgements in the source conversation. (#82642, #85475, #86569, #86705, #86706, #86770)
·WhatsApp/QQ/Twitch/IRC/Slack: restore WhatsApp ack identity and group-drop warnings, make QQ Bot media respect `OPENCLAW_HOME`, serialize Twitch auth disconnects, store IRC channel routes canonically, and keep Slack downloaded files out of reply media. (#83833, #85309, #85777, #85794, #85906, #86318, #86697)
·Discord/voice: improve voice playback and wake replies, bucket large model picker menus, merge media captions into one message, route metadata through configured proxies, restore numeric channel sends, suppress self-reply echoes, and tighten wake matching without breaking fuzzy wake phrases. (#80227, #86238, #86487, #86571, #86595, #86601)
·Codex: preserve native web-search metadata, keep oversized native thread reuse, bridge CLI API-key auth into the app server, preserve sandbox bootstrap path style, recover context-window prompt errors, honor yolo approval policy, disable native thread personality, and route compaction through Codex auth. (#85378, #85542, #85891, #85909, #86408)
·Agents/runtime: enforce session lock max-hold reclaim, release embedded-attempt locks on all exits, treat aborted subagent runs as terminal, avoid runtime model hydration on hot paths, disclose scoped session list counts, derive overflow budgets from provider errors, and keep fallback errors scoped to the active model candidate. (#70473, #85764, #86014, #86134, #86427, #86944)
·Config/update/doctor: retry config recovery after failed backup restore, skip shell env fallback on Windows, exclude prerelease tags from the stable git channel, support deep config edits, warn instead of aborting on unreadable cron stores, prune stale bundled plugin paths, and avoid duplicate restart prompts when the Gateway is already healthy. (#85739, #85787, #86060, #86260, #86384, #86533)
·Install/release: support Alpine CLI installs and runtime floors, prefer trusted startup argv runtime fallback roots, reject stale CLI node runtimes, avoid npm `min-release-age` installer failures, bound npm/package/Docker install phases, restore config parent ownership in Docker, seed Docker lockfile package tarballs before prune, make release/plugin prerelease checks fail closed instead of hanging or false-greening, and use host-visible Crabbox local work roots for Docker-backed proof. (#85491)
·Windows daemon: keep Scheduled Task gateway launches running on battery power and avoid workgroup-machine prompts for a domain user during task installation. (#59299)
·Security: avoid printing Gateway tokens in Docker, validate plugin model-pattern regexes safely, escape transcript metadata field names, harden session allowlist glob matching, audit Claude permission overrides under YOLO, and require explicit allow for ACP auto approvals. (#85849, #85934, #86046, #86557)
·Media/images: replace Sharp with Rastermill, keep EXIF normalization best-effort, normalize HEIC/HEIF before image descriptions, route Codex image API keys through OpenAI, preserve image compression metadata, and auto-scale live tool result caps. (#85776, #86037, #86437, #86857, #86923)
·Memory: prevent semantic vector indexes from silently degrading when embeddings are unavailable, stop doctor OOMs on large session stores, preserve sidecar hooks/artifacts, write fallback dream diaries, use CJK-aware dreaming dedupe, and avoid per-file watcher FD fan-out. (#80613, #82928, #85060, #85704, #85967, #86701)
·Agents/sessions: include visibility metadata on restricted `sessions_list` results so scoped counts are clearly reported without widening access or exposing hidden-session counts. (#86944)
·Gateway/DNS: validate wide-area discovery domains before deriving zone paths or writing zone files, so invalid `discovery.wideArea.domain` and `dns setup --domain` values fail with a DNS-name diagnostic instead of falling through to unrelated configuration errors.
·Agents/BTW: route fallback side-question streams through the embedded stream resolver so Anthropic-compatible MiniMax requests use the same capped transport as normal chat. (#86312)
·Telegram: treat `/command@TargetBot` bot-command entities as explicit mentions for the addressed bot so `requireMention` groups no longer drop targeted commands or captions. Fixes #84462. (#86553)
·CI: bound Docker/Bash E2E tarball npm installs with `OPENCLAW_E2E_NPM_INSTALL_TIMEOUT` so package, onboarding, plugin, and upgrade lanes fail instead of hanging on a stuck npm install.
·CI: fail Parallels npm-update smoke jobs after the guest command timeout and cleanup backstop instead of only logging a timeout line.
·CI: bound kitchen-sink RPC HTTP probes so stalled gateway readiness or response bodies fail and retry instead of wedging the walker.
·CI: keep `OPENCLAW_TESTBOX=1 pnpm check:changed` delegating to Blacksmith Testbox through Crabbox without forwarding local Testbox or worker env into the remote command.
·CI: send KILL after the TERM grace period for manual checkout fetch timeouts so stuck Testbox and workflow checkout retries cannot hang behind a wedged `git fetch`.
·CI: send KILL after the TERM grace period for Bun global install smoke command timeouts so trapped `openclaw` child processes cannot wedge the scheduled install smoke.
·iMessage: thread current channel/account inbound attachment roots into the image tool so iMessage-saved attachments under `~/Library/Messages/Attachments` (including the wildcard `/Users/*/Library/Messages/Attachments` root) are read through the existing inbound path policy instead of being rejected as `path-not-allowed`. Literal `localRoots` stays workspace-scoped. Fixes #30170. (#86569)
·QQ Bot: respect `OPENCLAW_HOME` for outbound media path resolution so `<qqmedia>` sends no longer silently fail when `HOME` and `OPENCLAW_HOME` differ (Docker / multi-user hosts). Persisted QQ Bot data (sessions, known users, refs) stays anchored on the OS home for upgrade compatibility. Fixes #83562.
·Update: report the primary malformed `openclaw.extensions` payload error without adding a duplicate missing-main diagnostic. (#86596)
·Control UI: keep host-local Markdown file paths inert while preserving app-relative links. (#86620)
·Gateway: dampen repeated unauthenticated device-required probes per URL while preserving explicit-auth and paired recovery paths. (#86575)
·IRC: store inbound channel routes with the canonical `channel:#name` target and join transient channel sends before writing. (#85906)
·Usage: surface unknown all-zero model pricing as missing cost entries instead of a confident `$0` total. (#85882)
·Agents/Codex: honor yolo app-server approval policy only for the full `never` plus `danger-full-access` case. (#85909)
·Gateway/Gmail: clear Gmail watcher renewal intervals on re-entry so hot reloads do not leak lifecycle timers. (#82947)
·Logging: exit cleanly on broken stdout/stderr pipes without masking existing failure exit codes. (#80059)
·Gateway/security: escape transcript metadata field names while extracting oversized session line prefixes. (#85934)
·Plugins/security: validate manifest model pattern regexes with the safe-regex compiler so unsafe patterns are ignored before matching. (#86046)
·Discord: route gateway metadata REST lookups through the configured Discord proxy so proxied accounts do not fall back to direct `discord.com` connections before opening the WebSocket. Fixes #80227.
·Agents/media: hydrate current-turn image attachments from filename-derived MIME types so active vision can see generated or forwarded images whose source omitted an image content type. (#84812)
·Agents/fs: point workspace-only scratch-path guidance at in-workspace temp directories while keeping host-root writes rejected by the tool guard. (#86501)
·Agents/media: keep async cron media completions scoped to their run session while preserving direct delivery for stale generated-media success and failure notifications. (#86529)
·Gateway: emit plugin `session_end`/`session_start` hooks when `agent.send` rotates or replaces a session id, keeping hook lifecycle state aligned with `sessions.changed` notifications. Fixes #83507. (#85875)
·OpenShell/SSH: reject malformed generated exec commands before sandbox/session setup so unresolved workflow placeholders fail fast instead of reaching the remote shell. Fixes #72373.
·Google: stop normalizing `gemini-3.1-flash-lite` to the retired preview endpoint and update Flash Lite alias guidance to the GA model id. Fixes #86151. (#86240)
·Installer: make Alpine apk installs cover Git, verify the Node runtime floor, try `nodejs-current`, and report Alpine version guidance when repositories only provide older Node packages.
·Agents/status: prefer the active Claude CLI OAuth auth label over an unused Anthropic env API-key label for equivalent runtime aliases. Fixes #80184. (#86570)
·Agents/media: send direct fallback for generated media still missing after an active requester wake fails. (#85489)
·Agents: derive overflow compaction budgets from provider-reported and synthetic over-budget token counts so confirmed context overflows compact before retrying. (#70473)
·Agents/Codex: recover Codex context-window prompt errors through overflow compaction and surface reset guidance when recovery is exhausted. (#85542)
·Agents/Codex: allow Codex app-server runs to bootstrap from `CODEX_API_KEY` or `OPENAI_API_KEY` when no Codex auth profile is configured.
·Agents/Codex: keep selected Codex runtime routing on OpenAI-Codex while preserving direct OpenAI API-key compaction fallback. (#86408)
·Agent transcript: include OpenClaw agent session logs when finding local transcript candidates.
·Crabbox: bootstrap raw AWS macOS shell commands wrapped in absolute `time` paths so RSS probes can run Node and pnpm on fresh macOS runners.
·Crabbox: bootstrap raw AWS macOS shell commands even when setup statements precede Node or pnpm usage.
·TUI/local: skip unnecessary secret resolution, gateway model catalog loading, bootstrap, and skill scans in explicit local-model runs so startup reaches the model request faster.
·Sessions/doctor: load large session stores without clone amplification during read-only doctor checks and reclaim stale `sessions.json.*.tmp` sidecars. Fixes #56827.
·Tests: clean successful plugin gateway gauntlet isolated temp roots while keeping an explicit preservation switch for failed/debug runs.
·Plugins/perf: reuse derived plugin metadata snapshots for the lifetime of the process so reply-time skill setup no longer rescans plugin metadata on every turn.
·Discord/OpenAI voice: keep wake-name master consults using the current speaker context after ignored ambient transcripts and shorten the default capture silence grace.
·Doctor: skip redundant Gateway restart prompts when a recent supervisor restart leaves the Gateway healthy. Fixes #86518. (#86533)
·Cron: restore suspended cron lanes to the configured/default concurrency instead of falling back to one after quota or circuit-breaker auto-resume.
·Gateway: keep session-only Control UI tool-start mirrors flowing during diagnostic queue pressure instead of silently dropping non-terminal tool updates.
·Agents/memory: return optional not-found context for missing date-only daily memory reads instead of logging benign first-run `ENOENT` failures. Fixes #82928.
·Discord: merge streamed text captions into following media block replies so captions and attachments send as one message. (#86487)
·Gateway: avoid sending duplicate tool-event frames to Control UI connections that are subscribed by both run and session.
·Discord/OpenAI voice: accept broader edge-position fuzzy wake-name transcripts while keeping ambient speech gated.
·Discord/OpenAI voice: accept longer leading wake-name mistranscripts such as "Open Club" for OpenClaw.
·Agents/OpenAI-compatible: stop ModelStudio-compatible chat requests before sending system/tool-only payloads that have no usable user or assistant turn. (#86177)
·Gateway/plugins: reuse plugin package realpath checks while building installed plugin indexes so startup avoids repeated filesystem resolution work.
·Kilo Gateway: send string `stop` sequences as arrays so Kilo accepts OpenAI-compatible chat completions. (#86461)
·Discord/OpenAI voice: accept leading fuzzy wake-name transcripts such as "Monty" or "Moti" for a Molty agent while keeping ambient speech gated.
·Media understanding: convert HEIC and HEIF images to JPEG before image description providers run so iPhone photos work in direct and configured image-description flows. (#86037)
·Agents: release embedded-attempt session locks from outer teardown so post-prompt exceptions cannot wedge later requests behind `SessionWriteLockTimeoutError`. Fixes #86014.
·Discord/OpenAI voice: rotate Realtime sessions at provider max duration without logging the expected session-expiry event as an error.
·Sessions: skip metadata-only entries during QMD-slugified session lookup so one incomplete row does not block transcript hit resolution. (#86327)
·Agents/media: derive bundled plugin local-media trust from plugin tool metadata instead of importing the full plugin registry on subscription paths. (#84409)
·Image tool: keep config-backed custom-provider API keys usable for auto-discovered vision models, including deferred image-tool execution without env keys or auth profiles. (#85733)
·Memory/local embeddings: run local GGUF embeddings in an isolated worker sidecar and degrade to configured fallback or keyword search on worker failure so native embedding crashes do not take down the Gateway. (#85348)
·Gateway: clear the runtime config snapshot before `SIGUSR1` in-process restarts so config changes survive the next gateway loop. (#86388)
·Models: show OAuth delegation markers as configured `models.json` auth while keeping runtime route usability checks strict. (#86378)
·Cron: seed active scheduled and manual cron task rows with a progress summary so status surfaces do not look blank while jobs run. (#86313)
·Cron: preserve unsupported persisted cron payload rows during routine store writes while keeping those rows non-runnable. Fixes #84922. (#86415)
·Updater: exclude prerelease git tags from stable channel resolution so source updates do not check out newer alpha/rc/preview/canary tags. (#86260)
·Security/Audit: flag webhook `hooks.token` reuse of active Gateway password auth in `openclaw security audit` while keeping password-mode startup compatibility. (#84338)
·QQBot: derive the outbound reply watchdog from configured agent and provider timeouts so slow local model replies are not cut off at five minutes. Fixes #85267. (#85271)
·Agents/heartbeat: stop heartbeat turns after the first valid `heartbeat_respond` so repeated response loops do not burn tokens. (#86357)
·Tasks: keep retained lost tasks out of default status health counts, explain their cleanup window during maintenance, and prune lost task records after 24 hours instead of the general 7-day terminal retention.
·Memory-core: keep REM dreaming focused on live light-staged memories and mark staged entries as considered so old recall history no longer dominates fresh candidates. (#86302)
·Memory: abort sync instead of downgrading an existing semantic vector index to FTS-only when the configured embedding provider is temporarily unavailable. (#85704)
·Telegram: propagate forum topic names through the account-scoped topic cache for native command context and topic create/edit actions. (#86299)
·Slack: keep downloaded read-only files out of reply media so Slack file reads do not echo files back to the conversation. (#86318)
·Cron: accept leading-plus relative durations such as `+5m` for one-shot `--at` schedules. (#86341)
·Agents/media: preserve async-started media tool metadata so background generation starts no longer surface generic incomplete-turn warnings while replay stays unsafe. (#85933)
·Docker E2E: dedupe scheduler lane resources so npm/service package lanes are not over-counted and serialized unnecessarily.
·QA/diagnostics: add a collector-backed OpenTelemetry smoke lane, make the OTLP payload leak check scenario-aware, and keep source QA builds from failing on optional dependency imports resolved through pnpm's temp module path.
·Crabbox: bootstrap Git metadata for sparse remote changed gates so raw synced workspaces can run `pnpm check:changed` from the intended diff.
·xAI/LM Studio: avoid buffering ordinary bracketed or `final` prose until stream completion while watching for plain-text tool-call fallbacks.
·Doctor: warn and continue when the cron job store exists but cannot be read so later health checks still run. Fixes #86102. (#86384)
·Discord: suppress a bot's previous reply body and referenced media from prompt context when a user replies to that bot message, while keeping reply metadata for routing. (#86238)
·Discord: restore bare numeric channel IDs for outbound message-tool sends while keeping explicit DM targets unambiguous. (#86571)
·Docker E2E: avoid rebuilding the Control UI twice while preparing the shared OpenClaw package tarball for package-backed scenario runs.
·Tests: avoid rebuilding the Control UI twice during the installer Docker smoke now that `pnpm build` includes `ui:build`.
·Tests: give QA config mutation RPCs enough native Windows budget to finish gateway config writes and restart settle after hot scenario runs.
·Tests: keep the gateway restart-inflight QA scenario focused on restart recovery on native Windows by allowing expected embedded prompt handoff errors and using the Windows-safe timeout budget.
·QA-Lab: make the synthetic OpenAI provider honor generic `reply exactly:` directives after required kickoff reads so restart-recovery scenarios do not fall through to generic repo-summary prose.
·Gateway: abort active `agent` RPC runs during forced restart shutdown so stale in-process turns cannot keep writing a session after the Gateway lifecycle restarts.
·Crabbox: sync clean sparse worktrees through a temporary full checkout even when reusing an existing lease so tracked build-time files are not omitted.
·Build: route `scripts/ui.js` through the shared pnpm runner and keep Control UI chunking helpers in sparse-included source so native Windows Corepack builds can produce `dist/control-ui`.
·Tests: give the memory fallback QA scenario enough turn budget to exercise native Windows gateway runs instead of failing on the client timeout while the mock agent is still dispatching.
·Tests: collect QA gateway CPU/RSS metrics on native Windows and give the channel baseline enough turn budget to report slow gateway runs instead of timing out before proof.
·Install/update: bypass npm `min-release-age` policies with `--min-release-age=0` instead of `--before` so hosted installers keep working on npm versions that reject the combined config. (#84749)
·Diagnostics: reclaim wedged session lanes when stale active-run bookkeeping blocks queued work despite no forward progress. Fixes #85639.
·WebChat: keep message-tool replies visible in the chat while still summarizing internal tool results for the model. Fixes #86347.
·Gateway/perf: fail startup benchmark samples when the Gateway process exits before benchmark teardown, including signal deaths after readiness probes.
·Gateway/perf: fail restart benchmark samples when the Gateway exits before benchmark teardown, including clean exits and signal deaths after successful restart probes.
·Agents/tests: keep model catalog visibility on static selection helpers so catalog visibility checks avoid the broad model-selection barrel import.
·Agents/commitments: serialize commitment store load-modify-save writes so concurrent heartbeat and CLI updates no longer lose dismissal, sent, or attempt state. (#81153)
·xAI/LM Studio: promote plain-text tool-call fallbacks into structured tool calls and strip leaked internal tool syntax before user-facing delivery. (#86222)
·CLI: suppress benign self-update version-skew warnings during package post-update finalization.
·Gateway/perf: tighten restart and startup benchmark failure handling so long profiling runs, failed probes, and fresh Linux runners no longer produce false passing or `n/a` results.
·Checks: keep intentional Knip unused-file findings optional so full CI and sparse proof workspaces stay aligned.
·Docker: restore writable `~/.config` in runtime images. Fixes #85968.
·Plugin SDK: keep legacy root diagnostic subscriptions connected when built plugin SDK aliases resolve diagnostic helpers through a separate module graph.
·Diagnostics: export alertable OTel and Prometheus signals for blocked tools, model failover, stale sessions, liveness warnings, oversized payloads, and webhook ingress while fixing shared OTLP endpoints with query strings.
·Tests: normalize macOS canonical temp paths in exec allowlists, fs-safe trash assertions, installed plugin matching, Telegram topic-name stores, and built ACPX MCP server expectations so native macOS proof runners cover the intended behavior.
·Codex/app-server: preserve message-tool-only source reply delivery mode on active runs so sub-agent completion wakeups can steer the active Codex turn instead of being rejected. (#86287)
·Tests: sample the Windows kitchen-sink RPC gateway directly and serialize RSS probes so native runs keep the memory guard active.
·Tests: normalize bundled plugin lifecycle probe paths and state-root lookup so native Windows release sweeps accept valid packaged plugin installs.
·Agents/Claude CLI: route live native Bash permission requests through OpenClaw exec policy so Claude turns no longer stall on `control_request`, and document that OpenClaw exec policy is authoritative. Fixes #80819. (#86330, from #81971)
·Security audit: warn when YOLO OpenClaw exec policy overrides a restrictive raw Claude `--permission-mode` for managed live sessions. (#86557)
·Config: keep benign legacy metadata write anomalies out of default doctor and config command output while preserving explicit anomaly logging for diagnostics.
·Codex: log when implicit app-server `never` approvals are promoted for OpenClaw tool policy, including whether the trigger was a `before_tool_call` hook or trusted tool policy.
·Codex harness: make subscription usage-limit errors without reset times explain that OpenClaw cannot determine the reset and point users to wait until Codex is available, use another Codex account, or switch to another configured model/provider.
·Google Vertex: support production ADC modes such as Workload Identity Federation, service-account credentials, and metadata-server ADC for the native Vertex transport. (#83971)
·Telegram: route normal `[telegram][diag]` polling diagnostics through `runtime.log` while keeping non-diag warnings and persistence failures on `runtime.error`, so healthy polling startup no longer looks like an error. Fixes #82957. (#82958)
·Providers/Ollama: strip inline Kimi cloud reasoning prefixes from streamed and final visible replies while keeping ordinary Kimi answers append-only. (#86286)
·Gateway: require Talk secret authority before setup-code handoff can include Talk secrets. (#85690)
·Agents: keep fallback error reporting scoped to the active model candidate so stale prior-provider quota/auth text is not reported for later fallback attempts. (#86134)
·iMessage: dedupe watcher startup when `channels.imessage.accounts` lists both `default` and a named account that point at the same local Messages source, so the gateway no longer spawns two `imsg rpc` processes or doubles inbound replies; the dedupe is scoped to watcher startup, leaving duplicate accounts addressable for outbound sends, status, and capability listings, and `openclaw doctor` flags the redundant account with a rebinding hint. Fixes #65141. (#86705)

Release verification

·npm package: https://www.npmjs.com/package/openclaw/v/2026.5.26
·registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.5.26.tgz
·integrity: `sha512-ne6ESyXmspmWO7JlSAWFp1ACmk/um2bnEGnEkiHd4BK62XRUt82DBCCpBGcLsMKA+zNG9G938dA+zCNJCKvUFA==`
·full release validation: https://github.com/openclaw/openclaw/actions/runs/26508372964
·release checks and package acceptance: https://github.com/openclaw/openclaw/actions/runs/26508649633
·plugin npm publish: https://github.com/openclaw/openclaw/actions/runs/26510827501
·plugin ClawHub publish: https://github.com/openclaw/openclaw/actions/runs/26510832030
·OpenClaw npm publish: https://github.com/openclaw/openclaw/actions/runs/26511283421
·published-package smoke: `OpenClaw 2026.5.26 (10ad3aa)` and `plugins list --json` returned 46 bundled plugins from a clean temp HOME.
·npm package: https://www.npmjs.com/package/openclaw/v/2026.5.26
·registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.5.26.tgz
·integrity: sha512-ne6ESyXmspmWO7JlSAWFp1ACmk/um2bnEGnEkiHd4BK62XRUt82DBCCpBGcLsMKA+zNG9G938dA+zCNJCKvUFA==
·full release CI report: https://github.com/openclaw/releases/blob/main/evidence/2026.5.26/release-evidence.md
·npm preflight: https://github.com/openclaw/openclaw/actions/runs/26508373036
·full release validation: https://github.com/openclaw/openclaw/actions/runs/26508372964
·plugin npm publish: https://github.com/openclaw/openclaw/actions/runs/26510827501
·plugin ClawHub publish: https://github.com/openclaw/openclaw/actions/runs/26510832030
·OpenClaw npm publish: https://github.com/openclaw/openclaw/actions/runs/26511283421
·macOS preflight/sign/notarize: https://github.com/openclaw/releases/actions/runs/26508373159
·macOS validation: https://github.com/openclaw/releases/actions/runs/26512430969
·macOS publish/appcast: https://github.com/openclaw/releases/actions/runs/26512779540
·appcast: https://github.com/openclaw/openclaw/blob/main/appcast.xml
·macOS zip: https://github.com/openclaw/openclaw/releases/download/v2026.5.26/OpenClaw-2026.5.26.zip
·macOS dmg: https://github.com/openclaw/openclaw/releases/download/v2026.5.26/OpenClaw-2026.5.26.dmg
·macOS dSYM: https://github.com/openclaw/openclaw/releases/download/v2026.5.26/OpenClaw-2026.5.26.dSYM.zip

v2026.5.26-beta.2pre-release2026-05-27

openclaw 2026.5.26-beta.2

GitHub ↗

Highlights

·Faster Gateway and replies: startup avoids repeated plugin, channel, session, usage-cost, warning, scheduled-service, and filesystem scans; visible replies separate user-facing sends from slower follow-up work; Gateway runtime/session caches churn less under load.
·Transcripts are core: transcript-backed meeting summaries, source-provider chunks, cleaned user turns, media provenance, Codex mirrors, WebChat replies, and CLI/TUI replay now use one more reliable transcript path.
·More channels are production-ready: Telegram keeps typing/progress context and forum topics, iMessage handles attachment roots, remote media staging, and duplicate local Messages sources, WhatsApp restores group/media behavior, Discord improves voice playback and model picking, and Signal/iMessage/WhatsApp get reaction approvals.
·Better voice and Talk: realtime Talk runs can be inspected, steered, cancelled, or followed up from Web UI and Discord voice; wake-name handling is more tolerant without letting ambient speech trigger agents.
·Safer content boundaries: Browser snapshot reads honor SSRF policy, system-event text cannot spoof nested prompt markers, fetched file text is wrapped as external content, ClickClack inbound sender allowlists run before agent dispatch, stale device tokens are rejected, and serialized tool-call text is scrubbed from replies.
·Providers, Codex, and local models are steadier: named auth profiles, OpenAI sampling params, Codex app-server resume/timeout/usage-limit recovery, dynamic tool-schema guards, xAI usage-limit surfacing, Ollama top-p normalization, and local approval resolution reduce provider-specific dead ends.
·More reliable install/update/release paths: Alpine installs, trusted runtime fallback roots, stable update channels, Docker/package timeouts, Windows Scheduled Tasks, Windows/macOS proof lanes, Testbox/Crabbox delegation, plugin publish checks, and macOS runner bootstraps all got hardened.
·Better observability: Activity tab, gateway secret-prep traces, tool/model stream progress, explicit fast-mode status, systemd Gateway hygiene, OpenTelemetry LLM spans, release performance evidence, and richer telemetry signals make failures easier to inspect.

Changes

·Transcripts: add core transcript capture and source-provider support for transcript-backed meeting summaries, including the renamed Transcripts docs, CLI surface, source-provider chunks, and cleaned user-turn persistence.
·Auth: add named model login profiles and supported credential migration for Hermes, OpenCode, and Codex auth profiles, with explicit opt-out and non-interactive controls. (#85667)
·Diagnostics: trace gateway secret preparation, classify skill/tool usage, surface model stream progress, add OpenTelemetry LLM content spans, and expose alertable telemetry for blocked tools, failover, stale sessions, liveness, oversized payloads, and webhook ingress. (#83019, #80370, #86191)
·Channels: add Signal reaction approvals, iMessage thumb approval reactions, and WhatsApp thumb approval reaction support so mobile approval flows work without textual `/approve` commands. (#85894, #85952, #85477)
·Agents/API: forward OpenAI sampling params through the Gateway and expose estimated context-budget status for active agent runs. (#84094)
·TUI/status: queue prompts submitted while an agent is busy and show explicit fast-mode state plus richer systemd Gateway hygiene in status output. (#86722, #87115, #86976)
·Exec approvals: hide durable approval actions that are unavailable for the current prompt and keep approval runtime tokens local-only so stale prompts cannot offer misleading controls. (#86270, #86359)
·Plugin SDK: add reaction approval helpers and keep diagnostic event root exports discoverable across function-name and alias-bound module graphs. (#86735, #87084)
·Android/iOS: add the Android pair-new-gateway action and improve mobile Talk mode surfaces, including iOS realtime Talk mode and Android offline voice/gateway recovery. (#86798, #86355)
·Performance: cache plugin metadata snapshots, package realpaths, stable gateway metadata, model cost indexes, channel resolution, usage-cost indexes, and session/auth hot-path facts so common Gateway and reply paths do less rediscovery. (#84649, #85843, #86517, #86678)
·Voice: expose shared realtime turn-context tracking through the realtime voice SDK and reuse it for Discord speaker attribution and wake-name context recovery.
·Voice: reuse shared realtime output activity tracking in Google Meet command and node audio bridges, including recent-output checks for local barge-in detection.
·Voice: expose shared realtime output activity tracking through the realtime voice SDK and reuse it for Discord playback activity and barge-in decisions.
·Voice: expose shared realtime consult question matching, speakable-result extraction, and alias-aware forced-consult coordination through the realtime voice SDK, then reuse it in Gateway Talk, Voice Call, and Discord voice paths.
·Voice: share activation-name matching and consult-transcript screening through the realtime voice SDK so Discord, browser voice, and meeting surfaces can reuse one implementation.
·Cron: default `cron.maxConcurrentRuns` to 8 so scheduled automations and their isolated agent turns can make progress in parallel without explicit configuration.
·QA-Lab: add `qa coverage --match <query>` so focused proof selection can discover matching scenarios from existing metadata before running live or remote lanes.
·Discord/model picker: surface an alpha-bucket select (e.g. `A–G (12) · H–N (18) · O–Z (5)`) when the provider list or a provider's model list exceeds 25 items, so configs with `provider/*` wildcards stay one click from the right page instead of paginating through prev/next; falls back to numeric chunks when every item shares the same first letter.
·Control UI: add an ephemeral Activity tab for sanitized live tool activity summaries without persisting raw telemetry. Fixes #12831.
·Build: include `ui:build` in the `full` and `ciArtifacts` profiles of `scripts/build-all.mjs` so `pnpm build` always rebuilds `dist/control-ui` after `tsdown` cleans `dist`, removing the second-command requirement and the missing-asset failure mode for source/runtime installs and CI artifact uploads. (#85206)
·iOS: improve Talk mode with direct realtime voice sessions, compact toolbar status, and responsive voice waveform feedback. (#86355)
·Media: replace the Sharp image backend with Rastermill for metadata, resizing, EXIF orientation, and PNG alpha-preserving optimization so OpenClaw no longer installs Sharp or the WhatsApp Jimp fallback for image processing. (#86437)
·Codex: update the bundled Codex CLI to 0.134.0 and keep native compaction disabled for budget-triggered app-server turns so OpenClaw owns the recovery boundary. (#86772)

Fixes

·Memory/security: reject prompt-like text submitted through the explicit `memory_store` tool before embedding or storage, matching the existing auto-capture prompt-injection filter. (#87142)
·Gateway/security: enable the default auth rate limiter for remote non-browser and HTTP gateway auth failures when `gateway.auth.rateLimit` is unset, while preserving the loopback exemption. (#87148)
·Security/content boundaries: validate Browser snapshot tab URLs against SSRF policy before ChromeMCP or direct CDP reads, sanitize queued system-event text so untrusted plugin/channel labels cannot spoof nested prompt markers, wrap fetched file text and metadata as external content, apply ClickClack `allowFrom` sender allowlists before agent dispatch, reject RPCs from invalidated device-token clients during rotation, require staged sandbox media refs, and scrub serialized tool-call text from replies. (#78526, #87094, #87062, #83741, #70707, #86924)
·Transcripts/user turns: persist CLI, WebChat, media, follow-up, hook, and Codex-mirror user turns to the admitted session target; keep cleaned transcript text, inline image routing, provenance metadata, replay hooks, and fallback paths idempotent when runtimes fail or restart.
·TUI/status/onboarding/UI: queue busy TUI prompts instead of dropping them, preserve the configured default model during onboarding, show failed tool results as errors, show config-open failures in Control UI, keep status JSON plugin scans healthy, preserve xAI usage-limit errors locally, and expose explicit fast-mode/systemd state. (#86722, #87000, #85786, #87108, #87001, #86614, #87115, #86976)
·Plugin commands/SDK: preserve plugin LLM command auth, bind native plugin command dispatch to the host agent's LLM auth, keep `onDiagnosticEvent` exports discoverable through `Function.name`, stabilize diagnostic event root aliases, correlate pathless read diagnostics, suppress transient runner failures in channel command paths, and repair local approval resolution. (#85936, #87084, #86977, #87069, #86771)
·Codex/providers: keep WebChat delivery hints out of user prompts, avoid false queued-terminal idle timeouts, share the native hook relay registry, quarantine unsupported dynamic tool schemas, preserve Claude resumed-session system prompts, normalize greedy Ollama `top_p`, preserve per-agent thinking defaults for ingress runs, and avoid native compaction takeover on budget-triggered Codex turns. (#87096, #73950, #87049, #86689, #86772)
·Gateway/perf/release: reuse startup-warning metadata and prepared auth stores, avoid cloning live-switch and lifecycle session caches on read paths, defer warning and scheduled-service fallback imports, trim Gateway session/startup/runtime CPU churn, skip duplicate turn session touches, stop chat timeout fallback cascades, drop stale subagent announce history, bound benchmark/watch/kitchen-sink teardown waits, bound macOS/package/onboarding/plugin smoke commands, bound install finalization probes, resolve Parallels npm-update commands from guest `PATH`, and bootstrap raw AWS macOS Node/pnpm commands through `/usr/bin/env`. (#86997)
·Reply/perf: reduce visible reply delivery latency by preserving Telegram typing/progress context, lazy-loading slash-command startup metadata, avoiding hot-path model hydration, flag-gating Codex profiler timing, deferring context compaction maintenance, and tracking delivery timing. (#86989, #86990, #86991, #86992, #86993, #86994)
·Reply/source delivery: keep TUI, Control UI, media, TTS, transcript, and Codex source-reply finals live without duplicate terminal events or stale replay artifacts.
·Agents/replay: repair legacy tool results before replay, preserve `sessions_spawn` transcript payloads, restore current guard checks, stage sandboxed workspace media, and keep duplicate transcripts tool display metadata from reappearing. (#82203, #86934, #87025)
·Agents/sessions: handle active-fallback failures in `sessions_send` so fallback routing reports the real failure and does not leave callers with an ambiguous dropped send. (#86638)
·Agents/hooks/subagents: enforce default hook agent allowlists, recover failed subagent lifecycle completions, and keep node task lifecycle cleanup from closing the Gateway listener. (#86101)
·Codex: project newer OpenClaw chat history into resumed app-server threads and keep Codex turn timeouts inside the Codex runtime boundary so timeouts do not poison shared app-server clients or fall through to unrelated provider fallback. (#86677, #86476)
·Config/doctor/update: narrow profiled tool-section doctor repair, keep runtime-injected legacy web-search provider config out of user-authored config validation, and keep prerelease tags excluded from stable updater resolution. (#87030, #86818, #86559)
·CLI/Windows: add a Windows-only stack-size respawn for stack-heavy startup paths, default CLI logs to local timestamps, and validate timeout/banner TTY state more strictly. (#87031, #85387)
·Locking/security: require owner identity proof before stale plugin lock removal, memoize session lock owner arguments, and avoid writing default exec approval stores unless policy state actually changed. (#86814, #86964)
·Install/release: bound Docker package build, inventory, pack, and tarball preparation with process-group timeouts; pin shrinkwrap patch drift to the pnpm lock; harden macOS restart and dSYM packaging; and run release Docker/live timeout wrappers in the foreground so child processes cannot wedge gates.
·Telegram/network: treat `ENETDOWN` as a transient pre-connect network failure so Telegram sends, gateway unhandled-rejection handling, and cron network retries follow the same recovery path as sibling network outages. (#86762)
·Telegram: preserve inbound text entities, overlapping DM replies, account topic cache sidecars, outbound reply context, targeted bot-command mentions, durable group retry targets, forum topic names, and native progress callbacks. (#83873, #85361, #85555, #85656, #85709, #86299, #86553)
·iMessage: read image attachments from local Messages attachment roots, dedupe duplicate local Messages-source accounts, seed direct DM history, fix image/group media attachment commands, advance catchup cursors after live handling, and keep slash-command acknowledgements in the source conversation. (#82642, #85475, #86569, #86705, #86706, #86770)
·WhatsApp/QQ/Twitch/IRC/Slack: restore WhatsApp ack identity and group-drop warnings, make QQ Bot media respect `OPENCLAW_HOME`, serialize Twitch auth disconnects, store IRC channel routes canonically, and keep Slack downloaded files out of reply media. (#83833, #85309, #85777, #85794, #85906, #86318, #86697)
·Discord/voice: improve voice playback and wake replies, bucket large model picker menus, merge media captions into one message, route metadata through configured proxies, restore numeric channel sends, suppress self-reply echoes, and tighten wake matching without breaking fuzzy wake phrases. (#80227, #86238, #86487, #86571, #86595, #86601)
·Codex: preserve native web-search metadata, keep oversized native thread reuse, bridge CLI API-key auth into the app server, preserve sandbox bootstrap path style, recover context-window prompt errors, honor yolo approval policy, disable native thread personality, and route compaction through Codex auth. (#85378, #85542, #85891, #85909, #86408)
·Agents/runtime: enforce session lock max-hold reclaim, release embedded-attempt locks on all exits, treat aborted subagent runs as terminal, avoid runtime model hydration on hot paths, disclose scoped session list counts, derive overflow budgets from provider errors, and keep fallback errors scoped to the active model candidate. (#70473, #85764, #86014, #86134, #86427, #86944)
·Config/update/doctor: retry config recovery after failed backup restore, skip shell env fallback on Windows, exclude prerelease tags from the stable git channel, support deep config edits, warn instead of aborting on unreadable cron stores, prune stale bundled plugin paths, and avoid duplicate restart prompts when the Gateway is already healthy. (#85739, #85787, #86060, #86260, #86384, #86533)
·Install/release: support Alpine CLI installs and runtime floors, prefer trusted startup argv runtime fallback roots, reject stale CLI node runtimes, avoid npm `min-release-age` installer failures, bound npm/package/Docker install phases, restore config parent ownership in Docker, seed Docker lockfile package tarballs before prune, make release/plugin prerelease checks fail closed instead of hanging or false-greening, and use host-visible Crabbox local work roots for Docker-backed proof. (#85491)
·Windows daemon: keep Scheduled Task gateway launches running on battery power and avoid workgroup-machine prompts for a domain user during task installation. (#59299)
·Security: avoid printing Gateway tokens in Docker, validate plugin model-pattern regexes safely, escape transcript metadata field names, harden session allowlist glob matching, audit Claude permission overrides under YOLO, and require explicit allow for ACP auto approvals. (#85849, #85934, #86046, #86557)
·Media/images: replace Sharp with Rastermill, keep EXIF normalization best-effort, normalize HEIC/HEIF before image descriptions, route Codex image API keys through OpenAI, preserve image compression metadata, and auto-scale live tool result caps. (#85776, #86037, #86437, #86857, #86923)
·Memory: prevent semantic vector indexes from silently degrading when embeddings are unavailable, stop doctor OOMs on large session stores, preserve sidecar hooks/artifacts, write fallback dream diaries, use CJK-aware dreaming dedupe, and avoid per-file watcher FD fan-out. (#80613, #82928, #85060, #85704, #85967, #86701)
·Agents/sessions: include visibility metadata on restricted `sessions_list` results so scoped counts are clearly reported without widening access or exposing hidden-session counts. (#86944)
·Gateway/DNS: validate wide-area discovery domains before deriving zone paths or writing zone files, so invalid `discovery.wideArea.domain` and `dns setup --domain` values fail with a DNS-name diagnostic instead of falling through to unrelated configuration errors.
·Agents/BTW: route fallback side-question streams through the embedded stream resolver so Anthropic-compatible MiniMax requests use the same capped transport as normal chat. (#86312)
·Telegram: treat `/command@TargetBot` bot-command entities as explicit mentions for the addressed bot so `requireMention` groups no longer drop targeted commands or captions. Fixes #84462. (#86553)
·CI: bound Docker/Bash E2E tarball npm installs with `OPENCLAW_E2E_NPM_INSTALL_TIMEOUT` so package, onboarding, plugin, and upgrade lanes fail instead of hanging on a stuck npm install.
·CI: fail Parallels npm-update smoke jobs after the guest command timeout and cleanup backstop instead of only logging a timeout line.
·CI: bound kitchen-sink RPC HTTP probes so stalled gateway readiness or response bodies fail and retry instead of wedging the walker.
·CI: keep `OPENCLAW_TESTBOX=1 pnpm check:changed` delegating to Blacksmith Testbox through Crabbox without forwarding local Testbox or worker env into the remote command.
·CI: send KILL after the TERM grace period for manual checkout fetch timeouts so stuck Testbox and workflow checkout retries cannot hang behind a wedged `git fetch`.
·CI: send KILL after the TERM grace period for Bun global install smoke command timeouts so trapped `openclaw` child processes cannot wedge the scheduled install smoke.
·iMessage: thread current channel/account inbound attachment roots into the image tool so iMessage-saved attachments under `~/Library/Messages/Attachments` (including the wildcard `/Users/*/Library/Messages/Attachments` root) are read through the existing inbound path policy instead of being rejected as `path-not-allowed`. Literal `localRoots` stays workspace-scoped. Fixes #30170. (#86569)
·QQ Bot: respect `OPENCLAW_HOME` for outbound media path resolution so `<qqmedia>` sends no longer silently fail when `HOME` and `OPENCLAW_HOME` differ (Docker / multi-user hosts). Persisted QQ Bot data (sessions, known users, refs) stays anchored on the OS home for upgrade compatibility. Fixes #83562.
·Update: report the primary malformed `openclaw.extensions` payload error without adding a duplicate missing-main diagnostic. (#86596)
·Control UI: keep host-local Markdown file paths inert while preserving app-relative links. (#86620)
·Gateway: dampen repeated unauthenticated device-required probes per URL while preserving explicit-auth and paired recovery paths. (#86575)
·IRC: store inbound channel routes with the canonical `channel:#name` target and join transient channel sends before writing. (#85906)
·Usage: surface unknown all-zero model pricing as missing cost entries instead of a confident `$0` total. (#85882)
·Agents/Codex: honor yolo app-server approval policy only for the full `never` plus `danger-full-access` case. (#85909)
·Gateway/Gmail: clear Gmail watcher renewal intervals on re-entry so hot reloads do not leak lifecycle timers. (#82947)
·Logging: exit cleanly on broken stdout/stderr pipes without masking existing failure exit codes. (#80059)
·Gateway/security: escape transcript metadata field names while extracting oversized session line prefixes. (#85934)
·Plugins/security: validate manifest model pattern regexes with the safe-regex compiler so unsafe patterns are ignored before matching. (#86046)
·Discord: route gateway metadata REST lookups through the configured Discord proxy so proxied accounts do not fall back to direct `discord.com` connections before opening the WebSocket. Fixes #80227.
·Agents/media: hydrate current-turn image attachments from filename-derived MIME types so active vision can see generated or forwarded images whose source omitted an image content type. (#84812)
·Agents/fs: point workspace-only scratch-path guidance at in-workspace temp directories while keeping host-root writes rejected by the tool guard. (#86501)
·Agents/media: keep async cron media completions scoped to their run session while preserving direct delivery for stale generated-media success and failure notifications. (#86529)
·Gateway: emit plugin `session_end`/`session_start` hooks when `agent.send` rotates or replaces a session id, keeping hook lifecycle state aligned with `sessions.changed` notifications. Fixes #83507. (#85875)
·OpenShell/SSH: reject malformed generated exec commands before sandbox/session setup so unresolved workflow placeholders fail fast instead of reaching the remote shell. Fixes #72373.
·Google: stop normalizing `gemini-3.1-flash-lite` to the retired preview endpoint and update Flash Lite alias guidance to the GA model id. Fixes #86151. (#86240)
·Installer: make Alpine apk installs cover Git, verify the Node runtime floor, try `nodejs-current`, and report Alpine version guidance when repositories only provide older Node packages.
·Agents/status: prefer the active Claude CLI OAuth auth label over an unused Anthropic env API-key label for equivalent runtime aliases. Fixes #80184. (#86570)
·Agents/media: send direct fallback for generated media still missing after an active requester wake fails. (#85489)
·Agents: derive overflow compaction budgets from provider-reported and synthetic over-budget token counts so confirmed context overflows compact before retrying. (#70473)
·Agents/Codex: recover Codex context-window prompt errors through overflow compaction and surface reset guidance when recovery is exhausted. (#85542)
·Agents/Codex: allow Codex app-server runs to bootstrap from `CODEX_API_KEY` or `OPENAI_API_KEY` when no Codex auth profile is configured.
·Agents/Codex: keep selected Codex runtime routing on OpenAI-Codex while preserving direct OpenAI API-key compaction fallback. (#86408)
·Agent transcript: include OpenClaw agent session logs when finding local transcript candidates.
·Crabbox: bootstrap raw AWS macOS shell commands wrapped in absolute `time` paths so RSS probes can run Node and pnpm on fresh macOS runners.
·Crabbox: bootstrap raw AWS macOS shell commands even when setup statements precede Node or pnpm usage.
·TUI/local: skip unnecessary secret resolution, gateway model catalog loading, bootstrap, and skill scans in explicit local-model runs so startup reaches the model request faster.
·Sessions/doctor: load large session stores without clone amplification during read-only doctor checks and reclaim stale `sessions.json.*.tmp` sidecars. Fixes #56827.
·Tests: clean successful plugin gateway gauntlet isolated temp roots while keeping an explicit preservation switch for failed/debug runs.
·Plugins/perf: reuse derived plugin metadata snapshots for the lifetime of the process so reply-time skill setup no longer rescans plugin metadata on every turn.
·Discord/OpenAI voice: keep wake-name master consults using the current speaker context after ignored ambient transcripts and shorten the default capture silence grace.
·Doctor: skip redundant Gateway restart prompts when a recent supervisor restart leaves the Gateway healthy. Fixes #86518. (#86533)
·Cron: restore suspended cron lanes to the configured/default concurrency instead of falling back to one after quota or circuit-breaker auto-resume.
·Gateway: keep session-only Control UI tool-start mirrors flowing during diagnostic queue pressure instead of silently dropping non-terminal tool updates.
·Agents/memory: return optional not-found context for missing date-only daily memory reads instead of logging benign first-run `ENOENT` failures. Fixes #82928.
·Discord: merge streamed text captions into following media block replies so captions and attachments send as one message. (#86487)
·Gateway: avoid sending duplicate tool-event frames to Control UI connections that are subscribed by both run and session.
·Discord/OpenAI voice: accept broader edge-position fuzzy wake-name transcripts while keeping ambient speech gated.
·Discord/OpenAI voice: accept longer leading wake-name mistranscripts such as "Open Club" for OpenClaw.
·Agents/OpenAI-compatible: stop ModelStudio-compatible chat requests before sending system/tool-only payloads that have no usable user or assistant turn. (#86177)
·Gateway/plugins: reuse plugin package realpath checks while building installed plugin indexes so startup avoids repeated filesystem resolution work.
·Kilo Gateway: send string `stop` sequences as arrays so Kilo accepts OpenAI-compatible chat completions. (#86461)
·Discord/OpenAI voice: accept leading fuzzy wake-name transcripts such as "Monty" or "Moti" for a Molty agent while keeping ambient speech gated.
·Media understanding: convert HEIC and HEIF images to JPEG before image description providers run so iPhone photos work in direct and configured image-description flows. (#86037)
·Agents: release embedded-attempt session locks from outer teardown so post-prompt exceptions cannot wedge later requests behind `SessionWriteLockTimeoutError`. Fixes #86014.
·Discord/OpenAI voice: rotate Realtime sessions at provider max duration without logging the expected session-expiry event as an error.
·Sessions: skip metadata-only entries during QMD-slugified session lookup so one incomplete row does not block transcript hit resolution. (#86327)
·Agents/media: derive bundled plugin local-media trust from plugin tool metadata instead of importing the full plugin registry on subscription paths. (#84409)
·Image tool: keep config-backed custom-provider API keys usable for auto-discovered vision models, including deferred image-tool execution without env keys or auth profiles. (#85733)
·Memory/local embeddings: run local GGUF embeddings in an isolated worker sidecar and degrade to configured fallback or keyword search on worker failure so native embedding crashes do not take down the Gateway. (#85348)
·Gateway: clear the runtime config snapshot before `SIGUSR1` in-process restarts so config changes survive the next gateway loop. (#86388)
·Models: show OAuth delegation markers as configured `models.json` auth while keeping runtime route usability checks strict. (#86378)
·Cron: seed active scheduled and manual cron task rows with a progress summary so status surfaces do not look blank while jobs run. (#86313)
·Cron: preserve unsupported persisted cron payload rows during routine store writes while keeping those rows non-runnable. Fixes #84922. (#86415)
·Updater: exclude prerelease git tags from stable channel resolution so source updates do not check out newer alpha/rc/preview/canary tags. (#86260)
·Security/Audit: flag webhook `hooks.token` reuse of active Gateway password auth in `openclaw security audit` while keeping password-mode startup compatibility. (#84338)
·QQBot: derive the outbound reply watchdog from configured agent and provider timeouts so slow local model replies are not cut off at five minutes. Fixes #85267. (#85271)
·Agents/heartbeat: stop heartbeat turns after the first valid `heartbeat_respond` so repeated response loops do not burn tokens. (#86357)
·Tasks: keep retained lost tasks out of default status health counts, explain their cleanup window during maintenance, and prune lost task records after 24 hours instead of the general 7-day terminal retention.
·Memory-core: keep REM dreaming focused on live light-staged memories and mark staged entries as considered so old recall history no longer dominates fresh candidates. (#86302)
·Memory: abort sync instead of downgrading an existing semantic vector index to FTS-only when the configured embedding provider is temporarily unavailable. (#85704)
·Telegram: propagate forum topic names through the account-scoped topic cache for native command context and topic create/edit actions. (#86299)
·Slack: keep downloaded read-only files out of reply media so Slack file reads do not echo files back to the conversation. (#86318)
·Cron: accept leading-plus relative durations such as `+5m` for one-shot `--at` schedules. (#86341)
·Agents/media: preserve async-started media tool metadata so background generation starts no longer surface generic incomplete-turn warnings while replay stays unsafe. (#85933)
·Docker E2E: dedupe scheduler lane resources so npm/service package lanes are not over-counted and serialized unnecessarily.
·QA/diagnostics: add a collector-backed OpenTelemetry smoke lane, make the OTLP payload leak check scenario-aware, and keep source QA builds from failing on optional dependency imports resolved through pnpm's temp module path.
·Crabbox: bootstrap Git metadata for sparse remote changed gates so raw synced workspaces can run `pnpm check:changed` from the intended diff.
·xAI/LM Studio: avoid buffering ordinary bracketed or `final` prose until stream completion while watching for plain-text tool-call fallbacks.
·Doctor: warn and continue when the cron job store exists but cannot be read so later health checks still run. Fixes #86102. (#86384)
·Discord: suppress a bot's previous reply body and referenced media from prompt context when a user replies to that bot message, while keeping reply metadata for routing. (#86238)
·Discord: restore bare numeric channel IDs for outbound message-tool sends while keeping explicit DM targets unambiguous. (#86571)
·Docker E2E: avoid rebuilding the Control UI twice while preparing the shared OpenClaw package tarball for package-backed scenario runs.
·Tests: avoid rebuilding the Control UI twice during the installer Docker smoke now that `pnpm build` includes `ui:build`.
·Tests: give QA config mutation RPCs enough native Windows budget to finish gateway config writes and restart settle after hot scenario runs.
·Tests: keep the gateway restart-inflight QA scenario focused on restart recovery on native Windows by allowing expected embedded prompt handoff errors and using the Windows-safe timeout budget.
·QA-Lab: make the synthetic OpenAI provider honor generic `reply exactly:` directives after required kickoff reads so restart-recovery scenarios do not fall through to generic repo-summary prose.
·Gateway: abort active `agent` RPC runs during forced restart shutdown so stale in-process turns cannot keep writing a session after the Gateway lifecycle restarts.
·Crabbox: sync clean sparse worktrees through a temporary full checkout even when reusing an existing lease so tracked build-time files are not omitted.
·Build: route `scripts/ui.js` through the shared pnpm runner and keep Control UI chunking helpers in sparse-included source so native Windows Corepack builds can produce `dist/control-ui`.
·Tests: give the memory fallback QA scenario enough turn budget to exercise native Windows gateway runs instead of failing on the client timeout while the mock agent is still dispatching.
·Tests: collect QA gateway CPU/RSS metrics on native Windows and give the channel baseline enough turn budget to report slow gateway runs instead of timing out before proof.
·Install/update: bypass npm `min-release-age` policies with `--min-release-age=0` instead of `--before` so hosted installers keep working on npm versions that reject the combined config. (#84749)
·Diagnostics: reclaim wedged session lanes when stale active-run bookkeeping blocks queued work despite no forward progress. Fixes #85639.
·WebChat: keep message-tool replies visible in the chat while still summarizing internal tool results for the model. Fixes #86347.
·Gateway/perf: fail startup benchmark samples when the Gateway process exits before benchmark teardown, including signal deaths after readiness probes.
·Gateway/perf: fail restart benchmark samples when the Gateway exits before benchmark teardown, including clean exits and signal deaths after successful restart probes.
·Agents/tests: keep model catalog visibility on static selection helpers so catalog visibility checks avoid the broad model-selection barrel import.
·Agents/commitments: serialize commitment store load-modify-save writes so concurrent heartbeat and CLI updates no longer lose dismissal, sent, or attempt state. (#81153)
·xAI/LM Studio: promote plain-text tool-call fallbacks into structured tool calls and strip leaked internal tool syntax before user-facing delivery. (#86222)
·CLI: suppress benign self-update version-skew warnings during package post-update finalization.
·Gateway/perf: tighten restart and startup benchmark failure handling so long profiling runs, failed probes, and fresh Linux runners no longer produce false passing or `n/a` results.
·Checks: keep intentional Knip unused-file findings optional so full CI and sparse proof workspaces stay aligned.
·Docker: restore writable `~/.config` in runtime images. Fixes #85968.
·Plugin SDK: keep legacy root diagnostic subscriptions connected when built plugin SDK aliases resolve diagnostic helpers through a separate module graph.
·Diagnostics: export alertable OTel and Prometheus signals for blocked tools, model failover, stale sessions, liveness warnings, oversized payloads, and webhook ingress while fixing shared OTLP endpoints with query strings.
·Tests: normalize macOS canonical temp paths in exec allowlists, fs-safe trash assertions, installed plugin matching, Telegram topic-name stores, and built ACPX MCP server expectations so native macOS proof runners cover the intended behavior.
·Codex/app-server: preserve message-tool-only source reply delivery mode on active runs so sub-agent completion wakeups can steer the active Codex turn instead of being rejected. (#86287)
·Tests: sample the Windows kitchen-sink RPC gateway directly and serialize RSS probes so native runs keep the memory guard active.
·Tests: normalize bundled plugin lifecycle probe paths and state-root lookup so native Windows release sweeps accept valid packaged plugin installs.
·Agents/Claude CLI: route live native Bash permission requests through OpenClaw exec policy so Claude turns no longer stall on `control_request`, and document that OpenClaw exec policy is authoritative. Fixes #80819. (#86330, from #81971)
·Security audit: warn when YOLO OpenClaw exec policy overrides a restrictive raw Claude `--permission-mode` for managed live sessions. (#86557)
·Config: keep benign legacy metadata write anomalies out of default doctor and config command output while preserving explicit anomaly logging for diagnostics.
·Codex: log when implicit app-server `never` approvals are promoted for OpenClaw tool policy, including whether the trigger was a `before_tool_call` hook or trusted tool policy.
·Codex harness: make subscription usage-limit errors without reset times explain that OpenClaw cannot determine the reset and point users to wait until Codex is available, use another Codex account, or switch to another configured model/provider.
·Google Vertex: support production ADC modes such as Workload Identity Federation, service-account credentials, and metadata-server ADC for the native Vertex transport. (#83971)
·Telegram: route normal `[telegram][diag]` polling diagnostics through `runtime.log` while keeping non-diag warnings and persistence failures on `runtime.error`, so healthy polling startup no longer looks like an error. Fixes #82957. (#82958)
·Providers/Ollama: strip inline Kimi cloud reasoning prefixes from streamed and final visible replies while keeping ordinary Kimi answers append-only. (#86286)
·Gateway: require Talk secret authority before setup-code handoff can include Talk secrets. (#85690)
·Agents: keep fallback error reporting scoped to the active model candidate so stale prior-provider quota/auth text is not reported for later fallback attempts. (#86134)
·iMessage: dedupe watcher startup when `channels.imessage.accounts` lists both `default` and a named account that point at the same local Messages source, so the gateway no longer spawns two `imsg rpc` processes or doubles inbound replies; the dedupe is scoped to watcher startup, leaving duplicate accounts addressable for outbound sends, status, and capability listings, and `openclaw doctor` flags the redundant account with a rebinding hint. Fixes #65141. (#86705)

Release verification

·npm package: https://www.npmjs.com/package/openclaw/v/2026.5.26-beta.2
·registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.5.26-beta.2.tgz
·integrity: `sha512-F+rBfB6DKUviVcDrsyVjx1w27HcKrBJ3VC3SLI22y4mooPGTanWl3opV/OdThnNo7KC3k5jihUTJGHE+xXMNKA==`
·full release CI report: https://github.com/openclaw/releases/blob/main/evidence/2026.5.26-beta.2/release-evidence.md
·release publish: https://github.com/openclaw/openclaw/actions/runs/26497692739
·npm preflight: https://github.com/openclaw/openclaw/actions/runs/26495937267
·full release validation: https://github.com/openclaw/openclaw/actions/runs/26495937332
·plugin npm publish: https://github.com/openclaw/openclaw/actions/runs/26497899701
·plugin ClawHub publish: https://github.com/openclaw/openclaw/actions/runs/26497902867
·OpenClaw npm publish: https://github.com/openclaw/openclaw/actions/runs/26498211086
·package acceptance smoke: https://github.com/openclaw/openclaw/actions/runs/26499133359
·npm Telegram beta E2E: https://github.com/openclaw/openclaw/actions/runs/26499800625

v2026.5.26-beta.1pre-release2026-05-26

openclaw 2026.5.26-beta.1

GitHub ↗

Highlights

·Faster replies and startup: visible reply delivery now separates user-facing sends from slower follow-up work, command/model/plugin metadata is reused on hot paths, and Gateway startup avoids repeated plugin, channel, session, usage-cost, and filesystem scans.
·Better voice and Talk: realtime Talk runs can be inspected, steered, cancelled, or followed up from Web UI and Discord voice; wake-name handling is more tolerant without letting ambient speech trigger agents.
·More channels are production-ready: Telegram keeps typing/progress context and forum topics, iMessage handles attachment roots and duplicate local Messages sources, WhatsApp restores group/media behavior, Discord improves voice playback and model picking, and Signal/iMessage get reaction approvals.
·Safer agents: Codex app-server auth, compaction, source replies, sandbox path handling, and usage-limit recovery are more robust; OpenAI-compatible providers avoid empty-tool and malformed payload failures.
·More reliable replay and installs: legacy tool results, subagent spawn payloads, stale lock ownership, Windows stack-heavy startup, macOS restart validation, and Docker package preparation all fail less surprisingly.
·Better install/update/release confidence: Alpine installs, stable update channels, Docker/package timeouts, Windows/macOS proof lanes, Testbox/Crabbox delegation, and plugin publish checks all got hardened.
·New observability: Activity tab, gateway secret-prep traces, tool/model stream progress, OpenTelemetry LLM spans, release performance evidence, and richer missing telemetry signals make failures easier to inspect.

Changes

·Transcripts: add core transcript capture and source-provider support for transcript-backed meeting summaries, including the renamed Transcripts docs and CLI surface.
·Auth: add named model login profiles and supported credential migration for Hermes, OpenCode, and Codex auth profiles, with explicit opt-out and non-interactive controls. (#85667)
·Diagnostics: trace gateway secret preparation, classify skill/tool usage, surface model stream progress, add OpenTelemetry LLM content spans, and expose alertable telemetry for blocked tools, failover, stale sessions, liveness, oversized payloads, and webhook ingress. (#83019, #80370, #86191)
·Channels: add Signal reaction approvals, iMessage thumb approval reactions, and WhatsApp thumb approval reaction support so mobile approval flows work without textual `/approve` commands. (#85894, #85952, #85477)
·Agents/API: forward OpenAI sampling params through the Gateway and expose estimated context-budget status for active agent runs. (#84094)
·Android/iOS: add the Android pair-new-gateway action and improve mobile Talk mode surfaces, including iOS realtime Talk mode and Android offline voice/gateway recovery. (#86798, #86355)
·Performance: cache plugin metadata snapshots, package realpaths, stable gateway metadata, model cost indexes, channel resolution, usage-cost indexes, and session/auth hot-path facts so common Gateway and reply paths do less rediscovery. (#84649, #85843, #86517, #86678)
·Voice: expose shared realtime turn-context tracking through the realtime voice SDK and reuse it for Discord speaker attribution and wake-name context recovery.
·Voice: reuse shared realtime output activity tracking in Google Meet command and node audio bridges, including recent-output checks for local barge-in detection.
·Voice: expose shared realtime output activity tracking through the realtime voice SDK and reuse it for Discord playback activity and barge-in decisions.
·Voice: expose shared realtime consult question matching, speakable-result extraction, and alias-aware forced-consult coordination through the realtime voice SDK, then reuse it in Gateway Talk, Voice Call, and Discord voice paths.
·Voice: share activation-name matching and consult-transcript screening through the realtime voice SDK so Discord, browser voice, and meeting surfaces can reuse one implementation.
·Cron: default `cron.maxConcurrentRuns` to 8 so scheduled automations and their isolated agent turns can make progress in parallel without explicit configuration.
·QA-Lab: add `qa coverage --match <query>` so focused proof selection can discover matching scenarios from existing metadata before running live or remote lanes.
·Discord/model picker: surface an alpha-bucket select (e.g. `A–G (12) · H–N (18) · O–Z (5)`) when the provider list or a provider's model list exceeds 25 items, so configs with `provider/*` wildcards stay one click from the right page instead of paginating through prev/next; falls back to numeric chunks when every item shares the same first letter.
·Control UI: add an ephemeral Activity tab for sanitized live tool activity summaries without persisting raw telemetry. Fixes #12831.
·Build: include `ui:build` in the `full` and `ciArtifacts` profiles of `scripts/build-all.mjs` so `pnpm build` always rebuilds `dist/control-ui` after `tsdown` cleans `dist`, removing the second-command requirement and the missing-asset failure mode for source/runtime installs and CI artifact uploads. (#85206)
·iOS: improve Talk mode with direct realtime voice sessions, compact toolbar status, and responsive voice waveform feedback. (#86355)
·Media: replace the Sharp image backend with Rastermill for metadata, resizing, EXIF orientation, and PNG alpha-preserving optimization so OpenClaw no longer installs Sharp or the WhatsApp Jimp fallback for image processing. (#86437)

Fixes

·Reply/perf: reduce visible reply delivery latency by preserving Telegram typing/progress context, lazy-loading slash-command startup metadata, avoiding hot-path model hydration, flag-gating Codex profiler timing, deferring context compaction maintenance, and tracking delivery timing. (#86989, #86990, #86991, #86992, #86993, #86994)
·Reply/source delivery: keep TUI, Control UI, media, TTS, transcript, and Codex source-reply finals live without duplicate terminal events or stale replay artifacts.
·Agents/replay: repair legacy tool results before replay, preserve `sessions_spawn` transcript payloads, restore current guard checks, stage sandboxed workspace media, and keep duplicate transcripts tool display metadata from reappearing. (#82203, #86934, #87025)
·Codex: project newer OpenClaw chat history into resumed app-server threads and keep Codex turn timeouts inside the Codex runtime boundary so timeouts do not poison shared app-server clients or fall through to unrelated provider fallback. (#86677, #86476)
·Config/doctor/update: narrow profiled tool-section doctor repair, keep runtime-injected legacy web-search provider config out of user-authored config validation, and keep prerelease tags excluded from stable updater resolution. (#87030, #86818, #86559)
·CLI/Windows: add a Windows-only stack-size respawn for stack-heavy startup paths, default CLI logs to local timestamps, and validate timeout/banner TTY state more strictly. (#87031, #85387)
·Locking/security: require owner identity proof before stale plugin lock removal, memoize session lock owner arguments, and avoid writing default exec approval stores unless policy state actually changed. (#86814, #86964)
·Install/release: bound Docker package build, inventory, pack, and tarball preparation with process-group timeouts; pin shrinkwrap patch drift to the pnpm lock; harden macOS restart and dSYM packaging; and run release Docker/live timeout wrappers in the foreground so child processes cannot wedge gates.
·Telegram/network: treat `ENETDOWN` as a transient pre-connect network failure so Telegram sends, gateway unhandled-rejection handling, and cron network retries follow the same recovery path as sibling network outages. (#86762)
·Telegram: preserve inbound text entities, overlapping DM replies, account topic cache sidecars, outbound reply context, targeted bot-command mentions, durable group retry targets, forum topic names, and native progress callbacks. (#83873, #85361, #85555, #85656, #85709, #86299, #86553)
·iMessage: read image attachments from local Messages attachment roots, dedupe duplicate local Messages-source accounts, seed direct DM history, fix image/group media attachment commands, advance catchup cursors after live handling, and keep slash-command acknowledgements in the source conversation. (#82642, #85475, #86569, #86705, #86706, #86770)
·WhatsApp/QQ/Twitch/IRC/Slack: restore WhatsApp ack identity and group-drop warnings, make QQ Bot media respect `OPENCLAW_HOME`, serialize Twitch auth disconnects, store IRC channel routes canonically, and keep Slack downloaded files out of reply media. (#83833, #85309, #85777, #85794, #85906, #86318, #86697)
·Discord/voice: improve voice playback and wake replies, bucket large model picker menus, merge media captions into one message, route metadata through configured proxies, restore numeric channel sends, suppress self-reply echoes, and tighten wake matching without breaking fuzzy wake phrases. (#80227, #86238, #86487, #86571, #86595, #86601)
·Codex: preserve native web-search metadata, keep oversized native thread reuse, bridge CLI API-key auth into the app server, preserve sandbox bootstrap path style, recover context-window prompt errors, honor yolo approval policy, disable native thread personality, and route compaction through Codex auth. (#85378, #85542, #85891, #85909, #86408)
·Agents/runtime: enforce session lock max-hold reclaim, release embedded-attempt locks on all exits, treat aborted subagent runs as terminal, avoid runtime model hydration on hot paths, disclose scoped session list counts, derive overflow budgets from provider errors, and keep fallback errors scoped to the active model candidate. (#70473, #85764, #86014, #86134, #86427, #86944)
·Config/update/doctor: retry config recovery after failed backup restore, skip shell env fallback on Windows, exclude prerelease tags from the stable git channel, support deep config edits, warn instead of aborting on unreadable cron stores, prune stale bundled plugin paths, and avoid duplicate restart prompts when the Gateway is already healthy. (#85739, #85787, #86060, #86260, #86384, #86533)
·Install/release: support Alpine CLI installs and runtime floors, avoid npm `min-release-age` installer failures, bound npm/package/Docker install phases, restore config parent ownership in Docker, seed Docker lockfile package tarballs before prune, and make release/plugin prerelease checks fail closed instead of hanging or false-greening. (#85491)
·Security: avoid printing Gateway tokens in Docker, validate plugin model-pattern regexes safely, escape transcript metadata field names, harden session allowlist glob matching, audit Claude permission overrides under YOLO, and require explicit allow for ACP auto approvals. (#85849, #85934, #86046, #86557)
·Media/images: replace Sharp with Rastermill, keep EXIF normalization best-effort, normalize HEIC/HEIF before image descriptions, route Codex image API keys through OpenAI, preserve image compression metadata, and auto-scale live tool result caps. (#85776, #86037, #86437, #86857, #86923)
·Memory: prevent semantic vector indexes from silently degrading when embeddings are unavailable, stop doctor OOMs on large session stores, preserve sidecar hooks/artifacts, write fallback dream diaries, use CJK-aware dreaming dedupe, and avoid per-file watcher FD fan-out. (#80613, #82928, #85060, #85704, #85967, #86701)
·Agents/sessions: include visibility metadata on restricted `sessions_list` results so scoped counts are clearly reported without widening access or exposing hidden-session counts. (#86944)
·Gateway/DNS: validate wide-area discovery domains before deriving zone paths or writing zone files, so invalid `discovery.wideArea.domain` and `dns setup --domain` values fail with a DNS-name diagnostic instead of falling through to unrelated configuration errors.
·Agents/BTW: route fallback side-question streams through the embedded stream resolver so Anthropic-compatible MiniMax requests use the same capped transport as normal chat. (#86312)
·Telegram: treat `/command@TargetBot` bot-command entities as explicit mentions for the addressed bot so `requireMention` groups no longer drop targeted commands or captions. Fixes #84462. (#86553)
·CI: bound Docker/Bash E2E tarball npm installs with `OPENCLAW_E2E_NPM_INSTALL_TIMEOUT` so package, onboarding, plugin, and upgrade lanes fail instead of hanging on a stuck npm install.
·CI: keep `OPENCLAW_TESTBOX=1 pnpm check:changed` delegating to Blacksmith Testbox through Crabbox without forwarding local Testbox or worker env into the remote command.
·CI: send KILL after the TERM grace period for manual checkout fetch timeouts so stuck Testbox and workflow checkout retries cannot hang behind a wedged `git fetch`.
·CI: send KILL after the TERM grace period for Bun global install smoke command timeouts so trapped `openclaw` child processes cannot wedge the scheduled install smoke.
·iMessage: thread current channel/account inbound attachment roots into the image tool so iMessage-saved attachments under `~/Library/Messages/Attachments` (including the wildcard `/Users/*/Library/Messages/Attachments` root) are read through the existing inbound path policy instead of being rejected as `path-not-allowed`. Literal `localRoots` stays workspace-scoped. Fixes #30170. (#86569)
·QQ Bot: respect `OPENCLAW_HOME` for outbound media path resolution so `<qqmedia>` sends no longer silently fail when `HOME` and `OPENCLAW_HOME` differ (Docker / multi-user hosts). Persisted QQ Bot data (sessions, known users, refs) stays anchored on the OS home for upgrade compatibility. Fixes #83562.
·Update: report the primary malformed `openclaw.extensions` payload error without adding a duplicate missing-main diagnostic. (#86596)
·Control UI: keep host-local Markdown file paths inert while preserving app-relative links. (#86620)
·Gateway: dampen repeated unauthenticated device-required probes per URL while preserving explicit-auth and paired recovery paths. (#86575)
·IRC: store inbound channel routes with the canonical `channel:#name` target and join transient channel sends before writing. (#85906)
·Usage: surface unknown all-zero model pricing as missing cost entries instead of a confident `$0` total. (#85882)
·Agents/Codex: honor yolo app-server approval policy only for the full `never` plus `danger-full-access` case. (#85909)
·Gateway/Gmail: clear Gmail watcher renewal intervals on re-entry so hot reloads do not leak lifecycle timers. (#82947)
·Logging: exit cleanly on broken stdout/stderr pipes without masking existing failure exit codes. (#80059)
·Gateway/security: escape transcript metadata field names while extracting oversized session line prefixes. (#85934)
·Plugins/security: validate manifest model pattern regexes with the safe-regex compiler so unsafe patterns are ignored before matching. (#86046)
·Discord: route gateway metadata REST lookups through the configured Discord proxy so proxied accounts do not fall back to direct `discord.com` connections before opening the WebSocket. Fixes #80227.
·Agents/media: hydrate current-turn image attachments from filename-derived MIME types so active vision can see generated or forwarded images whose source omitted an image content type. (#84812)
·Agents/fs: point workspace-only scratch-path guidance at in-workspace temp directories while keeping host-root writes rejected by the tool guard. (#86501)
·Agents/media: keep async cron media completions scoped to their run session while preserving direct delivery for stale generated-media success and failure notifications. (#86529)
·Gateway: emit plugin `session_end`/`session_start` hooks when `agent.send` rotates or replaces a session id, keeping hook lifecycle state aligned with `sessions.changed` notifications. Fixes #83507. (#85875)
·OpenShell/SSH: reject malformed generated exec commands before sandbox/session setup so unresolved workflow placeholders fail fast instead of reaching the remote shell. Fixes #72373.
·Google: stop normalizing `gemini-3.1-flash-lite` to the retired preview endpoint and update Flash Lite alias guidance to the GA model id. Fixes #86151. (#86240)
·Installer: make Alpine apk installs cover Git, verify the Node runtime floor, try `nodejs-current`, and report Alpine version guidance when repositories only provide older Node packages.
·Agents/status: prefer the active Claude CLI OAuth auth label over an unused Anthropic env API-key label for equivalent runtime aliases. Fixes #80184. (#86570)
·Agents/media: send direct fallback for generated media still missing after an active requester wake fails. (#85489)
·Agents: derive overflow compaction budgets from provider-reported and synthetic over-budget token counts so confirmed context overflows compact before retrying. (#70473)
·Agents/Codex: recover Codex context-window prompt errors through overflow compaction and surface reset guidance when recovery is exhausted. (#85542)
·Agents/Codex: allow Codex app-server runs to bootstrap from `CODEX_API_KEY` or `OPENAI_API_KEY` when no Codex auth profile is configured.
·Agents/Codex: keep selected Codex runtime routing on OpenAI-Codex while preserving direct OpenAI API-key compaction fallback. (#86408)
·Agent transcript: include OpenClaw agent session logs when finding local transcript candidates.
·Crabbox: bootstrap raw AWS macOS shell commands wrapped in absolute `time` paths so RSS probes can run Node and pnpm on fresh macOS runners.
·Crabbox: bootstrap raw AWS macOS shell commands even when setup statements precede Node or pnpm usage.
·TUI/local: skip unnecessary secret resolution, gateway model catalog loading, bootstrap, and skill scans in explicit local-model runs so startup reaches the model request faster.
·Sessions/doctor: load large session stores without clone amplification during read-only doctor checks and reclaim stale `sessions.json.*.tmp` sidecars. Fixes #56827.
·Tests: clean successful plugin gateway gauntlet isolated temp roots while keeping an explicit preservation switch for failed/debug runs.
·Plugins/perf: reuse derived plugin metadata snapshots for the lifetime of the process so reply-time skill setup no longer rescans plugin metadata on every turn.
·Discord/OpenAI voice: keep wake-name master consults using the current speaker context after ignored ambient transcripts and shorten the default capture silence grace.
·Doctor: skip redundant Gateway restart prompts when a recent supervisor restart leaves the Gateway healthy. Fixes #86518. (#86533)
·Cron: restore suspended cron lanes to the configured/default concurrency instead of falling back to one after quota or circuit-breaker auto-resume.
·Gateway: keep session-only Control UI tool-start mirrors flowing during diagnostic queue pressure instead of silently dropping non-terminal tool updates.
·Agents/memory: return optional not-found context for missing date-only daily memory reads instead of logging benign first-run `ENOENT` failures. Fixes #82928.
·Discord: merge streamed text captions into following media block replies so captions and attachments send as one message. (#86487)
·Gateway: avoid sending duplicate tool-event frames to Control UI connections that are subscribed by both run and session.
·Discord/OpenAI voice: accept broader edge-position fuzzy wake-name transcripts while keeping ambient speech gated.
·Discord/OpenAI voice: accept longer leading wake-name mistranscripts such as "Open Club" for OpenClaw.
·Agents/OpenAI-compatible: stop ModelStudio-compatible chat requests before sending system/tool-only payloads that have no usable user or assistant turn. (#86177)
·Gateway/plugins: reuse plugin package realpath checks while building installed plugin indexes so startup avoids repeated filesystem resolution work.
·Kilo Gateway: send string `stop` sequences as arrays so Kilo accepts OpenAI-compatible chat completions. (#86461)
·Discord/OpenAI voice: accept leading fuzzy wake-name transcripts such as "Monty" or "Moti" for a Molty agent while keeping ambient speech gated.
·Media understanding: convert HEIC and HEIF images to JPEG before image description providers run so iPhone photos work in direct and configured image-description flows. (#86037)
·Agents: release embedded-attempt session locks from outer teardown so post-prompt exceptions cannot wedge later requests behind `SessionWriteLockTimeoutError`. Fixes #86014.
·Discord/OpenAI voice: rotate Realtime sessions at provider max duration without logging the expected session-expiry event as an error.
·Sessions: skip metadata-only entries during QMD-slugified session lookup so one incomplete row does not block transcript hit resolution. (#86327)
·Agents/media: derive bundled plugin local-media trust from plugin tool metadata instead of importing the full plugin registry on subscription paths. (#84409)
·Image tool: keep config-backed custom-provider API keys usable for auto-discovered vision models, including deferred image-tool execution without env keys or auth profiles. (#85733)
·Memory/local embeddings: run local GGUF embeddings in an isolated worker sidecar and degrade to configured fallback or keyword search on worker failure so native embedding crashes do not take down the Gateway. (#85348)
·Gateway: clear the runtime config snapshot before `SIGUSR1` in-process restarts so config changes survive the next gateway loop. (#86388)
·Models: show OAuth delegation markers as configured `models.json` auth while keeping runtime route usability checks strict. (#86378)
·Cron: seed active scheduled and manual cron task rows with a progress summary so status surfaces do not look blank while jobs run. (#86313)
·Cron: preserve unsupported persisted cron payload rows during routine store writes while keeping those rows non-runnable. Fixes #84922. (#86415)
·Updater: exclude prerelease git tags from stable channel resolution so source updates do not check out newer alpha/rc/preview/canary tags. (#86260)
·Security/Audit: flag webhook `hooks.token` reuse of active Gateway password auth in `openclaw security audit` while keeping password-mode startup compatibility. (#84338)
·QQBot: derive the outbound reply watchdog from configured agent and provider timeouts so slow local model replies are not cut off at five minutes. Fixes #85267. (#85271)
·Agents/heartbeat: stop heartbeat turns after the first valid `heartbeat_respond` so repeated response loops do not burn tokens. (#86357)
·Tasks: keep retained lost tasks out of default status health counts, explain their cleanup window during maintenance, and prune lost task records after 24 hours instead of the general 7-day terminal retention.
·Memory-core: keep REM dreaming focused on live light-staged memories and mark staged entries as considered so old recall history no longer dominates fresh candidates. (#86302)
·Memory: abort sync instead of downgrading an existing semantic vector index to FTS-only when the configured embedding provider is temporarily unavailable. (#85704)
·Telegram: propagate forum topic names through the account-scoped topic cache for native command context and topic create/edit actions. (#86299)
·Slack: keep downloaded read-only files out of reply media so Slack file reads do not echo files back to the conversation. (#86318)
·Cron: accept leading-plus relative durations such as `+5m` for one-shot `--at` schedules. (#86341)
·Agents/media: preserve async-started media tool metadata so background generation starts no longer surface generic incomplete-turn warnings while replay stays unsafe. (#85933)
·Docker E2E: dedupe scheduler lane resources so npm/service package lanes are not over-counted and serialized unnecessarily.
·QA/diagnostics: add a collector-backed OpenTelemetry smoke lane, make the OTLP payload leak check scenario-aware, and keep source QA builds from failing on optional dependency imports resolved through pnpm's temp module path.
·Crabbox: bootstrap Git metadata for sparse remote changed gates so raw synced workspaces can run `pnpm check:changed` from the intended diff.
·xAI/LM Studio: avoid buffering ordinary bracketed or `final` prose until stream completion while watching for plain-text tool-call fallbacks.
·Doctor: warn and continue when the cron job store exists but cannot be read so later health checks still run. Fixes #86102. (#86384)
·Discord: suppress a bot's previous reply body and referenced media from prompt context when a user replies to that bot message, while keeping reply metadata for routing. (#86238)
·Discord: restore bare numeric channel IDs for outbound message-tool sends while keeping explicit DM targets unambiguous. (#86571)
·Docker E2E: avoid rebuilding the Control UI twice while preparing the shared OpenClaw package tarball for package-backed scenario runs.
·Tests: avoid rebuilding the Control UI twice during the installer Docker smoke now that `pnpm build` includes `ui:build`.
·Tests: give QA config mutation RPCs enough native Windows budget to finish gateway config writes and restart settle after hot scenario runs.
·Tests: keep the gateway restart-inflight QA scenario focused on restart recovery on native Windows by allowing expected embedded prompt handoff errors and using the Windows-safe timeout budget.
·QA-Lab: make the synthetic OpenAI provider honor generic `reply exactly:` directives after required kickoff reads so restart-recovery scenarios do not fall through to generic repo-summary prose.
·Gateway: abort active `agent` RPC runs during forced restart shutdown so stale in-process turns cannot keep writing a session after the Gateway lifecycle restarts.
·Crabbox: sync clean sparse worktrees through a temporary full checkout even when reusing an existing lease so tracked build-time files are not omitted.
·Build: route `scripts/ui.js` through the shared pnpm runner and keep Control UI chunking helpers in sparse-included source so native Windows Corepack builds can produce `dist/control-ui`.
·Tests: give the memory fallback QA scenario enough turn budget to exercise native Windows gateway runs instead of failing on the client timeout while the mock agent is still dispatching.
·Tests: collect QA gateway CPU/RSS metrics on native Windows and give the channel baseline enough turn budget to report slow gateway runs instead of timing out before proof.
·Install/update: bypass npm `min-release-age` policies with `--min-release-age=0` instead of `--before` so hosted installers keep working on npm versions that reject the combined config. (#84749)
·Diagnostics: reclaim wedged session lanes when stale active-run bookkeeping blocks queued work despite no forward progress. Fixes #85639.
·WebChat: keep message-tool replies visible in the chat while still summarizing internal tool results for the model. Fixes #86347.
·Gateway/perf: fail startup benchmark samples when the Gateway process exits before benchmark teardown, including signal deaths after readiness probes.
·Gateway/perf: fail restart benchmark samples when the Gateway exits before benchmark teardown, including clean exits and signal deaths after successful restart probes.
·Agents/tests: keep model catalog visibility on static selection helpers so catalog visibility checks avoid the broad model-selection barrel import.
·Agents/commitments: serialize commitment store load-modify-save writes so concurrent heartbeat and CLI updates no longer lose dismissal, sent, or attempt state. (#81153)
·xAI/LM Studio: promote plain-text tool-call fallbacks into structured tool calls and strip leaked internal tool syntax before user-facing delivery. (#86222)
·CLI: suppress benign self-update version-skew warnings during package post-update finalization.
·Gateway/perf: tighten restart and startup benchmark failure handling so long profiling runs, failed probes, and fresh Linux runners no longer produce false passing or `n/a` results.
·Checks: keep intentional Knip unused-file findings optional so full CI and sparse proof workspaces stay aligned.
·Docker: restore writable `~/.config` in runtime images. Fixes #85968.
·Plugin SDK: keep legacy root diagnostic subscriptions connected when built plugin SDK aliases resolve diagnostic helpers through a separate module graph.
·Diagnostics: export alertable OTel and Prometheus signals for blocked tools, model failover, stale sessions, liveness warnings, oversized payloads, and webhook ingress while fixing shared OTLP endpoints with query strings.
·Tests: normalize macOS canonical temp paths in exec allowlists, fs-safe trash assertions, installed plugin matching, Telegram topic-name stores, and built ACPX MCP server expectations so native macOS proof runners cover the intended behavior.
·Codex/app-server: preserve message-tool-only source reply delivery mode on active runs so sub-agent completion wakeups can steer the active Codex turn instead of being rejected. (#86287)
·Tests: sample the Windows kitchen-sink RPC gateway directly and serialize RSS probes so native runs keep the memory guard active.
·Tests: normalize bundled plugin lifecycle probe paths and state-root lookup so native Windows release sweeps accept valid packaged plugin installs.
·Agents/Claude CLI: route live native Bash permission requests through OpenClaw exec policy so Claude turns no longer stall on `control_request`, and document that OpenClaw exec policy is authoritative. Fixes #80819. (#86330, from #81971)
·Security audit: warn when YOLO OpenClaw exec policy overrides a restrictive raw Claude `--permission-mode` for managed live sessions. (#86557)
·Config: keep benign legacy metadata write anomalies out of default doctor and config command output while preserving explicit anomaly logging for diagnostics.
·Codex: log when implicit app-server `never` approvals are promoted for OpenClaw tool policy, including whether the trigger was a `before_tool_call` hook or trusted tool policy.
·Codex harness: make subscription usage-limit errors without reset times explain that OpenClaw cannot determine the reset and point users to wait until Codex is available, use another Codex account, or switch to another configured model/provider.
·Google Vertex: support production ADC modes such as Workload Identity Federation, service-account credentials, and metadata-server ADC for the native Vertex transport. (#83971)
·Telegram: route normal `[telegram][diag]` polling diagnostics through `runtime.log` while keeping non-diag warnings and persistence failures on `runtime.error`, so healthy polling startup no longer looks like an error. Fixes #82957. (#82958)
·Providers/Ollama: strip inline Kimi cloud reasoning prefixes from streamed and final visible replies while keeping ordinary Kimi answers append-only. (#86286)
·Gateway: require Talk secret authority before setup-code handoff can include Talk secrets. (#85690)
·Agents: keep fallback error reporting scoped to the active model candidate so stale prior-provider quota/auth text is not reported for later fallback attempts. (#86134)
·iMessage: dedupe watcher startup when `channels.imessage.accounts` lists both `default` and a named account that point at the same local Messages source, so the gateway no longer spawns two `imsg rpc` processes or doubles inbound replies; the dedupe is scoped to watcher startup, leaving duplicate accounts addressable for outbound sends, status, and capability listings, and `openclaw doctor` flags the redundant account with a rebinding hint. Fixes #65141. (#86705)

v2026.5.25-beta.1pre-release2026-05-26

openclaw 2026.5.25-beta.1

GitHub ↗

Beta 1 late fixes

·iMessage: thread current channel/account inbound attachment roots into the image tool so iMessage-saved attachments under `~/Library/Messages/Attachments` (including wildcard roots) are read through the existing inbound path policy instead of being rejected as `path-not-allowed`. Fixes #30170. (#86569)
·iMessage: dedupe watcher startup when `channels.imessage.accounts` lists both `default` and a named account pointing at the same local Messages source, preventing duplicate `imsg rpc` processes and doubled inbound replies while leaving duplicate accounts usable for outbound sends/status. Fixes #65141. (#86705)
·Codex: preserve sandbox bootstrap path style when remapping workspace instruction files across host and sandbox paths.

Fixes

·Installer: let the local-prefix CLI installer use Alpine's `apk` Node.js, npm, and Git packages on musl Linux instead of downloading glibc Node tarballs that fail `node:sqlite`.
·Checks: prefilter tracked conflict-marker scans so changed checks avoid reading every repository file on clean runs.
·Plugins: allow linked local plugin paths to probe TypeScript source entries without requiring compiled package output, restoring source-checkout plugin development on native Windows.
·CLI: route source-checkout build output to stderr before launching OpenClaw commands so stale local builds do not corrupt `--json` stdout.
·Installer: install Node.js through `apk` on Alpine Linux instead of falling through to the NodeSource package-manager path.
·Agents/perf: cache manifest-backed CLI provider descriptors and fallback provider resolution so model fallback retries avoid repeated bundled provider runtime scans while still invalidating across plugin reloads.
·Installer: detect musl Linux shells such as Alpine as Linux instead of rejecting them before npm install.
·Windows: run direct Node package scripts with env overrides through a cross-platform launcher so gateway, TUI, Docker-all, generated-module formatting, and optional Discord native opus installer entrypoints work on native Windows.
·Tests: run Vitest import timing entrypoints through a Node wrapper so native Windows package scripts can collect import diagnostics.
·Control UI: split large build-time runtime dependencies into stable chunks so Linux/Docker install and package builds stay below the app chunk warning threshold.
·Tests: run `test:max` and `test:changed:max` through a Node wrapper so high-worker Vitest entrypoints work on native Windows.
·Tests: retry transient loopback HTTP resets in the kitchen-sink RPC walk so native Windows readiness probes do not fail after the gateway is already ready.
·Tests: run `test:serial` through a Node wrapper so targeted serial Vitest commands work on native Windows.
·Tests: normalize Vitest config path assertions so the infra config suite runs on native Windows paths.
·Installer: avoid the incompatible generated `--before` install filter when raw npm `min-release-age` config is present. (#85491)
·Agents/MCP: bound bundled MCP `tools/list` catalog discovery so hung MCP servers do not block session tool materialization. (#85063)
·Channels/iMessage: recover malformed anchorless group watch payloads by GUID before debounce/routing, and drop unrecoverable payloads instead of replying to the sender DM. Fixes #84470. Refs #84503.
·Channels/iMessage: advance the startup catchup cursor from live-handled rows after a completed catchup pass, including rows received while catchup is still running, so restarts do not replay them. (#85475)
·Tests: mount the shared Windows command helper into bare Docker E2E harness containers so published upgrade-survivor config walks can start on Linux.
·Tests: keep the plugin binding command escape Docker smoke focused on its intended Vitest cases and skip source-only install lifecycle scripts.
·Tests: let the generic plugin install E2E assertions use a configurable temp root and Windows home-relative install paths.
·Tests: keep kitchen-sink plugin assertion fixtures on a configurable temp root so native Windows runs no longer skip full-surface diagnostic coverage.
·Tests: fail Gateway startup benchmarks when a child startup never produces ready probes or process metrics instead of reporting all `n/a` samples as passing.
·Config/secrets: allow exec SecretRef ids to include `#` selectors so AWS-style `secret#json_key` ids validate consistently. (#80731)
·Tests: keep the Telegram user credential helper on platform temp and path APIs so native Windows credential export and restore commands do not write through POSIX-only paths.
·Installer: include the optional verify phase in the progress counter so `--verify` shows `[4/4] Verifying installation` instead of `[4/3]`.
·Crabbox: let the wrapper find a sibling Crabbox checkout from linked Git worktrees so Codex worktrees can run remote gates without a PATH shim.
·CI: tolerate the standard `--` option separator in shared helper flag parsing so perf and test commands accept package-manager argument forwarding.
·Tests: preserve `--` passthrough arguments in live-media, live-shard, and extension batch harnesses so Vitest filters are not misread or silently ignored.
·Crabbox: default AWS macOS runner requests to on-demand capacity so EC2 Mac proof commands do not fail on the unsupported Spot market default.
·Tests: run upgrade-survivor config recipe commands through the Windows npm shim so native Windows package walks keep baseline config coverage.
·Image tool: use bundled Anthropic media limits when resolving image compression policy without provider-runtime hooks.
·Tests: fail the kitchen-sink RPC Docker walk when gateway RSS sampling is unavailable instead of silently disabling the per-process memory guard.
·Tests: suppress the current Rolldown plugin timing warning format in the Vitest wrapper so tiny focused runs do not drown useful stderr in repeated build-timing noise.
·Models/OpenRouter: use endpoint-specific OpenRouter context limits from `top_provider` metadata so provider-routed models no longer overstate available context. (#85949)
·Crabbox: sync clean sparse-checkout remote changed gates from a temporary full checkout with local-only commits overlaid as worktree changes so git-backed script checks can seed the runner repository.
·Agents: avoid loading bundled channel plugins while resolving completion delivery policy and queue defaults on subagent handoff paths.
·Tests: allow split Vitest config shards through the explicit-target preflight so CI shard jobs run their intended projects.
·Tests: make startup memory and startup bench smoke scripts build CLI startup artifacts when run from a fresh source checkout.
·iMessage: mark authorized slash-command turns as text-sourced commands so `/status`, `/new`, and `/restart` acknowledgements return to the source conversation. (#82642)
·Crabbox: install Corepack shims into the writable hydration `PNPM_HOME` so local AWS runner hydration no longer tries to overwrite `/usr/local/bin/pnpm`.
·Live tests: fail Gateway live model sweeps when selected coverage is lost to timeouts or stale high-signal filters instead of reporting false missing-profile coverage, and pin Docker OpenAI gateway coverage to the current `gpt-5.5` lane.
·Tests: fail Docker resource-ceiling checks when stats samples or configured limits are invalid instead of silently reporting zero peaks.
·Auth/Codex: emit a one-shot actionable `log.warn` from the embedded legacy Codex OAuth sidecar loader when the only available seed lives in the macOS Keychain, naming `openclaw doctor --fix` and macOS Keychain instead of letting the credential silently fall through to a downstream `No API key found for provider "openai-codex"`.
·Agents: fail closed when provider-less session models match multiple provider-prefixed runtime policies so CLI runtime routing no longer depends on config order. (#85970)
·Control UI/agents: keep collapsed tool rows readable without early ellipses, preserve raw expanded tool details, and make post-compaction AGENTS.md reinjection opt-in to avoid duplicated project context. Fixes #45649 and #45488.
·npm package: https://www.npmjs.com/package/openclaw/v/2026.5.25-beta.1
·registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.5.25-beta.1.tgz
·integrity: sha512-aTxlF5Cls7/JTg3sjalOiZTa62kVzulOcKlkjNDuVfF1iJlwoo+L3T9i+V/Byp2tjs2V3lhdQ71kc7QVlAu1dg==
·release branch/tag SHA: f5b52bddb50d48a803891f265dee1eb540ef4108
·focused local tests: `pnpm test src/agents/tools/image-tool.test.ts src/agents/tools/media-tool-shared.test.ts src/media/channel-inbound-roots.fast-path.test.ts extensions/imessage/src/accounts.test.ts extensions/imessage/src/channel.runtime.test.ts extensions/imessage/src/doctor.test.ts extensions/codex/src/app-server/run-attempt.test.ts test/scripts/package-acceptance-workflow.test.ts -- --reporter=dot`
·focused local type proof: `pnpm check:test-types`
·npm preflight: https://github.com/openclaw/openclaw/actions/runs/26443590151
·npm publish: https://github.com/openclaw/openclaw/actions/runs/26444459399
·note: beta publish intentionally used npm preflight proof only; full release validation is still required before stable/latest promotion.

v2026.5.24-beta.2pre-release2026-05-24

openclaw 2026.5.24-beta.2

GitHub ↗

Changes

·iMessage: support thumb-approval reactions — `👍` (Like tapback) resolves an approval as `allow-once` and `👎` resolves as `deny`, with the explicit-approver allowlist read from `channels.imessage.allowFrom`; `allow-always` stays on the manual `/approve <id> allow-always` text fallback. Mirrors the WhatsApp behavior from #85477.
·Gateway/perf: reuse process-stable channel catalog reads, avoid repeated bundled-channel boundary checks, and rotate gateway watch CPU profiles so benchmark runs do not accumulate unbounded artifacts.
·Gateway/perf: cache stable install-record, channel-catalog, bundled-channel, and Telegram session-store metadata during process-local hot paths to reduce repeated JSON and manifest reads.
·Gateway/perf: reuse immutable plugin metadata snapshots across startup, config, model, channel, setup, and secret metadata readers so hot paths avoid repeated plugin file stats and manifest registry reloads.
·Talk/realtime: let WebUI and Discord voice callers ask for active OpenClaw run status, cancel, steer, or queue follow-up work while a consult is still running. (#84231)
·Discord/voice: add realtime wake-name gating with agent-name defaults and raise profile bootstrap context budget for longer `USER.md`/`SOUL.md` files.
·Gateway/perf: lazy-load startup-idle plugin work, core gateway method handlers, and the embedded ACPX runtime so Gateway health and ready signals no longer wait on unused handler trees or ACPX probes.
·Gateway/perf: cache plugin SDK public-surface alias maps and skip irrelevant macOS Linuxbrew PATH probes so Gateway startup avoids repeated filesystem walks and slow missing-directory stats.
·Image tool: add adaptive model-aware image compression with an `agents.defaults.imageQuality` preference for choosing token-efficient, balanced, or high-detail media handling.
·Meeting Notes: add a source-only external meeting-notes plugin and SDK source-provider contract outside the core npm package, with auto-start capture config, manual transcript imports, read-only `openclaw meeting-notes` CLI access, and Discord voice as the first live source.
·Meeting Notes/Discord: release channel account startup before meeting-notes auto-capture, wait for the Discord voice manager during gateway boot, and stop plugin services before channel shutdown so voice capture state remains available during startup and cleanup.
·Docs/channels/config: add Signal `configPath`, Telegram wildcard topic defaults, local-time backup archive names, Termux home fallback, include-path validation, secret-scanner-safe placeholder guidance, Gemini CLI/Antigravity media guidance, and macOS VM auto-login guidance.
·Docs: clarify model-usage portability, Codex migration prerequisites, status bootstrap wording, thread-bound subagent limits, hook ownership, and config-preserving safety guidance.
·Docs: clarify README onboarding and Gateway startup paths, WhatsApp QR/408 recovery, cron output language prompts, skill advanced features, gateway upstream 403 troubleshooting, and plugin fallback override guidance.
·Docs: clarify context-pruning ratio bounds, local dashboard recovery, CLI env markers, remote onboarding token behavior, and Peekaboo Bridge permissions for subprocess agents.
·Docs: clarify browser CDP diagnostics, Plugin SDK allowlist imports, status-reaction timing defaults, queue steering behavior, limited-tool troubleshooting, cron HEARTBEAT handling, Telegram multi-agent groups, Bitwarden SecretRef setup, and EasyRunner deployments.
·CLI/models: let `openclaw models auth login` store a single returned provider auth profile under a requested `--profile-id`, and document named Codex OAuth profile setup. (#49315)
·Crabbox/Testbox: run clean sparse-checkout Testbox syncs from a temporary full checkout and route remote changed gates through Corepack pnpm.
·Docs: clarify IPv4-only Gateway BYOH binding, trusted-proxy scope clearing, Android pairing approval, macOS Accessibility grants, Zalo profile env vars, password-store SecretRef setup, and Chinese memory navigation.
·Docs: consolidate GLM under Z.AI, add the Upstash Box install guide and Gateway exposure runbook, clarify MEDIA directives, Copilot and Voyage setup, config path quoting, real behavior proof, and memory-file write guidance.
·Docs: clarify media provider credentials, Codex/OpenClaw code-mode boundaries, Slack and Telegram ack reactions, Feishu dynamic agents, secrets plaintext boundaries, memory guidance, and Chinese glossary terms.
·Packaging: exclude documentation images and assets from the npm tarball, reducing published package size without affecting runtime docs search or CLI behavior.
·Media understanding: stop auto-probing Gemini CLI and use Antigravity CLI only as a lower-priority image/video fallback after configured provider APIs.
·Diagnostics: emit sanitized `secrets.prepare` timeline spans for Gateway secret preparation so operators can distinguish secret startup latency without exposing provider names, secret ids, or secret values. (#83019)
·Diagnostics: export bounded skill usage metrics/spans and tool source/owner labels for core, plugin, MCP, and channel tool execution without exposing raw paths or session identifiers. (#80370)
·Agents/subagents: limit default sub-agent bootstrap context to `AGENTS.md` and `TOOLS.md`, keeping persona, identity, user, memory, heartbeat, and setup files out of delegated workers by default. (#85283)
·Maintainer skills: require clean autoreview before surfacing bug-sweep PR URLs and treat changelog-only conflicts as routine busy-main churn.
·Maintainer skills: exclude plugin SDK/API boundary work from `openclaw-landable-bug-sweep` so bugbash sweeps stay focused on small paper-cut fixes.
·QA-Lab/diagnostics: extend the OpenTelemetry smoke harness to prove trace, metric, and log export, and add first-class Prometheus and observability smoke aliases.
·Plugin SDK: add a generic channel-message poll sender so channel plugins can expose poll delivery without depending on channel-specific SDK facades.
·Plugin SDK/cron delivery: route cron delivery through the modern target resolver and outbound session-route APIs, deprecate parser-backed target helpers and `plugin-sdk/messaging-targets`, and move bundled callers to `plugin-sdk/channel-targets`.
·Crabbox: keep the local wrapper's provider validation synced with the installed Crabbox binary while preserving supported aliases such as `docker` and `blacksmith`. (#85302)
·Maintainer skills: add `openclaw-landable-bug-sweep` for producing five small, reviewed, CI-green OpenClaw bugfix PRs from issue/PR sweeps.
·Control UI/chat: add search and Load More pagination to the chat session picker, keeping initial session loads bounded while making older conversations reachable. (#85237)
·CLI/onboarding: start classic onboarding when bare `openclaw` runs before an authored config exists, while keeping configured installs on Crestodian. (#72343)
·Discord: allow configuring a bounded `agentComponents.ttlMs` callback registry lifetime for long-running component workflows, with per-account overrides and a 24-hour cap. (#84189)
·xAI/Grok: reuse xAI OAuth auth profiles for Grok `web_search`, thread active-agent auth through web search, add Grok model aliases, and let media providers declare default operation timeouts. (#85182)
·Plugin SDK: add row-level session workflow helpers and deprecate `loadSessionStore` so plugins can read and patch sessions without depending on the legacy whole-store shape. (#84693)
·Gateway/plugins: reuse a compatible Gateway startup plugin registry during dispatch so safe plugin dispatches avoid redundant registry loading. (#84324)
·Plugins/SDK: add a general `embeddingProviders` capability contract and registration API so embeddings can become a reusable provider surface outside memory-specific adapters.
·Dependencies: refresh provider, plugin, UI, and tooling packages, update `protobufjs` to 8.4.0 to clear the current npm advisory, and carry the Claude ACP completion patch forward to `@agentclientprotocol/claude-agent-acp` 0.36.1.
·Agents/tools: remove the old sender-owner tool gating path so configured tools stay visible for trusted sessions while command and channel-action auth still carry real sender identity.
·QA-Lab: add curated mock JSONL replay fixtures and first-drift reporting for runtime-parity audits. (#80323, refs #80176)
·QA-Lab: add a QA bus tool-trace visibility scenario for sanitized tool-call assertions.
·QA-Lab: replace generic evidence framing in seeded scenario prompts with concrete observed QA behavior.
·QA-Lab: list named scenario packs in the coverage report so personal-agent privacy coverage stays visible in audits.
·QA-Lab: list live transport lane membership in the coverage report so real transport checks stay separate from seeded qa-channel scenarios.
·Release/package: run package integrity checks before package acceptance lanes so public install/update validation fails before private QA assets can leak into the package.
·QA-Lab: include the optional 100-turn runtime parity soak in release-soak artifacts so long-run Codex/Pi transcript drift stays visible outside the default gate. (#80395)
·QA-Lab: add a live-only long-context progress watchdog scenario for Codex app-server timeout and stalled-run sentinels. (#80323)
·QA-Lab: tag gateway restart recovery and streaming final-integrity scenarios as live-only runtime parity lanes. (#80323)
·QA-Lab: add a personal-agent failure recovery scenario that checks honest partial status, retry boundaries, and local recovery artifacts. (#83872)
·QA-Lab: include an opt-in `update.run` package self-upgrade sentinel for destructive latest-package recovery checks.
·QA-Lab: add Codex plugin lifecycle and auth-profile fixture coverage for missing installs, pinned-version drift, first-turn install ordering, and doctor migration safety. (#80323, refs #80174)
·Models/perf: pre-warm the provider auth-state map at gateway startup so `/models` and every model-listing call short-circuits the per-provider plugin / external-CLI discovery on the hot path. Per-call cost drops from ~20 s to ~5 ms (~4,100×); the one-time startup warm resets and re-warms after hot reloads. (#84816)
·Release/security: ship the root npm package and OpenClaw-owned npm plugins with generated shrinkwrap, support bundled plugin runtime dependencies for suitable plugin tarballs, and require review for lockfile/shrinkwrap changes so published installs use locked dependency graphs.
·Tests/perf: isolate doctor core health check unit coverage from real skills/workspace discovery so `doctor-core-checks` no longer dominates unit perf while keeping one real skills-readiness smoke. (#84493)

Fixes

·Gateway/update: avoid fetching unrelated tags during dev-channel git updates so moved release tags do not block branch-based updates. (#84737)
·CLI/update: suppress the expected future-config warning while an old update parent hands off to the freshly installed post-core process.
·MiniMax: store OAuth token expiry as an absolute millisecond timestamp so OAuth profiles no longer appear expired on every request. (#83480)
·Agents/Anthropic: strip missing or blank thinking signatures for signed-thinking providers even when recovery supplies a narrow replay policy without signature preservation. Fixes #84430. (#84448)
·Agents/channels: send a visible notice when an aborted main session cannot be resumed after restart, including Telegram group targets. (#85805)
·Discord/voice: serialize overlapping voice joins, retry aborted startup readiness within the configured timeout, upgrade meeting-notes-only sessions to realtime when the normal follow join arrives, detach promoted meeting-notes ownership without leaving voice, and include `OpenClaw` in default realtime wake names.
·Gateway/restart: honor the configured restart drain budget for embedded runs and avoid spending the deferral timeout twice after forced restart timeouts. (#85708)
·Gateway/boot: run `BOOT.md` startup checks in an isolated boot session so gateway restarts do not overwrite the agent's main session mapping. (#85479)
·Meeting Notes: include a speaker-labeled transcript section in generated summaries so Discord group voice captures show who said each captured utterance.
·Discord/voice: recover stale realtime playback state when Discord stream-close/player-idle events do not arrive, and keep generated runtime plugin aliases available after postbuild rewrites.
·Discord/voice: keep realtime playback running when meeting notes attaches to an existing voice session or a realtime consult starts, and route realtime user transcripts into meeting notes.
·Config/secrets: preflight active runtime SecretRefs before root and include config writes persist, and roll back unchanged file/env state when post-write refresh fails. Fixes #46531. (#84454)
·CLI/models: preserve SecretRef-backed custom provider `apiKey` markers when `models status` regenerates `models.json`, avoiding resolved plaintext secrets on disk. Fixes #84632. (#84658)
·WhatsApp/auto-reply: deliver deferred media replies through the foreground reply fence so overlapping no-reply turns no longer hide already visible responses. (#85517)
·Sessions/security: replace agent-to-agent wildcard allowlist regexes with a precompiled linear matcher so cross-agent access checks avoid backtracking-prone patterns. (#85849)
·WebChat: keep the run-complete indicator in progress until deferred history replay renders the assistant reply, so Done no longer appears before response text. (#85374)
·Agents/tools: give timed-out or cancelled process trees a bounded SIGTERM cleanup window before SIGKILL while preserving tree-aware cancellation. Fixes #66399. (#85865)
·Agents/subagents: treat aborted subagent stop reasons as killed terminal failures so parent sessions get error announcements instead of silent success. Fixes #72293. (#85860)
·Agents/providers: clamp proxy-like OpenAI Chat Completions output caps against the final request payload so strict local/API-compatible servers no longer reject prompts that already consume part of the context window. Fixes #83086. (#85889)
·Agents/compaction: skip agent-harness preflight for provider-owned CLI runtime sessions so over-threshold Claude CLI sessions continue through normal compaction instead of failing on a missing harness. Fixes #84857. (#84878)
·Codex/app-server: keep successful native hook relays available through a short post-turn grace window so late Codex hook subprocesses can finish policy enforcement without clearing a replacement relay. (#83987)
·Control UI/config: save form-mode edits from the source config snapshot so runtime-only provider defaults like empty `models.providers.<id>.baseUrl` are not written back and rejected. Fixes #85831.
·Browser/existing-session: launch Chrome DevTools MCP with usage statistics disabled by default so its telemetry watchdog stays off unless an operator explicitly opts in. (#85886)
·Telegram: normalize legacy durable group retry targets before retry sends, polls, and pins so group retries keep using the real chat id. (#85656)
·Agents/PDF: route MiniMax PDF fallback policy through plugin metadata so MiniMax uses text extraction instead of VLM image fallback. (#85590, fixes #85575)
·CLI/plugins: tighten timeout, numeric option, media payload, permission, profile/TLS, plugin metadata, JSON, and remote URL handling; prevent stuck progress/app-server/IRC/Synology/Twitch waits; and keep imported chat history ordering stable.
·Telegram/config: suppress the missing `accounts.default` warning when `channels.telegram.defaultAccount` names a configured account that also sorts first. Fixes #83948.
·Telegram: serialize visible topic replies through core reply-lane admission so heartbeat and queued follow-up turns cannot continue ownerless or misroute responses. (#85709)
·WebChat: summarize internal message-tool source replies so tool cards no longer duplicate the visible reply body. (#84773)
·Gateway/WebChat: hide duplicate `gateway-injected` assistant rows when Cursor ACP already persisted the same `acp-runtime` reply. Fixes #85741.
·WebChat: scope the visible attachment button to its own composer file input so clicking Upload reliably opens the file picker. (#83952, fixes #47983)
·Gateway: preserve deferred lifecycle-error cleanup across later non-terminal events so provider timeouts can persist failed session state instead of leaving sessions stuck running. (#85256, fixes #63819)
·Gateway/update: stop treating inherited macOS `XPC_SERVICE_NAME` values as launchd supervision during update respawn, so GUI-spawned gateways use detached respawn instead of exiting for a missing LaunchAgent. Fixes #85224.
·Agents/subagents: report tool-only child progress during timeout summaries instead of showing no visible output.
·Telegram/ACP: preserve explicit `:topic:` conversation suffixes when inbound ACP targets do not carry a separate thread id.
·Browser/proxy: bypass the managed proxy for the exact local managed Chrome CDP readiness and DevTools WebSocket endpoints, so `openclaw browser start` works when the operator proxy blocks loopback egress. (#83255)
·Ollama: bypass the managed proxy for configured local embedding origins while keeping SSRF guardrails on unconfigured targets.
·OpenAI/images: route Codex API-key image generation through the native OpenAI Images API instead of the Codex OAuth streaming backend, avoiding 401s from valid API keys.
·Agents/OpenAI completions: omit empty tool payload fields for proxy-like OpenAI-compatible endpoints so strict vLLM-style servers accept tool-free turns. (#85835)
·Sandbox: keep workspace skill mounts read-only for remote container-cwd file operations and reject symlinked skill roots before creating protected overlays. (#85591)
·Scripts/Windows: route remaining QA, release, profile, and live-media `pnpm` launches through the managed runner so native Windows avoids brittle `.cmd` execution and shell-argv warnings.
·Release: align generated config/API baselines and the meeting-notes plugin version so release preflight stays green on native Windows.
·Install/Windows: run Git hook setup through a Node prepare helper so native Windows installs no longer print POSIX shell errors.
·Checks/Windows: chunk and serialize extension oxlint shards on native Windows so changed gates avoid Go-backed linter memory spikes.
·Release/Windows: run installed `openclaw.cmd` verification through explicit `cmd.exe` wrapping so npm prepublish/postpublish checks avoid Node shell-argv warnings.
·Release/Windows: run release-check npm pack/install/root probes through the shared npm runner so native Windows avoids bare `npm` lookup and `.cmd` shell-argv handling.
·Release/Windows: run cross-OS release check `.cmd` shims through explicit `cmd.exe` wrapping so native Windows install and gateway probes avoid Node shell-argv handling.
·Control UI/Windows: run i18n Pi, npm, and pnpm helper commands through explicit Windows runners so native Windows translation sync avoids brittle `.cmd` launches.
·Scripts/Windows: run the Z.AI fallback repro through the shared pnpm runner so native Windows avoids raw `.cmd` launches.
·Codex/Windows: run app-server protocol formatting through the shared pnpm runner so native Windows avoids raw `.cmd` launches.
·Plugins/Windows: run plugin npm package staging through the shared npm runner so native Windows release checks avoid bare `npm` lookup and `.cmd` shell-argv handling.
·Checks/Windows: route full `pnpm check` stage commands through the managed child runner so Windows avoids Node shell-argv deprecation warnings there too.
·Agents/fs: allow workspace-only host write/edit tools to write through in-workspace symlink directory parents while preserving outside-workspace symlink rejection. Fixes #84696.
·Checks/Windows: run managed child commands through explicit `cmd.exe` wrapping instead of Node shell mode with argv, avoiding Node 24 subprocess deprecation warnings during changed checks.
·Gateway: omit internal stream-error placeholder entries from agent prompt history so failed assistant turns are not replayed as model-authored text. (#85652)
·Sessions: enforce the session write-lock max-hold policy during lock acquisition so long-held locks can be reclaimed before the stale-lock window. (#85764)
·Sessions/status: preserve user-facing model, fallback, usage, and cost attribution when internal subagent handoff runs use fallback models. (#85726, fixes #85082)
·Install/update: honor `OPENCLAW_HOME` when deriving default dev checkout and installer onboarding paths, while keeping explicit `OPENCLAW_GIT_DIR` and `OPENCLAW_CONFIG_PATH` overrides authoritative. Fixes #54014.
·Models: prune retired Groq, GitHub Copilot, OpenAI, xAI, and old Claude catalog entries, with doctor migration to upgrade existing configs to current provider refs.
·Plugins/Gateway: treat non-empty return values from plugin gateway method handlers as successful responses so `openclaw gateway call` no longer times out after completed plugin work. Fixes #59470.
·Doctor/update: recognize junction-backed source checkouts as git installs by comparing canonical paths before showing package-manager update guidance. Fixes #82215.
·Channels: honor `/verbose on` for tool/progress summaries across direct chats, groups, channels, and forum topics while preserving quiet default behavior. (#85488)
·Update: keep the detached gateway restart handoff best-effort when the restart script process cannot be spawned. (#83892)
·Telegram: persist the prompt-context message cache through plugin state and record bot-authored replies after sends and draft streaming so later turns can include prior assistant replies without relying on the JSON sidecar. (#85231)
·Agents/subagents: keep Codex persona and user workspace files turn-scoped so native Codex subagents inherit only shared tool guidance by default. (#85811)
·CLI/skills: show an all-ready note with next-step commands when skill setup has no missing dependencies to install. (#85032)
·Microsoft Foundry: route DeepSeek V4 Pro and Flash models through the Foundry Responses API while keeping older DeepSeek models on their existing path. (#85549)
·Status/usage: show configured cost estimates for AWS SDK models in full usage output while keeping token-only usage replies cost-free. (#85619)
·Agents/OpenAI Responses: retry non-visible reasoning-only turns for OpenAI Responses API families instead of treating them as empty failed turns. (#85603)
·Directive tags: preserve message and content-part object identity when display stripping makes no directive-tag changes. (#85682)
·Telegram: send local `path`/`filePath` and structured attachment media from `sendMessage` actions instead of dropping them or sending text-only messages. (#85219)
·Sessions/status: show the estimated context budget when fresh provider usage is unavailable and clear stale estimates across session resets and compaction boundaries. (#84830)
·Gateway/config: pin relative `OPENCLAW_STATE_DIR` overrides to an absolute path at startup so later working-directory changes cannot retarget gateway state. (#52264)
·Checks/Parallels: make changed-lane scripts, shrinkwrap generation, and Parallels package smoke host commands run through native Windows-safe paths and `npm`/`pnpm` shims.
·Release/package: run npm release, prepublish, and postpublish verification through Windows-safe npm command shims so native Windows checks can execute `npm.cmd` instead of treating it as a binary.
·Agents/harness: pass CLI runtime aliases through harness selection so provider-owned CLI aliases no longer get rejected before reaching the right runtime. (#85631)
·Secrets: show the irreversible apply warning after interactive `secrets configure` confirmation so confirmed migrations still get the final safety prompt. (#85638)
·Agents/CLI output: ignore cumulative Claude `stream-json` result usage when assistant usage events are present, preventing inflated cache-read accounting. (#85625)
·CLI: keep `waitForever()` alive by leaving its keep-alive interval ref'd so the public helper no longer exits immediately with Node's unsettled-await code. (#85694)
·Agents/bootstrap: guard bootstrap name checks against missing file names so malformed bootstrap entries warn and truncate instead of crashing. Fixes #85523. (#85615)
·CLI/tasks: reject partially numeric `openclaw tasks audit --limit` values so audit limits must be real positive integers instead of accepting strings like `5abc`. (#84901)
·Status/diagnostics: bound deep Docker audit probes so `openclaw status --deep` reports slow container checks instead of hanging behind unbounded inspection. (#85476)
·Providers/Anthropic: migrate 1M context handling to GA-capable Claude 4.x models by sizing eligible models at 1M without the retired `context-1m-2025-08-07` beta, ignoring that retired beta in older configs, and preserving OAuth-required Anthropic beta headers. (#45613)
·Cron/Telegram: parse forum-topic delivery targets through the Telegram plugin instead of cron core, including `:topic:` and `:topicId` forms for announce delivery.
·Twitch: keep stale message-handler cleanup callbacks from removing newer handler registrations for the same account, preserving inbound message delivery after reconnects. Fixes #83888. (#85425)
·Control UI/chat: keep light-mode model, thinking, config, and agents select arrows visible without tiling background icons. Fixes #85713.
·Memory/LanceDB: expose public memory artifacts through the active memory provider bridge so memory-wiki imports durable memory files, daily notes, dream reports, and event logs without depending on memory-core internals. Fixes #83604. (#85060)
·Crabbox: keep AWS hydration compatible with local Actions replay by inlining the hydrate workflow's Node/pnpm setup instead of invoking repo-local composite actions.
·Agents/subagents: simplify native sub-agent completion handoff so children report their latest visible assistant result to the requester without using `message`, while keeping parent-owned message-tool delivery policy intact. Fixes #85070. (#85089)
·Docker setup: stop printing the Gateway bearer token in setup logs and printed follow-up commands.
·Gateway: defer channel account startup work until HTTP readiness and remove startup model prewarm, avoiding startup event-loop stalls and timer-delay warnings.
·Models/perf: reuse plugin metadata during models.json planning, keep bundled catalog augmentation manifest/static, and use static provider catalogs for metadata-only startup discovery so provider model normalization, auth discovery, and Gateway startup metadata do not reload broad plugin runtimes.
·Agents: let embedded compaction fallback retries proceed when PI-compatible candidates do not need agent harness plugin preparation.
·Agents/tools: honor configured custom provider API keys when deciding whether media, image-generation, video-generation, music-generation, and PDF tools are available. (#85570)
·StepFun: stop advertising stale generic API key auth choices so onboarding only offers runtime-backed Standard and Step Plan choices.
·Diagnostics: keep OpenTelemetry log bodies behind explicit content capture and scrub scoped agent-session keys from OpenTelemetry and Prometheus labels while preserving bounded queue-lane prefixes.
·Windows installer: fail Git checkout installs when `pnpm install` or `pnpm build` fails instead of writing a wrapper to a missing CLI build.
·Sessions: surface previous-transcript archive failures during `/new` rotation so disk rename errors are logged instead of silently hiding stranded transcript files. Fixes #81984. (#85586, from #82081)
·TUI/agents: mirror internal-ui message-tool replies into final chat output so message-tool-only agents remain visible in `openclaw tui`. Fixes #85538.
·Gateway/TUI: preserve source-reply metadata through reply normalization and emit message-tool-only agent replies over the live chat stream so `openclaw tui` renders Codex replies without waiting for a history refresh.
·Codex/TUI: keep long source-reply runs alive after Codex reasoning completes so delayed visible `message` calls can still reach `openclaw tui`.
·TUI: keep quiet active runs busy after the response watchdog notice instead of reopening the prompt and encouraging duplicate submissions while the backend turn is still running.
·Agents: preserve the latest assistant thinking blocks while stripping invalid replay signatures from older turns, and retry Anthropic thinking failures without thinking replay. Fixes #85557.
·Agents: keep parallel OpenAI-compatible tool-call deltas in separate argument buffers so interleaved tool calls no longer corrupt streamed arguments. (#82263)
·Telegram: avoid false pairing prompts after transient pairing-store read failures while preserving configured `allowFrom` and per-DM pairing authorization. (#85555)
·Memory/doctor: report missing or unusable QMD workspace directories as workspace failures instead of generic binary failures. (#63167)
·Debug proxy: record CONNECT client-socket errors and destroy the paired upstream socket so abrupt client disconnects no longer leak tunnel resources. (#82444)
·Diffs: continue hydrating later diff cards when one card fails so a single broken card no longer blanks the whole diff viewer. (#84775)
·Mac app: use the native settings sidebar window chrome so the sidebar toggle stays on the left and content no longer clips under oversized titlebar padding.
·QA-Lab/Codex: bundle auth/plugin fixture imports for flow scenarios and let terminal async media tools end Codex app-server turns without timing out. (#80397, refs #80323)
·WhatsApp: persist inbound message delivery state through plugin state before dispatch and delay read receipts until handler completion, so retryable failures can redeliver without adding a plugin-local disk cache.
·Gateway/agents: preserve fresh session overrides and metadata when stale cached agent-session entries race with store updates, so subagent model/provider overrides and routing policy survive concurrent writes. (#19328)
·Control UI/chat: keep chat session search inline with the session selector so the header no longer shows a duplicate standalone search row.
·Control UI/chat: collapse focused-mode header chrome and suppress hidden-header scroll updates so focus mode no longer jumps while scrolling.
·Codex app-server: restart the native app-server and retry once when server-side compaction times out, so preflight compaction stalls recover instead of failing every dispatch. (#85500)
·Restore Control UI gateway token pairing [AI]. (#85459)
·OpenAI video: honor configured provider request private-network opt-in for local/custom video endpoints so explicitly trusted mock and self-hosted providers are not blocked.
·OpenAI video: send uploaded video edit requests to the documented `/videos/edits` endpoint with a `video` file instead of posting MP4 references to `/videos`.
·Agents/channels: preserve message-tool delivery evidence through gateway agent completion handoffs so successful generated media sends are not followed by false failure messages.
·CLI/update: repair managed npm plugin `openclaw` peer links during post-core convergence and reject stale or wrong-target peer links before restart. (#83794)
·CLI/agents: default new omitted-account bindings to all accounts when the channel has multiple configured accounts, and clarify account-scope docs. (#49769)
·Codex app-server: let authorized `/codex` control commands such as `/codex detach` escape plugin-owned conversation bindings while keeping unknown or unauthorized slash text routed to the bound plugin. Fixes #85157. (#85188)
·Auto-reply/models: keep `/models` browse replies fast by sharing the bounded read-only catalog path with Gateway model listing. (#84735)
·Browser/Doctor: read macOS Chrome app bundle versions from `Info.plist` before spawning Chrome and extend the fallback version probe timeout, avoiding false cold-cache warnings from Gatekeeper latency. Fixes #85418.
·Codex app-server: disable native Code Mode when the effective exec host is `node` and keep OpenClaw `exec`/`process` available, so `/exec host=node` routes shell commands through the selected node instead of the gateway. Fixes #85012. (#85090)
·Agents: bound embedded auto-compaction session write-lock watchdogs to the compaction timeout instead of the full run timeout, so stuck compaction cannot hold the live session lock for the whole run window. (#84949)
·Gateway/agents: return phase-aware `agent.wait` timeout attribution and only cool auth profiles on provider-started timeouts. Refs #65504.
·Gateway/systemd: launch managed update handoff helpers in a transient user scope so systemd-supervised Update Now flows survive the gateway unit restart. Fixes #84068.
·Gateway: defer provider auth-state prewarm until after startup readiness so early gateway tool/session requests are not blocked by provider auth discovery. (#85272)
·Gateway/models: coalesce provider auth-state rewarms after auth-profile failures and log event-loop delay for warm/rewarm work, so provider auth bursts no longer stack full auth sweeps behind channel replies.
·Gateway/models: stop cancelled provider auth-state prewarms from continuing full provider sweeps, so reload and auth-failure bursts no longer keep startup busy.
·Agents/Codex: show the first plan update as a transient chat status notice without counting it as final assistant content.
·CLI/update: walk the macOS process ancestry and honor the inherited Gateway runtime PID before package updates stop the managed Gateway service, so nested in-band updater children can refuse instead of killing the LaunchAgent-supervised Gateway that owns them. Fixes #85120.
·Gateway/LaunchAgent: wait for launchd reload bootout to finish and fall back to kickstart when bootstrap races, so reload handoff does not leave the service deregistered. Fixes #84630. (#84641)
·Gateway/LaunchAgent: treat a concurrent launchd bootstrap as a successful restart when the service is already loaded, avoiding false macOS Gateway restart failures. Fixes #84721. (#84722)
·Gateway/service: include the active `openclaw` command bin directory in managed service PATH generation and doctor audit expectations for npm-global macOS installs. Fixes #84201. (#84475)
·Control UI/chat: disable the thinking selector for known non-reasoning models instead of showing duplicate Off choices. Fixes #84069.
·Memory: expand `~` in configured extra memory paths before resolving them, so home-relative folders are not treated as workspace-relative. Fixes #58026.
·Skills: treat `openclaw.os: macos` as Darwin when checking skill requirements, so macOS-only skills no longer report as missing on macOS hosts. Fixes #61338.
·Control UI/logs: strip ANSI escape sequences from displayed Gateway log messages so color codes no longer appear as raw text. Fixes #64399.
·Docker: pre-create the workspace and auth-profile config mount points with `node` ownership so first-run named volumes do not start root-owned. Fixes #85076.
·Telegram: pass configured markdown table mode through outbound markdown chunking so chunked sends render tables consistently. Fixes #85085.
·Diagnostics/OTel: drop snake_case diagnostic id attributes alongside camelCase ids so exported telemetry cannot leak run, session, message, chat, trace, or tool-call identifiers. (#72645)
·CLI/update: preserve managed Gateway service environment during package cutovers so macOS LaunchAgent repair/restart reads the pre-update service state instead of caller shell state. (#83026)
·Agents/providers: honor per-model `api` and `baseUrl` overrides in custom provider auth hooks and transport selection. Fixes #80487. (#80488)
·Gateway/restart: eager-load the lifecycle runtime before in-place upgrade signal handling so package replacement does not deadlock restart imports. (#84890)
·CLI/update: start managed Gateway update handoff helpers from a stable existing directory and tolerate deleted cwd/package roots during macOS LaunchAgent handoff. Fixes #83808. (#83875)
·Skills: watch each shared skill directory once across agent workspaces instead of once per agent, preventing file-descriptor exhaustion (`EMFILE`) that disposed bundle-mcp processes and stalled sessions on multi-agent gateways. Fixes #84968. (#85130)
·Release/security: keep generated npm shrinkwrap package versions inside the pnpm lock graph so published package locks cannot bypass pnpm dependency age and override policy.
·Cron: honor `cron.retry.retryOn: ["network"]` for common network error codes such as `EAI_AGAIN`, `EHOSTUNREACH`, and `ENETUNREACH`.
·Gateway chat: broadcast returned agent-run error payloads after an agent starts so ACP/WebChat clients receive terminal idle-timeout errors. Fixes #84945.
·Gateway chat display: preserve OpenAI-compatible `prompt_tokens`, `completion_tokens`, and `total_tokens` usage fields in sanitized chat history so llama.cpp sessions keep context counts. Fixes #77992.
·Dashboard/CLI: allow macOS browser launching through `open` even when SSH environment variables are present, while preserving Linux SSH no-display protection. Fixes #67088.
·Codex app-server: keep native web search observations out of mirrored chat transcripts while preserving available action query metadata in tool progress telemetry. Fixes #85109.
·OpenCode Go: strip unsupported Kimi reasoning replay fields before provider requests so repeated `kimi-k2.6` turns do not fail schema validation. Fixes #83812.
·Browser/CDP: add a WSL2 portproxy self-loop hint when Chrome DevTools endpoints accept connections but return an empty HTTP reply. Fixes #59209.
·Agents/tools: add bounded tool-policy audit log entries that identify which allow/deny rule removed tools or blocked a sandboxed tool call. Fixes #55801.
·CLI/logs: read implicit local Gateway logs through the passive backend client path so `openclaw logs --follow` does not register as a paired device, and use the active Linux systemd journal instead of stale configured-file fallbacks when live local RPC is unavailable. Fixes #83656 and #66841.
·Agents/OpenAI: preserve structured provider error code, type, and redacted body metadata on boundary-aware transport failures.
·Doctor/Codex: point native Codex asset warnings at the canonical `openclaw migrate plan codex` preview command. Fixes #84948.
·CLI/models: make `capability model auth logout --agent` remove auth profiles from the selected non-default agent store. Fixes #85092.
·Gateway/models: reuse prepared provider auth metadata during model-listing auth checks so repeated lookups avoid broad plugin discovery while preserving synthetic local auth.
·CLI/status: suppress systemd user-service setup hints when `openclaw status --deep` can already reach a running Gateway RPC service. Fixes #85094.
·CLI/devices: recover local approval when a same-device repair request replaces the request ID being approved.
·CLI/agents: retry transient normal-close Gateway handshakes before falling back to embedded `openclaw agent` execution.
·CLI/update: keep managed Gateway service stop/restart status lines out of `openclaw update --json` stdout so package-update automation can parse the JSON payload.
·Plugins: resolve OpenClaw plugin SDK subpaths for native external plugin runtimes without mutating package installs or broadening process-wide module resolution.
·Agents/OpenAI: preserve Responses and Chat Completions `reasoning_tokens` usage metadata without double-counting it in aggregate output tokens. (#85319)
·Control UI/chat: convert pasted `data:image/...;base64,...` clipboard text into an image attachment instead of dumping the payload into the composer. Fixes #62604.
·Providers/Gemini: strip fractional seconds from web-search time range filters so Gemini accepts freshness-bound search requests. (#85071)
·OpenAI Codex: preserve image input support for sparse `openai-codex/gpt-5.5` catalog rows. (#85095)
·CLI/models: add a piped or pasted API-key path for OpenAI Codex auth and warn when API keys are pasted into token-mode auth. (#85533)
·Telegram: dead-letter missing-harness isolated ingress failures so a poisoned spooled update no longer blocks later same-lane messages. Fixes #85470. (#85605)
·Plugins/discovery: strip `-plugin` package suffixes when deriving plugin id hints so package names line up with manifest ids. (#85170)
·Tlon: stop advertising a non-existent agent tool contract in the plugin manifest.
·Telegram: preserve fenced code block languages through Markdown rendering so Telegram receives `language-*` code classes. (#85209)
·Windows installer: run npm and Corepack command shims from a Windows-local directory so installs launched from WSL2 UNC paths do not fail before OpenClaw is installed.
·Windows updates: roll back git-backed updates to the previous checkout when dependency install, build, UI build, or doctor repair fails.
·Windows installer: persist user-local portable Git on PATH and activate the repo-pinned pnpm version for git-backed installs and updates.
·Windows installer: bootstrap a user-local portable Node.js when native Windows has no Node and no winget, Chocolatey, or Scoop, so first-run installs can continue on raw hosts.
·Windows installer: extract the downloaded portable Node.js directory with native `tar` before falling back to .NET zip extraction, avoiding PowerShell 5.1 archive and path-length failures.
·fix(integrations): enforce channel read target allowlists [AI]. (#84982)
·Agents/heartbeat: route single-owner `session.dmScope=main` direct-message exec and cron event wakes back to the agent main session so async completions no longer strand context in orphan direct-DM queues. Fixes #71581. (#83743)
·Agents/code-mode: expose outer code-mode `exec` source through the `command` hook alias with `toolKind`/`toolInputKind` discriminators so exec-shaped policies can distinguish code-mode cells. (#83483)
·Agents/code mode: return structured timeout and runtime-unavailable error codes for known worker failures. Fixes #83389. (#83444)
·QA-Lab: isolate multi-scenario suite workers when scenarios need startup config patches, preventing message-routing config from leaking into unrelated scenarios.
·QA-Lab: make the commitments heartbeat-target-none scenario request an immediate heartbeat instead of waiting for the next scheduled heartbeat.
·Codex/Plugin SDK: deliver Codex-native subagent completions through a generic harness task runtime so harness-backed plugins can mirror durable task lifecycle and completion delivery without Codex-specific SDK imports. (#83445)
·Gateway CLI: surface local post-challenge connect assembly failures immediately instead of waiting for the wrapper timeout. Fixes #68944. (#85253)
·Messages: strip unsupported web-search citation control markers from outbound replies before they reach WebChat or external channels. Fixes #85193. (#85204)
·Agents/exec: treat denied exec approvals as terminal instead of feeding them back into agent follow-up work, and recognize Chinese stop phrases in abort handling. Fixes #69386. (#85194)
·CLI/agents: abort accepted Gateway-backed `openclaw agent` runs on SIGINT/SIGTERM so cron and supervisor timeouts do not leave remote agent work alive. Fixes #71710. (#84381)
·Codex app-server: retry replay-safe stdio client-close turns once using structured failure metadata, while surfacing idle `turn/completed` timeouts instead of blindly replaying active shared-server turns.
·Codex app-server: reject command overrides that embed Node or package-manager arguments and point users to `appServer.args`, so Windows startup avoids shell parsing failures. (#84417)
·Agents/Copilot: drop unsafe GitHub Copilot Responses reasoning replay items before send so Telegram direct sessions no longer fail on overlong replay IDs. Fixes #85197. (#85198)
·UI: add accessible tooltips to the topbar color-mode buttons so System, Light, and Dark choices are labeled on hover and focus. (#85227)
·fix: constrain Windows task script names [AI]. (#85064)
·Control UI: keep the chat session picker from hiding older or cross-agent configured conversations while preserving the bounded configured-agent refresh. (#85211)
·Agents/Anthropic: preserve unsafe integer tool-call input values in streamed Anthropic tool-use JSON, preventing Discord-style IDs from being rounded before dispatch. Fixes #47229. (#83063)
·Agents/Codex: estimate tool-heavy prompt pressure at the LLM boundary before provider submission, so persistent sessions compact before overflowing context windows. (#85541)
·Agents/hooks: wait for local one-shot CLI and Codex `agent_end` plugin hooks before process cleanup so terminal observability flushes reliably. (#85007)
·Providers/Google: preserve Gemini 3 cron `thinkingDefault: "low"` when stale catalog metadata says `reasoning:false`, so scheduled runs keep provider-supported thinking instead of downgrading to off. (#85185)
·CLI/agents: allow `openclaw agent --session-key` to target explicit session keys, including agent-scoped legacy keys. (#85121)
·Auto-reply/ACP: wait for same-channel block reply delivery before starting tool work, while still honoring ACP dispatch aborts so stopped turns do not wait on slow channel sends. (#83722)
·Codex/ACP: mark required child-run completions that only report progress, omit a final deliverable, or fail requester delivery as blocked while preserving real final reports. (#85110)
·Channels: treat bare abort messages such as `stop`, `abort`, and `wait` as immediate control commands in inbound debounce paths so stop requests are not delayed behind pending message coalescing. (#83348)
·Channels/message tool: resolve configured external channel plugins during in-agent channel selection, so `openclaw agent --local` message-tool sends no longer report an available channel as unavailable. (#85022)
·Agents/heartbeat: honor group/channel `message_tool` visible-reply policy and model-specific Codex runtime config for scheduled heartbeat runs, so failed internal tool output stays private. Fixes #85310. (#85357)
·Gateway/ACP: close child ACP sessions spawned via `sessions_spawn` when their parent session is reset or deleted, instead of leaving orphaned `claude-agent-acp` processes that accumulate and exhaust memory. Fixes #68916. (#85190)
·Codex app-server: block native execution paths when OpenClaw exec resolves to a node host while preserving the first-party CLI node binding path. Fixes #85012. (#85534)
·Diagnostics: bound cleanup timeout detail logs, emit drop summaries when async diagnostic bursts exceed the queue cap, and surface async queue drops through diagnostic telemetry.
·Agents/subagents: surface blocked child-run completions as errors instead of successful subagent finishes. (#80886)
·Context engines: fail closed with a descriptive error when the selected agent runtime cannot satisfy declared context-engine host requirements.
·Agents/Pi: treat accepted embedded `sessions_spawn` child-session handoffs as terminal progress so parent turns no longer report false non-deliverable failures. (#85054)
·CLI/models: resolve `openclaw models set` aliases from the runtime config while keeping authored aliases ahead of runtime-only defaults. (#83262)
·Doctor: show personal Codex CLI asset notices as info instead of warnings. Fixes #84859.
·WhatsApp: update Baileys to `7.0.0-rc13` and drop the obsolete logger type patch.
·CLI/update: pre-pack GitHub/git package update targets before the staged npm install, restoring `openclaw update --tag main` for one-off package updates. (#81296)
·Gateway: mirror successful same-source message-tool sends into session transcripts so delivered replies stay in later history/context. (#84837)
·Media generation: keep image, music, and video completion delivery from duplicating or losing task ownership when generated media finishes through active session replies. (#84006)
·CLI/doctor: remove stale bundled plugin load paths from old versioned OpenClaw package roots after pnpm/npm upgrades. Fixes #58626.
·Infra/json: retry transient `File changed during read` races while loading JSON state so config and state reads recover instead of failing the turn. (#84285)
·Plugins/providers: fail closed for workspace provider plugins during setup-mode discovery unless explicitly trusted, preventing untrusted workspace plugin code from running during provider setup. (#81069)
·Providers/Ollama: resolve configured Ollama Cloud `OLLAMA_API_KEY` markers to the real discovery key so cloud provider entries keep authenticated model catalog access. (#85037)
·Discord: keep persistent component registry fallback warnings actionable by forwarding structured error and cause metadata through the runtime logger. Fixes #84185. (#84190)
·Gateway/sessions: preserve compatible session auth profile overrides when switching models within the same provider, including provider-auth aliases. Fixes #81837. (#81886)
·Gateway/status: surface inbound delivery telemetry counters and transport-liveness warnings in `openclaw status --all`. Fixes #49577. (#72724)
·Docker: prune package-excluded plugin source workspaces and dependency closures so runtime images do not keep packages for plugins that were not opted in.
·Providers/Ollama: treat Docker/OrbStack host aliases as local Ollama endpoints so `ollama-local` marker auth works when OpenClaw runs inside a VM/container and Ollama runs on the host. Fixes #84875.
·QA-Lab: keep explicitly searchable/deferred OpenClaw dynamic tool rows report-only by default so tool-coverage gates do not treat mock discovery gaps as hard product failures. (#80319)
·Agents/config: keep non-Google provider model refs from being rewritten by Google Gemini preview-id normalization. (#84762)
·Installer: require a real controlling terminal before launching onboarding so headless `curl | bash` installs finish cleanly after installing the CLI.
·Agents/Codex: promote a completed final assistant response when a prompt timeout races Codex app-server completion instead of returning an empty timeout envelope. Refs #84516.
·Codex app-server: keep interrupted turn statuses from being treated as OpenClaw aborts by themselves, so tool-only turns remain eligible for no-visible-answer recovery. Fixes #84492.
·Agents: cap heartbeat model bleed context hints by the stored session window when runtime model metadata is unavailable, so overflow recovery advice does not suggest a larger window than the active session actually has.
·Control UI/Web Push: use `https://openclaw.ai` as the generated default VAPID subject instead of the old localhost mailbox so iOS PWA push setup uses an Apple-acceptable subject when `OPENCLAW_VAPID_SUBJECT` is unset. Fixes #83134. (#83317)
·Control UI: distinguish inherited thinking-off settings from explicit Off selections so the thinking selector no longer shows two identical Off rows. (#85223)
·Agents/Pi: keep embedded session transcript writes from tripping false takeover detection after packaged npm onboarding agent turns.
·Codex/TUI: surface Codex-native post-turn compaction failures instead of continuing uncompacted, and keep successful native compaction serialized before local idle/next-turn handling. Fixes #84305. (#85160)
·Memory/search: stop recall tracking from writing dreaming side-effect artifacts when `dreaming.enabled=false`, while preserving normal search results. Fixes #84436. (#84444)
·Diffs: render viewer toolbar icons from a closed icon-name map instead of HTML strings, removing the toolbar icon XSS sink. (#83955)
·QA: keep `pnpm qa:e2e` self-check runs inside the private QA runtime envelope even when inherited shell env disables bundled plugins.
·fix(config): validate browser sandbox bind sources [AI]. (#84799)
·doctor: constrain legacy plugin cleanup paths [AI]. (#84801)
·Update/doctor: prune stale local bundled plugin install records that point at old compiled bundled output so current bundled plugin schemas win after upgrade. (#84863)
·Providers/Ollama: preserve native Ollama tool-call IDs across assistant replay so Gemini over Ollama Cloud can keep its hidden function-call thought-signature handle.
·Discord: keep session recovery and `/stop` abort ownership on the source dispatch lane while bound ACP turns continue routing to their target session, so stalled pre-run work and late replies are cleared instead of leaking after stop. Fixes #84477. (#85100)
·Discord/voice-call: keep forced realtime voice consult diagnostics in debug logs instead of agent prompts, so callers do not hear OpenClaw policy text when the provider misses `openclaw_agent_consult`. (#84411)
·Codex app-server: mark missing turn completion after observed execution as replay-unsafe and release the session so follow-up turns can run. Fixes #84076. (#85107)
·Codex app-server: give visible `message` dynamic tool sends a longer timeout budget so slow channel delivery can return its own result or error instead of hitting the 30-second Codex wrapper. (#85216)
·Codex app-server: add a dedicated post-tool raw assistant completion idle timeout config so trusted heavy turns can wait longer after tool handoff without weakening final assistant release.
·Matrix: keep explicitly configured two-person rooms on the room route before stale `m.direct` or strict two-member DM fallback can bypass mention gating. Fixes #85017. (#85137)
·Agents/subagents: require explicit subagent allowlist targets to be configured agents so stale deleted-agent ids are omitted from `agents_list` and rejected by `sessions_spawn`. Fixes #84811. (#85154)
·PDF tool: time out idle remote PDF body reads after 120 seconds so stalled remote documents return an error instead of wedging the session. Fixes #68649. (#84768)
·Diagnostics/OpenTelemetry plugin: suppress handled OTLP exporter promise rejections so collector shutdowns no longer crash the Gateway. (#81085)
·Agents/exec: omit raw command text and env values from denied exec failure logs while keeping safe correlation metadata. Fixes #85049. (#85140)
·Media-understanding: restore the 4096-token default for image descriptions so reasoning-capable vision models no longer truncate before returning text, while preserving smaller model caps. (#84932)
·Media/audio: skip empty structured sherpa-onnx transcripts instead of treating the raw JSON payload as spoken text. (#84667)
·Agents/exec: preserve inherited XDG base-directory environment values for subprocesses while still rejecting agent-supplied XDG overrides. Fixes #84854. (#85139)
·Node/Linux: keep `OPENCLAW_GATEWAY_TOKEN` out of generated systemd unit files by writing node service token values to a node-specific env file. (#84408)
·Memory-core/dreaming: reuse stable narrative subagent session keys per workspace and phase while keeping per-run idempotency and bounded cleanup, so stale `dreaming-narrative-*` sessions do not accumulate. Fixes #68252, #69187, and #70402. (#70464)
·Trajectory/support: tolerate partial skill snapshot entries when building support metadata so rejected skill path scans no longer abort trajectory capture. (#71185)
·TUI: coalesce repeated idle Esc abort notices into a single `no active run xN` system row instead of appending duplicate rows.
·Telegram: honor `channels.telegram.pollingStallThresholdMs` in the default isolated polling path, restarting silent workers instead of leaving inbound updates wedged. Fixes #83950. (#84861)
·Telegram: dedupe replayed message dispatches by Telegram chat/message identity so isolated-ingress replays do not trigger duplicate model dispatches. Fixes #84886. (#85208)
·Slack: suppress reasoning payloads before reply delivery and dispatch accounting, so Slack monitor, slash-command, fallback, and direct reply paths do not leak model reasoning. Fixes #84319. (#84322)
·Slack: deliver native plugin approval prompts and updates when Slack native approvals are enabled, while keeping plugin approval authorization separate from exec approvers.
·Slack: keep native plugin approval prompts in the originating app conversation thread when the live Slack turn source is a `D...` conversation.
·Agents/Pi: disable the embedded pi-coding-agent runtime auto-retry so OpenClaw's own retry and failover loop does not replay failed tool calls through a nested SDK retry. Fixes #73781. (#74434)
·CLI/perf: keep `setup --help`, `onboard --help`, and `configure --help` out of the full wizard runtime while preserving the existing help output. (#84488)
·CLI/perf: keep `agents --help` out of agents action/runtime imports so help, completion, and command discovery paths avoid loading the full agents runtime. (#84483)
·CLI/perf: keep `secrets --help` and `nodes --help` on the precomputed help path so parent help avoids loading action-heavy command runtime modules. (#84818)
·CLI/perf: serve `doctor`, `gateway`, `models`, and `plugins` parent help from startup metadata so common subcommand help avoids full CLI program construction. (#84786)
·Codex/Lossless: keep context-engine history on the canonical run session when Telegram DMs use per-peer runtime policy keys. Fixes #84936. (#84954)
·Codex: keep heartbeat response tool schemas durable without exposing dynamic tools disabled by turn policy, so heartbeat wakeups can reuse threads while scoped tool allowlists stay enforced. (#84681)
·Auth/OAuth: skip the refresh adapter when a stored OAuth credential has no refresh token so agent turns fail fast on missing-key instead of waiting on the 120s refresh timeout.
·Auth/Codex: load legacy OAuth sidecar credentials in the embedded runner's secrets-runtime auth loaders so Telegram replies, cron-triggered turns, and other isolated sub-agent lanes can reach the existing #83312 refresh-and-rewrite migration instead of failing with `No API key found for provider "openai-codex"` until the user runs `openclaw doctor`.
·Codex/failover: classify `deactivated_workspace` as a permanent auth failure so configured fallback models can advance when a Codex workspace is deactivated. (#55893)
·Exec: keep configured `tools.exec.pathPrepend` entries ahead of user shell startup PATH changes on POSIX gateway runs. (#81403)
·Gateway/sessions: allow shared-secret bearer callers to read and stream session history without an explicit scope header. (#81815)
·Agents/embedded runner: classify HTML auth provider responses as `auth_html` and return a re-authentication hint instead of the CDN-blocked copy that `upstream_html` returns. Cloudflare Access login pages, nginx basic-auth challenges, and gateway login walls all produce HTML auth bodies that were previously misdiagnosed as transient CDN blocks. (#79900)
·TUI/streaming watchdog: dismiss the `This response is taking longer than expected` notice as soon as a chat event for the same run arrives, so the message no longer sits next to the recovered response when the run was only briefly silent. Refs #67052, #69081 (closed), prior attempt #69026.
·Agents/Pi: tolerate OpenClaw-owned transcript writes while embedded prompts are released for model I/O, keeping long-running Feishu, Slack, Telegram, and cron turns from failing with false session-takeover errors. Fixes #84059. (#84250)

Release verification

·npm package: https://www.npmjs.com/package/openclaw/v/2026.5.24-beta.2
·registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.5.24-beta.2.tgz
·integrity: `sha512-NYz9vhtY+BFKvC+tEz68dGtlONdgpMYd3xJFx4b2Z6v0VDF9Cxb4ypUQzWMklQCLngpB9LMTCmKHEPeDEEo2uQ==`
·full release CI report: https://github.com/openclaw/releases/blob/main/evidence/2026.5.24-beta.2/release-evidence.md
·release publish: https://github.com/openclaw/openclaw/actions/runs/26379964767
·npm preflight: https://github.com/openclaw/openclaw/actions/runs/26378908349
·full release validation: https://github.com/openclaw/openclaw/actions/runs/26378909141
·plugin npm publish: https://github.com/openclaw/openclaw/actions/runs/26380049649
·plugin ClawHub publish: https://github.com/openclaw/openclaw/actions/runs/26380051057
·OpenClaw npm publish: https://github.com/openclaw/openclaw/actions/runs/26380445312
·npm Telegram beta E2E: https://github.com/openclaw/openclaw/actions/runs/26386836610

v2026.5.24-beta.1pre-release2026-05-24

openclaw 2026.5.24-beta.1

GitHub ↗

Changes

·Gateway/perf: reuse process-stable channel catalog reads, avoid repeated bundled-channel boundary checks, and rotate gateway watch CPU profiles so benchmark runs do not accumulate unbounded artifacts.
·Gateway/perf: cache stable install-record, channel-catalog, bundled-channel, and Telegram session-store metadata during process-local hot paths to reduce repeated JSON and manifest reads.
·Gateway/perf: reuse immutable plugin metadata snapshots across startup, config, model, channel, setup, and secret metadata readers so hot paths avoid repeated plugin file stats and manifest registry reloads.
·Talk/realtime: let WebUI and Discord voice callers ask for active OpenClaw run status, cancel, steer, or queue follow-up work while a consult is still running. (#84231)
·Discord/voice: add realtime wake-name gating with agent-name defaults and raise profile bootstrap context budget for longer `USER.md`/`SOUL.md` files.
·Gateway/perf: lazy-load startup-idle plugin work, core gateway method handlers, and the embedded ACPX runtime so Gateway health and ready signals no longer wait on unused handler trees or ACPX probes.
·Gateway/perf: cache plugin SDK public-surface alias maps and skip irrelevant macOS Linuxbrew PATH probes so Gateway startup avoids repeated filesystem walks and slow missing-directory stats.
·Image tool: add adaptive model-aware image compression with an `agents.defaults.imageQuality` preference for choosing token-efficient, balanced, or high-detail media handling.
·Meeting Notes: add a source-only external meeting-notes plugin and SDK source-provider contract outside the core npm package, with auto-start capture config, manual transcript imports, read-only `openclaw meeting-notes` CLI access, and Discord voice as the first live source.
·Meeting Notes/Discord: release channel account startup before meeting-notes auto-capture, wait for the Discord voice manager during gateway boot, and stop plugin services before channel shutdown so voice capture state remains available during startup and cleanup.
·Docs/channels/config: add Signal `configPath`, Telegram wildcard topic defaults, local-time backup archive names, Termux home fallback, include-path validation, secret-scanner-safe placeholder guidance, Gemini CLI/Antigravity media guidance, and macOS VM auto-login guidance.
·Docs: clarify model-usage portability, Codex migration prerequisites, status bootstrap wording, thread-bound subagent limits, hook ownership, and config-preserving safety guidance.
·Docs: clarify README onboarding and Gateway startup paths, WhatsApp QR/408 recovery, cron output language prompts, skill advanced features, gateway upstream 403 troubleshooting, and plugin fallback override guidance.
·Docs: clarify context-pruning ratio bounds, local dashboard recovery, CLI env markers, remote onboarding token behavior, and Peekaboo Bridge permissions for subprocess agents.
·Docs: clarify browser CDP diagnostics, Plugin SDK allowlist imports, status-reaction timing defaults, queue steering behavior, limited-tool troubleshooting, cron HEARTBEAT handling, Telegram multi-agent groups, Bitwarden SecretRef setup, and EasyRunner deployments.
·CLI/models: let `openclaw models auth login` store a single returned provider auth profile under a requested `--profile-id`, and document named Codex OAuth profile setup. (#49315)
·Crabbox/Testbox: run clean sparse-checkout Testbox syncs from a temporary full checkout and route remote changed gates through Corepack pnpm.
·Docs: clarify IPv4-only Gateway BYOH binding, trusted-proxy scope clearing, Android pairing approval, macOS Accessibility grants, Zalo profile env vars, password-store SecretRef setup, and Chinese memory navigation.
·Docs: consolidate GLM under Z.AI, add the Upstash Box install guide and Gateway exposure runbook, clarify MEDIA directives, Copilot and Voyage setup, config path quoting, real behavior proof, and memory-file write guidance.
·Docs: clarify media provider credentials, Codex/OpenClaw code-mode boundaries, Slack and Telegram ack reactions, Feishu dynamic agents, secrets plaintext boundaries, memory guidance, and Chinese glossary terms.
·Packaging: exclude documentation images and assets from the npm tarball, reducing published package size without affecting runtime docs search or CLI behavior.
·Media understanding: stop auto-probing Gemini CLI and use Antigravity CLI only as a lower-priority image/video fallback after configured provider APIs.
·Diagnostics: emit sanitized `secrets.prepare` timeline spans for Gateway secret preparation so operators can distinguish secret startup latency without exposing provider names, secret ids, or secret values. (#83019)
·Diagnostics: export bounded skill usage metrics/spans and tool source/owner labels for core, plugin, MCP, and channel tool execution without exposing raw paths or session identifiers. (#80370)
·Agents/subagents: limit default sub-agent bootstrap context to `AGENTS.md` and `TOOLS.md`, keeping persona, identity, user, memory, heartbeat, and setup files out of delegated workers by default. (#85283)
·Maintainer skills: require clean autoreview before surfacing bug-sweep PR URLs and treat changelog-only conflicts as routine busy-main churn.
·Maintainer skills: exclude plugin SDK/API boundary work from `openclaw-landable-bug-sweep` so bugbash sweeps stay focused on small paper-cut fixes.
·QA-Lab/diagnostics: extend the OpenTelemetry smoke harness to prove trace, metric, and log export, and add first-class Prometheus and observability smoke aliases.
·Plugin SDK: add a generic channel-message poll sender so channel plugins can expose poll delivery without depending on channel-specific SDK facades.
·Plugin SDK/cron delivery: route cron delivery through the modern target resolver and outbound session-route APIs, deprecate parser-backed target helpers and `plugin-sdk/messaging-targets`, and move bundled callers to `plugin-sdk/channel-targets`.
·Crabbox: keep the local wrapper's provider validation synced with the installed Crabbox binary while preserving supported aliases such as `docker` and `blacksmith`. (#85302)
·Maintainer skills: add `openclaw-landable-bug-sweep` for producing five small, reviewed, CI-green OpenClaw bugfix PRs from issue/PR sweeps.
·Control UI/chat: add search and Load More pagination to the chat session picker, keeping initial session loads bounded while making older conversations reachable. (#85237)
·CLI/onboarding: start classic onboarding when bare `openclaw` runs before an authored config exists, while keeping configured installs on Crestodian. (#72343)
·Discord: allow configuring a bounded `agentComponents.ttlMs` callback registry lifetime for long-running component workflows, with per-account overrides and a 24-hour cap. (#84189)
·xAI/Grok: reuse xAI OAuth auth profiles for Grok `web_search`, thread active-agent auth through web search, add Grok model aliases, and let media providers declare default operation timeouts. (#85182)
·Plugin SDK: add row-level session workflow helpers and deprecate `loadSessionStore` so plugins can read and patch sessions without depending on the legacy whole-store shape. (#84693)
·Gateway/plugins: reuse a compatible Gateway startup plugin registry during dispatch so safe plugin dispatches avoid redundant registry loading. (#84324)
·Plugins/SDK: add a general `embeddingProviders` capability contract and registration API so embeddings can become a reusable provider surface outside memory-specific adapters.
·Dependencies: refresh provider, plugin, UI, and tooling packages, update `protobufjs` to 8.4.0 to clear the current npm advisory, and carry the Claude ACP completion patch forward to `@agentclientprotocol/claude-agent-acp` 0.36.1.
·Agents/tools: remove the old sender-owner tool gating path so configured tools stay visible for trusted sessions while command and channel-action auth still carry real sender identity.
·QA-Lab: add curated mock JSONL replay fixtures and first-drift reporting for runtime-parity audits. (#80323, refs #80176)
·QA-Lab: add a QA bus tool-trace visibility scenario for sanitized tool-call assertions.
·QA-Lab: replace generic evidence framing in seeded scenario prompts with concrete observed QA behavior.
·QA-Lab: list named scenario packs in the coverage report so personal-agent privacy coverage stays visible in audits.
·QA-Lab: list live transport lane membership in the coverage report so real transport checks stay separate from seeded qa-channel scenarios.
·Release/package: run package integrity checks before package acceptance lanes so public install/update validation fails before private QA assets can leak into the package.
·QA-Lab: include the optional 100-turn runtime parity soak in release-soak artifacts so long-run Codex/Pi transcript drift stays visible outside the default gate. (#80395)
·QA-Lab: add a live-only long-context progress watchdog scenario for Codex app-server timeout and stalled-run sentinels. (#80323)
·QA-Lab: tag gateway restart recovery and streaming final-integrity scenarios as live-only runtime parity lanes. (#80323)
·QA-Lab: add a personal-agent failure recovery scenario that checks honest partial status, retry boundaries, and local recovery artifacts. (#83872)
·QA-Lab: include an opt-in `update.run` package self-upgrade sentinel for destructive latest-package recovery checks.
·QA-Lab: add Codex plugin lifecycle and auth-profile fixture coverage for missing installs, pinned-version drift, first-turn install ordering, and doctor migration safety. (#80323, refs #80174)
·Models/perf: pre-warm the provider auth-state map at gateway startup so `/models` and every model-listing call short-circuits the per-provider plugin / external-CLI discovery on the hot path. Per-call cost drops from ~20 s to ~5 ms (~4,100×); the one-time startup warm resets and re-warms after hot reloads. (#84816)
·Release/security: ship the root npm package and OpenClaw-owned npm plugins with generated shrinkwrap, support bundled plugin runtime dependencies for suitable plugin tarballs, and require review for lockfile/shrinkwrap changes so published installs use locked dependency graphs.
·Tests/perf: isolate doctor core health check unit coverage from real skills/workspace discovery so `doctor-core-checks` no longer dominates unit perf while keeping one real skills-readiness smoke. (#84493)

Fixes

·Gateway/update: avoid fetching unrelated tags during dev-channel git updates so moved release tags do not block branch-based updates. (#84737)
·MiniMax: store OAuth token expiry as an absolute millisecond timestamp so OAuth profiles no longer appear expired on every request. (#83480)
·Agents/Anthropic: strip missing or blank thinking signatures for signed-thinking providers even when recovery supplies a narrow replay policy without signature preservation. Fixes #84430. (#84448)
·Agents/channels: send a visible notice when an aborted main session cannot be resumed after restart, including Telegram group targets. (#85805)
·Discord/voice: serialize overlapping voice joins, retry aborted startup readiness within the configured timeout, upgrade meeting-notes-only sessions to realtime when the normal follow join arrives, detach promoted meeting-notes ownership without leaving voice, and include `OpenClaw` in default realtime wake names.
·Gateway/restart: honor the configured restart drain budget for embedded runs and avoid spending the deferral timeout twice after forced restart timeouts. (#85708)
·Gateway/boot: run `BOOT.md` startup checks in an isolated boot session so gateway restarts do not overwrite the agent's main session mapping. (#85479)
·Meeting Notes: include a speaker-labeled transcript section in generated summaries so Discord group voice captures show who said each captured utterance.
·Discord/voice: recover stale realtime playback state when Discord stream-close/player-idle events do not arrive, and keep generated runtime plugin aliases available after postbuild rewrites.
·Discord/voice: keep realtime playback running when meeting notes attaches to an existing voice session or a realtime consult starts, and route realtime user transcripts into meeting notes.
·Config/secrets: preflight active runtime SecretRefs before root and include config writes persist, and roll back unchanged file/env state when post-write refresh fails. Fixes #46531. (#84454)
·CLI/models: preserve SecretRef-backed custom provider `apiKey` markers when `models status` regenerates `models.json`, avoiding resolved plaintext secrets on disk. Fixes #84632. (#84658)
·WhatsApp/auto-reply: deliver deferred media replies through the foreground reply fence so overlapping no-reply turns no longer hide already visible responses. (#85517)
·Sessions/security: replace agent-to-agent wildcard allowlist regexes with a precompiled linear matcher so cross-agent access checks avoid backtracking-prone patterns. (#85849)
·WebChat: keep the run-complete indicator in progress until deferred history replay renders the assistant reply, so Done no longer appears before response text. (#85374)
·Agents/tools: give timed-out or cancelled process trees a bounded SIGTERM cleanup window before SIGKILL while preserving tree-aware cancellation. Fixes #66399. (#85865)
·Agents/subagents: treat aborted subagent stop reasons as killed terminal failures so parent sessions get error announcements instead of silent success. Fixes #72293. (#85860)
·Agents/providers: clamp proxy-like OpenAI Chat Completions output caps against the final request payload so strict local/API-compatible servers no longer reject prompts that already consume part of the context window. Fixes #83086. (#85889)
·Agents/compaction: skip agent-harness preflight for provider-owned CLI runtime sessions so over-threshold Claude CLI sessions continue through normal compaction instead of failing on a missing harness. Fixes #84857. (#84878)
·Codex/app-server: keep successful native hook relays available through a short post-turn grace window so late Codex hook subprocesses can finish policy enforcement without clearing a replacement relay. (#83987)
·Control UI/config: save form-mode edits from the source config snapshot so runtime-only provider defaults like empty `models.providers.<id>.baseUrl` are not written back and rejected. Fixes #85831.
·Browser/existing-session: launch Chrome DevTools MCP with usage statistics disabled by default so its telemetry watchdog stays off unless an operator explicitly opts in. (#85886)
·Telegram: normalize legacy durable group retry targets before retry sends, polls, and pins so group retries keep using the real chat id. (#85656)
·Agents/PDF: route MiniMax PDF fallback policy through plugin metadata so MiniMax uses text extraction instead of VLM image fallback. (#85590, fixes #85575)
·CLI/plugins: tighten timeout, numeric option, media payload, permission, profile/TLS, plugin metadata, JSON, and remote URL handling; prevent stuck progress/app-server/IRC/Synology/Twitch waits; and keep imported chat history ordering stable.
·Telegram/config: suppress the missing `accounts.default` warning when `channels.telegram.defaultAccount` names a configured account that also sorts first. Fixes #83948.
·WebChat: summarize internal message-tool source replies so tool cards no longer duplicate the visible reply body. (#84773)
·Gateway/WebChat: hide duplicate `gateway-injected` assistant rows when Cursor ACP already persisted the same `acp-runtime` reply. Fixes #85741.
·WebChat: scope the visible attachment button to its own composer file input so clicking Upload reliably opens the file picker. (#83952, fixes #47983)
·Gateway: preserve deferred lifecycle-error cleanup across later non-terminal events so provider timeouts can persist failed session state instead of leaving sessions stuck running. (#85256, fixes #63819)
·Gateway/update: stop treating inherited macOS `XPC_SERVICE_NAME` values as launchd supervision during update respawn, so GUI-spawned gateways use detached respawn instead of exiting for a missing LaunchAgent. Fixes #85224.
·Agents/subagents: report tool-only child progress during timeout summaries instead of showing no visible output.
·Telegram/ACP: preserve explicit `:topic:` conversation suffixes when inbound ACP targets do not carry a separate thread id.
·Browser/proxy: bypass the managed proxy for the exact local managed Chrome CDP readiness and DevTools WebSocket endpoints, so `openclaw browser start` works when the operator proxy blocks loopback egress. (#83255)
·Ollama: bypass the managed proxy for configured local embedding origins while keeping SSRF guardrails on unconfigured targets.
·OpenAI/images: route Codex API-key image generation through the native OpenAI Images API instead of the Codex OAuth streaming backend, avoiding 401s from valid API keys.
·Agents/OpenAI completions: omit empty tool payload fields for proxy-like OpenAI-compatible endpoints so strict vLLM-style servers accept tool-free turns. (#85835)
·Sandbox: keep workspace skill mounts read-only for remote container-cwd file operations and reject symlinked skill roots before creating protected overlays. (#85591)
·Scripts/Windows: route remaining QA, release, profile, and live-media `pnpm` launches through the managed runner so native Windows avoids brittle `.cmd` execution and shell-argv warnings.
·Release: align generated config/API baselines and the meeting-notes plugin version so release preflight stays green on native Windows.
·Install/Windows: run Git hook setup through a Node prepare helper so native Windows installs no longer print POSIX shell errors.
·Checks/Windows: chunk and serialize extension oxlint shards on native Windows so changed gates avoid Go-backed linter memory spikes.
·Release/Windows: run installed `openclaw.cmd` verification through explicit `cmd.exe` wrapping so npm prepublish/postpublish checks avoid Node shell-argv warnings.
·Plugins/Windows: run plugin npm package staging through the shared npm runner so native Windows release checks avoid bare `npm` lookup and `.cmd` shell-argv handling.
·Checks/Windows: route full `pnpm check` stage commands through the managed child runner so Windows avoids Node shell-argv deprecation warnings there too.
·Agents/fs: allow workspace-only host write/edit tools to write through in-workspace symlink directory parents while preserving outside-workspace symlink rejection. Fixes #84696.
·Checks/Windows: run managed child commands through explicit `cmd.exe` wrapping instead of Node shell mode with argv, avoiding Node 24 subprocess deprecation warnings during changed checks.
·Gateway: omit internal stream-error placeholder entries from agent prompt history so failed assistant turns are not replayed as model-authored text. (#85652)
·Sessions: enforce the session write-lock max-hold policy during lock acquisition so long-held locks can be reclaimed before the stale-lock window. (#85764)
·Sessions/status: preserve user-facing model, fallback, usage, and cost attribution when internal subagent handoff runs use fallback models. (#85726, fixes #85082)
·Install/update: honor `OPENCLAW_HOME` when deriving default dev checkout and installer onboarding paths, while keeping explicit `OPENCLAW_GIT_DIR` and `OPENCLAW_CONFIG_PATH` overrides authoritative. Fixes #54014.
·Models: prune retired Groq, GitHub Copilot, OpenAI, xAI, and old Claude catalog entries, with doctor migration to upgrade existing configs to current provider refs.
·Plugins/Gateway: treat non-empty return values from plugin gateway method handlers as successful responses so `openclaw gateway call` no longer times out after completed plugin work. Fixes #59470.
·Doctor/update: recognize junction-backed source checkouts as git installs by comparing canonical paths before showing package-manager update guidance. Fixes #82215.
·Channels: honor `/verbose on` for tool/progress summaries across direct chats, groups, channels, and forum topics while preserving quiet default behavior. (#85488)
·Update: keep the detached gateway restart handoff best-effort when the restart script process cannot be spawned. (#83892)
·Telegram: persist the prompt-context message cache through plugin state and record bot-authored replies after sends and draft streaming so later turns can include prior assistant replies without relying on the JSON sidecar. (#85231)
·Agents/subagents: keep Codex persona and user workspace files turn-scoped so native Codex subagents inherit only shared tool guidance by default. (#85811)
·CLI/skills: show an all-ready note with next-step commands when skill setup has no missing dependencies to install. (#85032)
·Microsoft Foundry: route DeepSeek V4 Pro and Flash models through the Foundry Responses API while keeping older DeepSeek models on their existing path. (#85549)
·Status/usage: show configured cost estimates for AWS SDK models in full usage output while keeping token-only usage replies cost-free. (#85619)
·Agents/OpenAI Responses: retry non-visible reasoning-only turns for OpenAI Responses API families instead of treating them as empty failed turns. (#85603)
·Directive tags: preserve message and content-part object identity when display stripping makes no directive-tag changes. (#85682)
·Telegram: send local `path`/`filePath` and structured attachment media from `sendMessage` actions instead of dropping them or sending text-only messages. (#85219)
·Sessions/status: show the estimated context budget when fresh provider usage is unavailable and clear stale estimates across session resets and compaction boundaries. (#84830)
·Gateway/config: pin relative `OPENCLAW_STATE_DIR` overrides to an absolute path at startup so later working-directory changes cannot retarget gateway state. (#52264)
·Checks/Parallels: make changed-lane scripts, shrinkwrap generation, and Parallels package smoke host commands run through native Windows-safe paths and `npm`/`pnpm` shims.
·Release/package: run npm release, prepublish, and postpublish verification through Windows-safe npm command shims so native Windows checks can execute `npm.cmd` instead of treating it as a binary.
·Agents/harness: pass CLI runtime aliases through harness selection so provider-owned CLI aliases no longer get rejected before reaching the right runtime. (#85631)
·Secrets: show the irreversible apply warning after interactive `secrets configure` confirmation so confirmed migrations still get the final safety prompt. (#85638)
·Agents/CLI output: ignore cumulative Claude `stream-json` result usage when assistant usage events are present, preventing inflated cache-read accounting. (#85625)
·CLI: keep `waitForever()` alive by leaving its keep-alive interval ref'd so the public helper no longer exits immediately with Node's unsettled-await code. (#85694)
·Agents/bootstrap: guard bootstrap name checks against missing file names so malformed bootstrap entries warn and truncate instead of crashing. Fixes #85523. (#85615)
·CLI/tasks: reject partially numeric `openclaw tasks audit --limit` values so audit limits must be real positive integers instead of accepting strings like `5abc`. (#84901)
·Status/diagnostics: bound deep Docker audit probes so `openclaw status --deep` reports slow container checks instead of hanging behind unbounded inspection. (#85476)
·Providers/Anthropic: migrate 1M context handling to GA-capable Claude 4.x models by sizing eligible models at 1M without the retired `context-1m-2025-08-07` beta, ignoring that retired beta in older configs, and preserving OAuth-required Anthropic beta headers. (#45613)
·Cron/Telegram: parse forum-topic delivery targets through the Telegram plugin instead of cron core, including `:topic:` and `:topicId` forms for announce delivery.
·Twitch: keep stale message-handler cleanup callbacks from removing newer handler registrations for the same account, preserving inbound message delivery after reconnects. Fixes #83888. (#85425)
·Control UI/chat: keep light-mode model, thinking, config, and agents select arrows visible without tiling background icons. Fixes #85713.
·Memory/LanceDB: expose public memory artifacts through the active memory provider bridge so memory-wiki imports durable memory files, daily notes, dream reports, and event logs without depending on memory-core internals. Fixes #83604. (#85060)
·Crabbox: keep AWS hydration compatible with local Actions replay by inlining the hydrate workflow's Node/pnpm setup instead of invoking repo-local composite actions.
·Agents/subagents: simplify native sub-agent completion handoff so children report their latest visible assistant result to the requester without using `message`, while keeping parent-owned message-tool delivery policy intact. Fixes #85070. (#85089)
·Docker setup: stop printing the Gateway bearer token in setup logs and printed follow-up commands.
·Gateway: defer channel account startup work until HTTP readiness and remove startup model prewarm, avoiding startup event-loop stalls and timer-delay warnings.
·Models/perf: reuse plugin metadata during models.json planning, keep bundled catalog augmentation manifest/static, and use static provider catalogs for metadata-only startup discovery so provider model normalization, auth discovery, and Gateway startup metadata do not reload broad plugin runtimes.
·Agents: let embedded compaction fallback retries proceed when PI-compatible candidates do not need agent harness plugin preparation.
·Agents/tools: honor configured custom provider API keys when deciding whether media, image-generation, video-generation, music-generation, and PDF tools are available. (#85570)
·StepFun: stop advertising stale generic API key auth choices so onboarding only offers runtime-backed Standard and Step Plan choices.
·Diagnostics: keep OpenTelemetry log bodies behind explicit content capture and scrub scoped agent-session keys from OpenTelemetry and Prometheus labels while preserving bounded queue-lane prefixes.
·Windows installer: fail Git checkout installs when `pnpm install` or `pnpm build` fails instead of writing a wrapper to a missing CLI build.
·Sessions: surface previous-transcript archive failures during `/new` rotation so disk rename errors are logged instead of silently hiding stranded transcript files. Fixes #81984. (#85586, from #82081)
·TUI/agents: mirror internal-ui message-tool replies into final chat output so message-tool-only agents remain visible in `openclaw tui`. Fixes #85538.
·Gateway/TUI: preserve source-reply metadata through reply normalization and emit message-tool-only agent replies over the live chat stream so `openclaw tui` renders Codex replies without waiting for a history refresh.
·Codex/TUI: keep long source-reply runs alive after Codex reasoning completes so delayed visible `message` calls can still reach `openclaw tui`.
·TUI: keep quiet active runs busy after the response watchdog notice instead of reopening the prompt and encouraging duplicate submissions while the backend turn is still running.
·Agents: preserve the latest assistant thinking blocks while stripping invalid replay signatures from older turns, and retry Anthropic thinking failures without thinking replay. Fixes #85557.
·Agents: keep parallel OpenAI-compatible tool-call deltas in separate argument buffers so interleaved tool calls no longer corrupt streamed arguments. (#82263)
·Memory/doctor: report missing or unusable QMD workspace directories as workspace failures instead of generic binary failures. (#63167)
·Debug proxy: record CONNECT client-socket errors and destroy the paired upstream socket so abrupt client disconnects no longer leak tunnel resources. (#82444)
·Diffs: continue hydrating later diff cards when one card fails so a single broken card no longer blanks the whole diff viewer. (#84775)
·Mac app: use the native settings sidebar window chrome so the sidebar toggle stays on the left and content no longer clips under oversized titlebar padding.
·QA-Lab/Codex: bundle auth/plugin fixture imports for flow scenarios and let terminal async media tools end Codex app-server turns without timing out. (#80397, refs #80323)
·WhatsApp: persist inbound message delivery state through plugin state before dispatch and delay read receipts until handler completion, so retryable failures can redeliver without adding a plugin-local disk cache.
·Gateway/agents: preserve fresh session overrides and metadata when stale cached agent-session entries race with store updates, so subagent model/provider overrides and routing policy survive concurrent writes. (#19328)
·Control UI/chat: keep chat session search inline with the session selector so the header no longer shows a duplicate standalone search row.
·Control UI/chat: collapse focused-mode header chrome and suppress hidden-header scroll updates so focus mode no longer jumps while scrolling.
·Codex app-server: restart the native app-server and retry once when server-side compaction times out, so preflight compaction stalls recover instead of failing every dispatch. (#85500)
·Restore Control UI gateway token pairing [AI]. (#85459)
·OpenAI video: honor configured provider request private-network opt-in for local/custom video endpoints so explicitly trusted mock and self-hosted providers are not blocked.
·OpenAI video: send uploaded video edit requests to the documented `/videos/edits` endpoint with a `video` file instead of posting MP4 references to `/videos`.
·Agents/channels: preserve message-tool delivery evidence through gateway agent completion handoffs so successful generated media sends are not followed by false failure messages.
·CLI/update: repair managed npm plugin `openclaw` peer links during post-core convergence and reject stale or wrong-target peer links before restart. (#83794)
·CLI/agents: default new omitted-account bindings to all accounts when the channel has multiple configured accounts, and clarify account-scope docs. (#49769)
·Codex app-server: let authorized `/codex` control commands such as `/codex detach` escape plugin-owned conversation bindings while keeping unknown or unauthorized slash text routed to the bound plugin. Fixes #85157. (#85188)
·Auto-reply/models: keep `/models` browse replies fast by sharing the bounded read-only catalog path with Gateway model listing. (#84735)
·Browser/Doctor: read macOS Chrome app bundle versions from `Info.plist` before spawning Chrome and extend the fallback version probe timeout, avoiding false cold-cache warnings from Gatekeeper latency. Fixes #85418.
·Codex app-server: disable native Code Mode when the effective exec host is `node` and keep OpenClaw `exec`/`process` available, so `/exec host=node` routes shell commands through the selected node instead of the gateway. Fixes #85012. (#85090)
·Agents: bound embedded auto-compaction session write-lock watchdogs to the compaction timeout instead of the full run timeout, so stuck compaction cannot hold the live session lock for the whole run window. (#84949)
·Gateway/agents: return phase-aware `agent.wait` timeout attribution and only cool auth profiles on provider-started timeouts. Refs #65504.
·Gateway/systemd: launch managed update handoff helpers in a transient user scope so systemd-supervised Update Now flows survive the gateway unit restart. Fixes #84068.
·Gateway: defer provider auth-state prewarm until after startup readiness so early gateway tool/session requests are not blocked by provider auth discovery. (#85272)
·Gateway/models: coalesce provider auth-state rewarms after auth-profile failures and log event-loop delay for warm/rewarm work, so provider auth bursts no longer stack full auth sweeps behind channel replies.
·Gateway/models: stop cancelled provider auth-state prewarms from continuing full provider sweeps, so reload and auth-failure bursts no longer keep startup busy.
·Agents/Codex: show the first plan update as a transient chat status notice without counting it as final assistant content.
·CLI/update: walk the macOS process ancestry and honor the inherited Gateway runtime PID before package updates stop the managed Gateway service, so nested in-band updater children can refuse instead of killing the LaunchAgent-supervised Gateway that owns them. Fixes #85120.
·Gateway/LaunchAgent: wait for launchd reload bootout to finish and fall back to kickstart when bootstrap races, so reload handoff does not leave the service deregistered. Fixes #84630. (#84641)
·Gateway/LaunchAgent: treat a concurrent launchd bootstrap as a successful restart when the service is already loaded, avoiding false macOS Gateway restart failures. Fixes #84721. (#84722)
·Gateway/service: include the active `openclaw` command bin directory in managed service PATH generation and doctor audit expectations for npm-global macOS installs. Fixes #84201. (#84475)
·Control UI/chat: disable the thinking selector for known non-reasoning models instead of showing duplicate Off choices. Fixes #84069.
·Memory: expand `~` in configured extra memory paths before resolving them, so home-relative folders are not treated as workspace-relative. Fixes #58026.
·Skills: treat `openclaw.os: macos` as Darwin when checking skill requirements, so macOS-only skills no longer report as missing on macOS hosts. Fixes #61338.
·Control UI/logs: strip ANSI escape sequences from displayed Gateway log messages so color codes no longer appear as raw text. Fixes #64399.
·Docker: pre-create the workspace and auth-profile config mount points with `node` ownership so first-run named volumes do not start root-owned. Fixes #85076.
·Telegram: pass configured markdown table mode through outbound markdown chunking so chunked sends render tables consistently. Fixes #85085.
·Diagnostics/OTel: drop snake_case diagnostic id attributes alongside camelCase ids so exported telemetry cannot leak run, session, message, chat, trace, or tool-call identifiers. (#72645)
·CLI/update: preserve managed Gateway service environment during package cutovers so macOS LaunchAgent repair/restart reads the pre-update service state instead of caller shell state. (#83026)
·Agents/providers: honor per-model `api` and `baseUrl` overrides in custom provider auth hooks and transport selection. Fixes #80487. (#80488)
·Gateway/restart: eager-load the lifecycle runtime before in-place upgrade signal handling so package replacement does not deadlock restart imports. (#84890)
·CLI/update: start managed Gateway update handoff helpers from a stable existing directory and tolerate deleted cwd/package roots during macOS LaunchAgent handoff. Fixes #83808. (#83875)
·Skills: watch each shared skill directory once across agent workspaces instead of once per agent, preventing file-descriptor exhaustion (`EMFILE`) that disposed bundle-mcp processes and stalled sessions on multi-agent gateways. Fixes #84968. (#85130)
·Release/security: keep generated npm shrinkwrap package versions inside the pnpm lock graph so published package locks cannot bypass pnpm dependency age and override policy.
·Cron: honor `cron.retry.retryOn: ["network"]` for common network error codes such as `EAI_AGAIN`, `EHOSTUNREACH`, and `ENETUNREACH`.
·Gateway chat: broadcast returned agent-run error payloads after an agent starts so ACP/WebChat clients receive terminal idle-timeout errors. Fixes #84945.
·Gateway chat display: preserve OpenAI-compatible `prompt_tokens`, `completion_tokens`, and `total_tokens` usage fields in sanitized chat history so llama.cpp sessions keep context counts. Fixes #77992.
·Dashboard/CLI: allow macOS browser launching through `open` even when SSH environment variables are present, while preserving Linux SSH no-display protection. Fixes #67088.
·Codex app-server: keep native web search observations out of mirrored chat transcripts while preserving available action query metadata in tool progress telemetry. Fixes #85109.
·OpenCode Go: strip unsupported Kimi reasoning replay fields before provider requests so repeated `kimi-k2.6` turns do not fail schema validation. Fixes #83812.
·Browser/CDP: add a WSL2 portproxy self-loop hint when Chrome DevTools endpoints accept connections but return an empty HTTP reply. Fixes #59209.
·Agents/tools: add bounded tool-policy audit log entries that identify which allow/deny rule removed tools or blocked a sandboxed tool call. Fixes #55801.
·CLI/logs: read implicit local Gateway logs through the passive backend client path so `openclaw logs --follow` does not register as a paired device, and use the active Linux systemd journal instead of stale configured-file fallbacks when live local RPC is unavailable. Fixes #83656 and #66841.
·Agents/OpenAI: preserve structured provider error code, type, and redacted body metadata on boundary-aware transport failures.
·Doctor/Codex: point native Codex asset warnings at the canonical `openclaw migrate plan codex` preview command. Fixes #84948.
·CLI/models: make `capability model auth logout --agent` remove auth profiles from the selected non-default agent store. Fixes #85092.
·Gateway/models: reuse prepared provider auth metadata during model-listing auth checks so repeated lookups avoid broad plugin discovery while preserving synthetic local auth.
·CLI/status: suppress systemd user-service setup hints when `openclaw status --deep` can already reach a running Gateway RPC service. Fixes #85094.
·CLI/devices: recover local approval when a same-device repair request replaces the request ID being approved.
·CLI/agents: retry transient normal-close Gateway handshakes before falling back to embedded `openclaw agent` execution.
·CLI/update: keep managed Gateway service stop/restart status lines out of `openclaw update --json` stdout so package-update automation can parse the JSON payload.
·Plugins: resolve OpenClaw plugin SDK subpaths for native external plugin runtimes without mutating package installs or broadening process-wide module resolution.
·Agents/OpenAI: preserve Responses and Chat Completions `reasoning_tokens` usage metadata without double-counting it in aggregate output tokens. (#85319)
·Control UI/chat: convert pasted `data:image/...;base64,...` clipboard text into an image attachment instead of dumping the payload into the composer. Fixes #62604.
·Providers/Gemini: strip fractional seconds from web-search time range filters so Gemini accepts freshness-bound search requests. (#85071)
·OpenAI Codex: preserve image input support for sparse `openai-codex/gpt-5.5` catalog rows. (#85095)
·CLI/models: add a piped or pasted API-key path for OpenAI Codex auth and warn when API keys are pasted into token-mode auth. (#85533)
·Telegram: dead-letter missing-harness isolated ingress failures so a poisoned spooled update no longer blocks later same-lane messages. Fixes #85470. (#85605)
·Plugins/discovery: strip `-plugin` package suffixes when deriving plugin id hints so package names line up with manifest ids. (#85170)
·Tlon: stop advertising a non-existent agent tool contract in the plugin manifest.
·Telegram: preserve fenced code block languages through Markdown rendering so Telegram receives `language-*` code classes. (#85209)
·Windows installer: run npm and Corepack command shims from a Windows-local directory so installs launched from WSL2 UNC paths do not fail before OpenClaw is installed.
·Windows updates: roll back git-backed updates to the previous checkout when dependency install, build, UI build, or doctor repair fails.
·Windows installer: persist user-local portable Git on PATH and activate the repo-pinned pnpm version for git-backed installs and updates.
·Windows installer: bootstrap a user-local portable Node.js when native Windows has no Node and no winget, Chocolatey, or Scoop, so first-run installs can continue on raw hosts.
·Windows installer: extract the downloaded portable Node.js directory with native `tar` before falling back to .NET zip extraction, avoiding PowerShell 5.1 archive and path-length failures.
·fix(integrations): enforce channel read target allowlists [AI]. (#84982)
·Agents/heartbeat: route single-owner `session.dmScope=main` direct-message exec and cron event wakes back to the agent main session so async completions no longer strand context in orphan direct-DM queues. Fixes #71581. (#83743)
·Agents/code-mode: expose outer code-mode `exec` source through the `command` hook alias with `toolKind`/`toolInputKind` discriminators so exec-shaped policies can distinguish code-mode cells. (#83483)
·Agents/code mode: return structured timeout and runtime-unavailable error codes for known worker failures. Fixes #83389. (#83444)
·QA-Lab: isolate multi-scenario suite workers when scenarios need startup config patches, preventing message-routing config from leaking into unrelated scenarios.
·QA-Lab: make the commitments heartbeat-target-none scenario request an immediate heartbeat instead of waiting for the next scheduled heartbeat.
·Codex/Plugin SDK: deliver Codex-native subagent completions through a generic harness task runtime so harness-backed plugins can mirror durable task lifecycle and completion delivery without Codex-specific SDK imports. (#83445)
·Gateway CLI: surface local post-challenge connect assembly failures immediately instead of waiting for the wrapper timeout. Fixes #68944. (#85253)
·Messages: strip unsupported web-search citation control markers from outbound replies before they reach WebChat or external channels. Fixes #85193. (#85204)
·Agents/exec: treat denied exec approvals as terminal instead of feeding them back into agent follow-up work, and recognize Chinese stop phrases in abort handling. Fixes #69386. (#85194)
·CLI/agents: abort accepted Gateway-backed `openclaw agent` runs on SIGINT/SIGTERM so cron and supervisor timeouts do not leave remote agent work alive. Fixes #71710. (#84381)
·Codex app-server: retry replay-safe stdio client-close turns once using structured failure metadata, while surfacing idle `turn/completed` timeouts instead of blindly replaying active shared-server turns.
·Codex app-server: reject command overrides that embed Node or package-manager arguments and point users to `appServer.args`, so Windows startup avoids shell parsing failures. (#84417)
·Agents/Copilot: drop unsafe GitHub Copilot Responses reasoning replay items before send so Telegram direct sessions no longer fail on overlong replay IDs. Fixes #85197. (#85198)
·UI: add accessible tooltips to the topbar color-mode buttons so System, Light, and Dark choices are labeled on hover and focus. (#85227)
·fix: constrain Windows task script names [AI]. (#85064)
·Control UI: keep the chat session picker from hiding older or cross-agent configured conversations while preserving the bounded configured-agent refresh. (#85211)
·Agents/Anthropic: preserve unsafe integer tool-call input values in streamed Anthropic tool-use JSON, preventing Discord-style IDs from being rounded before dispatch. Fixes #47229. (#83063)
·Agents/Codex: estimate tool-heavy prompt pressure at the LLM boundary before provider submission, so persistent sessions compact before overflowing context windows. (#85541)
·Agents/hooks: wait for local one-shot CLI and Codex `agent_end` plugin hooks before process cleanup so terminal observability flushes reliably. (#85007)
·Providers/Google: preserve Gemini 3 cron `thinkingDefault: "low"` when stale catalog metadata says `reasoning:false`, so scheduled runs keep provider-supported thinking instead of downgrading to off. (#85185)
·CLI/agents: allow `openclaw agent --session-key` to target explicit session keys, including agent-scoped legacy keys. (#85121)
·Auto-reply/ACP: wait for same-channel block reply delivery before starting tool work, while still honoring ACP dispatch aborts so stopped turns do not wait on slow channel sends. (#83722)
·Codex/ACP: mark required child-run completions that only report progress, omit a final deliverable, or fail requester delivery as blocked while preserving real final reports. (#85110)
·Channels: treat bare abort messages such as `stop`, `abort`, and `wait` as immediate control commands in inbound debounce paths so stop requests are not delayed behind pending message coalescing. (#83348)
·Channels/message tool: resolve configured external channel plugins during in-agent channel selection, so `openclaw agent --local` message-tool sends no longer report an available channel as unavailable. (#85022)
·Agents/heartbeat: honor group/channel `message_tool` visible-reply policy and model-specific Codex runtime config for scheduled heartbeat runs, so failed internal tool output stays private. Fixes #85310. (#85357)
·Gateway/ACP: close child ACP sessions spawned via `sessions_spawn` when their parent session is reset or deleted, instead of leaving orphaned `claude-agent-acp` processes that accumulate and exhaust memory. Fixes #68916. (#85190)
·Codex app-server: block native execution paths when OpenClaw exec resolves to a node host while preserving the first-party CLI node binding path. Fixes #85012. (#85534)
·Diagnostics: bound cleanup timeout detail logs, emit drop summaries when async diagnostic bursts exceed the queue cap, and surface async queue drops through diagnostic telemetry.
·Agents/subagents: surface blocked child-run completions as errors instead of successful subagent finishes. (#80886)
·Context engines: fail closed with a descriptive error when the selected agent runtime cannot satisfy declared context-engine host requirements.
·Agents/Pi: treat accepted embedded `sessions_spawn` child-session handoffs as terminal progress so parent turns no longer report false non-deliverable failures. (#85054)
·CLI/models: resolve `openclaw models set` aliases from the runtime config while keeping authored aliases ahead of runtime-only defaults. (#83262)
·Doctor: show personal Codex CLI asset notices as info instead of warnings. Fixes #84859.
·WhatsApp: update Baileys to `7.0.0-rc13` and drop the obsolete logger type patch.
·CLI/update: pre-pack GitHub/git package update targets before the staged npm install, restoring `openclaw update --tag main` for one-off package updates. (#81296)
·Gateway: mirror successful same-source message-tool sends into session transcripts so delivered replies stay in later history/context. (#84837)
·Media generation: keep image, music, and video completion delivery from duplicating or losing task ownership when generated media finishes through active session replies. (#84006)
·CLI/doctor: remove stale bundled plugin load paths from old versioned OpenClaw package roots after pnpm/npm upgrades. Fixes #58626.
·Infra/json: retry transient `File changed during read` races while loading JSON state so config and state reads recover instead of failing the turn. (#84285)
·Plugins/providers: fail closed for workspace provider plugins during setup-mode discovery unless explicitly trusted, preventing untrusted workspace plugin code from running during provider setup. (#81069)
·Providers/Ollama: resolve configured Ollama Cloud `OLLAMA_API_KEY` markers to the real discovery key so cloud provider entries keep authenticated model catalog access. (#85037)
·Discord: keep persistent component registry fallback warnings actionable by forwarding structured error and cause metadata through the runtime logger. Fixes #84185. (#84190)
·Gateway/sessions: preserve compatible session auth profile overrides when switching models within the same provider, including provider-auth aliases. Fixes #81837. (#81886)
·Gateway/status: surface inbound delivery telemetry counters and transport-liveness warnings in `openclaw status --all`. Fixes #49577. (#72724)
·Docker: prune package-excluded plugin source workspaces and dependency closures so runtime images do not keep packages for plugins that were not opted in.
·Providers/Ollama: treat Docker/OrbStack host aliases as local Ollama endpoints so `ollama-local` marker auth works when OpenClaw runs inside a VM/container and Ollama runs on the host. Fixes #84875.
·QA-Lab: keep explicitly searchable/deferred OpenClaw dynamic tool rows report-only by default so tool-coverage gates do not treat mock discovery gaps as hard product failures. (#80319)
·Agents/config: keep non-Google provider model refs from being rewritten by Google Gemini preview-id normalization. (#84762)
·Installer: require a real controlling terminal before launching onboarding so headless `curl | bash` installs finish cleanly after installing the CLI.
·Agents/Codex: promote a completed final assistant response when a prompt timeout races Codex app-server completion instead of returning an empty timeout envelope. Refs #84516.
·Codex app-server: keep interrupted turn statuses from being treated as OpenClaw aborts by themselves, so tool-only turns remain eligible for no-visible-answer recovery. Fixes #84492.
·Agents: cap heartbeat model bleed context hints by the stored session window when runtime model metadata is unavailable, so overflow recovery advice does not suggest a larger window than the active session actually has.
·Control UI/Web Push: use `https://openclaw.ai` as the generated default VAPID subject instead of the old localhost mailbox so iOS PWA push setup uses an Apple-acceptable subject when `OPENCLAW_VAPID_SUBJECT` is unset. Fixes #83134. (#83317)
·Control UI: distinguish inherited thinking-off settings from explicit Off selections so the thinking selector no longer shows two identical Off rows. (#85223)
·Agents/Pi: keep embedded session transcript writes from tripping false takeover detection after packaged npm onboarding agent turns.
·Codex/TUI: surface Codex-native post-turn compaction failures instead of continuing uncompacted, and keep successful native compaction serialized before local idle/next-turn handling. Fixes #84305. (#85160)
·Memory/search: stop recall tracking from writing dreaming side-effect artifacts when `dreaming.enabled=false`, while preserving normal search results. Fixes #84436. (#84444)
·Diffs: render viewer toolbar icons from a closed icon-name map instead of HTML strings, removing the toolbar icon XSS sink. (#83955)
·QA: keep `pnpm qa:e2e` self-check runs inside the private QA runtime envelope even when inherited shell env disables bundled plugins.
·fix(config): validate browser sandbox bind sources [AI]. (#84799)
·doctor: constrain legacy plugin cleanup paths [AI]. (#84801)
·Update/doctor: prune stale local bundled plugin install records that point at old compiled bundled output so current bundled plugin schemas win after upgrade. (#84863)
·Providers/Ollama: preserve native Ollama tool-call IDs across assistant replay so Gemini over Ollama Cloud can keep its hidden function-call thought-signature handle.
·Discord: keep session recovery and `/stop` abort ownership on the source dispatch lane while bound ACP turns continue routing to their target session, so stalled pre-run work and late replies are cleared instead of leaking after stop. Fixes #84477. (#85100)
·Discord/voice-call: keep forced realtime voice consult diagnostics in debug logs instead of agent prompts, so callers do not hear OpenClaw policy text when the provider misses `openclaw_agent_consult`. (#84411)
·Codex app-server: mark missing turn completion after observed execution as replay-unsafe and release the session so follow-up turns can run. Fixes #84076. (#85107)
·Codex app-server: give visible `message` dynamic tool sends a longer timeout budget so slow channel delivery can return its own result or error instead of hitting the 30-second Codex wrapper. (#85216)
·Codex app-server: add a dedicated post-tool raw assistant completion idle timeout config so trusted heavy turns can wait longer after tool handoff without weakening final assistant release.
·Matrix: keep explicitly configured two-person rooms on the room route before stale `m.direct` or strict two-member DM fallback can bypass mention gating. Fixes #85017. (#85137)
·Agents/subagents: require explicit subagent allowlist targets to be configured agents so stale deleted-agent ids are omitted from `agents_list` and rejected by `sessions_spawn`. Fixes #84811. (#85154)
·PDF tool: time out idle remote PDF body reads after 120 seconds so stalled remote documents return an error instead of wedging the session. Fixes #68649. (#84768)
·Diagnostics/OpenTelemetry plugin: suppress handled OTLP exporter promise rejections so collector shutdowns no longer crash the Gateway. (#81085)
·Agents/exec: omit raw command text and env values from denied exec failure logs while keeping safe correlation metadata. Fixes #85049. (#85140)
·Media-understanding: restore the 4096-token default for image descriptions so reasoning-capable vision models no longer truncate before returning text, while preserving smaller model caps. (#84932)
·Media/audio: skip empty structured sherpa-onnx transcripts instead of treating the raw JSON payload as spoken text. (#84667)
·Agents/exec: preserve inherited XDG base-directory environment values for subprocesses while still rejecting agent-supplied XDG overrides. Fixes #84854. (#85139)
·Node/Linux: keep `OPENCLAW_GATEWAY_TOKEN` out of generated systemd unit files by writing node service token values to a node-specific env file. (#84408)
·Memory-core/dreaming: reuse stable narrative subagent session keys per workspace and phase while keeping per-run idempotency and bounded cleanup, so stale `dreaming-narrative-*` sessions do not accumulate. Fixes #68252, #69187, and #70402. (#70464)
·Trajectory/support: tolerate partial skill snapshot entries when building support metadata so rejected skill path scans no longer abort trajectory capture. (#71185)
·TUI: coalesce repeated idle Esc abort notices into a single `no active run xN` system row instead of appending duplicate rows.
·Telegram: honor `channels.telegram.pollingStallThresholdMs` in the default isolated polling path, restarting silent workers instead of leaving inbound updates wedged. Fixes #83950. (#84861)
·Telegram: dedupe replayed message dispatches by Telegram chat/message identity so isolated-ingress replays do not trigger duplicate model dispatches. Fixes #84886. (#85208)
·Slack: suppress reasoning payloads before reply delivery and dispatch accounting, so Slack monitor, slash-command, fallback, and direct reply paths do not leak model reasoning. Fixes #84319. (#84322)
·Slack: deliver native plugin approval prompts and updates when Slack native approvals are enabled, while keeping plugin approval authorization separate from exec approvers.
·Slack: keep native plugin approval prompts in the originating app conversation thread when the live Slack turn source is a `D...` conversation.
·Agents/Pi: disable the embedded pi-coding-agent runtime auto-retry so OpenClaw's own retry and failover loop does not replay failed tool calls through a nested SDK retry. Fixes #73781. (#74434)
·CLI/perf: keep `setup --help`, `onboard --help`, and `configure --help` out of the full wizard runtime while preserving the existing help output. (#84488)
·CLI/perf: keep `agents --help` out of agents action/runtime imports so help, completion, and command discovery paths avoid loading the full agents runtime. (#84483)
·CLI/perf: keep `secrets --help` and `nodes --help` on the precomputed help path so parent help avoids loading action-heavy command runtime modules. (#84818)
·CLI/perf: serve `doctor`, `gateway`, `models`, and `plugins` parent help from startup metadata so common subcommand help avoids full CLI program construction. (#84786)
·Codex/Lossless: keep context-engine history on the canonical run session when Telegram DMs use per-peer runtime policy keys. Fixes #84936. (#84954)
·Codex: keep heartbeat response tool schemas durable without exposing dynamic tools disabled by turn policy, so heartbeat wakeups can reuse threads while scoped tool allowlists stay enforced. (#84681)
·Auth/OAuth: skip the refresh adapter when a stored OAuth credential has no refresh token so agent turns fail fast on missing-key instead of waiting on the 120s refresh timeout.
·Auth/Codex: load legacy OAuth sidecar credentials in the embedded runner's secrets-runtime auth loaders so Telegram replies, cron-triggered turns, and other isolated sub-agent lanes can reach the existing #83312 refresh-and-rewrite migration instead of failing with `No API key found for provider "openai-codex"` until the user runs `openclaw doctor`.
·Codex/failover: classify `deactivated_workspace` as a permanent auth failure so configured fallback models can advance when a Codex workspace is deactivated. (#55893)
·Exec: keep configured `tools.exec.pathPrepend` entries ahead of user shell startup PATH changes on POSIX gateway runs. (#81403)
·Gateway/sessions: allow shared-secret bearer callers to read and stream session history without an explicit scope header. (#81815)
·Agents/embedded runner: classify HTML auth provider responses as `auth_html` and return a re-authentication hint instead of the CDN-blocked copy that `upstream_html` returns. Cloudflare Access login pages, nginx basic-auth challenges, and gateway login walls all produce HTML auth bodies that were previously misdiagnosed as transient CDN blocks. (#79900)
·TUI/streaming watchdog: dismiss the `This response is taking longer than expected` notice as soon as a chat event for the same run arrives, so the message no longer sits next to the recovered response when the run was only briefly silent. Refs #67052, #69081 (closed), prior attempt #69026.
·Agents/Pi: tolerate OpenClaw-owned transcript writes while embedded prompts are released for model I/O, keeping long-running Feishu, Slack, Telegram, and cron turns from failing with false session-takeover errors. Fixes #84059. (#84250)

Release verification

·npm package: https://www.npmjs.com/package/openclaw/v/2026.5.24-beta.1
·registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.5.24-beta.1.tgz
·integrity: `sha512-dGiCraGkifa+Zps/FHYCdnSUE2CJ28I3uSl5SVWHpEUZLGmkXoCC69ollYf+jMrRElhO7J9Hqy2Qt7p+PvBclA==`
·full release CI report: https://github.com/openclaw/releases/blob/main/evidence/2026.5.24-beta.1/release-evidence.md
·release publish: https://github.com/openclaw/openclaw/actions/runs/26364043947
·npm preflight: https://github.com/openclaw/openclaw/actions/runs/26362633423
·full release validation: https://github.com/openclaw/openclaw/actions/runs/26362633403
·plugin npm publish: https://github.com/openclaw/openclaw/actions/runs/26364110488
·plugin ClawHub publish: dispatched separately, not awaited by this proof: https://github.com/openclaw/openclaw/actions/runs/26364111683
·OpenClaw npm publish: https://github.com/openclaw/openclaw/actions/runs/26364159610
·npm Telegram beta E2E: https://github.com/openclaw/openclaw/actions/runs/26364277200

v2026.5.222026-05-24

openclaw 2026.5.22

GitHub ↗

Changes

·Gateway/perf: reuse process-stable channel catalog reads, avoid repeated bundled-channel boundary checks, and rotate gateway watch CPU profiles so benchmark runs do not accumulate unbounded artifacts.
·Gateway/perf: reuse immutable plugin metadata snapshots across startup, config, model, channel, setup, and secret metadata readers so hot paths avoid repeated plugin file stats and manifest registry reloads.
·Gateway/perf: lazy-load startup-idle plugin work, core gateway method handlers, and the embedded ACPX runtime so Gateway health and ready signals no longer wait on unused handler trees or ACPX probes.
·Gateway/perf: cache plugin SDK public-surface alias maps and skip irrelevant macOS Linuxbrew PATH probes so Gateway startup avoids repeated filesystem walks and slow missing-directory stats.
·Meeting Notes: add a source-only external meeting-notes plugin and SDK source-provider contract outside the core npm package, with auto-start capture config, manual transcript imports, read-only `openclaw meeting-notes` CLI access, and Discord voice as the first live source.
·Docs/channels/config: add Signal `configPath`, Telegram wildcard topic defaults, local-time backup archive names, Termux home fallback, include-path validation, secret-scanner-safe placeholder guidance, Gemini CLI/Antigravity media guidance, and macOS VM auto-login guidance.
·Docs: clarify model-usage portability, Codex migration prerequisites, status bootstrap wording, thread-bound subagent limits, hook ownership, and config-preserving safety guidance.
·Docs: clarify README onboarding and Gateway startup paths, WhatsApp QR/408 recovery, cron output language prompts, skill advanced features, gateway upstream 403 troubleshooting, and plugin fallback override guidance.
·Docs: clarify context-pruning ratio bounds, local dashboard recovery, CLI env markers, remote onboarding token behavior, and Peekaboo Bridge permissions for subprocess agents.
·Docs: clarify browser CDP diagnostics, Plugin SDK allowlist imports, status-reaction timing defaults, queue steering behavior, limited-tool troubleshooting, cron HEARTBEAT handling, Telegram multi-agent groups, Bitwarden SecretRef setup, and EasyRunner deployments.
·Crabbox/Testbox: run clean sparse-checkout Testbox syncs from a temporary full checkout and route remote changed gates through Corepack pnpm.
·Docs: clarify IPv4-only Gateway BYOH binding, trusted-proxy scope clearing, Android pairing approval, macOS Accessibility grants, Zalo profile env vars, password-store SecretRef setup, and Chinese memory navigation.
·Docs: consolidate GLM under Z.AI, add the Upstash Box install guide and Gateway exposure runbook, clarify MEDIA directives, Copilot and Voyage setup, config path quoting, real behavior proof, and memory-file write guidance.
·Docs: clarify media provider credentials, Codex/OpenClaw code-mode boundaries, Slack and Telegram ack reactions, Feishu dynamic agents, secrets plaintext boundaries, memory guidance, and Chinese glossary terms.
·Packaging: exclude documentation images and assets from the npm tarball, reducing published package size without affecting runtime docs search or CLI behavior.
·Media understanding: stop auto-probing Gemini CLI and use Antigravity CLI only as a lower-priority image/video fallback after configured provider APIs.
·Agents/subagents: limit default sub-agent bootstrap context to `AGENTS.md` and `TOOLS.md`, keeping persona, identity, user, memory, heartbeat, and setup files out of delegated workers by default. (#85283)
·Maintainer skills: exclude plugin SDK/API boundary work from `openclaw-landable-bug-sweep` so bugbash sweeps stay focused on small paper-cut fixes.
·QA-Lab/diagnostics: extend the OpenTelemetry smoke harness to prove trace, metric, and log export, and add first-class Prometheus and observability smoke aliases.
·Plugin SDK: add a generic channel-message poll sender so channel plugins can expose poll delivery without depending on channel-specific SDK facades.
·Crabbox: keep the local wrapper's provider validation synced with the installed Crabbox binary while preserving supported aliases such as `docker` and `blacksmith`. (#85302)
·Maintainer skills: add `openclaw-landable-bug-sweep` for producing five small, reviewed, CI-green OpenClaw bugfix PRs from issue/PR sweeps.
·Control UI/chat: add search and Load More pagination to the chat session picker, keeping initial session loads bounded while making older conversations reachable. (#85237)
·CLI/onboarding: start classic onboarding when bare `openclaw` runs before an authored config exists, while keeping configured installs on Crestodian. (#72343)
·Discord: allow configuring a bounded `agentComponents.ttlMs` callback registry lifetime for long-running component workflows, with per-account overrides and a 24-hour cap. (#84189)
·xAI/Grok: reuse xAI OAuth auth profiles for Grok `web_search`, thread active-agent auth through web search, add Grok model aliases, and let media providers declare default operation timeouts. (#85182)
·Plugin SDK: add row-level session workflow helpers and deprecate `loadSessionStore` so plugins can read and patch sessions without depending on the legacy whole-store shape. (#84693)
·Gateway/plugins: reuse a compatible Gateway startup plugin registry during dispatch so safe plugin dispatches avoid redundant registry loading. (#84324)
·Plugins/SDK: add a general `embeddingProviders` capability contract and registration API so embeddings can become a reusable provider surface outside memory-specific adapters.
·Dependencies: refresh provider, plugin, UI, and tooling packages, update `protobufjs` to 8.4.0 to clear the current npm advisory, and carry the Claude ACP completion patch forward to `@agentclientprotocol/claude-agent-acp` 0.36.1.
·Agents/tools: remove the old sender-owner tool gating path so configured tools stay visible for trusted sessions while command and channel-action auth still carry real sender identity.
·QA-Lab: add curated mock JSONL replay fixtures and first-drift reporting for runtime-parity audits. (#80323, refs #80176)
·QA-Lab: add a QA bus tool-trace visibility scenario for sanitized tool-call assertions.
·QA-Lab: replace generic evidence framing in seeded scenario prompts with concrete observed QA behavior.
·QA-Lab: list named scenario packs in the coverage report so personal-agent privacy coverage stays visible in audits.
·QA-Lab: list live transport lane membership in the coverage report so real transport checks stay separate from seeded qa-channel scenarios.
·Release/package: run package integrity checks before package acceptance lanes so public install/update validation fails before private QA assets can leak into the package.
·QA-Lab: include the optional 100-turn runtime parity soak in release-soak artifacts so long-run Codex/Pi transcript drift stays visible outside the default gate. (#80395)
·QA-Lab: add a live-only long-context progress watchdog scenario for Codex app-server timeout and stalled-run sentinels. (#80323)
·QA-Lab: tag gateway restart recovery and streaming final-integrity scenarios as live-only runtime parity lanes. (#80323)
·QA-Lab: add a personal-agent failure recovery scenario that checks honest partial status, retry boundaries, and local recovery artifacts. (#83872)
·QA-Lab: include an opt-in `update.run` package self-upgrade sentinel for destructive latest-package recovery checks.
·QA-Lab: add Codex plugin lifecycle and auth-profile fixture coverage for missing installs, pinned-version drift, first-turn install ordering, and doctor migration safety. (#80323, refs #80174)
·Models/perf: pre-warm the provider auth-state map at gateway startup so `/models` and every model-listing call short-circuits the per-provider plugin / external-CLI discovery on the hot path. Per-call cost drops from ~20 s to ~5 ms (~4,100×); the one-time startup warm resets and re-warms after hot reloads. (#84816)
·Release/security: ship the root npm package and OpenClaw-owned npm plugins with generated shrinkwrap, support bundled plugin runtime dependencies for suitable plugin tarballs, and require review for lockfile/shrinkwrap changes so published installs use locked dependency graphs.
·Tests/perf: isolate doctor core health check unit coverage from real skills/workspace discovery so `doctor-core-checks` no longer dominates unit perf while keeping one real skills-readiness smoke. (#84493)

Fixes

·WebChat: summarize internal message-tool source replies so tool cards no longer duplicate the visible reply body. (#84773)
·Gateway: preserve deferred lifecycle-error cleanup across later non-terminal events so provider timeouts can persist failed session state instead of leaving sessions stuck running. (#85256, fixes #63819)
·Agents/subagents: report tool-only child progress during timeout summaries instead of showing no visible output.
·Telegram/ACP: preserve explicit `:topic:` conversation suffixes when inbound ACP targets do not carry a separate thread id.
·Browser/proxy: bypass the managed proxy for the exact local managed Chrome CDP readiness and DevTools WebSocket endpoints, so `openclaw browser start` works when the operator proxy blocks loopback egress. (#83255)
·Ollama: bypass the managed proxy for configured local embedding origins while keeping SSRF guardrails on unconfigured targets.
·OpenAI/images: route Codex API-key image generation through the native OpenAI Images API instead of the Codex OAuth streaming backend, avoiding 401s from valid API keys.
·Agents/OpenAI completions: omit empty tool payload fields for proxy-like OpenAI-compatible endpoints so strict vLLM-style servers accept tool-free turns. (#85835)
·Checks/Windows: route full `pnpm check` stage commands through the managed child runner so Windows avoids Node shell-argv deprecation warnings there too.
·Checks/Windows: run managed child commands through explicit `cmd.exe` wrapping instead of Node shell mode with argv, avoiding Node 24 subprocess deprecation warnings during changed checks.
·Gateway: omit internal stream-error placeholder entries from agent prompt history so failed assistant turns are not replayed as model-authored text. (#85652)
·Sessions: enforce the session write-lock max-hold policy during lock acquisition so long-held locks can be reclaimed before the stale-lock window. (#85764)
·Models: prune retired Groq, GitHub Copilot, OpenAI, xAI, and old Claude catalog entries, with doctor migration to upgrade existing configs to current provider refs.
·Doctor/update: recognize junction-backed source checkouts as git installs by comparing canonical paths before showing package-manager update guidance. Fixes #82215.
·Channels: honor `/verbose on` for tool/progress summaries across direct chats, groups, channels, and forum topics while preserving quiet default behavior. (#85488)
·CLI/skills: show an all-ready note with next-step commands when skill setup has no missing dependencies to install. (#85032)
·Microsoft Foundry: route DeepSeek V4 Pro and Flash models through the Foundry Responses API while keeping older DeepSeek models on their existing path. (#85549)
·Status/usage: show configured cost estimates for AWS SDK models in full usage output while keeping token-only usage replies cost-free. (#85619)
·Agents/OpenAI Responses: retry non-visible reasoning-only turns for OpenAI Responses API families instead of treating them as empty failed turns. (#85603)
·Directive tags: preserve message and content-part object identity when display stripping makes no directive-tag changes. (#85682)
·Telegram: send local `path`/`filePath` and structured attachment media from `sendMessage` actions instead of dropping them or sending text-only messages. (#85219)
·Sessions/status: show the estimated context budget when fresh provider usage is unavailable and clear stale estimates across session resets and compaction boundaries. (#84830)
·Gateway/config: pin relative `OPENCLAW_STATE_DIR` overrides to an absolute path at startup so later working-directory changes cannot retarget gateway state. (#52264)
·Release/package: run npm release, prepublish, and postpublish verification through Windows-safe npm command shims so native Windows checks can execute `npm.cmd` instead of treating it as a binary.
·Agents/harness: pass CLI runtime aliases through harness selection so provider-owned CLI aliases no longer get rejected before reaching the right runtime. (#85631)
·Secrets: show the irreversible apply warning after interactive `secrets configure` confirmation so confirmed migrations still get the final safety prompt. (#85638)
·Agents/CLI output: ignore cumulative Claude `stream-json` result usage when assistant usage events are present, preventing inflated cache-read accounting. (#85625)
·CLI: keep `waitForever()` alive by leaving its keep-alive interval ref'd so the public helper no longer exits immediately with Node's unsettled-await code. (#85694)
·Agents/bootstrap: guard bootstrap name checks against missing file names so malformed bootstrap entries warn and truncate instead of crashing. Fixes #85523. (#85615)
·CLI/tasks: reject partially numeric `openclaw tasks audit --limit` values so audit limits must be real positive integers instead of accepting strings like `5abc`. (#84901)
·Status/diagnostics: bound deep Docker audit probes so `openclaw status --deep` reports slow container checks instead of hanging behind unbounded inspection. (#85476)
·Providers/Anthropic: migrate 1M context handling to GA-capable Claude 4.x models by sizing eligible models at 1M without the retired `context-1m-2025-08-07` beta, ignoring that retired beta in older configs, and preserving OAuth-required Anthropic beta headers. (#45613)
·Cron/Telegram: parse forum-topic delivery targets through the Telegram plugin instead of cron core, including `:topic:` and `:topicId` forms for announce delivery.
·Twitch: keep stale message-handler cleanup callbacks from removing newer handler registrations for the same account, preserving inbound message delivery after reconnects. Fixes #83888. (#85425)
·Memory/LanceDB: expose public memory artifacts through the active memory provider bridge so memory-wiki imports durable memory files, daily notes, dream reports, and event logs without depending on memory-core internals. Fixes #83604. (#85060)
·Crabbox: keep AWS hydration compatible with local Actions replay by inlining the hydrate workflow's Node/pnpm setup instead of invoking repo-local composite actions.
·Agents/subagents: simplify native sub-agent completion handoff so children report their latest visible assistant result to the requester without using `message`, while keeping parent-owned message-tool delivery policy intact. Fixes #85070. (#85089)
·Docker setup: stop printing the Gateway bearer token in setup logs and printed follow-up commands.
·Agents: let embedded compaction fallback retries proceed when PI-compatible candidates do not need agent harness plugin preparation.
·Agents/tools: honor configured custom provider API keys when deciding whether media, image-generation, video-generation, music-generation, and PDF tools are available. (#85570)
·StepFun: stop advertising stale generic API key auth choices so onboarding only offers runtime-backed Standard and Step Plan choices.
·Diagnostics: keep OpenTelemetry log bodies behind explicit content capture and scrub scoped agent-session keys from OpenTelemetry and Prometheus labels while preserving bounded queue-lane prefixes.
·Windows installer: fail Git checkout installs when `pnpm install` or `pnpm build` fails instead of writing a wrapper to a missing CLI build.
·Sessions: surface previous-transcript archive failures during `/new` rotation so disk rename errors are logged instead of silently hiding stranded transcript files. Fixes #81984. (#85586, from #82081)
·TUI/agents: mirror internal-ui message-tool replies into final chat output so message-tool-only agents remain visible in `openclaw tui`. Fixes #85538.
·Agents: keep parallel OpenAI-compatible tool-call deltas in separate argument buffers so interleaved tool calls no longer corrupt streamed arguments. (#82263)
·Memory/doctor: report missing or unusable QMD workspace directories as workspace failures instead of generic binary failures. (#63167)
·Debug proxy: record CONNECT client-socket errors and destroy the paired upstream socket so abrupt client disconnects no longer leak tunnel resources. (#82444)
·Diffs: continue hydrating later diff cards when one card fails so a single broken card no longer blanks the whole diff viewer. (#84775)
·Mac app: use the native settings sidebar window chrome so the sidebar toggle stays on the left and content no longer clips under oversized titlebar padding.
·QA-Lab/Codex: bundle auth/plugin fixture imports for flow scenarios and let terminal async media tools end Codex app-server turns without timing out. (#80397, refs #80323)
·Gateway/agents: preserve fresh session overrides and metadata when stale cached agent-session entries race with store updates, so subagent model/provider overrides and routing policy survive concurrent writes. (#19328)
·Control UI/chat: keep chat session search inline with the session selector so the header no longer shows a duplicate standalone search row.
·Control UI/chat: collapse focused-mode header chrome and suppress hidden-header scroll updates so focus mode no longer jumps while scrolling.
·Codex app-server: restart the native app-server and retry once when server-side compaction times out, so preflight compaction stalls recover instead of failing every dispatch. (#85500)
·Restore Control UI gateway token pairing [AI]. (#85459)
·OpenAI video: honor configured provider request private-network opt-in for local/custom video endpoints so explicitly trusted mock and self-hosted providers are not blocked.
·OpenAI video: send uploaded video edit requests to the documented `/videos/edits` endpoint with a `video` file instead of posting MP4 references to `/videos`.
·Agents/channels: preserve message-tool delivery evidence through gateway agent completion handoffs so successful generated media sends are not followed by false failure messages.
·CLI/update: repair managed npm plugin `openclaw` peer links during post-core convergence and reject stale or wrong-target peer links before restart. (#83794)
·CLI/agents: default new omitted-account bindings to all accounts when the channel has multiple configured accounts, and clarify account-scope docs. (#49769)
·Codex app-server: let authorized `/codex` control commands such as `/codex detach` escape plugin-owned conversation bindings while keeping unknown or unauthorized slash text routed to the bound plugin. Fixes #85157. (#85188)
·Auto-reply/models: keep `/models` browse replies fast by sharing the bounded read-only catalog path with Gateway model listing. (#84735)
·Codex app-server: disable native Code Mode when the effective exec host is `node` and keep OpenClaw `exec`/`process` available, so `/exec host=node` routes shell commands through the selected node instead of the gateway. Fixes #85012. (#85090)
·Agents: bound embedded auto-compaction session write-lock watchdogs to the compaction timeout instead of the full run timeout, so stuck compaction cannot hold the live session lock for the whole run window. (#84949)
·Gateway/agents: return phase-aware `agent.wait` timeout attribution and only cool auth profiles on provider-started timeouts. Refs #65504.
·Gateway: defer provider auth-state prewarm until after startup readiness so early gateway tool/session requests are not blocked by provider auth discovery. (#85272)
·Gateway/models: coalesce provider auth-state rewarms after auth-profile failures and log event-loop delay for warm/rewarm work, so provider auth bursts no longer stack full auth sweeps behind channel replies.
·Gateway/models: stop cancelled provider auth-state prewarms from continuing full provider sweeps, so reload and auth-failure bursts no longer keep startup busy.
·Agents/Codex: show the first plan update as a transient chat status notice without counting it as final assistant content.
·CLI/update: walk the macOS process ancestry and honor the inherited Gateway runtime PID before package updates stop the managed Gateway service, so nested in-band updater children can refuse instead of killing the LaunchAgent-supervised Gateway that owns them. Fixes #85120.
·Gateway/LaunchAgent: wait for launchd reload bootout to finish and fall back to kickstart when bootstrap races, so reload handoff does not leave the service deregistered. Fixes #84630. (#84641)
·Gateway/LaunchAgent: treat a concurrent launchd bootstrap as a successful restart when the service is already loaded, avoiding false macOS Gateway restart failures. Fixes #84721. (#84722)
·Gateway/service: include the active `openclaw` command bin directory in managed service PATH generation and doctor audit expectations for npm-global macOS installs. Fixes #84201. (#84475)
·Control UI/chat: disable the thinking selector for known non-reasoning models instead of showing duplicate Off choices. Fixes #84069.
·Memory: expand `~` in configured extra memory paths before resolving them, so home-relative folders are not treated as workspace-relative. Fixes #58026.
·Skills: treat `openclaw.os: macos` as Darwin when checking skill requirements, so macOS-only skills no longer report as missing on macOS hosts. Fixes #61338.
·Control UI/logs: strip ANSI escape sequences from displayed Gateway log messages so color codes no longer appear as raw text. Fixes #64399.
·Docker: pre-create the workspace and auth-profile config mount points with `node` ownership so first-run named volumes do not start root-owned. Fixes #85076.
·Telegram: pass configured markdown table mode through outbound markdown chunking so chunked sends render tables consistently. Fixes #85085.
·CLI/update: preserve managed Gateway service environment during package cutovers so macOS LaunchAgent repair/restart reads the pre-update service state instead of caller shell state. (#83026)
·Agents/providers: honor per-model `api` and `baseUrl` overrides in custom provider auth hooks and transport selection. Fixes #80487. (#80488)
·Gateway/restart: eager-load the lifecycle runtime before in-place upgrade signal handling so package replacement does not deadlock restart imports. (#84890)
·CLI/update: start managed Gateway update handoff helpers from a stable existing directory and tolerate deleted cwd/package roots during macOS LaunchAgent handoff. Fixes #83808. (#83875)
·Skills: watch each shared skill directory once across agent workspaces instead of once per agent, preventing file-descriptor exhaustion (`EMFILE`) that disposed bundle-mcp processes and stalled sessions on multi-agent gateways. Fixes #84968. (#85130)
·Release/security: keep generated npm shrinkwrap package versions inside the pnpm lock graph so published package locks cannot bypass pnpm dependency age and override policy.
·Cron: honor `cron.retry.retryOn: ["network"]` for common network error codes such as `EAI_AGAIN`, `EHOSTUNREACH`, and `ENETUNREACH`.
·Gateway chat: broadcast returned agent-run error payloads after an agent starts so ACP/WebChat clients receive terminal idle-timeout errors. Fixes #84945.
·Gateway chat display: preserve OpenAI-compatible `prompt_tokens`, `completion_tokens`, and `total_tokens` usage fields in sanitized chat history so llama.cpp sessions keep context counts. Fixes #77992.
·Dashboard/CLI: allow macOS browser launching through `open` even when SSH environment variables are present, while preserving Linux SSH no-display protection. Fixes #67088.
·Codex app-server: keep native web search observations out of mirrored chat transcripts while preserving tool progress telemetry. Fixes #85109.
·OpenCode Go: strip unsupported Kimi reasoning replay fields before provider requests so repeated `kimi-k2.6` turns do not fail schema validation. Fixes #83812.
·Browser/CDP: add a WSL2 portproxy self-loop hint when Chrome DevTools endpoints accept connections but return an empty HTTP reply. Fixes #59209.
·Agents/OpenAI: preserve structured provider error code, type, and redacted body metadata on boundary-aware transport failures.
·Doctor/Codex: point native Codex asset warnings at the canonical `openclaw migrate plan codex` preview command. Fixes #84948.
·CLI/models: make `capability model auth logout --agent` remove auth profiles from the selected non-default agent store. Fixes #85092.
·Gateway/models: reuse prepared provider auth metadata during model-listing auth checks so repeated lookups avoid broad plugin discovery while preserving synthetic local auth.
·CLI/status: suppress systemd user-service setup hints when `openclaw status --deep` can already reach a running Gateway RPC service. Fixes #85094.
·CLI/devices: recover local approval when a same-device repair request replaces the request ID being approved.
·CLI/agents: retry transient normal-close Gateway handshakes before falling back to embedded `openclaw agent` execution.
·CLI/update: keep managed Gateway service stop/restart status lines out of `openclaw update --json` stdout so package-update automation can parse the JSON payload.
·Plugins: resolve OpenClaw plugin SDK subpaths for native external plugin runtimes without mutating package installs or broadening process-wide module resolution.
·Agents/OpenAI: preserve Responses and Chat Completions `reasoning_tokens` usage metadata without double-counting it in aggregate output tokens. (#85319)
·Control UI/chat: convert pasted `data:image/...;base64,...` clipboard text into an image attachment instead of dumping the payload into the composer. Fixes #62604.
·Providers/Gemini: strip fractional seconds from web-search time range filters so Gemini accepts freshness-bound search requests. (#85071)
·OpenAI Codex: preserve image input support for sparse `openai-codex/gpt-5.5` catalog rows. (#85095)
·CLI/models: add a piped or pasted API-key path for OpenAI Codex auth and warn when API keys are pasted into token-mode auth. (#85533)
·Telegram: dead-letter missing-harness isolated ingress failures so a poisoned spooled update no longer blocks later same-lane messages. Fixes #85470. (#85605)
·Plugins/discovery: strip `-plugin` package suffixes when deriving plugin id hints so package names line up with manifest ids. (#85170)
·Tlon: stop advertising a non-existent agent tool contract in the plugin manifest.
·Telegram: preserve fenced code block languages through Markdown rendering so Telegram receives `language-*` code classes. (#85209)
·Windows installer: run npm and Corepack command shims from a Windows-local directory so installs launched from WSL2 UNC paths do not fail before OpenClaw is installed.
·Windows updates: roll back git-backed updates to the previous checkout when dependency install, build, UI build, or doctor repair fails.
·Windows installer: persist user-local portable Git on PATH and activate the repo-pinned pnpm version for git-backed installs and updates.
·Windows installer: bootstrap a user-local portable Node.js when native Windows has no Node and no winget, Chocolatey, or Scoop, so first-run installs can continue on raw hosts.
·Windows installer: extract the downloaded portable Node.js directory with native `tar` before falling back to .NET zip extraction, avoiding PowerShell 5.1 archive and path-length failures.
·fix(integrations): enforce channel read target allowlists [AI]. (#84982)
·Agents/heartbeat: route single-owner `session.dmScope=main` direct-message exec and cron event wakes back to the agent main session so async completions no longer strand context in orphan direct-DM queues. Fixes #71581. (#83743)
·Agents/code-mode: expose outer code-mode `exec` source through the `command` hook alias with `toolKind`/`toolInputKind` discriminators so exec-shaped policies can distinguish code-mode cells. (#83483)
·Agents/code mode: return structured timeout and runtime-unavailable error codes for known worker failures. Fixes #83389. (#83444)
·QA-Lab: isolate multi-scenario suite workers when scenarios need startup config patches, preventing message-routing config from leaking into unrelated scenarios.
·QA-Lab: make the commitments heartbeat-target-none scenario request an immediate heartbeat instead of waiting for the next scheduled heartbeat.
·Codex/Plugin SDK: deliver Codex-native subagent completions through a generic harness task runtime so harness-backed plugins can mirror durable task lifecycle and completion delivery without Codex-specific SDK imports. (#83445)
·Gateway CLI: surface local post-challenge connect assembly failures immediately instead of waiting for the wrapper timeout. Fixes #68944. (#85253)
·Messages: strip unsupported web-search citation control markers from outbound replies before they reach WebChat or external channels. Fixes #85193. (#85204)
·Agents/exec: treat denied exec approvals as terminal instead of feeding them back into agent follow-up work, and recognize Chinese stop phrases in abort handling. Fixes #69386. (#85194)
·CLI/agents: abort accepted Gateway-backed `openclaw agent` runs on SIGINT/SIGTERM so cron and supervisor timeouts do not leave remote agent work alive. Fixes #71710. (#84381)
·Codex app-server: retry replay-safe stdio client-close turns once using structured failure metadata, while surfacing idle `turn/completed` timeouts instead of blindly replaying active shared-server turns.
·Codex app-server: reject command overrides that embed Node or package-manager arguments and point users to `appServer.args`, so Windows startup avoids shell parsing failures. (#84417)
·Agents/Copilot: drop unsafe GitHub Copilot Responses reasoning replay items before send so Telegram direct sessions no longer fail on overlong replay IDs. Fixes #85197. (#85198)
·UI: add accessible tooltips to the topbar color-mode buttons so System, Light, and Dark choices are labeled on hover and focus. (#85227)
·fix: constrain Windows task script names [AI]. (#85064)
·Control UI: keep the chat session picker from hiding older or cross-agent configured conversations while preserving the bounded configured-agent refresh. (#85211)
·Agents/Anthropic: preserve unsafe integer tool-call input values in streamed Anthropic tool-use JSON, preventing Discord-style IDs from being rounded before dispatch. Fixes #47229. (#83063)
·Agents/Codex: estimate tool-heavy prompt pressure at the LLM boundary before provider submission, so persistent sessions compact before overflowing context windows. (#85541)
·Agents/hooks: wait for local one-shot CLI and Codex `agent_end` plugin hooks before process cleanup so terminal observability flushes reliably. (#85007)
·Providers/Google: preserve Gemini 3 cron `thinkingDefault: "low"` when stale catalog metadata says `reasoning:false`, so scheduled runs keep provider-supported thinking instead of downgrading to off. (#85185)
·CLI/agents: allow `openclaw agent --session-key` to target explicit session keys, including agent-scoped legacy keys. (#85121)
·Auto-reply/ACP: wait for same-channel block reply delivery before starting tool work, while still honoring ACP dispatch aborts so stopped turns do not wait on slow channel sends. (#83722)
·Codex/ACP: mark required child-run completions that only report progress, omit a final deliverable, or fail requester delivery as blocked while preserving real final reports. (#85110)
·Channels: treat bare abort messages such as `stop`, `abort`, and `wait` as immediate control commands in inbound debounce paths so stop requests are not delayed behind pending message coalescing. (#83348)
·Channels/message tool: resolve configured external channel plugins during in-agent channel selection, so `openclaw agent --local` message-tool sends no longer report an available channel as unavailable. (#85022)
·Agents/heartbeat: honor group/channel `message_tool` visible-reply policy and model-specific Codex runtime config for scheduled heartbeat runs, so failed internal tool output stays private. Fixes #85310. (#85357)
·Gateway/ACP: close child ACP sessions spawned via `sessions_spawn` when their parent session is reset or deleted, instead of leaving orphaned `claude-agent-acp` processes that accumulate and exhaust memory. Fixes #68916. (#85190)
·Codex app-server: block native execution paths when OpenClaw exec resolves to a node host while preserving the first-party CLI node binding path. Fixes #85012. (#85534)
·Diagnostics: bound cleanup timeout detail logs, emit drop summaries when async diagnostic bursts exceed the queue cap, and surface async queue drops through diagnostic telemetry.
·Agents/subagents: surface blocked child-run completions as errors instead of successful subagent finishes. (#80886)
·Context engines: fail closed with a descriptive error when the selected agent runtime cannot satisfy declared context-engine host requirements.
·Agents/Pi: treat accepted embedded `sessions_spawn` child-session handoffs as terminal progress so parent turns no longer report false non-deliverable failures. (#85054)
·CLI/models: resolve `openclaw models set` aliases from the runtime config while keeping authored aliases ahead of runtime-only defaults. (#83262)
·Doctor: show personal Codex CLI asset notices as info instead of warnings. Fixes #84859.
·WhatsApp: update Baileys to `7.0.0-rc13` and drop the obsolete logger type patch.
·CLI/update: pre-pack GitHub/git package update targets before the staged npm install, restoring `openclaw update --tag main` for one-off package updates. (#81296)
·Gateway: mirror successful same-source message-tool sends into session transcripts so delivered replies stay in later history/context. (#84837)
·Media generation: keep image, music, and video completion delivery from duplicating or losing task ownership when generated media finishes through active session replies. (#84006)
·Infra/json: retry transient `File changed during read` races while loading JSON state so config and state reads recover instead of failing the turn. (#84285)
·Plugins/providers: fail closed for workspace provider plugins during setup-mode discovery unless explicitly trusted, preventing untrusted workspace plugin code from running during provider setup. (#81069)
·Providers/Ollama: resolve configured Ollama Cloud `OLLAMA_API_KEY` markers to the real discovery key so cloud provider entries keep authenticated model catalog access. (#85037)
·Discord: keep persistent component registry fallback warnings actionable by forwarding structured error and cause metadata through the runtime logger. Fixes #84185. (#84190)
·Gateway/sessions: preserve compatible session auth profile overrides when switching models within the same provider, including provider-auth aliases. Fixes #81837. (#81886)
·Gateway/status: surface inbound delivery telemetry counters and transport-liveness warnings in `openclaw status --all`. Fixes #49577. (#72724)
·Docker: prune package-excluded plugin source workspaces and dependency closures so runtime images do not keep packages for plugins that were not opted in.
·Providers/Ollama: treat Docker/OrbStack host aliases as local Ollama endpoints so `ollama-local` marker auth works when OpenClaw runs inside a VM/container and Ollama runs on the host. Fixes #84875.
·QA-Lab: keep explicitly searchable/deferred OpenClaw dynamic tool rows report-only by default so tool-coverage gates do not treat mock discovery gaps as hard product failures. (#80319)
·Agents/config: keep non-Google provider model refs from being rewritten by Google Gemini preview-id normalization. (#84762)
·Installer: require a real controlling terminal before launching onboarding so headless `curl | bash` installs finish cleanly after installing the CLI.
·Agents/Codex: promote a completed final assistant response when a prompt timeout races Codex app-server completion instead of returning an empty timeout envelope. Refs #84516.
·Codex app-server: keep interrupted turn statuses from being treated as OpenClaw aborts by themselves, so tool-only turns remain eligible for no-visible-answer recovery. Fixes #84492.
·Agents: cap heartbeat model bleed context hints by the stored session window when runtime model metadata is unavailable, so overflow recovery advice does not suggest a larger window than the active session actually has.
·Control UI/Web Push: use `https://openclaw.ai` as the generated default VAPID subject instead of the old localhost mailbox so iOS PWA push setup uses an Apple-acceptable subject when `OPENCLAW_VAPID_SUBJECT` is unset. Fixes #83134. (#83317)
·Control UI: distinguish inherited thinking-off settings from explicit Off selections so the thinking selector no longer shows two identical Off rows. (#85223)
·Agents/Pi: keep embedded session transcript writes from tripping false takeover detection after packaged npm onboarding agent turns.
·Codex/TUI: surface Codex-native post-turn compaction failures instead of continuing uncompacted, and keep successful native compaction serialized before local idle/next-turn handling. Fixes #84305. (#85160)
·Memory/search: stop recall tracking from writing dreaming side-effect artifacts when `dreaming.enabled=false`, while preserving normal search results. Fixes #84436. (#84444)
·Diffs: render viewer toolbar icons from a closed icon-name map instead of HTML strings, removing the toolbar icon XSS sink. (#83955)
·QA: keep `pnpm qa:e2e` self-check runs inside the private QA runtime envelope even when inherited shell env disables bundled plugins.
·fix(config): validate browser sandbox bind sources [AI]. (#84799)
·doctor: constrain legacy plugin cleanup paths [AI]. (#84801)
·Update/doctor: prune stale local bundled plugin install records that point at old compiled bundled output so current bundled plugin schemas win after upgrade. (#84863)
·Providers/Ollama: preserve native Ollama tool-call IDs across assistant replay so Gemini over Ollama Cloud can keep its hidden function-call thought-signature handle.
·Discord: keep session recovery and `/stop` abort ownership on the source dispatch lane while bound ACP turns continue routing to their target session, so stalled pre-run work and late replies are cleared instead of leaking after stop. Fixes #84477. (#85100)
·Codex app-server: mark missing turn completion after observed execution as replay-unsafe and release the session so follow-up turns can run. Fixes #84076. (#85107)
·Codex app-server: give visible `message` dynamic tool sends a longer timeout budget so slow channel delivery can return its own result or error instead of hitting the 30-second Codex wrapper. (#85216)
·Codex app-server: add a dedicated post-tool raw assistant completion idle timeout config so trusted heavy turns can wait longer after tool handoff without weakening final assistant release.
·Matrix: keep explicitly configured two-person rooms on the room route before stale `m.direct` or strict two-member DM fallback can bypass mention gating. Fixes #85017. (#85137)
·Agents/subagents: require explicit subagent allowlist targets to be configured agents so stale deleted-agent ids are omitted from `agents_list` and rejected by `sessions_spawn`. Fixes #84811. (#85154)
·PDF tool: time out idle remote PDF body reads after 120 seconds so stalled remote documents return an error instead of wedging the session. Fixes #68649. (#84768)
·Diagnostics/OpenTelemetry plugin: suppress handled OTLP exporter promise rejections so collector shutdowns no longer crash the Gateway. (#81085)
·Agents/exec: omit raw command text and env values from denied exec failure logs while keeping safe correlation metadata. Fixes #85049. (#85140)
·Media/audio: skip empty structured sherpa-onnx transcripts instead of treating the raw JSON payload as spoken text. (#84667)
·Agents/exec: preserve inherited XDG base-directory environment values for subprocesses while still rejecting agent-supplied XDG overrides. Fixes #84854. (#85139)
·Node/Linux: keep `OPENCLAW_GATEWAY_TOKEN` out of generated systemd unit files by writing node service token values to a node-specific env file. (#84408)
·Memory-core/dreaming: reuse stable narrative subagent session keys per workspace and phase while keeping per-run idempotency and bounded cleanup, so stale `dreaming-narrative-*` sessions do not accumulate. Fixes #68252, #69187, and #70402. (#70464)
·Trajectory/support: tolerate partial skill snapshot entries when building support metadata so rejected skill path scans no longer abort trajectory capture. (#71185)
·TUI: coalesce repeated idle Esc abort notices into a single `no active run xN` system row instead of appending duplicate rows.
·Telegram: honor `channels.telegram.pollingStallThresholdMs` in the default isolated polling path, restarting silent workers instead of leaving inbound updates wedged. Fixes #83950. (#84861)
·Telegram: dedupe replayed message dispatches by Telegram chat/message identity so isolated-ingress replays do not trigger duplicate model dispatches. Fixes #84886. (#85208)
·Slack: suppress reasoning payloads before reply delivery and dispatch accounting, so Slack monitor, slash-command, fallback, and direct reply paths do not leak model reasoning. Fixes #84319. (#84322)
·Slack: deliver native plugin approval prompts and updates when Slack native approvals are enabled, while keeping plugin approval authorization separate from exec approvers.
·Slack: keep native plugin approval prompts in the originating app conversation thread when the live Slack turn source is a `D...` conversation.
·Agents/Pi: disable the embedded pi-coding-agent runtime auto-retry so OpenClaw's own retry and failover loop does not replay failed tool calls through a nested SDK retry. Fixes #73781. (#74434)
·CLI/perf: keep `setup --help`, `onboard --help`, and `configure --help` out of the full wizard runtime while preserving the existing help output. (#84488)
·CLI/perf: keep `agents --help` out of agents action/runtime imports so help, completion, and command discovery paths avoid loading the full agents runtime. (#84483)
·CLI/perf: keep `secrets --help` and `nodes --help` on the precomputed help path so parent help avoids loading action-heavy command runtime modules. (#84818)
·CLI/perf: serve `doctor`, `gateway`, `models`, and `plugins` parent help from startup metadata so common subcommand help avoids full CLI program construction. (#84786)
·Codex/Lossless: keep context-engine history on the canonical run session when Telegram DMs use per-peer runtime policy keys. Fixes #84936. (#84954)
·Codex: keep heartbeat response tool schemas durable without exposing dynamic tools disabled by turn policy, so heartbeat wakeups can reuse threads while scoped tool allowlists stay enforced. (#84681)
·Auth/OAuth: skip the refresh adapter when a stored OAuth credential has no refresh token so agent turns fail fast on missing-key instead of waiting on the 120s refresh timeout.
·Auth/Codex: load legacy OAuth sidecar credentials in the embedded runner's secrets-runtime auth loaders so Telegram replies, cron-triggered turns, and other isolated sub-agent lanes can reach the existing #83312 refresh-and-rewrite migration instead of failing with `No API key found for provider "openai-codex"` until the user runs `openclaw doctor`.
·Codex/failover: classify `deactivated_workspace` as a permanent auth failure so configured fallback models can advance when a Codex workspace is deactivated. (#55893)
·Exec: keep configured `tools.exec.pathPrepend` entries ahead of user shell startup PATH changes on POSIX gateway runs. (#81403)
·Gateway/sessions: allow shared-secret bearer callers to read and stream session history without an explicit scope header. (#81815)
·Agents/embedded runner: classify HTML auth provider responses as `auth_html` and return a re-authentication hint instead of the CDN-blocked copy that `upstream_html` returns. Cloudflare Access login pages, nginx basic-auth challenges, and gateway login walls all produce HTML auth bodies that were previously misdiagnosed as transient CDN blocks. (#79900)
·TUI/streaming watchdog: dismiss the `This response is taking longer than expected` notice as soon as a chat event for the same run arrives, so the message no longer sits next to the recovered response when the run was only briefly silent. Refs #67052, #69081 (closed), prior attempt #69026.
·Agents/Pi: tolerate OpenClaw-owned transcript writes while embedded prompts are released for model I/O, keeping long-running Feishu, Slack, Telegram, and cron turns from failing with false session-takeover errors. Fixes #84059. (#84250)
·npm package: https://www.npmjs.com/package/openclaw/v/2026.5.22
·registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.5.22.tgz
·integrity: sha512-m+zgBELGbCHjWB1IWF5WSWNPr480cMKOMff2OF72c8A0AMD4hC/9+qwYtzjYmGkETcffnB711JymlVsQnh2Tow==
·npm publish: https://github.com/openclaw/openclaw/actions/runs/26350601931
·npm preflight: https://github.com/openclaw/openclaw/actions/runs/26348274555
·full release CI report: https://github.com/openclaw/openclaw/actions/runs/26348274024
·release checks report: https://github.com/openclaw/openclaw/actions/runs/26348357741
·plugin npm recovery publish: https://github.com/openclaw/openclaw/actions/runs/26350155030
·plugin ClawHub publish: https://github.com/openclaw/openclaw/actions/runs/26349516036
·macOS preflight/sign/notarize: https://github.com/openclaw/releases/actions/runs/26348276222
·macOS validation: https://github.com/openclaw/releases/actions/runs/26348275696
·macOS publish/appcast: https://github.com/openclaw/releases/actions/runs/26348989219
·appcast: https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml
·macOS zip: https://github.com/openclaw/openclaw/releases/download/v2026.5.22/OpenClaw-2026.5.22.zip
·macOS dmg: https://github.com/openclaw/openclaw/releases/download/v2026.5.22/OpenClaw-2026.5.22.dmg
·macOS dSYM: https://github.com/openclaw/openclaw/releases/download/v2026.5.22/OpenClaw-2026.5.22.dSYM.zip

v2026.5.22-beta.1pre-release2026-05-23

openclaw 2026.5.22-beta.1

GitHub ↗

Changes

·Docs: clarify README onboarding and Gateway startup paths, WhatsApp QR/408 recovery, cron output language prompts, skill advanced features, gateway upstream 403 troubleshooting, and plugin fallback override guidance.
·Docs: clarify context-pruning ratio bounds, local dashboard recovery, CLI env markers, remote onboarding token behavior, and Peekaboo Bridge permissions for subprocess agents.
·Docs: clarify browser CDP diagnostics, Plugin SDK allowlist imports, status-reaction timing defaults, queue steering behavior, limited-tool troubleshooting, cron HEARTBEAT handling, Telegram multi-agent groups, Bitwarden SecretRef setup, and EasyRunner deployments.
·Crabbox/Testbox: run clean sparse-checkout Testbox syncs from a temporary full checkout and route remote changed gates through Corepack pnpm.
·Docs: clarify IPv4-only Gateway BYOH binding, trusted-proxy scope clearing, Android pairing approval, macOS Accessibility grants, Zalo profile env vars, password-store SecretRef setup, and Chinese memory navigation.
·Docs: consolidate GLM under Z.AI, add the Upstash Box install guide and Gateway exposure runbook, clarify MEDIA directives, Copilot and Voyage setup, config path quoting, real behavior proof, and memory-file write guidance.
·Docs: clarify media provider credentials, Codex/OpenClaw code-mode boundaries, Slack and Telegram ack reactions, Feishu dynamic agents, secrets plaintext boundaries, memory guidance, and Chinese glossary terms.
·Packaging: exclude documentation images and assets from the npm tarball, reducing published package size without affecting runtime docs search or CLI behavior.
·Media understanding: stop auto-probing Gemini CLI and use Antigravity CLI only as a lower-priority image/video fallback after configured provider APIs.
·Agents/subagents: limit default sub-agent bootstrap context to `AGENTS.md` and `TOOLS.md`, keeping persona, identity, user, memory, heartbeat, and setup files out of delegated workers by default. (#85283)
·Maintainer skills: exclude plugin SDK/API boundary work from `openclaw-landable-bug-sweep` so bugbash sweeps stay focused on small paper-cut fixes.
·QA-Lab/diagnostics: extend the OpenTelemetry smoke harness to prove trace, metric, and log export, and add first-class Prometheus and observability smoke aliases.
·Plugin SDK: add a generic channel-message poll sender so channel plugins can expose poll delivery without depending on channel-specific SDK facades.
·Crabbox: keep the local wrapper's provider validation synced with the installed Crabbox binary while preserving supported aliases such as `docker` and `blacksmith`. (#85302)
·Maintainer skills: add `openclaw-landable-bug-sweep` for producing five small, reviewed, CI-green OpenClaw bugfix PRs from issue/PR sweeps.
·Control UI/chat: add search and Load More pagination to the chat session picker, keeping initial session loads bounded while making older conversations reachable. (#85237)
·CLI/onboarding: start classic onboarding when bare `openclaw` runs before an authored config exists, while keeping configured installs on Crestodian. (#72343)
·Discord: allow configuring a bounded `agentComponents.ttlMs` callback registry lifetime for long-running component workflows, with per-account overrides and a 24-hour cap. (#84189)
·xAI/Grok: reuse xAI OAuth auth profiles for Grok `web_search`, thread active-agent auth through web search, add Grok model aliases, and let media providers declare default operation timeouts. (#85182)
·Plugin SDK: add row-level session workflow helpers and deprecate `loadSessionStore` so plugins can read and patch sessions without depending on the legacy whole-store shape. (#84693)
·Gateway/plugins: reuse a compatible Gateway startup plugin registry during dispatch so safe plugin dispatches avoid redundant registry loading. (#84324)
·Plugins/SDK: add a general `embeddingProviders` capability contract and registration API so embeddings can become a reusable provider surface outside memory-specific adapters.
·Dependencies: refresh provider, plugin, UI, and tooling packages, update `protobufjs` to 8.4.0 to clear the current npm advisory, and carry the Claude ACP completion patch forward to `@agentclientprotocol/claude-agent-acp` 0.36.1.
·Agents/tools: remove the old sender-owner tool gating path so configured tools stay visible for trusted sessions while command and channel-action auth still carry real sender identity.
·QA-Lab: add curated mock JSONL replay fixtures and first-drift reporting for runtime-parity audits. (#80323, refs #80176)
·QA-Lab: add a QA bus tool-trace visibility scenario for sanitized tool-call assertions.
·QA-Lab: replace generic evidence framing in seeded scenario prompts with concrete observed QA behavior.
·QA-Lab: list named scenario packs in the coverage report so personal-agent privacy coverage stays visible in audits.
·QA-Lab: list live transport lane membership in the coverage report so real transport checks stay separate from seeded qa-channel scenarios.
·Release/package: run package integrity checks before package acceptance lanes so public install/update validation fails before private QA assets can leak into the package.
·QA-Lab: include the optional 100-turn runtime parity soak in release-soak artifacts so long-run Codex/Pi transcript drift stays visible outside the default gate. (#80395)
·QA-Lab: add a live-only long-context progress watchdog scenario for Codex app-server timeout and stalled-run sentinels. (#80323)
·QA-Lab: tag gateway restart recovery and streaming final-integrity scenarios as live-only runtime parity lanes. (#80323)
·QA-Lab: add a personal-agent failure recovery scenario that checks honest partial status, retry boundaries, and local recovery artifacts. (#83872)
·QA-Lab: include an opt-in `update.run` package self-upgrade sentinel for destructive latest-package recovery checks.
·QA-Lab: add Codex plugin lifecycle and auth-profile fixture coverage for missing installs, pinned-version drift, first-turn install ordering, and doctor migration safety. (#80323, refs #80174)
·Models/perf: pre-warm the provider auth-state map at gateway startup so `/models` and every model-listing call short-circuits the per-provider plugin / external-CLI discovery on the hot path. Per-call cost drops from ~20 s to ~5 ms (~4,100×); the one-time startup warm resets and re-warms after hot reloads. (#84816)
·Release/security: ship the root npm package and OpenClaw-owned npm plugins with generated shrinkwrap, support bundled plugin runtime dependencies for suitable plugin tarballs, and require review for lockfile/shrinkwrap changes so published installs use locked dependency graphs.
·Tests/perf: isolate doctor core health check unit coverage from real skills/workspace discovery so `doctor-core-checks` no longer dominates unit perf while keeping one real skills-readiness smoke. (#84493)

Fixes

·Agents/tools: honor configured custom provider API keys when deciding whether media, image-generation, video-generation, music-generation, and PDF tools are available. (#85570)
·StepFun: stop advertising stale generic API key auth choices so onboarding only offers runtime-backed Standard and Step Plan choices.
·Diagnostics: keep OpenTelemetry log bodies behind explicit content capture and scrub scoped agent-session keys from OpenTelemetry and Prometheus labels while preserving bounded queue-lane prefixes.
·Windows installer: fail Git checkout installs when `pnpm install` or `pnpm build` fails instead of writing a wrapper to a missing CLI build.
·Sessions: surface previous-transcript archive failures during `/new` rotation so disk rename errors are logged instead of silently hiding stranded transcript files. Fixes #81984. (#85586, from #82081)
·TUI/agents: mirror internal-ui message-tool replies into final chat output so message-tool-only agents remain visible in `openclaw tui`. Fixes #85538.
·Agents: keep parallel OpenAI-compatible tool-call deltas in separate argument buffers so interleaved tool calls no longer corrupt streamed arguments. (#82263)
·Memory/doctor: report missing or unusable QMD workspace directories as workspace failures instead of generic binary failures. (#63167)
·Debug proxy: record CONNECT client-socket errors and destroy the paired upstream socket so abrupt client disconnects no longer leak tunnel resources. (#82444)
·Diffs: continue hydrating later diff cards when one card fails so a single broken card no longer blanks the whole diff viewer. (#84775)
·Mac app: use the native settings sidebar window chrome so the sidebar toggle stays on the left and content no longer clips under oversized titlebar padding.
·QA-Lab/Codex: bundle auth/plugin fixture imports for flow scenarios and let terminal async media tools end Codex app-server turns without timing out. (#80397, refs #80323)
·Gateway/agents: preserve fresh session overrides and metadata when stale cached agent-session entries race with store updates, so subagent model/provider overrides and routing policy survive concurrent writes. (#19328)
·Control UI/chat: keep chat session search inline with the session selector so the header no longer shows a duplicate standalone search row.
·Control UI/chat: collapse focused-mode header chrome and suppress hidden-header scroll updates so focus mode no longer jumps while scrolling.
·Codex app-server: restart the native app-server and retry once when server-side compaction times out, so preflight compaction stalls recover instead of failing every dispatch. (#85500)
·Restore Control UI gateway token pairing [AI]. (#85459)
·OpenAI video: honor configured provider request private-network opt-in for local/custom video endpoints so explicitly trusted mock and self-hosted providers are not blocked.
·OpenAI video: send uploaded video edit requests to the documented `/videos/edits` endpoint with a `video` file instead of posting MP4 references to `/videos`.
·Agents/channels: preserve message-tool delivery evidence through gateway agent completion handoffs so successful generated media sends are not followed by false failure messages.
·CLI/update: repair managed npm plugin `openclaw` peer links during post-core convergence and reject stale or wrong-target peer links before restart. (#83794)
·CLI/agents: default new omitted-account bindings to all accounts when the channel has multiple configured accounts, and clarify account-scope docs. (#49769)
·Codex app-server: let authorized `/codex` control commands such as `/codex detach` escape plugin-owned conversation bindings while keeping unknown or unauthorized slash text routed to the bound plugin. Fixes #85157. (#85188)
·Auto-reply/models: keep `/models` browse replies fast by sharing the bounded read-only catalog path with Gateway model listing. (#84735)
·Codex app-server: disable native Code Mode when the effective exec host is `node` and keep OpenClaw `exec`/`process` available, so `/exec host=node` routes shell commands through the selected node instead of the gateway. Fixes #85012. (#85090)
·Agents: bound embedded auto-compaction session write-lock watchdogs to the compaction timeout instead of the full run timeout, so stuck compaction cannot hold the live session lock for the whole run window. (#84949)
·Gateway/agents: return phase-aware `agent.wait` timeout attribution and only cool auth profiles on provider-started timeouts. Refs #65504.
·Gateway: defer provider auth-state prewarm until after startup readiness so early gateway tool/session requests are not blocked by provider auth discovery. (#85272)
·Gateway/models: coalesce provider auth-state rewarms after auth-profile failures and log event-loop delay for warm/rewarm work, so provider auth bursts no longer stack full auth sweeps behind channel replies.
·Gateway/models: stop cancelled provider auth-state prewarms from continuing full provider sweeps, so reload and auth-failure bursts no longer keep startup busy.
·Agents/Codex: show the first plan update as a transient chat status notice without counting it as final assistant content.
·CLI/update: walk the macOS process ancestry and honor the inherited Gateway runtime PID before package updates stop the managed Gateway service, so nested in-band updater children can refuse instead of killing the LaunchAgent-supervised Gateway that owns them. Fixes #85120.
·Gateway/LaunchAgent: wait for launchd reload bootout to finish and fall back to kickstart when bootstrap races, so reload handoff does not leave the service deregistered. Fixes #84630. (#84641)
·Gateway/LaunchAgent: treat a concurrent launchd bootstrap as a successful restart when the service is already loaded, avoiding false macOS Gateway restart failures. Fixes #84721. (#84722)
·Gateway/service: include the active `openclaw` command bin directory in managed service PATH generation and doctor audit expectations for npm-global macOS installs. Fixes #84201. (#84475)
·Control UI/chat: disable the thinking selector for known non-reasoning models instead of showing duplicate Off choices. Fixes #84069.
·Memory: expand `~` in configured extra memory paths before resolving them, so home-relative folders are not treated as workspace-relative. Fixes #58026.
·Skills: treat `openclaw.os: macos` as Darwin when checking skill requirements, so macOS-only skills no longer report as missing on macOS hosts. Fixes #61338.
·Control UI/logs: strip ANSI escape sequences from displayed Gateway log messages so color codes no longer appear as raw text. Fixes #64399.
·Docker: pre-create the workspace and auth-profile config mount points with `node` ownership so first-run named volumes do not start root-owned. Fixes #85076.
·Telegram: pass configured markdown table mode through outbound markdown chunking so chunked sends render tables consistently. Fixes #85085.
·CLI/update: preserve managed Gateway service environment during package cutovers so macOS LaunchAgent repair/restart reads the pre-update service state instead of caller shell state. (#83026)
·Agents/providers: honor per-model `api` and `baseUrl` overrides in custom provider auth hooks and transport selection. Fixes #80487. (#80488)
·Gateway/restart: eager-load the lifecycle runtime before in-place upgrade signal handling so package replacement does not deadlock restart imports. (#84890)
·CLI/update: start managed Gateway update handoff helpers from a stable existing directory and tolerate deleted cwd/package roots during macOS LaunchAgent handoff. Fixes #83808. (#83875)
·Skills: watch each shared skill directory once across agent workspaces instead of once per agent, preventing file-descriptor exhaustion (`EMFILE`) that disposed bundle-mcp processes and stalled sessions on multi-agent gateways. Fixes #84968. (#85130)
·Release/security: keep generated npm shrinkwrap package versions inside the pnpm lock graph so published package locks cannot bypass pnpm dependency age and override policy.
·Cron: honor `cron.retry.retryOn: ["network"]` for common network error codes such as `EAI_AGAIN`, `EHOSTUNREACH`, and `ENETUNREACH`.
·Gateway chat: broadcast returned agent-run error payloads after an agent starts so ACP/WebChat clients receive terminal idle-timeout errors. Fixes #84945.
·Gateway chat display: preserve OpenAI-compatible `prompt_tokens`, `completion_tokens`, and `total_tokens` usage fields in sanitized chat history so llama.cpp sessions keep context counts. Fixes #77992.
·Dashboard/CLI: allow macOS browser launching through `open` even when SSH environment variables are present, while preserving Linux SSH no-display protection. Fixes #67088.
·Codex app-server: keep native web search observations out of mirrored chat transcripts while preserving tool progress telemetry. Fixes #85109.
·OpenCode Go: strip unsupported Kimi reasoning replay fields before provider requests so repeated `kimi-k2.6` turns do not fail schema validation. Fixes #83812.
·Browser/CDP: add a WSL2 portproxy self-loop hint when Chrome DevTools endpoints accept connections but return an empty HTTP reply. Fixes #59209.
·Agents/OpenAI: preserve structured provider error code, type, and redacted body metadata on boundary-aware transport failures.
·Doctor/Codex: point native Codex asset warnings at the canonical `openclaw migrate plan codex` preview command. Fixes #84948.
·CLI/models: make `capability model auth logout --agent` remove auth profiles from the selected non-default agent store. Fixes #85092.
·Gateway/models: reuse prepared provider auth metadata during model-listing auth checks so repeated lookups avoid broad plugin discovery while preserving synthetic local auth.
·CLI/status: suppress systemd user-service setup hints when `openclaw status --deep` can already reach a running Gateway RPC service. Fixes #85094.
·CLI/devices: recover local approval when a same-device repair request replaces the request ID being approved.
·CLI/agents: retry transient normal-close Gateway handshakes before falling back to embedded `openclaw agent` execution.
·CLI/update: keep managed Gateway service stop/restart status lines out of `openclaw update --json` stdout so package-update automation can parse the JSON payload.
·Plugins: resolve OpenClaw plugin SDK subpaths for native external plugin runtimes without mutating package installs or broadening process-wide module resolution.
·Agents/OpenAI: preserve Responses and Chat Completions `reasoning_tokens` usage metadata without double-counting it in aggregate output tokens. (#85319)
·Control UI/chat: convert pasted `data:image/...;base64,...` clipboard text into an image attachment instead of dumping the payload into the composer. Fixes #62604.
·Providers/Gemini: strip fractional seconds from web-search time range filters so Gemini accepts freshness-bound search requests. (#85071)
·OpenAI Codex: preserve image input support for sparse `openai-codex/gpt-5.5` catalog rows. (#85095)
·CLI/models: add a piped or pasted API-key path for OpenAI Codex auth and warn when API keys are pasted into token-mode auth. (#85533)
·Telegram: dead-letter missing-harness isolated ingress failures so a poisoned spooled update no longer blocks later same-lane messages. Fixes #85470. (#85605)
·Plugins/discovery: strip `-plugin` package suffixes when deriving plugin id hints so package names line up with manifest ids. (#85170)
·Tlon: stop advertising a non-existent agent tool contract in the plugin manifest.
·Telegram: preserve fenced code block languages through Markdown rendering so Telegram receives `language-*` code classes. (#85209)
·Windows installer: run npm and Corepack command shims from a Windows-local directory so installs launched from WSL2 UNC paths do not fail before OpenClaw is installed.
·Windows updates: roll back git-backed updates to the previous checkout when dependency install, build, UI build, or doctor repair fails.
·Windows installer: persist user-local portable Git on PATH and activate the repo-pinned pnpm version for git-backed installs and updates.
·Windows installer: bootstrap a user-local portable Node.js when native Windows has no Node and no winget, Chocolatey, or Scoop, so first-run installs can continue on raw hosts.
·Windows installer: extract the downloaded portable Node.js directory with native `tar` before falling back to .NET zip extraction, avoiding PowerShell 5.1 archive and path-length failures.
·fix(integrations): enforce channel read target allowlists [AI]. (#84982)
·Agents/heartbeat: route single-owner `session.dmScope=main` direct-message exec and cron event wakes back to the agent main session so async completions no longer strand context in orphan direct-DM queues. Fixes #71581. (#83743)
·Agents/code-mode: expose outer code-mode `exec` source through the `command` hook alias with `toolKind`/`toolInputKind` discriminators so exec-shaped policies can distinguish code-mode cells. (#83483)
·Agents/code mode: return structured timeout and runtime-unavailable error codes for known worker failures. Fixes #83389. (#83444)
·QA-Lab: isolate multi-scenario suite workers when scenarios need startup config patches, preventing message-routing config from leaking into unrelated scenarios.
·QA-Lab: make the commitments heartbeat-target-none scenario request an immediate heartbeat instead of waiting for the next scheduled heartbeat.
·Codex/Plugin SDK: deliver Codex-native subagent completions through a generic harness task runtime so harness-backed plugins can mirror durable task lifecycle and completion delivery without Codex-specific SDK imports. (#83445)
·Gateway CLI: surface local post-challenge connect assembly failures immediately instead of waiting for the wrapper timeout. Fixes #68944. (#85253)
·Messages: strip unsupported web-search citation control markers from outbound replies before they reach WebChat or external channels. Fixes #85193. (#85204)
·Agents/exec: treat denied exec approvals as terminal instead of feeding them back into agent follow-up work, and recognize Chinese stop phrases in abort handling. Fixes #69386. (#85194)
·CLI/agents: abort accepted Gateway-backed `openclaw agent` runs on SIGINT/SIGTERM so cron and supervisor timeouts do not leave remote agent work alive. Fixes #71710. (#84381)
·Codex app-server: retry replay-safe stdio client-close turns once using structured failure metadata, while surfacing idle `turn/completed` timeouts instead of blindly replaying active shared-server turns.
·Codex app-server: reject command overrides that embed Node or package-manager arguments and point users to `appServer.args`, so Windows startup avoids shell parsing failures. (#84417)
·Agents/Copilot: drop unsafe GitHub Copilot Responses reasoning replay items before send so Telegram direct sessions no longer fail on overlong replay IDs. Fixes #85197. (#85198)
·UI: add accessible tooltips to the topbar color-mode buttons so System, Light, and Dark choices are labeled on hover and focus. (#85227)
·fix: constrain Windows task script names [AI]. (#85064)
·Control UI: keep the chat session picker from hiding older or cross-agent configured conversations while preserving the bounded configured-agent refresh. (#85211)
·Agents/Anthropic: preserve unsafe integer tool-call input values in streamed Anthropic tool-use JSON, preventing Discord-style IDs from being rounded before dispatch. Fixes #47229. (#83063)
·Agents/Codex: estimate tool-heavy prompt pressure at the LLM boundary before provider submission, so persistent sessions compact before overflowing context windows. (#85541)
·Agents/hooks: wait for local one-shot CLI and Codex `agent_end` plugin hooks before process cleanup so terminal observability flushes reliably. (#85007)
·Providers/Google: preserve Gemini 3 cron `thinkingDefault: "low"` when stale catalog metadata says `reasoning:false`, so scheduled runs keep provider-supported thinking instead of downgrading to off. (#85185)
·CLI/agents: allow `openclaw agent --session-key` to target explicit session keys, including agent-scoped legacy keys. (#85121)
·Auto-reply/ACP: wait for same-channel block reply delivery before starting tool work, while still honoring ACP dispatch aborts so stopped turns do not wait on slow channel sends. (#83722)
·Codex/ACP: mark required child-run completions that only report progress, omit a final deliverable, or fail requester delivery as blocked while preserving real final reports. (#85110)
·Channels: treat bare abort messages such as `stop`, `abort`, and `wait` as immediate control commands in inbound debounce paths so stop requests are not delayed behind pending message coalescing. (#83348)
·Channels/message tool: resolve configured external channel plugins during in-agent channel selection, so `openclaw agent --local` message-tool sends no longer report an available channel as unavailable. (#85022)
·Agents/heartbeat: honor group/channel `message_tool` visible-reply policy and model-specific Codex runtime config for scheduled heartbeat runs, so failed internal tool output stays private. Fixes #85310. (#85357)
·Gateway/ACP: close child ACP sessions spawned via `sessions_spawn` when their parent session is reset or deleted, instead of leaving orphaned `claude-agent-acp` processes that accumulate and exhaust memory. Fixes #68916. (#85190)
·Codex app-server: block native execution paths when OpenClaw exec resolves to a node host while preserving the first-party CLI node binding path. Fixes #85012. (#85534)
·Diagnostics: bound cleanup timeout detail logs, emit drop summaries when async diagnostic bursts exceed the queue cap, and surface async queue drops through diagnostic telemetry.
·Agents/subagents: surface blocked child-run completions as errors instead of successful subagent finishes. (#80886)
·Context engines: fail closed with a descriptive error when the selected agent runtime cannot satisfy declared context-engine host requirements.
·Agents/Pi: treat accepted embedded `sessions_spawn` child-session handoffs as terminal progress so parent turns no longer report false non-deliverable failures. (#85054)
·CLI/models: resolve `openclaw models set` aliases from the runtime config while keeping authored aliases ahead of runtime-only defaults. (#83262)
·Doctor: show personal Codex CLI asset notices as info instead of warnings. Fixes #84859.
·WhatsApp: update Baileys to `7.0.0-rc13` and drop the obsolete logger type patch.
·CLI/update: pre-pack GitHub/git package update targets before the staged npm install, restoring `openclaw update --tag main` for one-off package updates. (#81296)
·Gateway: mirror successful same-source message-tool sends into session transcripts so delivered replies stay in later history/context. (#84837)
·Media generation: keep image, music, and video completion delivery from duplicating or losing task ownership when generated media finishes through active session replies. (#84006)
·Infra/json: retry transient `File changed during read` races while loading JSON state so config and state reads recover instead of failing the turn. (#84285)
·Plugins/providers: fail closed for workspace provider plugins during setup-mode discovery unless explicitly trusted, preventing untrusted workspace plugin code from running during provider setup. (#81069)
·Providers/Ollama: resolve configured Ollama Cloud `OLLAMA_API_KEY` markers to the real discovery key so cloud provider entries keep authenticated model catalog access. (#85037)
·Discord: keep persistent component registry fallback warnings actionable by forwarding structured error and cause metadata through the runtime logger. Fixes #84185. (#84190)
·Gateway/sessions: preserve compatible session auth profile overrides when switching models within the same provider, including provider-auth aliases. Fixes #81837. (#81886)
·Gateway/status: surface inbound delivery telemetry counters and transport-liveness warnings in `openclaw status --all`. Fixes #49577. (#72724)
·Docker: prune package-excluded plugin source workspaces and dependency closures so runtime images do not keep packages for plugins that were not opted in.
·Providers/Ollama: treat Docker/OrbStack host aliases as local Ollama endpoints so `ollama-local` marker auth works when OpenClaw runs inside a VM/container and Ollama runs on the host. Fixes #84875.
·QA-Lab: keep explicitly searchable/deferred OpenClaw dynamic tool rows report-only by default so tool-coverage gates do not treat mock discovery gaps as hard product failures. (#80319)
·Agents/config: keep non-Google provider model refs from being rewritten by Google Gemini preview-id normalization. (#84762)
·Installer: require a real controlling terminal before launching onboarding so headless `curl | bash` installs finish cleanly after installing the CLI.
·Agents/Codex: promote a completed final assistant response when a prompt timeout races Codex app-server completion instead of returning an empty timeout envelope. Refs #84516.
·Codex app-server: keep interrupted turn statuses from being treated as OpenClaw aborts by themselves, so tool-only turns remain eligible for no-visible-answer recovery. Fixes #84492.
·Agents: cap heartbeat model bleed context hints by the stored session window when runtime model metadata is unavailable, so overflow recovery advice does not suggest a larger window than the active session actually has.
·Control UI/Web Push: use `https://openclaw.ai` as the generated default VAPID subject instead of the old localhost mailbox so iOS PWA push setup uses an Apple-acceptable subject when `OPENCLAW_VAPID_SUBJECT` is unset. Fixes #83134. (#83317)
·Control UI: distinguish inherited thinking-off settings from explicit Off selections so the thinking selector no longer shows two identical Off rows. (#85223)
·Agents/Pi: keep embedded session transcript writes from tripping false takeover detection after packaged npm onboarding agent turns.
·Codex/TUI: surface Codex-native post-turn compaction failures instead of continuing uncompacted, and keep successful native compaction serialized before local idle/next-turn handling. Fixes #84305. (#85160)
·Memory/search: stop recall tracking from writing dreaming side-effect artifacts when `dreaming.enabled=false`, while preserving normal search results. Fixes #84436. (#84444)
·Diffs: render viewer toolbar icons from a closed icon-name map instead of HTML strings, removing the toolbar icon XSS sink. (#83955)
·QA: keep `pnpm qa:e2e` self-check runs inside the private QA runtime envelope even when inherited shell env disables bundled plugins.
·fix(config): validate browser sandbox bind sources [AI]. (#84799)
·doctor: constrain legacy plugin cleanup paths [AI]. (#84801)
·Update/doctor: prune stale local bundled plugin install records that point at old compiled bundled output so current bundled plugin schemas win after upgrade. (#84863)
·Providers/Ollama: preserve native Ollama tool-call IDs across assistant replay so Gemini over Ollama Cloud can keep its hidden function-call thought-signature handle.
·Discord: keep session recovery and `/stop` abort ownership on the source dispatch lane while bound ACP turns continue routing to their target session, so stalled pre-run work and late replies are cleared instead of leaking after stop. Fixes #84477. (#85100)
·Codex app-server: mark missing turn completion after observed execution as replay-unsafe and release the session so follow-up turns can run. Fixes #84076. (#85107)
·Codex app-server: give visible `message` dynamic tool sends a longer timeout budget so slow channel delivery can return its own result or error instead of hitting the 30-second Codex wrapper. (#85216)
·Codex app-server: add a dedicated post-tool raw assistant completion idle timeout config so trusted heavy turns can wait longer after tool handoff without weakening final assistant release.
·Matrix: keep explicitly configured two-person rooms on the room route before stale `m.direct` or strict two-member DM fallback can bypass mention gating. Fixes #85017. (#85137)
·Agents/subagents: require explicit subagent allowlist targets to be configured agents so stale deleted-agent ids are omitted from `agents_list` and rejected by `sessions_spawn`. Fixes #84811. (#85154)
·PDF tool: time out idle remote PDF body reads after 120 seconds so stalled remote documents return an error instead of wedging the session. Fixes #68649. (#84768)
·Diagnostics/OpenTelemetry plugin: suppress handled OTLP exporter promise rejections so collector shutdowns no longer crash the Gateway. (#81085)
·Agents/exec: omit raw command text and env values from denied exec failure logs while keeping safe correlation metadata. Fixes #85049. (#85140)
·Media/audio: skip empty structured sherpa-onnx transcripts instead of treating the raw JSON payload as spoken text. (#84667)
·Agents/exec: preserve inherited XDG base-directory environment values for subprocesses while still rejecting agent-supplied XDG overrides. Fixes #84854. (#85139)
·Node/Linux: keep `OPENCLAW_GATEWAY_TOKEN` out of generated systemd unit files by writing node service token values to a node-specific env file. (#84408)
·Memory-core/dreaming: reuse stable narrative subagent session keys per workspace and phase while keeping per-run idempotency and bounded cleanup, so stale `dreaming-narrative-*` sessions do not accumulate. Fixes #68252, #69187, and #70402. (#70464)
·Trajectory/support: tolerate partial skill snapshot entries when building support metadata so rejected skill path scans no longer abort trajectory capture. (#71185)
·TUI: coalesce repeated idle Esc abort notices into a single `no active run xN` system row instead of appending duplicate rows.
·Telegram: honor `channels.telegram.pollingStallThresholdMs` in the default isolated polling path, restarting silent workers instead of leaving inbound updates wedged. Fixes #83950. (#84861)
·Telegram: dedupe replayed message dispatches by Telegram chat/message identity so isolated-ingress replays do not trigger duplicate model dispatches. Fixes #84886. (#85208)
·Slack: suppress reasoning payloads before reply delivery and dispatch accounting, so Slack monitor, slash-command, fallback, and direct reply paths do not leak model reasoning. Fixes #84319. (#84322)
·Slack: deliver native plugin approval prompts and updates when Slack native approvals are enabled, while keeping plugin approval authorization separate from exec approvers.
·Slack: keep native plugin approval prompts in the originating app conversation thread when the live Slack turn source is a `D...` conversation.
·Agents/Pi: disable the embedded pi-coding-agent runtime auto-retry so OpenClaw's own retry and failover loop does not replay failed tool calls through a nested SDK retry. Fixes #73781. (#74434)
·CLI/perf: keep `setup --help`, `onboard --help`, and `configure --help` out of the full wizard runtime while preserving the existing help output. (#84488)
·CLI/perf: keep `agents --help` out of agents action/runtime imports so help, completion, and command discovery paths avoid loading the full agents runtime. (#84483)
·CLI/perf: keep `secrets --help` and `nodes --help` on the precomputed help path so parent help avoids loading action-heavy command runtime modules. (#84818)
·CLI/perf: serve `doctor`, `gateway`, `models`, and `plugins` parent help from startup metadata so common subcommand help avoids full CLI program construction. (#84786)
·Codex/Lossless: keep context-engine history on the canonical run session when Telegram DMs use per-peer runtime policy keys. Fixes #84936. (#84954)
·Codex: keep heartbeat response tool schemas durable without exposing dynamic tools disabled by turn policy, so heartbeat wakeups can reuse threads while scoped tool allowlists stay enforced. (#84681)
·Auth/OAuth: skip the refresh adapter when a stored OAuth credential has no refresh token so agent turns fail fast on missing-key instead of waiting on the 120s refresh timeout.
·Auth/Codex: load legacy OAuth sidecar credentials in the embedded runner's secrets-runtime auth loaders so Telegram replies, cron-triggered turns, and other isolated sub-agent lanes can reach the existing #83312 refresh-and-rewrite migration instead of failing with `No API key found for provider "openai-codex"` until the user runs `openclaw doctor`.
·Codex/failover: classify `deactivated_workspace` as a permanent auth failure so configured fallback models can advance when a Codex workspace is deactivated. (#55893)
·Exec: keep configured `tools.exec.pathPrepend` entries ahead of user shell startup PATH changes on POSIX gateway runs. (#81403)
·Gateway/sessions: allow shared-secret bearer callers to read and stream session history without an explicit scope header. (#81815)
·Agents/embedded runner: classify HTML auth provider responses as `auth_html` and return a re-authentication hint instead of the CDN-blocked copy that `upstream_html` returns. Cloudflare Access login pages, nginx basic-auth challenges, and gateway login walls all produce HTML auth bodies that were previously misdiagnosed as transient CDN blocks. (#79900)
·TUI/streaming watchdog: dismiss the `This response is taking longer than expected` notice as soon as a chat event for the same run arrives, so the message no longer sits next to the recovered response when the run was only briefly silent. Refs #67052, #69081 (closed), prior attempt #69026.
·Agents/Pi: tolerate OpenClaw-owned transcript writes while embedded prompts are released for model I/O, keeping long-running Feishu, Slack, Telegram, and cron turns from failing with false session-takeover errors. Fixes #84059. (#84250)

Release Verification

·npm package: https://www.npmjs.com/package/openclaw/v/2026.5.22-beta.1
·registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.5.22-beta.1.tgz
·integrity: sha512-xSSTpkaHz0eMcaBxsrR+ySFg8LwSjM31ImP1y28twNMnCuvfqjU3cuyfnwHgM/25HbKXgRWKrXD448erm6RcvQ==
·npm preflight: https://github.com/openclaw/openclaw/actions/runs/26328338829
·npm publish: https://github.com/openclaw/openclaw/actions/runs/26329772865
·npm Telegram beta E2E: https://github.com/openclaw/openclaw/actions/runs/26329878304
·full release validation: pending; required before stable/latest promotion

v2026.5.202026-05-21

openclaw 2026.5.20

GitHub ↗

Changes

·Exec approvals: remove the old `cat SKILL.md && printf ... && <skill-wrapper>` allowlist compatibility path so skill files must be loaded with the read tool and only the real skill executable is auto-allowed.
·Discord: let voice sessions follow configured Discord users into voice channels, with allowed-channel checks, multi-user handoff, bounded reconciliation, and DAVE recovery preservation. (#84264)
·Discord/voice: include bounded `IDENTITY.md`, `USER.md`, and `SOUL.md` profile context in realtime voice session instructions by default, with `voice.realtime.bootstrapContextFiles: []` available to disable it. (#84499)
·Dependencies: bump the bundled Codex harness to `@openai/codex` `0.132.0` and refresh the app-server model-list docs for the new catalog.
·CLI/policy: add the bundled Policy plugin for policy-backed channel conformance checks, doctor lint findings, and opt-in workspace repair. (#80407)
·Agents/config: allow `agents.list[].experimental.localModelLean` so lean local-model mode can be enabled for one configured agent instead of globally.
·Providers/xAI: add device-code OAuth login so remote and headless setups can authorize xAI without a localhost browser callback. (#84005)
·Providers/OpenRouter: honor provider-level `params.provider` routing policy for OpenRouter requests, with model and agent params overriding the defaults.

Fixes

·CLI/tasks: include stale-running task maintenance decisions in `openclaw tasks maintenance --json` so retained and reconcile candidates explain backing-session, cron, CLI, and wedged-subagent state. (#84691)
·Codex app-server: keep system-prompt reports working when bootstrap hooks provide workspace files with only a path and content, so hook-supplied SOUL/IDENTITY/TOOLS/USER context still reports injected characters correctly. (#84736)
·Providers/MiniMax music: stop advertising `durationSeconds` control and remove prompt-injected duration hints, so `music_generate` reports MiniMax duration as an unsupported override instead of suggesting MiniMax can enforce track length. Fixes #84508.
·Doctor: warn when sandbox tool policy hides configured MCP server tools before provider requests. (#84699)
·WhatsApp: update Baileys to `7.0.0-rc12`.
·Build: suppress per-locale `rolldown-plugin-dts:fake-js` CommonJS dts warnings emitted while bundling the intentionally-inlined `zod/v4/locales/*.d.cts` files, so `pnpm build` output stays readable after the 0.25.1 plugin bump.
·CLI/nodes: route lazy plugin-registration logs to stderr for JSON-mode `openclaw nodes` commands so stdout stays parseable. (#84684)
·Approvals: route manual `/approve` decisions through the trusted approval runtime so active exec and plugin approvals no longer look unknown or expired.
·Mac app: update the About settings copyright year to 2026. (#84385)
·Dependencies: update `@openclaw/fs-safe` to `0.2.7` so OpenClaw's default Python-helper-off policy keeps best-effort Node write fallbacks for private stores, secret writes, run logs, and media attachments on Linux/macOS.
·Infra/secrets: restore the fail-closed contract for `tryReadSecretFileSync` so credential loaders that pass `rejectSymlink: true` (Telegram, LINE, Zalo, IRC, Nextcloud Talk tokens) refuse symlinked credential files instead of silently accepting them, and the infra-state CI shard's secret-file symlink test passes again.
·Browser: honor the configured image sanitization limit for screenshots and labeled snapshots so browser-captured images follow the same resize policy as other image results. (#84595)
·Doctor: remove unrecognized `models.providers.*.models[*].compat.thinkingFormat` values during `doctor --fix` so stale provider model config can validate after upgrade. Fixes #77803.
·Doctor: warn when `openclaw.json` stores plaintext secret-bearing config fields, including model provider API keys and sensitive provider headers. (#84718)
·Status: show the configured default, session-selected model, reason, clear hint, and docs link when a session remains pinned to a model that differs from `agents.defaults.model.primary`.
·WebChat: clear stale typing indicators when session change events mark the active chat run complete.
·Mac app: keep local packaging signed with a stable app identity for permission testing and fix Control UI production builds under current Vite/Highlight.js exports.
·macOS app: update the embedded Peekaboo bridge to 3.2.1 so OpenClaw-hosted UI automation works with current Peekaboo CLI capture flows.
·Cron: deliver preferred final assistant output for successful scheduled runs when trailing plain tool warnings remain in diagnostics instead of marking the run failed.
·fix(mattermost): fail closed on missing channel type [AI]. (#84091)
·Recheck rebuilt system.run argv [AI]. (#84090)
·CLI: keep the private QA subcommand out of exported command descriptors unless `OPENCLAW_ENABLE_PRIVATE_QA_CLI=1`, so root help and subcommand markers match runtime registration. (#84519)
·CLI/cron: bound `openclaw cron show` job lookup pagination so non-advancing or unbounded `cron.list` responses fail instead of hanging the command. Fixes #83856. (#83989)
·Agents/messages: stop message-tool-only turns after a successful source-channel `message` send while keeping transcript mirrors under the session write lock. (#84289)
·Agents: filter silent heartbeat response-tool transcript artifacts out of embedded context snapshots so later user turns are not polluted by heartbeat no-op messages. (#83477)
·Agents/OpenAI: log repeated strict tool-schema downgrade diagnostics once per provider/model/tool signature, reducing duplicate debug noise while preserving `strict=false` fallback behavior. Fixes #82930. (#82933)
·Agents/code mode: spell out the `exec` tool's JavaScript/TypeScript, no Node module, and catalog-bridge constraints in model-visible schema text so agents can use enabled tools without trial-and-error. (#84269)
·Codex: give `image_generate` dynamic-tool calls a 120s default watchdog when no per-call or configured image timeout is set, so image generation no longer falls back to the generic 30s bridge timeout. (#84254)
·Codex: avoid duplicate dynamic tool terminal diagnostics while large diagnostic backlogs drain without blocking tool responses. (#82937)
·CLI/message: include a stable top-level `messageId` in `openclaw message --json` output when channel sends return one. (#84191)
·Cron: preserve legacy top-level array `jobs.json` stores when loading or adding scheduled jobs so old cron jobs are no longer treated as an empty store during upgrade. Fixes #60799. (#84433)
·Gateway/agents: use an agent's `identity.name` in Gateway agent summaries when `agents.list[].name` is unset, so configured agent labels remain visible in clients. (#84355; refs #57835)
·Channels/replies: keep normal `/verbose` failed-tool progress compact in message-tool replies and prevent late text-only tool output from appearing after the final answer. (#84303)
·Plugins/hooks: apply a default 30-second timeout to `before_compaction` and `after_compaction` hooks so a hung plugin handler no longer blocks compaction completion. (#84153)
·Discord: preserve disabled presentation buttons when adapting and rendering Discord message controls. (#84188)
·Twitch: add a test-only client-manager registry reset helper so non-isolated Twitch tests can clear cached managers between cases. Fixes #83887. (#84244)
·Cron: run main-session scheduled work on a cron-owned wake lane while preserving reply delivery context, so background cron turns no longer block human main-session chat. Fixes #82766. (#82767)
·Cron: use structured embedded-run denial metadata for isolated scheduled tasks so blocked exec requests fail the job without treating ordinary assistant prose as a denial. (#84067)
·Cron: keep recovered tool warnings diagnostic for successful scheduled runs so final cron output is delivered instead of being replaced by a post-processing warning. (#84045)
·Plugins/perf: thread explicit plugin discovery results through `loadBundledCapabilityRuntimeRegistry`, `resolveBundledPluginSources`, and `listChannelCatalogEntries` so callers that already hold a discovery result skip redundant filesystem walks.
·harden update restart script creation [AI]. (#84088)
·Docker: keep the bundled Codex plugin in official release image keep lists so the default OpenAI agent harness remains available after Docker pruning. Fixes #83613. (#83626)
·CLI/channels: preserve the first line of `openclaw channels logs` output when the rolling tail window starts exactly on a line boundary, mirroring the already-fixed `readLogSlice` behavior in `src/logging/log-tail.ts`.
·Control UI: treat terminal session status as authoritative over stale active-run flags so completed terminal runs stop showing abort/live UI. (#84057)
·CLI: preserve embedded equals signs in inline root option values instead of truncating after the second separator. (#83995)
·Matrix/config: accept `messages.queue.byChannel.matrix` queue overrides and keep queue provider schema/type keys aligned for Matrix, Google Chat, and Mattermost.
·CLI: format `openclaw acp client` failures through the shared error formatter so object-shaped errors stay readable instead of printing `[object Object]`. Fixes #83904. (#84080)
·Providers/Ollama: default unknown-capabilities models to tool-capable so discovered native Ollama models can use tools when `/api/show` omits capabilities. (#84055)
·Installer/Windows: launch `install.ps1` onboarding as an attached child process so fresh native Windows installs do not freeze visibly at `Starting setup...` or corrupt the wizard's terminal rendering.
·CLI/update: keep restart health checks working across one-version CLI/Gateway protocol skew and use the managed Gateway service Node for all follow-up commands even when the package root is unchanged, so `openclaw update` no longer silently switches the gateway to a different Node binary when multiple Node installations are present.
·CLI/gateway: include the running Gateway version in `gateway status` JSON output, preserving existing server metadata while falling back to status RPC data for read probes. Fixes #56222.
·Memory/search: close local embedding providers when active-memory searches time out so pending local model loads and embedding contexts are aborted and released. (#83858)
·CLI/nodes: request pending node surface approval scopes before `openclaw nodes approve` so exec-capable node approval can use admin-scoped Gateway credentials instead of failing with `missing scope: operator.admin`. (#84392)
·Gateway: reject slow node event sends before outbound buffers grow unbounded and log the rejected payload diagnostic. (#84387)
·Agents: include bounded trajectory queued-writer diagnostics in `pi-trajectory-flush` timeout warnings so flush stalls show pending writes, queued bytes, and append state. Fixes #82961. (#82962)
·Agents/subagents: recover stale completion announces by retrying unsupported transcript-wait wakes without transcript waiting and forcing a message-tool handoff when the requester run is already stale. Fixes #83699. (#83700)
·Agents/subagents: constrain wildcard subagent target allowlists to configured agents while preserving explicitly listed compatibility targets. Fixes #84040. (#84357)
·Providers/Anthropic: route Anthropic model refs selected with Claude CLI auth through the Claude CLI runtime so shorthand refs such as `anthropic/opus-4.7` no longer fall back to embedded Anthropic billing. Fixes #84222. (#84374)
·Agents: honor explicit `models.providers.<id>.timeoutSeconds` values above the default idle watchdog for cloud and self-hosted providers, so long first-token waits no longer fall back at ~120s when the provider timeout is higher. (#83979)
·Agents/Codex: keep encrypted Responses reasoning replay provenance-bound so stale mirrored Codex transcripts drop invalid encrypted content before request assembly while preserving matching same-session replay. Fixes #83836. (#84367)
·Agents/subagents: skip stale embedded-run wake probes for dormant completion requesters, so late subagent completions go straight to requester-agent/direct handoff instead of producing `reason=no_active_run` queue noise. (#82964)
·CLI: retry config snapshot reads after a transient failure so one rejected read no longer poisons later commands in the same process. (#83931)
·Media: decode URL path basenames before using them as remote media fallback filenames, so files like `My%20Report.pdf` are surfaced as `My Report.pdf`. Fixes #84050. (#84052)
·WhatsApp: clarify inbound group diagnostics so observed but unregistered groups point to `channels.whatsapp.groups` without changing routing or sender authorization. (#83846)
·WhatsApp: drain pending outbound deliveries on a 30s periodic timer in addition to the reconnect handler, so messages enqueued while the provider is already connected no longer wait for the next reconnect to send. (#79083)
·CLI/TUI: include gateway plugin slash commands in TUI autocomplete, so connected sessions can suggest plugin-owned commands exposed by the running Gateway. (#83640)
·Gateway/mobile: restore QR setup-code handoff of bounded operator tokens for iOS and Android onboarding while keeping admin and pairing scopes out of bootstrap. (#83684)
·iOS: repair Release archive compilation for the TestFlight build. (#84255)
·Agents/compaction: bound plugin-owned CLI transcript compaction with the host safety timeout so a hung context engine can no longer stall post-turn cleanup. (#84083)
·Control UI/usage: truncate long context skill, tool, and file names in the usage panel while keeping the full name available on hover. (#42197)
·Codex: respect explicit `models auth order set` and `config.auth.order` precedence over stale `lastGood` in `/codex account`, and show `no working credential` when every explicit-order profile is ineligible instead of marking a lower-ranked profile as active. Fixes #84386. (#84412)
·Agents: honor `messages.suppressToolErrors` for mutating tool failures so configured chat surfaces do not receive separate warning payloads. (#81561)
·Agents/fallback: surface billing guidance for mixed rate-limit plus billing fallback exhaustion instead of generic failure copy. Fixes #79396. (#79489)

Release verification

·npm package: https://www.npmjs.com/package/openclaw/v/2026.5.20
·registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.5.20.tgz
·integrity: `sha512-cgshS76CxS3Vp9NGtJR2UGtVZxVR5/4rvok8DKGGL19DugAftNabsXfYajyAEiJ3dC8QTXNqF62MdQNzUnQe8Q==`
·full release CI report: https://github.com/openclaw/releases/blob/main/evidence/2026.5.20/release-evidence.md
·full release validation: https://github.com/openclaw/openclaw/actions/runs/26248546974
·full release validation manifest: https://github.com/openclaw/openclaw/actions/runs/26248546974/artifacts/7146395269
·normal full CI: https://github.com/openclaw/openclaw/actions/runs/26248760810
·release checks: https://github.com/openclaw/openclaw/actions/runs/26248762847
·plugin prerelease: https://github.com/openclaw/openclaw/actions/runs/26248761192
·npm preflight: https://github.com/openclaw/openclaw/actions/runs/26248551138
·release publish: https://github.com/openclaw/openclaw/actions/runs/26251157671
·plugin npm publish: https://github.com/openclaw/openclaw/actions/runs/26251316669
·plugin ClawHub publish: https://github.com/openclaw/openclaw/actions/runs/26251319171
·OpenClaw npm publish: https://github.com/openclaw/openclaw/actions/runs/26251677950
·npm Telegram package E2E: https://github.com/openclaw/openclaw/actions/runs/26252161788
·macOS preflight/sign/notarize: https://github.com/openclaw/releases/actions/runs/26252146980
·macOS validation: https://github.com/openclaw/releases/actions/runs/26253801999
·macOS publish/appcast: https://github.com/openclaw/releases/actions/runs/26253953375
·appcast: https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml
·macOS zip: https://github.com/openclaw/openclaw/releases/download/v2026.5.20/OpenClaw-2026.5.20.zip
·macOS dmg: https://github.com/openclaw/openclaw/releases/download/v2026.5.20/OpenClaw-2026.5.20.dmg
·macOS dSYM: https://github.com/openclaw/openclaw/releases/download/v2026.5.20/OpenClaw-2026.5.20.dSYM.zip

v2026.5.20-beta.2pre-release2026-05-21

openclaw 2026.5.20-beta.2

GitHub ↗

Changes

·Exec approvals: remove the old `cat SKILL.md && printf ... && <skill-wrapper>` allowlist compatibility path so skill files must be loaded with the read tool and only the real skill executable is auto-allowed.
·Discord: let voice sessions follow configured Discord users into voice channels, with allowed-channel checks, multi-user handoff, bounded reconciliation, and DAVE recovery preservation. (#84264)
·Discord/voice: include bounded `IDENTITY.md`, `USER.md`, and `SOUL.md` profile context in realtime voice session instructions by default, with `voice.realtime.bootstrapContextFiles: []` available to disable it. (#84499)
·Dependencies: bump the bundled Codex harness to `@openai/codex` `0.132.0` and refresh the app-server model-list docs for the new catalog.
·CLI/policy: add the bundled Policy plugin for policy-backed channel conformance checks, doctor lint findings, and opt-in workspace repair. (#80407)
·Agents/config: allow `agents.list[].experimental.localModelLean` so lean local-model mode can be enabled for one configured agent instead of globally.
·Providers/xAI: add device-code OAuth login so remote and headless setups can authorize xAI without a localhost browser callback. (#84005)
·Providers/OpenRouter: honor provider-level `params.provider` routing policy for OpenRouter requests, with model and agent params overriding the defaults.

Fixes

·CLI/tasks: include stale-running task maintenance decisions in `openclaw tasks maintenance --json` so retained and reconcile candidates explain backing-session, cron, CLI, and wedged-subagent state. (#84691)
·Codex app-server: keep system-prompt reports working when bootstrap hooks provide workspace files with only a path and content, so hook-supplied SOUL/IDENTITY/TOOLS/USER context still reports injected characters correctly. (#84736)
·Providers/MiniMax music: stop advertising `durationSeconds` control and remove prompt-injected duration hints, so `music_generate` reports MiniMax duration as an unsupported override instead of suggesting MiniMax can enforce track length. Fixes #84508.
·Doctor: warn when sandbox tool policy hides configured MCP server tools before provider requests. (#84699)
·WhatsApp: update Baileys to `7.0.0-rc12`.
·Build: suppress per-locale `rolldown-plugin-dts:fake-js` CommonJS dts warnings emitted while bundling the intentionally-inlined `zod/v4/locales/*.d.cts` files, so `pnpm build` output stays readable after the 0.25.1 plugin bump.
·CLI/nodes: route lazy plugin-registration logs to stderr for JSON-mode `openclaw nodes` commands so stdout stays parseable. (#84684)
·Approvals: route manual `/approve` decisions through the trusted approval runtime so active exec and plugin approvals no longer look unknown or expired.
·Mac app: update the About settings copyright year to 2026. (#84385)
·Dependencies: update `@openclaw/fs-safe` to `0.2.7` so OpenClaw's default Python-helper-off policy keeps best-effort Node write fallbacks for private stores, secret writes, run logs, and media attachments on Linux/macOS.
·Infra/secrets: restore the fail-closed contract for `tryReadSecretFileSync` so credential loaders that pass `rejectSymlink: true` (Telegram, LINE, Zalo, IRC, Nextcloud Talk tokens) refuse symlinked credential files instead of silently accepting them, and the infra-state CI shard's secret-file symlink test passes again.
·Browser: honor the configured image sanitization limit for screenshots and labeled snapshots so browser-captured images follow the same resize policy as other image results. (#84595)
·Doctor: remove unrecognized `models.providers.*.models[*].compat.thinkingFormat` values during `doctor --fix` so stale provider model config can validate after upgrade. Fixes #77803.
·Doctor: warn when `openclaw.json` stores plaintext secret-bearing config fields, including model provider API keys and sensitive provider headers. (#84718)
·Status: show the configured default, session-selected model, reason, clear hint, and docs link when a session remains pinned to a model that differs from `agents.defaults.model.primary`.
·WebChat: clear stale typing indicators when session change events mark the active chat run complete.
·Mac app: keep local packaging signed with a stable app identity for permission testing and fix Control UI production builds under current Vite/Highlight.js exports.
·macOS app: update the embedded Peekaboo bridge to 3.2.1 so OpenClaw-hosted UI automation works with current Peekaboo CLI capture flows.
·Cron: deliver preferred final assistant output for successful scheduled runs when trailing plain tool warnings remain in diagnostics instead of marking the run failed.
·fix(mattermost): fail closed on missing channel type [AI]. (#84091)
·Recheck rebuilt system.run argv [AI]. (#84090)
·CLI: keep the private QA subcommand out of exported command descriptors unless `OPENCLAW_ENABLE_PRIVATE_QA_CLI=1`, so root help and subcommand markers match runtime registration. (#84519)
·CLI/cron: bound `openclaw cron show` job lookup pagination so non-advancing or unbounded `cron.list` responses fail instead of hanging the command. Fixes #83856. (#83989)
·Agents/messages: stop message-tool-only turns after a successful source-channel `message` send while keeping transcript mirrors under the session write lock. (#84289)
·Agents: filter silent heartbeat response-tool transcript artifacts out of embedded context snapshots so later user turns are not polluted by heartbeat no-op messages. (#83477)
·Agents/OpenAI: log repeated strict tool-schema downgrade diagnostics once per provider/model/tool signature, reducing duplicate debug noise while preserving `strict=false` fallback behavior. Fixes #82930. (#82933)
·Agents/code mode: spell out the `exec` tool's JavaScript/TypeScript, no Node module, and catalog-bridge constraints in model-visible schema text so agents can use enabled tools without trial-and-error. (#84269)
·Codex: give `image_generate` dynamic-tool calls a 120s default watchdog when no per-call or configured image timeout is set, so image generation no longer falls back to the generic 30s bridge timeout. (#84254)
·Codex: avoid duplicate dynamic tool terminal diagnostics while large diagnostic backlogs drain without blocking tool responses. (#82937)
·CLI/message: include a stable top-level `messageId` in `openclaw message --json` output when channel sends return one. (#84191)
·Cron: preserve legacy top-level array `jobs.json` stores when loading or adding scheduled jobs so old cron jobs are no longer treated as an empty store during upgrade. Fixes #60799. (#84433)
·Gateway/agents: use an agent's `identity.name` in Gateway agent summaries when `agents.list[].name` is unset, so configured agent labels remain visible in clients. (#84355; refs #57835)
·Channels/replies: keep normal `/verbose` failed-tool progress compact in message-tool replies and prevent late text-only tool output from appearing after the final answer. (#84303)
·Plugins/hooks: apply a default 30-second timeout to `before_compaction` and `after_compaction` hooks so a hung plugin handler no longer blocks compaction completion. (#84153)
·Discord: preserve disabled presentation buttons when adapting and rendering Discord message controls. (#84188)
·Twitch: add a test-only client-manager registry reset helper so non-isolated Twitch tests can clear cached managers between cases. Fixes #83887. (#84244)
·Cron: run main-session scheduled work on a cron-owned wake lane while preserving reply delivery context, so background cron turns no longer block human main-session chat. Fixes #82766. (#82767)
·Cron: use structured embedded-run denial metadata for isolated scheduled tasks so blocked exec requests fail the job without treating ordinary assistant prose as a denial. (#84067)
·Cron: keep recovered tool warnings diagnostic for successful scheduled runs so final cron output is delivered instead of being replaced by a post-processing warning. (#84045)
·Plugins/perf: thread explicit plugin discovery results through `loadBundledCapabilityRuntimeRegistry`, `resolveBundledPluginSources`, and `listChannelCatalogEntries` so callers that already hold a discovery result skip redundant filesystem walks.
·harden update restart script creation [AI]. (#84088)
·Docker: keep the bundled Codex plugin in official release image keep lists so the default OpenAI agent harness remains available after Docker pruning. Fixes #83613. (#83626)
·CLI/channels: preserve the first line of `openclaw channels logs` output when the rolling tail window starts exactly on a line boundary, mirroring the already-fixed `readLogSlice` behavior in `src/logging/log-tail.ts`.
·Control UI: treat terminal session status as authoritative over stale active-run flags so completed terminal runs stop showing abort/live UI. (#84057)
·CLI: preserve embedded equals signs in inline root option values instead of truncating after the second separator. (#83995)
·Matrix/config: accept `messages.queue.byChannel.matrix` queue overrides and keep queue provider schema/type keys aligned for Matrix, Google Chat, and Mattermost.
·CLI: format `openclaw acp client` failures through the shared error formatter so object-shaped errors stay readable instead of printing `[object Object]`. Fixes #83904. (#84080)
·Providers/Ollama: default unknown-capabilities models to tool-capable so discovered native Ollama models can use tools when `/api/show` omits capabilities. (#84055)
·Installer/Windows: launch `install.ps1` onboarding as an attached child process so fresh native Windows installs do not freeze visibly at `Starting setup...` or corrupt the wizard's terminal rendering.
·CLI/update: keep restart health checks working across one-version CLI/Gateway protocol skew and use the managed Gateway service Node for all follow-up commands even when the package root is unchanged, so `openclaw update` no longer silently switches the gateway to a different Node binary when multiple Node installations are present.
·CLI/gateway: include the running Gateway version in `gateway status` JSON output, preserving existing server metadata while falling back to status RPC data for read probes. Fixes #56222.
·Memory/search: close local embedding providers when active-memory searches time out so pending local model loads and embedding contexts are aborted and released. (#83858)
·CLI/nodes: request pending node surface approval scopes before `openclaw nodes approve` so exec-capable node approval can use admin-scoped Gateway credentials instead of failing with `missing scope: operator.admin`. (#84392)
·Gateway: reject slow node event sends before outbound buffers grow unbounded and log the rejected payload diagnostic. (#84387)
·Agents: include bounded trajectory queued-writer diagnostics in `pi-trajectory-flush` timeout warnings so flush stalls show pending writes, queued bytes, and append state. Fixes #82961. (#82962)
·Agents/subagents: recover stale completion announces by retrying unsupported transcript-wait wakes without transcript waiting and forcing a message-tool handoff when the requester run is already stale. Fixes #83699. (#83700)
·Agents/subagents: constrain wildcard subagent target allowlists to configured agents while preserving explicitly listed compatibility targets. Fixes #84040. (#84357)
·Providers/Anthropic: route Anthropic model refs selected with Claude CLI auth through the Claude CLI runtime so shorthand refs such as `anthropic/opus-4.7` no longer fall back to embedded Anthropic billing. Fixes #84222. (#84374)
·Agents: honor explicit `models.providers.<id>.timeoutSeconds` values above the default idle watchdog for cloud and self-hosted providers, so long first-token waits no longer fall back at ~120s when the provider timeout is higher. (#83979)
·Agents/Codex: keep encrypted Responses reasoning replay provenance-bound so stale mirrored Codex transcripts drop invalid encrypted content before request assembly while preserving matching same-session replay. Fixes #83836. (#84367)
·Agents/subagents: skip stale embedded-run wake probes for dormant completion requesters, so late subagent completions go straight to requester-agent/direct handoff instead of producing `reason=no_active_run` queue noise. (#82964)
·CLI: retry config snapshot reads after a transient failure so one rejected read no longer poisons later commands in the same process. (#83931)
·Media: decode URL path basenames before using them as remote media fallback filenames, so files like `My%20Report.pdf` are surfaced as `My Report.pdf`. Fixes #84050. (#84052)
·WhatsApp: clarify inbound group diagnostics so observed but unregistered groups point to `channels.whatsapp.groups` without changing routing or sender authorization. (#83846)
·WhatsApp: drain pending outbound deliveries on a 30s periodic timer in addition to the reconnect handler, so messages enqueued while the provider is already connected no longer wait for the next reconnect to send. (#79083)
·CLI/TUI: include gateway plugin slash commands in TUI autocomplete, so connected sessions can suggest plugin-owned commands exposed by the running Gateway. (#83640)
·Gateway/mobile: restore QR setup-code handoff of bounded operator tokens for iOS and Android onboarding while keeping admin and pairing scopes out of bootstrap. (#83684)
·iOS: repair Release archive compilation for the TestFlight build. (#84255)
·Agents/compaction: bound plugin-owned CLI transcript compaction with the host safety timeout so a hung context engine can no longer stall post-turn cleanup. (#84083)
·Control UI/usage: truncate long context skill, tool, and file names in the usage panel while keeping the full name available on hover. (#42197)
·Codex: respect explicit `models auth order set` and `config.auth.order` precedence over stale `lastGood` in `/codex account`, and show `no working credential` when every explicit-order profile is ineligible instead of marking a lower-ranked profile as active. Fixes #84386. (#84412)
·Agents: honor `messages.suppressToolErrors` for mutating tool failures so configured chat surfaces do not receive separate warning payloads. (#81561)
·Agents/fallback: surface billing guidance for mixed rate-limit plus billing fallback exhaustion instead of generic failure copy. Fixes #79396. (#79489)

Release verification

·npm package: https://www.npmjs.com/package/openclaw/v/2026.5.20-beta.2
·registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.5.20-beta.2.tgz
·integrity: `sha512-+4KVWXl74QqLVS/ODKI9+xJXcW1O3pNw6VlNEnQ/lRJvdJbJfymVLOFrYer+2WI9dYH0V4UOoWT78Pfn3hZdOQ==`
·release publish: https://github.com/openclaw/openclaw/actions/runs/26236203338
·npm preflight: https://github.com/openclaw/openclaw/actions/runs/26234059241
·full release validation: https://github.com/openclaw/openclaw/actions/runs/26234053358
·plugin npm publish: https://github.com/openclaw/openclaw/actions/runs/26236412882
·plugin ClawHub publish: dispatched separately, not awaited by this proof: https://github.com/openclaw/openclaw/actions/runs/26236416443
·OpenClaw npm publish: https://github.com/openclaw/openclaw/actions/runs/26236812220
·npm Telegram beta E2E: https://github.com/openclaw/openclaw/actions/runs/26237173717
·Parallels all-OS npm update/fresh proof: pass; fresh openclaw@2026.5.19, same-guest update to 2026.5.20-beta.2, and fresh openclaw@2026.5.20-beta.2 on macOS/Windows/Linux; local artifact run `openclaw-parallels-npm-update.ur3ttx`

v2026.5.20-beta.1pre-release2026-05-21

openclaw 2026.5.20-beta.1

GitHub ↗

Changes

·Discord: let voice sessions follow configured Discord users into voice channels, with allowed-channel checks, multi-user handoff, bounded reconciliation, and DAVE recovery preservation. (#84264)
·Discord/voice: include bounded `IDENTITY.md`, `USER.md`, and `SOUL.md` profile context in realtime voice session instructions by default, with `voice.realtime.bootstrapContextFiles: []` available to disable it. (#84499)
·Dependencies: bump the bundled Codex harness to `@openai/codex` `0.132.0` and refresh the app-server model-list docs for the new catalog.
·CLI/policy: add the bundled Policy plugin for policy-backed channel conformance checks, doctor lint findings, and opt-in workspace repair. (#80407)
·Agents/config: allow `agents.list[].experimental.localModelLean` so lean local-model mode can be enabled for one configured agent instead of globally.
·Providers/xAI: add device-code OAuth login so remote and headless setups can authorize xAI without a localhost browser callback. (#84005)
·Providers/OpenRouter: honor provider-level `params.provider` routing policy for OpenRouter requests, with model and agent params overriding the defaults.

Fixes

·WhatsApp: update Baileys to `7.0.0-rc12`.
·Dependencies: update `@openclaw/fs-safe` to `0.2.7` so OpenClaw's default Python-helper-off policy keeps best-effort Node write fallbacks for private stores, secret writes, run logs, and media attachments on Linux/macOS.
·Browser: honor the configured image sanitization limit for screenshots and labeled snapshots so browser-captured images follow the same resize policy as other image results. (#84595)
·Doctor: remove unrecognized `models.providers.*.models[*].compat.thinkingFormat` values during `doctor --fix` so stale provider model config can validate after upgrade. Fixes #77803.
·Status: show the configured default, session-selected model, reason, clear hint, and docs link when a session remains pinned to a model that differs from `agents.defaults.model.primary`.
·Mac app: keep local packaging signed with a stable app identity for permission testing and fix Control UI production builds under current Vite/Highlight.js exports.
·macOS app: update the embedded Peekaboo bridge to 3.2.1 so OpenClaw-hosted UI automation works with current Peekaboo CLI capture flows.
·Cron: deliver preferred final assistant output for successful scheduled runs when trailing plain tool warnings remain in diagnostics instead of marking the run failed.
·fix(mattermost): fail closed on missing channel type [AI]. (#84091)
·Recheck rebuilt system.run argv [AI]. (#84090)
·CLI: keep the private QA subcommand out of exported command descriptors unless `OPENCLAW_ENABLE_PRIVATE_QA_CLI=1`, so root help and subcommand markers match runtime registration. (#84519)
·CLI/cron: bound `openclaw cron show` job lookup pagination so non-advancing or unbounded `cron.list` responses fail instead of hanging the command. Fixes #83856. (#83989)
·Agents/messages: stop message-tool-only turns after a successful source-channel `message` send while keeping transcript mirrors under the session write lock. (#84289)
·Agents: filter silent heartbeat response-tool transcript artifacts out of embedded context snapshots so later user turns are not polluted by heartbeat no-op messages. (#83477)
·Agents/OpenAI: log repeated strict tool-schema downgrade diagnostics once per provider/model/tool signature, reducing duplicate debug noise while preserving `strict=false` fallback behavior. Fixes #82930. (#82933)
·Agents/code mode: spell out the `exec` tool's JavaScript/TypeScript, no Node module, and catalog-bridge constraints in model-visible schema text so agents can use enabled tools without trial-and-error. (#84269)
·Codex: give `image_generate` dynamic-tool calls a 120s default watchdog when no per-call or configured image timeout is set, so image generation no longer falls back to the generic 30s bridge timeout. (#84254)
·Codex: avoid duplicate dynamic tool terminal diagnostics while large diagnostic backlogs drain without blocking tool responses. (#82937)
·CLI/message: include a stable top-level `messageId` in `openclaw message --json` output when channel sends return one. (#84191)
·Cron: preserve legacy top-level array `jobs.json` stores when loading or adding scheduled jobs so old cron jobs are no longer treated as an empty store during upgrade. Fixes #60799. (#84433)
·Gateway/agents: use an agent's `identity.name` in Gateway agent summaries when `agents.list[].name` is unset, so configured agent labels remain visible in clients. (#84355; refs #57835)
·Channels/replies: keep normal `/verbose` failed-tool progress compact in message-tool replies and prevent late text-only tool output from appearing after the final answer. (#84303)
·Plugins/hooks: apply a default 30-second timeout to `before_compaction` and `after_compaction` hooks so a hung plugin handler no longer blocks compaction completion. (#84153)
·Discord: preserve disabled presentation buttons when adapting and rendering Discord message controls. (#84188)
·Twitch: add a test-only client-manager registry reset helper so non-isolated Twitch tests can clear cached managers between cases. Fixes #83887. (#84244)
·Cron: run main-session scheduled work on a cron-owned wake lane while preserving reply delivery context, so background cron turns no longer block human main-session chat. Fixes #82766. (#82767)
·Cron: use structured embedded-run denial metadata for isolated scheduled tasks so blocked exec requests fail the job without treating ordinary assistant prose as a denial. (#84067)
·Cron: keep recovered tool warnings diagnostic for successful scheduled runs so final cron output is delivered instead of being replaced by a post-processing warning. (#84045)
·Plugins/perf: thread explicit plugin discovery results through `loadBundledCapabilityRuntimeRegistry`, `resolveBundledPluginSources`, and `listChannelCatalogEntries` so callers that already hold a discovery result skip redundant filesystem walks.
·harden update restart script creation [AI]. (#84088)
·Docker: keep the bundled Codex plugin in official release image keep lists so the default OpenAI agent harness remains available after Docker pruning. Fixes #83613. (#83626)
·CLI/channels: preserve the first line of `openclaw channels logs` output when the rolling tail window starts exactly on a line boundary, mirroring the already-fixed `readLogSlice` behavior in `src/logging/log-tail.ts`.
·Control UI: treat terminal session status as authoritative over stale active-run flags so completed terminal runs stop showing abort/live UI. (#84057)
·CLI: preserve embedded equals signs in inline root option values instead of truncating after the second separator. (#83995)
·Matrix/config: accept `messages.queue.byChannel.matrix` queue overrides and keep queue provider schema/type keys aligned for Matrix, Google Chat, and Mattermost.
·CLI: format `openclaw acp client` failures through the shared error formatter so object-shaped errors stay readable instead of printing `[object Object]`. Fixes #83904. (#84080)
·Providers/Ollama: default unknown-capabilities models to tool-capable so discovered native Ollama models can use tools when `/api/show` omits capabilities. (#84055)
·Installer/Windows: launch `install.ps1` onboarding as an attached child process so fresh native Windows installs do not freeze visibly at `Starting setup...` or corrupt the wizard's terminal rendering.
·CLI/update: keep restart health checks working across one-version CLI/Gateway protocol skew and use the managed Gateway service Node for all follow-up commands even when the package root is unchanged, so `openclaw update` no longer silently switches the gateway to a different Node binary when multiple Node installations are present.
·CLI/gateway: include the running Gateway version in `gateway status` JSON output, preserving existing server metadata while falling back to status RPC data for read probes. Fixes #56222.
·Memory/search: close local embedding providers when active-memory searches time out so pending local model loads and embedding contexts are aborted and released. (#83858)
·CLI/nodes: request pending node surface approval scopes before `openclaw nodes approve` so exec-capable node approval can use admin-scoped Gateway credentials instead of failing with `missing scope: operator.admin`. (#84392)
·Agents: include bounded trajectory queued-writer diagnostics in `pi-trajectory-flush` timeout warnings so flush stalls show pending writes, queued bytes, and append state. Fixes #82961. (#82962)
·Agents/subagents: recover stale completion announces by retrying unsupported transcript-wait wakes without transcript waiting and forcing a message-tool handoff when the requester run is already stale. Fixes #83699. (#83700)
·Agents/subagents: constrain wildcard subagent target allowlists to configured agents while preserving explicitly listed compatibility targets. Fixes #84040. (#84357)
·Providers/Anthropic: route Anthropic model refs selected with Claude CLI auth through the Claude CLI runtime so shorthand refs such as `anthropic/opus-4.7` no longer fall back to embedded Anthropic billing. Fixes #84222. (#84374)
·Agents: honor explicit `models.providers.<id>.timeoutSeconds` values above the default idle watchdog for cloud and self-hosted providers, so long first-token waits no longer fall back at ~120s when the provider timeout is higher. (#83979)
·Agents/Codex: keep encrypted Responses reasoning replay provenance-bound so stale mirrored Codex transcripts drop invalid encrypted content before request assembly while preserving matching same-session replay. Fixes #83836. (#84367)
·Agents/subagents: skip stale embedded-run wake probes for dormant completion requesters, so late subagent completions go straight to requester-agent/direct handoff instead of producing `reason=no_active_run` queue noise. (#82964)
·CLI: retry config snapshot reads after a transient failure so one rejected read no longer poisons later commands in the same process. (#83931)
·Media: decode URL path basenames before using them as remote media fallback filenames, so files like `My%20Report.pdf` are surfaced as `My Report.pdf`. Fixes #84050. (#84052)
·WhatsApp: clarify inbound group diagnostics so observed but unregistered groups point to `channels.whatsapp.groups` without changing routing or sender authorization. (#83846)
·WhatsApp: drain pending outbound deliveries on a 30s periodic timer in addition to the reconnect handler, so messages enqueued while the provider is already connected no longer wait for the next reconnect to send. (#79083)
·CLI/TUI: include gateway plugin slash commands in TUI autocomplete, so connected sessions can suggest plugin-owned commands exposed by the running Gateway. (#83640)
·Gateway/mobile: restore QR setup-code handoff of bounded operator tokens for iOS and Android onboarding while keeping admin and pairing scopes out of bootstrap. (#83684)
·iOS: repair Release archive compilation for the TestFlight build. (#84255)
·Agents/compaction: bound plugin-owned CLI transcript compaction with the host safety timeout so a hung context engine can no longer stall post-turn cleanup. (#84083)
·Control UI/usage: truncate long context skill, tool, and file names in the usage panel while keeping the full name available on hover. (#42197)
·Codex: respect explicit `models auth order set` and `config.auth.order` precedence over stale `lastGood` in `/codex account`, and show `no working credential` when every explicit-order profile is ineligible instead of marking a lower-ranked profile as active. Fixes #84386. (#84412)
·Agents: honor `messages.suppressToolErrors` for mutating tool failures so configured chat surfaces do not receive separate warning payloads. (#81561)
·Agents/fallback: surface billing guidance for mixed rate-limit plus billing fallback exhaustion instead of generic failure copy. Fixes #79396. (#79489)

Release verification

·npm package: https://www.npmjs.com/package/openclaw/v/2026.5.20-beta.1
·registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.5.20-beta.1.tgz
·integrity: sha512-6xBnBZqnqI4HoAs7CU1ZmzFDqPhe/aauKr0DsmMEReLvxap9DyLK7YPTTDU/A5v3dlSHlCgzFbVIvgTaUXgy4w==
·full release validation: https://github.com/openclaw/openclaw/actions/runs/26195853190
·npm preflight: https://github.com/openclaw/openclaw/actions/runs/26195855712
·publish: https://github.com/openclaw/openclaw/actions/runs/26196993217
·npm Telegram beta E2E: https://github.com/openclaw/openclaw/actions/runs/26198047747

v2026.5.192026-05-20

openclaw 2026.5.19

GitHub ↗

Changes

·Agents: clarify that fixes should default to clean bounded refactors, lean internals, and explicit plugin SDK/API deprecation paths.
·Dependencies: update `@openclaw/proxyline` to 0.3.3.
·Dependencies: update Pi packages to 0.75.1 and raise the minimum supported Node.js 22 line to 22.19.
·Docker/Podman: add `OPENCLAW_IMAGE_APT_PACKAGES` as the runtime-neutral image build arg for extra apt packages while keeping `OPENCLAW_DOCKER_APT_PACKAGES` as a legacy fallback. (#62431)
·Gateway/ACPX: attribute startup probe, config, runtime, and resource-count costs in restart traces without changing readiness behavior. (#83300)
·Gateway: overlap startup logging and plugin-service startup with channel sidecars to reduce restart ready latency while preserving `/readyz` sidecar gating. (#83301)
·Plugins/admin-http-rpc: allow trusted admin HTTP RPC clients to start and wait for web QR login flows. (#83259)
·Mac app: redesign Settings pages with consistent card layouts, cached navigation, cleaner permissions/voice/skills/cron/exec/debug panes, and steadier spacing around the native sidebar.
·Mac app: refine Voice & Talk recognition-language and wake-phrase settings so they use the same compact card rows as the rest of Settings.
·Skills: rename the repo-local Codex closeout review skill and helper to `autoreview` while preserving the Codex-first fallback behavior.
·Skills: add a meme-maker skill for curated template search, local SVG/PNG rendering, Imgflip hosted rendering, and Know Your Meme provenance links.
·Skills CLI: allow `openclaw skills install` and `openclaw skills update` to target shared managed skills with `--global`. (#74466)
·Browser: surface pending and recently handled modal dialogs in snapshots, return `blockedByDialog` when an action opens a modal, and allow `browser dialog --dialog-id` to answer pending dialogs.
·Browser CLI: add `openclaw browser evaluate --timeout-ms` so long-running page functions can extend both the evaluate action and request timeout budgets. (#83447)
·Codex app-server: scope OpenClaw prompt guidance by runtime surface so native Codex keeps Codex-owned base/personality instructions while OpenClaw contributes only runtime context, delivery guidance, and explicitly scoped command hints. (#83454)
·Docker/Podman: add `OPENCLAW_IMAGE_PIP_PACKAGES` for opt-in Python package installation in local image builds. (#83771)
·Agents/tools: shorten built-in tool descriptions and schema hints across media, messaging, sessions, cron, Gateway, web, image/PDF, TTS, nodes, and plan tools while preserving routing guardrails.
·Skills: add node inspector debugging, fused diagram generation, and throwaway spike workflow skills.
·CLI/plugins: add `defineToolPlugin` plus `openclaw plugins build`, `validate`, and `init` for typed simple tool plugins with generated manifest metadata, optional tool declarations, and context factories.
·Agents/skills: tighten bundled skill prompts and metadata, quote skill descriptions, refresh current CLI/API guidance, and update embedded sherpa-onnx runtime downloads.
·Skills: update the Obsidian skill to target the official `obsidian` CLI and require its registered binary instead of the third-party `obsidian-cli`.
·Skills: add a Python debugging skill for pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.
·Codex: add `/codex plugins list`, `enable`, and `disable` for managing configured native Codex plugins from chat without editing config by hand.
·Plugins/messages: add presentation capability limits for channel renderers, adapt rich message controls before native rendering, and mark legacy `interactive`/Slack directive producer APIs as deprecated.
·Plugins/subagents: store channel delivery routes as canonical session metadata and deprecate ad hoc subagent hook delivery-origin fields in favor of core route projection.
·Proxy: support HTTPS managed forward-proxy endpoints and scoped `proxy.tls.caFile` CA trust for proxy endpoint TLS. (#79171)
·QA-Lab: add first-hour 20-turn and optional 100-turn runtime parity scenarios, with tier metadata for standard and soak QA gates. Fixes #80338; refs #80337.
·QA-Lab: add `openclaw qa suite --runtime-parity-tier` and wire the standard Codex-vs-Pi tier into release checks separately from optional/live-only/soak lanes. Fixes #80337.
·QA-Lab: add a live-only Codex Pi-shaped Read vocabulary canary so runtime parity catches native workspace-read prompt compatibility drift. (#80323)
·QA-Lab: add live-only harness self-health scenarios for plugin hook crashes, manifest contract errors, and WebChat direct-reply self-message routing. (#80323)
·QA-Lab: add runtime tool fixture scenarios and coverage reporting for Codex-native workspace tools, OpenClaw dynamic tools, and optional plugin-backed tools. Fixes #80173.
·QA-Lab: expose runtime tool fixture coverage through `openclaw qa coverage --tools`, with optional suite-summary evaluation for parity gate artifacts.
·QA-Lab: schedule a live-frontier Codex-vs-Pi runtime token-efficiency artifact lane in the all-lanes QA workflow. Fixes #80175.
·QA-Lab: hard-gate required OpenClaw dynamic runtime-tool drift in the standard Codex-vs-Pi tier with a blocking release-check verifier and publish the tool coverage report artifact. Fixes #80339; refs #80319.
·QA-Lab: add the personal-agent approval-denial scenario so the benchmark pack verifies denied local reads stop cleanly without tool progress or fixture leaks. (#83150)
·QA-Lab: extend the personal-agent benchmark pack with a local task followthrough scenario for proof-backed pending, blocked, and done status reporting.
·QA-Lab: add a report-only dreaming shadow-trial scenario so candidate memory promotion can be evaluated without mutating `MEMORY.md`.
·Gateway/performance: add `pnpm test:restart:gateway` benchmark tooling for repeated restart readiness, downtime, trace, and resource-slope evidence. (#83299)
·Android: switch Talk Mode to realtime Gateway relay voice sessions with streaming mic input, realtime audio playback, tool-result bridging, and on-screen transcripts. (#83130)
·Gateway/config: expose config lookup reload metadata so tools can distinguish restart-required, hot-reloadable, and no-op fields before applying config edits. Fixes #81409. (#81612)
·Telegram: add allowlisted native DM draft previews for transient tool progress while keeping final answers on the normal persistent delivery path. (#83622)
·QA-Lab: add a personal-agent share-safe diagnostics artifact scenario so support handoffs keep useful status while omitting raw personal content.
·QA-Lab: add a personal-agent no-fake-progress scenario so completion claims stay tied to local evidence instead of unsupported external progress. (#83824)

Fixes

·CLI: reject explicit port numbers above 65535 before they reach Gateway or Node bind paths. Fixes #83900. (#84008)
·Codex app-server: preserve plugin tool auth profiles when Codex owns model transport so OpenClaw dynamic tools can resolve their provider credentials. (#83603)
·Memory/search: scan the JS-side fallback vector path (used when the sqlite-vec index is unavailable or has a mismatched dimension) in bounded rowid batches and yield to the event loop between batches so large chunk tables can no longer pin the Node.js main thread for multi-second windows. Also keeps the SQL prepared statement rooted in a local so node:sqlite cannot finalize it mid-scan under heap pressure. Fixes #81172.
·Memory Wiki: preserve fs-safe diagnostics when bridge source page writes fail for non-symlink filesystem safety reasons, so directory collisions are reported with the underlying error code. (#83776)
·Telegram: keep forum topics from blocking sibling topic traffic by routing inbound serialization, media/text buffers, and account API queues on topic-aware lanes. (#83829)
·Telegram: keep queued forum-topic follow-up messages from inheriting superseded source abort signals, so later same-topic user turns can still run and reply after an active turn is replaced. (#83827)
·CLI/update: bypass npm freshness filters consistently during managed package and plugin installs so freshly published release plugins remain installable.
·CLI/update: guide root-owned npm install EACCES recovery by stopping the managed Gateway before manual package replacement, then reinstalling and restarting the service. Fixes #83747. (#83757)
·Twitch: register refreshing chat tokens with Twurple's chat intent so automatic token refresh keeps chat access available. (#83750)
·Agents/subagents: keep collect-mode announce queues batching unresolved-origin items with compatible same-route messages and resume collection after a true cross-channel drain when a later compatible batch remains. Fixes #83577.
·Skills: refresh existing session skill snapshots when watched skill roots change, so changed extra skill directories take effect without starting a new session. Fixes #83782. (#83800)
·Providers/Anthropic: preserve native image input for current Claude model rows when stale local catalog data marks them text-only. (#83756)
·Providers/Anthropic: preserve Claude 4 image capability when configured model refs resolve through a stale local catalog row. (#83756)
·Providers/DeepSeek: normalize MCP tool schemas with `anyOf`/`oneOf` unions before normal and compaction requests reach DeepSeek, preventing union-shaped parameters from being rejected. (#83766)
·Control UI: render live tool progress from session-scoped `session.tool` Gateway events so externally started runs show their tool cards in the active session. (#83734)
·Outbound: resolve send-capable channel plugins from the active runtime registry when the pinned startup registry only has setup metadata. (#83733)
·Discord: preserve streamed reply previews when recovered tool-warning finals are delivered before or after the assistant's final reply. (#84169)
·Control UI: keep the chat delete confirmation popover clamped inside the visible viewport on small screens. (#83804)
·Browser: enforce current-tab URL allowlist checks for `/act` evaluate/batch actions and `/highlight` routes while leaving tab-management actions unblocked. (#78523)
·CI: require real-behavior-proof verdict markers to come from the ClawSweeper GitHub App before accepting exact-head proof. (#83692)
·Models: show the effective OpenAI/Codex auth profile in `/models` provider headers instead of falling back to the OpenAI env-key label. (#83697)
·CLI: include active bundled loopback MCP tools in CLI system prompts and reset provider-side CLI sessions when that prompt-visible tool surface changes. (#83785)
·Browser: keep a profile `cdpPort` when its `cdpUrl` omits a port, while still letting explicitly written URL ports win. (#82166)
·Agents/image generation: allow distinct `image_generate` prompts to start separate session-backed background tasks while same-prompt retries still return the active task status. (#83614)
·Gateway/WebChat: honor configured `channels.webchat.textChunkLimit` and `chunkMode` overrides when chunking WebChat replies. (#83713)
·Control UI: stop the chat reading indicator from sticking after an assistant response finishes. (#83515)
·Skills: reject empty or whitespace-only skill names and descriptions during quick validation. (#27061)
·Sessions: skip trailing custom transcript entries when checking tail assistant replies so embedded CLI gap-fill does not duplicate canonical assistant output. (#83635)
·Memory Wiki: keep `wiki_lint` tool output path-safe by reporting vault-internal lint reports as relative paths in tool text and details while preserving absolute report paths for CLI/file callers. (#83439)
·Telegram: keep verbose tool progress visible without mirroring non-final progress into active session transcripts, preventing embedded provider replies from aborting mid-run. (#83631)
·Telegram: log successful outbound text and media deliveries with account, chat, message, operation, thread, reply, silent, and chunk metadata while keeping message bodies out of logs. Fixes #83196. (#83247)
·Cron: link isolated scheduled task runs to their stable cron session so task status and cleanup can follow the backing agent run. (#83606)
·Codex app-server: mark Codex-native subagent task mirrors terminal when blocked or failed spawn-agent calls arrive with stale initializing child state, preventing task registry entries from staying running. Fixes #83852. (#83945)
·CLI: enforce the documented Node.js 22.19 runtime floor in the source launcher.
·Release stability: repair broad-gate regressions in requester-agent completion handoff, QA-Lab mock spawn attribution, Slack monitor test isolation, plugin uninstall peer fixtures, and Node-floor launcher contract coverage.
·Agents/replies: persist queued follow-up user messages and assistant error stubs only once across model-fallback retries, preventing repeated provider rejections from corrupted same-role session transcripts. Fixes #83404. (#83417)
·Telegram: preserve reply-target context for bare mention replies on runtime-only turns so the model sees the replied-to message body. Fixes #83767. (#83953)
·ClawHub: preserve configured base URL path prefixes when building API request URLs, so self-hosted ClawHub instances mounted under a subpath keep routing correctly. (#83982)
·Slack: persist delivered inbound message IDs and fail closed when same-channel thread replies lose their thread context, preventing delayed duplicate replies and accidental channel-root posts. Fixes #83521.
·Codex app-server: complete OpenClaw dynamic tool diagnostics at the request boundary so successful, failed, timed out, aborted, and blocked tool calls do not leave active tool state behind. Fixes #83474.
·Gateway/config: keep config writes from failing on unrelated unresolved auth-profile SecretRefs while preserving live auth-profile runtime snapshots.
·Gateway/sessions: clear stored CLI provider resume bindings on non-subagent `/reset` so the next turn starts a fresh provider-side CLI conversation instead of resuming old context. (#83448)
·Doctor: preserve legacy whole-agent Claude CLI intent by moving matching Anthropic model selections to model-scoped runtime policy before removing stale runtime pins. Fixes #83491.
·Discord/OpenAI: keep realtime Discord voice sessions hearing follow-up turns with OpenAI realtime and prebuffer assistant playback to avoid choppy starts. (#80505)
·LM Studio: resolve env-template API keys like `${LMSTUDIO_API_KEY}` through the standard SecretInput path instead of sending the raw template as the bearer token, and preserve header-auth and discovery-key precedence when the template is unset. Fixes #80495. (#80568)
·Discord/subagents: route the initial reply from thread-bound delegated sessions into the bound Discord thread instead of the parent channel. Fixes #83170. (#83172)
·Gateway/sessions: rotate failed agent sessions when their transcript file is missing instead of wedging per-channel lanes. Fixes #83488. (#83553)
·Agents: refresh final-delivery routing from fresh session state before declaring a no-send failure, keeping recovered runs on the normal durable delivery path. (#83835)
·Agents: guard final-delivery fresh session routing against mismatched logical sessions before reusing recovered delivery context. (#83928)
·Media: prevent image metadata probing from invoking external decoder delegates on unrecognized image bytes, and stop fallback chaining after real processing errors.
·Media: install Sharp with the root package and fall back to sips, Windows native imaging, ImageMagick, GraphicsMagick, or ffmpeg for image resizing/conversion when Sharp is unavailable. Fixes #83401.
·Telegram: deliver generated media completions back into forum topics by preserving topic IDs across requester-agent handoff. (#83556)
·Gateway: defer update-check startup until after readiness so package update checks no longer block sidecar-ready startup, while preserving update broadcasts and shutdown cleanup. (#83520)
·Telegram: keep `/btw` and read-only status commands from aborting active runs, and avoid retaining raw update payloads in timed-out spool tombstones. Refs #83272.
·Agents: log strict-agentic execution contract diagnostics only when the planning-only retry path actually triggers.
·Agents: stop embedded session takeover and session write-lock errors from consuming model fallbacks while preserving provider fallback metadata. Fixes #83510.
·Agents/video: hide `video_generate` reference-audio parameters unless a registered video provider supports audio inputs.
·Plugins: fall back to npm for official ClawHub updates when artifact downloads are unavailable, including beta-to-default fallback and dry-run version reporting.
·Plugins/xAI: echo PKCE challenge fields during OAuth authorization-code token exchange for xAI token-endpoint compatibility. (#83499)
·Codex app-server: hydrate current inbound image attachments before queued runs so Responses-backed agents receive Discord and other channel images as native vision input. Fixes #83466.
·Codex app-server: keep native code mode available without forcing code-mode-only so OpenClaw dynamic tool turns complete through the app-server tool bridge. Fixes #83109.
·Codex app-server: expose OpenClaw's sandbox-routed shell as `sandbox_exec`/`sandbox_process` for non-Docker sandbox backends so SSH sandbox agents keep a correctly routed shell path without shadowing Codex native shell. Fixes #80322.
·Release stability: recover stale session diagnostics and Codex OAuth fallback state so stuck runs and reused refresh tokens clear without blocking follow-up work. (#83503)
·Messages/TTS: apply TTS directives before message-tool sends reach core, gateway, or plugin delivery so opt-in message-tool rooms and proactive sends attach voice notes instead of leaking raw tags. Fixes #81598.
·Messages/Codex: keep Codex direct/source chats on message-tool visible delivery by default while documenting and testing `messages.visibleReplies: "automatic"` as the old-mode opt-out; channel wildcard model overrides now apply to direct chats before harness delivery defaults.
·Memory/QMD: keep archived session transcript hits visible after QMD export while preserving normal `.md` session ids that only resemble archive names. (#83518; fixes #83506)
·Codex app-server: preserve network access for sandboxed Codex code-mode turns when the OpenClaw sandbox allows outbound egress. Fixes #83347.
·Codex app-server: honor writable Docker bind mounts for sandboxed workspace-write turns while disabling native Code Mode when container-path aliases or read-only bind shadows cannot be represented safely host-side. Fixes #83737. (#83849)
·QA-Lab: keep the OTLP smoke decoder independent of removed OpenTelemetry generated-root internals.
·Messages: default group/channel visible replies to automatic final delivery again, keeping `message_tool` opt-in for ambient/shared rooms and tool-reliable models.
·CLI/TUI: force standalone `/exit` runs to terminate after `runTui` returns so onboarding-launched TUI children do not stay alive invisibly. (#83501)
·Agents/code mode: honor per-agent code-mode config in schema, runtime catalog activation, and model payload filtering. Fixes #83388.
·Agents/code mode: preserve agent, session, run, and channel context in `before_tool_call` hooks for top-level `exec`/`wait` dispatches. Fixes #83387.
·QQBot: shorten C2C typing indicators to a 10-second window renewed every 5 seconds, capped to keep a final passive-reply slot available. (#83469)
·Replies: keep final payload delivery after live preview updates so channels can finalize or send the completed answer instead of losing preview-only drafts. (#83468)
·Discord: deliver final replies in progress-mode preview streams instead of deduplicating the final visible message. (#83443)
·Providers/Xiaomi: replay MiMo Anthropic-compatible `reasoning_content` as provider-required thinking blocks even when OpenClaw thinking is disabled, fixing follow-up tool turns for `mimo-v2-flash`. Fixes #83407.
·Agents/exec approvals: forward approval-runtime credentials on agent-owned Gateway approval calls so approved async commands complete through the existing runtime path instead of stalling on unauthenticated follow-up calls.
·Gateway/skills: preflight remote macOS skill-bin refreshes with a WebSocket connectivity check so stale node sessions skip quickly instead of logging slow `system.which` timeout warnings.
·CLI/config: keep broken discovered plugins that are not referenced by active config from failing `openclaw config validate`, while preserving fatal errors for explicitly configured plugin entries.
·GitHub Copilot: drop unsafe native Responses reasoning replay items with non-replayable IDs before dispatch, preventing affected Copilot sessions from failing with `invalid_request_body`. Fixes #83220.
·Agents/Codex: fail closed when an explicitly requested Codex harness is not registered instead of silently trying configured model fallbacks. Fixes #83349.
·QA-Lab: make runtime tool coverage fail on missing required tool exercise instead of treating pass/pass parity envelope drift as missing coverage.
·Core/plugins: harden clawpatch-reported edge cases across gateway auth cleanup, Claude session id paths, plugin activation policy, apply-patch hunk handling, diagnostic redaction, and plugin metadata validation.
·UI: show reasoning choices as plain labels instead of leaking internal override wording in session and chat pickers.
·Mac app: avoid repeating the Configuration heading inside channel quick settings.
·Mac app: keep the Settings sidebar always visible and remove the redundant titlebar hide/show control.
·Mac app: normalize Settings pane content margins so pages share the same left and right rail.
·Mac app: prefer explicit private/Tailscale/LAN Gateway endpoints over SSH tunnels, preserve legacy loopback tunnel configs, persist transport choices, and show captured SSH stderr when tunneling really fails.
·Gateway/sessions: keep ACP/acpx and runtime child sessions visible in configured-only session lists when their owner or parent session belongs to a configured agent.
·Mac app: keep app-level menu commands and Dashboard failure states reachable when the remote Gateway is disconnected.
·Mac app: allow longer Gateway and Context errors to wrap in the menu instead of truncating the useful failure detail.
·Mac app: tighten remote Gateway fields in Settings so the Connection pane keeps readable labels and full action button text.
·Mac app: keep custom Settings card rows left-aligned and full-width so Discovery and status sections no longer appear centered or detached.
·Mac app: align Location permission controls to the same trailing column as the rest of Settings.
·Mac app: add Dashboard, Chat, Canvas, and Settings shortcuts to the Dock icon menu.
·Mac app: replace the Settings window's native split-view sidebar with an explicit layout so page content keeps its leading gutter when the sidebar is shown or hidden.
·Mac app: render channel quick config as aligned Settings rows and hide schema-only variants that cannot be edited safely from the quick pane.
·Gateway/webchat: hide internal runtime-context and other `display: false` transcript messages from Chat history and live message events. Fixes #83216.
·CLI/help: keep `gateway`, `doctor`, `status`, and `health` help registration out of action/runtime imports so subcommand `--help` stays lightweight in constrained terminals. Fixes #83228.
·CLI/help: show plugin-owned command help based on the active memory slot so LanceDB memory users see `ltm` instead of unavailable `memory` commands. Fixes #83745. (#83841)
·Cron/Discord: keep explicit announce runs in message-tool-only source-reply mode so scheduled agent turns post once instead of also echoing through automatic visible replies. Fixes #83261.
·Telegram: preserve forum-topic origin targets in inbound, audio-preflight, and skipped-message hook contexts so follow-up delivery stays bound to the originating topic. Fixes #83302.
·Telegram: retry HTTP 421 Misdirected Request send failures on a fresh fallback transport so transient edge-node routing errors no longer drop outbound replies. Fixes #48892. (#48908)
·Telegram: fail topic sends closed when Telegram reports `message thread not found` instead of retrying without `message_thread_id` into the base chat. Refs #83302.
·Config/subagents: remove ignored agent-model `timeoutMs` keys, keep subagent model config to primary/fallback selection, and clean shipped stale config through doctor. Fixes #83291.
·Mac app: align the Sessions settings pane with the standard Settings page gutter and row spacing.
·OpenAI/Codex: stop rejecting available `openai-codex` GPT-5.1, GPT-5.2, and GPT-5.3 model refs during config validation, while keeping removed Spark aliases suppressed. Fixes #83303.
·Plugins/xAI: complete OAuth-backed xAI login and sidecar auth fixes, including guarded loopback callback CORS handling, video generation polling/defaults, and native-host User-Agent attribution. (#83322)
·Codex app-server: preserve streamed native command output in mirrored transcripts and trajectory exports when final snapshots omit aggregated output. (#83200)
·Codex app-server: fail closed when chat or sender policy denies tools, disabling native code, app, environment, and user MCP surfaces for restricted turns. (#82374)
·Codex app-server: keep recent context-engine messages when oversized projected history is truncated, so short follow-ups in long channel sessions do not fall back to stale earlier turns. (#83127)
·Codex app-server: keep OpenClaw session spawning searchable while steering Codex-native delegation through native subagents, avoiding duplicate direct subagent surfaces. (#83329)
·Codex app-server: recover stale childless Codex-native subagent task mirrors during maintenance and allow their registry rows to be cancelled without an OpenClaw child session. (#82836)
·Feishu: return bound subagent delivery origins from session thread setup so Feishu subagent completions route back to the same DM or topic. (#83190)
·CLI/update: tailor post-update Gateway recovery hints by platform, showing systemd, LaunchAgent, Scheduled Task, or generic service-manager guidance instead of macOS-only recovery text. (#83096)
·Plugins: apply a default 15-second timeout to legacy `before_agent_start` hooks so hung plugin handlers no longer block agent startup. Fixes #48534. (#83136)
·Feishu: refresh inbound session delivery context for DM, group, and broadcast turns so later replies do not inherit stale WebChat routing. Fixes #78274.
·Agents/subagents: require the initial subagent registry save before reporting spawn accepted, returning a spawn error instead of losing an untracked run when the registry write fails. (#83146)
·QA-Lab/qa-channel: attach redacted agent tool-start traces to outbound `QaBusMessage` records so scenarios can assert actual tool use instead of relying only on reply text. Fixes #67637.
·QA-Lab: fail live runtime parity reports when assistant-message usage is missing, preventing `0 vs 0` live token rows from being reported as passing proof. Fixes #80411.
·QA-Lab: add a runtime token-efficiency sidecar report that classifies Codex savings separately from regressions and fails only positive Codex-over-Pi live token deltas above threshold. Fixes #81093.
·QA-Lab: fail Codex-backed OpenAI live runtime-pair runs before launching isolated workers when no portable Codex auth is available, while staging API-key fallbacks and configured Codex keys for isolated QA agents. Fixes #80412.
·QA-Lab: refresh parity gates, mock frontier fixtures, model scenarios, and workflow artifact lanes to compare GPT-5.5 against Claude Opus 4.7. Fixes #74262.
·QA-Lab: make mock parity dispatch provider-aware for source discovery and subagent scenarios so OpenAI and Anthropic lanes no longer share identical canned plans. Fixes #64879.
·QA-Lab: stop returning Control UI bearer tokens from unauthenticated bootstrap payloads and bind Docker harness ports to loopback-only host addresses. (#66355)
·Mac app: avoid a SwiftUI metadata crash when rendering the Cron Jobs settings pane.
·Agents/subagents: preserve run-mode keep subagent registry entries past the session sweep TTL, so kept subagent runs remain visible after cleanup completes. Fixes #83132. (#83168)
·Agents/OpenAI streams: yield via `setTimeout(0)` instead of `setImmediate` between bursty Responses chunks so abort timers can fire during the yield, keeping cancel-on-timeout responsive on hot streams. Refs #82462.
·Agents/Codex: keep legacy `oauthRef`-backed OAuth profiles usable while `openclaw doctor --fix` migrates them back to inline credentials, without creating new sidecar credentials. (#83312)
·Agents/Codex: load the selected provider owner alongside the Codex harness runtime so `openai-codex` models resolve when plugin allowlists scope runtime loading. Fixes #83380. (#83519)
·Telegram: fail stalled isolated-ingress handlers into tombstones and abort same-lane reply work before restarting, so later same-chat updates drain after a hung turn. Fixes #83272. (#83505)
·CLI/config: send SecretRef diagnostics to stderr so JSON command stdout remains parseable.
·CLI/doctor: seed Control UI allowed origins when migrating legacy non-loopback gateway bind host aliases like `0.0.0.0`. Fixes #83286.
·CLI/plugins: ship the bundled memory CLI as a package entry so package-installed `openclaw memory` commands register correctly.
·CLI/update: defer doctor-time plugin package installs during package swaps and seed post-core repair from the updated install registry, preventing duplicate reinstall failures.
·CLI/update: preserve old-parent-readable config metadata during legacy package handoffs, fall back only to official `@openclaw/*` npm plugin packages when ClawHub plugin artifacts are unavailable, and keep managed service package roots authoritative during updates.
·Feishu: detect SecretRef top-level credentials as a configured default account instead of treating object-backed app secrets as missing.
·Gateway/restart: keep ordinary unmanaged SIGUSR1/config restarts in-process instead of detach-spawning an orphaned child, preserving custom supervisor PID tracking while leaving update restarts on the fresh-process path. Fixes #65668.
·CLI/completion: resolve concrete PowerShell profile paths and reload commands during setup and doctor completion installation. Fixes #44296. (#83059)
·Telegram: keep isolated long polling below the hard `getUpdates` request guard so idle bot accounts with high `timeoutSeconds` do not false-disconnect and restart-loop. Fixes #83264.
·Providers/Google: preserve and recover Gemini 3 tool-call thought signatures during native replay so function-calling turns no longer fail with missing `thought_signature` 400s. Fixes #72879. (#80358)
·Telegram: skip transcript-only delivery mirrors and gateway-injected rows when resolving latest assistant text, preventing retained previews from replacing final replies with stale fragments. Fixes #83159. (#83362)
·Memory/QMD: keep lexical search on raw hyphenated queries while normalizing semantic QMD sub-searches, avoiding fallback to the builtin index for dashed identifiers and dates. Fixes #81328.
·Memory-core: distinguish sqlite-vec load failures from missing semantic vector embeddings in degraded `memory index` warnings, so vector recall diagnostics point at unresolved dimensions instead of blaming sqlite-vec when the store is ready. Fixes #75624. (#83056)
·Agents/subagents: preserve sandbox-peer controller ownership while routing completion announcements back to the originating run session, keeping subagent control and completion delivery scoped correctly. Fixes #80201. (#80242)
·Gateway: continue restarting remaining channels when one hot-reload channel restart fails, while still reporting aggregate reload failure and rolling back plugin pre-replace stops. Fixes #83054.
·Gateway/plugins: bind admin HTTP RPC dispatch to the accepting gateway instance so multi-gateway processes cannot execute plugin HTTP control-plane calls against another live gateway. Fixes #83486. (#83487)
·Telegram: keep hot-reload restarts from marking polling accounts manually stopped and restart isolated ingress cleanly after worker shutdown, preserving Telegram replies across config reloads. Fixes #83008. (#83410)
·Telegram/Ollama: pass current Telegram image attachments into native PI/Ollama vision turns so live photo prompts reach Ollama as native images. Fixes #83023. (#83516)
·Gateway/secrets: split the lightweight secrets runtime state and auth-store cache from the full secrets runtime and take a startup fast path when the gateway startup config has no SecretRef values, speeding up secrets startup while preserving cleanup and refresh semantics.
·Codex app-server: rotate oversized native Codex threads before resume and cap dynamic tool-result text entering native Codex sessions, preventing stale oversized context from surviving OpenClaw compaction. (#82981)
·Gateway/restart: drain pending replies and active chat runs during restart shutdown before sockets and channels close, aborting timed-out chat runs through the normal cleanup path. (#69121)
·Agents/Codex: use the Codex runtime context window for OpenAI-model preflight compaction and memory flush checks, so GPT-5.5 Codex sessions compact before hitting the smaller native context limit. Fixes #82982.
·QA-Lab: clean orphaned gateway temp roots when a suite parent exits and wait on gateway plus transport readiness after config restarts, reducing stale `qa-channel` noise from interrupted runs. Fixes #65506.
·QA-Lab: wake qa-bus long polls that arrive with stale future cursors after a bus restart, preserving reconnect readiness for harness clients. (#67142)
·QA-Lab: stage Multipass transfer scripts under OpenClaw's preferred temp root instead of raw OS temp paths, keeping the VM runner inside temp-path guardrails. (#64098)
·Agents/replies: keep surviving reply media and append a warning when other media references fail, so partial media normalization no longer drops failures silently.
·Config/models: accept `thinkingFormat: "together"` in model compat config so Together routes can opt into the Together-specific thinking response shape.
·Plugins/tokenjuice: bump the bundled tokenjuice runtime to 0.7.1, bringing Codex hook approval compatibility, pre-tool command wrapping fixes, and Rolldown/Vitest output compaction improvements into the OpenClaw plugin.
·Agents/OpenAI: stop post-processing GPT-5 final replies with hardcoded brevity caps, preserving full channel responses instead of appending synthetic ellipses, and log when strict-agentic GPT-5 execution activates. Fixes #82910.
·Mac app: refine the Settings General and Connection panes with cleaner status panels, card rows, and a single native titlebar sidebar toggle.
·Agents/media: deliver failed async image, music, and video generation completions directly when requester-session completion handoff fails, so channel users see provider errors instead of silent fallback stalls.
·Browser/CDP: keep loopback proxy bypass active across both `NO_PROXY` casings and redact home-relative Chrome MCP profile paths in attach-failure diagnostics.
·Agents/music: steer song, jingle, beat, anthem, and instrumental requests toward `music_generate` audio creation instead of lyric-only replies, and reserve `lyrics` for exact sung words.
·Codex app-server: record native Codex tool calls and results into trajectory artifacts so debug/trajectory exports capture the full Codex-native tool history, not just OpenClaw-bridged turns.
·Codex/app-server: keep bound conversation sessions on the owning agent runtime so native Codex control and follow-up turns do not fall back to the default agent client. Fixes #82954. (#82993)
·CLI/infer: run gateway model probes in fresh explicit sessions so one-shot provider checks do not inherit default agent transcript state. (#82861)
·Providers/Together: send video-generation requests to Together's v2 video API even when shared text-model config still points at the v1 base URL. (#82992)
·Browser CLI: preserve browser-level options on nested commands, skip option values during lazy command registration, and keep long-running wait/download/dialog hooks open for their advertised wait window.
·CLI/sessions: accept `openclaw sessions list` as an alias for `openclaw sessions`, matching other list-style commands. Fixes #81139. (#81163)
·Channels/stream previews: widen compact progress draft lines and cut prose at word boundaries while preserving command/path suffixes, with `streaming.progress.maxLineChars` for channel-specific tuning.
·CLI/plugins: have `openclaw plugins doctor` warn when a configured runtime needs a missing owner plugin, sharing the same install mapping as `openclaw doctor --fix`. Fixes #81326. (#81674)
·Agents/Codex: route OpenAI runs that resolve to `openai-codex` through the Codex provider and bootstrap OpenClaw's stored OAuth profile into the Codex harness when the harness owns transport, so `openai/*` model refs no longer fail with `No API key found for openai-codex` despite an existing Codex OAuth profile. (#82864)
·Agents/ACP: distinguish prompt-submitted and runtime-active child stalls from true interactive waits, including redacted proxy-env diagnostics for Codex ACP no-output runs. Fixes #44810.
·Agents/memory: explain that memory-triggered compaction exposes only `read` and append-only `write` when configured core tools are unavailable in `tools.allow` warnings. Fixes #82941.
·Agents/OpenAI: preserve deterministic tool payload ordering for prompt-cache reuse across OpenAI Responses and chat completions calls. (#82940)
·ACP/Codex: honor terminal ACP turn results so failed Codex/acpx runs are not recorded as successful after only progress text. Fixes #79522.
·Telegram: warn when a media group drops photos that fail to download, including albums where every photo is skipped. Fixes #55216. (#82987)
·Agents/diagnostics: treat repeated same-handle embedded-run cleanup as idempotent while preserving true replacement-handle mismatch diagnostics. Fixes #82959. (#82960)
·Agents/subagents: preserve high-priority `AGENTS.md` policy in bootstrap context when oversized files are trimmed, and warn agents to read the full policy file before relying on scoped rules. Fixes #82920. (#82921)
·Agents/skills: apply the full effective tool policy pipeline to inline `command-dispatch: tool` skill dispatch before owner-only filtering, preserving configured allow, deny, sandbox, sender, group, and subagent restrictions. (#78525)
·Codex: avoid spawning native hook relay subprocesses for post-tool/finalize events with no registered hook handlers while preserving pre-tool safety and approval relays. Fixes #76552. (#78004)
·Channel accounts: keep top-level default channel accounts visible when named accounts are added alongside default credential material, so mixed legacy/new account configs keep resolving `default` instead of silently dropping it.
·Agents/CLI: reject empty successful CLI subprocess replies as `empty_response` and keep them out of shared auth-profile health, so blank Claude CLI results no longer become green no-payload turns. Fixes #83231. (#83421)
·Codex/Telegram: synthesize native Codex tool progress from final turn snapshots so Telegram `/verbose` stays visible when command events arrive only at completion.
·Codex/Telegram: deliver Codex verbose tool summaries in direct message-tool-only turns while suppressing message-send and activity-log noise. (#83186)
·Mac app: make Channels settings open faster by deferring config-schema work, avoiding startup channel probes, caching decoded channel status rows, and showing only compact quick settings instead of the full generated channel schema.
·Control UI: include the Control UI and Gateway protocol versions in protocol-mismatch errors so stale app/dashboard pairings identify which side needs rebuilding or restarting.
·Gateway/protocol: restore Gateway WS protocol v4 and keep `message.action` room-event metadata on the existing `inboundTurnKind` wire field while preserving internal inbound-event classification.
·Agents/tools: prefer non-webchat session-key routes when the message tool has stale webchat context, so message-tool-only replies keep delivering to the originating channel. Fixes #82911. (#83004)
·Channels: keep direct-message last-route writes on isolated `per-channel-peer` sessions instead of contaminating the agent main session with channel delivery context. Fixes #36614.
·Mac app: move the Settings sidebar toggle into the native titlebar and tighten the General pane width.
·Mac app: keep visited Settings panes mounted so switching tabs no longer blanks and reloads their content.
·Mac app: make Config settings open from shallow schema lookups and load selected paths on demand instead of fetching and rendering the full generated config schema up front.
·Codex: sanitize inline image payloads before Codex app-server and OpenAI Responses replay, and clear poisoned Codex thread bindings after invalid image errors. Fixes #82878.
·Providers/GitHub Copilot: request identity-encoded Copilot API responses across token exchange, catalog, model calls, usage, and embeddings so compressed Business-account error payloads no longer reach JSON parsers as gzip bytes. Fixes #82871.
·Telegram: redact nested raw-update identifiers and user metadata before verbose raw update logging, preserving useful update/message ids without exposing chat, user, command, or profile details. (#82945)
·Telegram: preserve replied-to bot messages, captions, and media metadata in group reply chains so follow-up replies understand what the user is reacting to. (#82863)
·Providers/Together: update PI runtime packages to 0.74.1 and emit Together-style `reasoning.enabled`/`max_tokens` controls for reasoning-capable OpenAI-completions models.
·Agents/diagnostics: split slow embedded-run `attempt-dispatch` startup summaries into workspace, prompt, runtime-plan, and final dispatch subspans so traces identify the delayed setup phase. Fixes #82782. (#82783)
·Agents/Codex: flatten nested tool-result middleware blocks into bounded text so successful message sends are no longer replaced with `Tool output unavailable due to post-processing error`. Fixes #82912.
·CLI/media: accept HTTP(S) URLs in `openclaw infer image describe --file`, fetching remote images through the guarded media path instead of treating URLs as local files. Fixes #82837. (#82854)
·Agents/subagents: keep session-backed parent runs active when the child wait call times out before the child session has actually settled, so late subagent completions are reconciled instead of being lost. Fixes #82787.
·Control UI: advertise shared Gateway protocol constants in browser connect frames, fixing protocol mismatch handshakes after protocol constant drift. Fixes #82882.
·Gateway: add rollback protocol-mismatch diagnostics, including client protocol ranges in Gateway logs and deep status/doctor hints for stale client processes. Fixes #82841. (#82908)
·Agents/subagents: keep successful keep-mode completion payloads pending after final-delivery retry exhaustion, so requester recovery no longer loses final subagent results. Fixes #82583. (#82999)
·Gateway/auth: allow same-host trusted-proxy callers to use the documented local direct `gateway.auth.password` fallback after revisiting the #78684 fail-closed policy, while keeping token fallback rejected and forwarded-header requests on the trusted-proxy path. Fixes #82607. (#82953)
·Agents/subagents: wait for queued completion handoffs to reach the parent transcript before marking them announced, preventing busy parent runs from cleaning up before observing child results. Fixes #82913. (#83039)
·Agents/subagents: route group/channel subagent completions through message-tool-only handoffs when required and keep active-requester wake failures from dropping completion delivery. Fixes #82803.
·Memory-core: scan persisted memory source sessions on startup, comparing on-disk transcripts against the index and marking only missing/newer/resized files dirty for incremental sync. Fixes #82341. (#82341)
·Telegram: keep the top-level default account in the account list when named accounts or bindings are added alongside top-level credentials, preserving default polling while still letting named-only configs resolve to a single account. Fixes #82794. (#82794)
·CLI/models: reuse command-scoped plugin metadata across model listing, provider catalog, auth, and synthetic-auth checks, restoring fast `openclaw models` runs for plugin-heavy installs. Fixes #82881. (#83033)
·CLI/channels: show configured official external channels such as Discord in `openclaw channels list` when their plugin package is missing, including the install and doctor repair command instead of reporting no configured channels. Fixes #82813.
·Signal: preserve mixed-case group IDs through routing and session persistence so group auto-replies keep delivering after updates. Fixes #82827.
·Agents/tools: keep the `message` tool available in embedded runs when it is explicitly allowed through `tools.alsoAllow` or runtime tool allowlists, so channel plugins with custom reply delivery can still use configured message sends. Fixes #82833.
·WhatsApp: honor forced document delivery for outbound image, GIF, and video media so `forceDocument`/`asDocument` sends preserve original media bytes instead of using compressed media payloads. (#79272)
·WhatsApp: name outbound document attachments from their MIME type when no filename is provided, so PDF and CSV sends arrive as `file.pdf` and `file.csv` instead of an extensionless `file`.
·Process/diagnostics: report active lane blockers in lane wait warnings so `queueAhead=0` no longer hides commands waiting behind active work. Fixes #82791. (#82792)
·Process/diagnostics: stop counting the active processing turn as queued backlog in liveness warnings so transient max-only event-loop spikes do not surface as gateway warnings.
·Agents/replies: classify provider conversation-state rejections and return a clear message-channel error instead of auto-resetting or falling back to a generic runner failure. (#82616)
·Browser plugin: trust managed Chrome CDP diagnostics when launch HTTP probes race cold-start readiness, avoiding false startup failures. Fixes #82904. (#82986)
·Android: prompt before replacing a changed Gateway TLS thumbprint, showing the old and new SHA-256 fingerprints so users can accept expected certificate rotations instead of hard failing on pin mismatch. (#83077)
·CLI/status: render extra gateway-like service diagnostics as warning/info output instead of error output. Fixes #46930. (#82922)
·Agents/failover: classify Moonshot/Kimi exhausted-balance HTTP 429 payloads as billing instead of generic rate limits, preserving billing guidance and fallback behavior. Fixes #43447. (#83079)
·Plugin SDK: bundle `openclaw/plugin-sdk/zod` into the published package artifact and verify the packed zod subpath stays self-contained, so pnpm global installs can register plugins without a package-local `zod` symlink. Fixes #78398. (#78515)
·Providers/Google: drop compaction-truncated Gemini thought signatures before replay so malformed Base64 no longer aborts the next assistant turn. (#82995)
·Gateway/mobile: allow paired iOS and Android clients to refresh same-family OS metadata on authenticated reconnect instead of requiring a new approval. (#83490)
·WhatsApp: treat `upload-file` as a supported media send intent by lowering path/URL uploads through the channel's normal send-media transport. (#81883)
·iOS: end Live Activities when OpenClaw is connected, idle, or disconnected, and show compact attention states for approval-required reconnects. (#83597)
·Control UI: hide child nav items when collapsing the active sidebar group. Fixes #42167. (#42223)
·CI/proof: skip the real-behavior-proof gate for private org maintainers by minting a least-privilege (`members: read`) GitHub App token and checking active membership in the `maintainer` team, instead of treating `author_association=CONTRIBUTOR` as definitively external. (#83418)
·npm version: https://www.npmjs.com/package/openclaw/v/2026.5.19
·npm tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.5.19.tgz
·npm integrity: sha512-5Pn5hcRDVv3eeWYDp4IPPuvyz3yD+Vrdobykl/vi35/49ZldWUz02pDT5rTGMCInDelNZGaWoXAfm5vFdqha8g==
·npm publish time: 2026-05-20T20:20:41.341Z
·preflight: https://github.com/openclaw/openclaw/actions/runs/26177793383
·full release validation: https://github.com/openclaw/openclaw/actions/runs/26177793571
·publish wrapper: https://github.com/openclaw/openclaw/actions/runs/26185102888
·plugin npm publish: https://github.com/openclaw/openclaw/actions/runs/26185220516
·plugin ClawHub publish: https://github.com/openclaw/openclaw/actions/runs/26185223767
·OpenClaw npm publish: https://github.com/openclaw/openclaw/actions/runs/26187287455
·macOS public validation: https://github.com/openclaw/openclaw/actions/runs/26189320880
·macOS private validation: https://github.com/openclaw/releases/actions/runs/26189320867
·macOS signed notarized preflight: https://github.com/openclaw/releases/actions/runs/26189320869
·macOS asset/appcast publish: https://github.com/openclaw/releases/actions/runs/26191321220
·Sparkle appcast: https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml

v2026.5.19-beta.2pre-release2026-05-19

openclaw 2026.5.19-beta.2

GitHub ↗

Changes

·Agents: clarify that fixes should default to clean bounded refactors, lean internals, and explicit plugin SDK/API deprecation paths.
·Dependencies: update `@openclaw/proxyline` to 0.3.3.
·Dependencies: update Pi packages to 0.75.1 and raise the minimum supported Node.js 22 line to 22.19.
·Docker/Podman: add `OPENCLAW_IMAGE_APT_PACKAGES` as the runtime-neutral image build arg for extra apt packages while keeping `OPENCLAW_DOCKER_APT_PACKAGES` as a legacy fallback. (#62431)
·Gateway/ACPX: attribute startup probe, config, runtime, and resource-count costs in restart traces without changing readiness behavior. (#83300)
·Gateway: overlap startup logging and plugin-service startup with channel sidecars to reduce restart ready latency while preserving `/readyz` sidecar gating. (#83301)
·Plugins/admin-http-rpc: allow trusted admin HTTP RPC clients to start and wait for web QR login flows. (#83259)
·Mac app: redesign Settings pages with consistent card layouts, cached navigation, cleaner permissions/voice/skills/cron/exec/debug panes, and steadier spacing around the native sidebar.
·Mac app: refine Voice & Talk recognition-language and wake-phrase settings so they use the same compact card rows as the rest of Settings.
·Skills: rename the repo-local Codex closeout review skill and helper to `autoreview` while preserving the Codex-first fallback behavior.
·Skills: add a meme-maker skill for curated template search, local SVG/PNG rendering, Imgflip hosted rendering, and Know Your Meme provenance links.
·Skills CLI: allow `openclaw skills install` and `openclaw skills update` to target shared managed skills with `--global`. (#74466)
·Browser: surface pending and recently handled modal dialogs in snapshots, return `blockedByDialog` when an action opens a modal, and allow `browser dialog --dialog-id` to answer pending dialogs.
·Browser CLI: add `openclaw browser evaluate --timeout-ms` so long-running page functions can extend both the evaluate action and request timeout budgets. (#83447)
·Codex app-server: scope OpenClaw prompt guidance by runtime surface so native Codex keeps Codex-owned base/personality instructions while OpenClaw contributes only runtime context, delivery guidance, and explicitly scoped command hints. (#83454)
·Docker/Podman: add `OPENCLAW_IMAGE_PIP_PACKAGES` for opt-in Python package installation in local image builds. (#83771)
·Agents/tools: shorten built-in tool descriptions and schema hints across media, messaging, sessions, cron, Gateway, web, image/PDF, TTS, nodes, and plan tools while preserving routing guardrails.
·Skills: add node inspector debugging, fused diagram generation, and throwaway spike workflow skills.
·CLI/plugins: add `defineToolPlugin` plus `openclaw plugins build`, `validate`, and `init` for typed simple tool plugins with generated manifest metadata, optional tool declarations, and context factories.
·Agents/skills: tighten bundled skill prompts and metadata, quote skill descriptions, refresh current CLI/API guidance, and update embedded sherpa-onnx runtime downloads.
·Skills: update the Obsidian skill to target the official `obsidian` CLI and require its registered binary instead of the third-party `obsidian-cli`.
·Skills: add a Python debugging skill for pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.
·Codex: add `/codex plugins list`, `enable`, and `disable` for managing configured native Codex plugins from chat without editing config by hand.
·Plugins/messages: add presentation capability limits for channel renderers, adapt rich message controls before native rendering, and mark legacy `interactive`/Slack directive producer APIs as deprecated.
·Plugins/subagents: store channel delivery routes as canonical session metadata and deprecate ad hoc subagent hook delivery-origin fields in favor of core route projection.
·Proxy: support HTTPS managed forward-proxy endpoints and scoped `proxy.tls.caFile` CA trust for proxy endpoint TLS. (#79171)
·QA-Lab: add first-hour 20-turn and optional 100-turn runtime parity scenarios, with tier metadata for standard and soak QA gates. Fixes #80338; refs #80337.
·QA-Lab: add `openclaw qa suite --runtime-parity-tier` and wire the standard Codex-vs-Pi tier into release checks separately from optional/live-only/soak lanes. Fixes #80337.
·QA-Lab: add a live-only Codex Pi-shaped Read vocabulary canary so runtime parity catches native workspace-read prompt compatibility drift. (#80323)
·QA-Lab: add live-only harness self-health scenarios for plugin hook crashes, manifest contract errors, and WebChat direct-reply self-message routing. (#80323)
·QA-Lab: add runtime tool fixture scenarios and coverage reporting for Codex-native workspace tools, OpenClaw dynamic tools, and optional plugin-backed tools. Fixes #80173.
·QA-Lab: expose runtime tool fixture coverage through `openclaw qa coverage --tools`, with optional suite-summary evaluation for parity gate artifacts.
·QA-Lab: schedule a live-frontier Codex-vs-Pi runtime token-efficiency artifact lane in the all-lanes QA workflow. Fixes #80175.
·QA-Lab: hard-gate required OpenClaw dynamic runtime-tool drift in the standard Codex-vs-Pi tier with a blocking release-check verifier and publish the tool coverage report artifact. Fixes #80339; refs #80319.
·QA-Lab: add the personal-agent approval-denial scenario so the benchmark pack verifies denied local reads stop cleanly without tool progress or fixture leaks. (#83150)
·QA-Lab: extend the personal-agent benchmark pack with a local task followthrough scenario for proof-backed pending, blocked, and done status reporting.
·QA-Lab: add a report-only dreaming shadow-trial scenario so candidate memory promotion can be evaluated without mutating `MEMORY.md`.
·Gateway/performance: add `pnpm test:restart:gateway` benchmark tooling for repeated restart readiness, downtime, trace, and resource-slope evidence. (#83299)
·Android: switch Talk Mode to realtime Gateway relay voice sessions with streaming mic input, realtime audio playback, tool-result bridging, and on-screen transcripts. (#83130)
·Gateway/config: expose config lookup reload metadata so tools can distinguish restart-required, hot-reloadable, and no-op fields before applying config edits. Fixes #81409. (#81612)
·Telegram: add allowlisted native DM draft previews for transient tool progress while keeping final answers on the normal persistent delivery path. (#83622)
·QA-Lab: add a personal-agent share-safe diagnostics artifact scenario so support handoffs keep useful status while omitting raw personal content.
·QA-Lab: add a personal-agent no-fake-progress scenario so completion claims stay tied to local evidence instead of unsupported external progress. (#83824)

Fixes

·CLI: reject explicit port numbers above 65535 before they reach Gateway or Node bind paths. Fixes #83900. (#84008)
·Codex app-server: preserve plugin tool auth profiles when Codex owns model transport so OpenClaw dynamic tools can resolve their provider credentials. (#83603)
·Memory/search: scan the JS-side fallback vector path (used when the sqlite-vec index is unavailable or has a mismatched dimension) in bounded rowid batches and yield to the event loop between batches so large chunk tables can no longer pin the Node.js main thread for multi-second windows. Also keeps the SQL prepared statement rooted in a local so node:sqlite cannot finalize it mid-scan under heap pressure. Fixes #81172.
·Memory Wiki: preserve fs-safe diagnostics when bridge source page writes fail for non-symlink filesystem safety reasons, so directory collisions are reported with the underlying error code. (#83776)
·Telegram: keep forum topics from blocking sibling topic traffic by routing inbound serialization, media/text buffers, and account API queues on topic-aware lanes. (#83829)
·Telegram: keep queued forum-topic follow-up messages from inheriting superseded source abort signals, so later same-topic user turns can still run and reply after an active turn is replaced. (#83827)
·CLI/update: bypass npm freshness filters consistently during managed package and plugin installs so freshly published release plugins remain installable.
·CLI/update: guide root-owned npm install EACCES recovery by stopping the managed Gateway before manual package replacement, then reinstalling and restarting the service. Fixes #83747. (#83757)
·Twitch: register refreshing chat tokens with Twurple's chat intent so automatic token refresh keeps chat access available. (#83750)
·Agents/subagents: keep collect-mode announce queues batching unresolved-origin items with compatible same-route messages and resume collection after a true cross-channel drain when a later compatible batch remains. Fixes #83577.
·Skills: refresh existing session skill snapshots when watched skill roots change, so changed extra skill directories take effect without starting a new session. Fixes #83782. (#83800)
·Providers/Anthropic: preserve native image input for current Claude model rows when stale local catalog data marks them text-only. (#83756)
·Providers/Anthropic: preserve Claude 4 image capability when configured model refs resolve through a stale local catalog row. (#83756)
·Providers/DeepSeek: normalize MCP tool schemas with `anyOf`/`oneOf` unions before normal and compaction requests reach DeepSeek, preventing union-shaped parameters from being rejected. (#83766)
·Control UI: render live tool progress from session-scoped `session.tool` Gateway events so externally started runs show their tool cards in the active session. (#83734)
·Outbound: resolve send-capable channel plugins from the active runtime registry when the pinned startup registry only has setup metadata. (#83733)
·Discord: preserve streamed reply previews when recovered tool-warning finals are delivered before or after the assistant's final reply. (#84169)
·Control UI: keep the chat delete confirmation popover clamped inside the visible viewport on small screens. (#83804)
·Browser: enforce current-tab URL allowlist checks for `/act` evaluate/batch actions and `/highlight` routes while leaving tab-management actions unblocked. (#78523)
·CI: require real-behavior-proof verdict markers to come from the ClawSweeper GitHub App before accepting exact-head proof. (#83692)
·Models: show the effective OpenAI/Codex auth profile in `/models` provider headers instead of falling back to the OpenAI env-key label. (#83697)
·CLI: include active bundled loopback MCP tools in CLI system prompts and reset provider-side CLI sessions when that prompt-visible tool surface changes. (#83785)
·Browser: keep a profile `cdpPort` when its `cdpUrl` omits a port, while still letting explicitly written URL ports win. (#82166)
·Agents/image generation: allow distinct `image_generate` prompts to start separate session-backed background tasks while same-prompt retries still return the active task status. (#83614)
·Gateway/WebChat: honor configured `channels.webchat.textChunkLimit` and `chunkMode` overrides when chunking WebChat replies. (#83713)
·Control UI: stop the chat reading indicator from sticking after an assistant response finishes. (#83515)
·Skills: reject empty or whitespace-only skill names and descriptions during quick validation. (#27061)
·Sessions: skip trailing custom transcript entries when checking tail assistant replies so embedded CLI gap-fill does not duplicate canonical assistant output. (#83635)
·Memory Wiki: keep `wiki_lint` tool output path-safe by reporting vault-internal lint reports as relative paths in tool text and details while preserving absolute report paths for CLI/file callers. (#83439)
·Telegram: keep verbose tool progress visible without mirroring non-final progress into active session transcripts, preventing embedded provider replies from aborting mid-run. (#83631)
·Telegram: log successful outbound text and media deliveries with account, chat, message, operation, thread, reply, silent, and chunk metadata while keeping message bodies out of logs. Fixes #83196. (#83247)
·Cron: link isolated scheduled task runs to their stable cron session so task status and cleanup can follow the backing agent run. (#83606)
·Codex app-server: mark Codex-native subagent task mirrors terminal when blocked or failed spawn-agent calls arrive with stale initializing child state, preventing task registry entries from staying running. Fixes #83852. (#83945)
·CLI: enforce the documented Node.js 22.19 runtime floor in the source launcher.
·Release stability: repair broad-gate regressions in requester-agent completion handoff, QA-Lab mock spawn attribution, Slack monitor test isolation, plugin uninstall peer fixtures, and Node-floor launcher contract coverage.
·Agents/replies: persist queued follow-up user messages and assistant error stubs only once across model-fallback retries, preventing repeated provider rejections from corrupted same-role session transcripts. Fixes #83404. (#83417)
·Telegram: preserve reply-target context for bare mention replies on runtime-only turns so the model sees the replied-to message body. Fixes #83767. (#83953)
·ClawHub: preserve configured base URL path prefixes when building API request URLs, so self-hosted ClawHub instances mounted under a subpath keep routing correctly. (#83982)
·Slack: persist delivered inbound message IDs and fail closed when same-channel thread replies lose their thread context, preventing delayed duplicate replies and accidental channel-root posts. Fixes #83521.
·Codex app-server: complete OpenClaw dynamic tool diagnostics at the request boundary so successful, failed, timed out, aborted, and blocked tool calls do not leave active tool state behind. Fixes #83474.
·Gateway/config: keep config writes from failing on unrelated unresolved auth-profile SecretRefs while preserving live auth-profile runtime snapshots.
·Gateway/sessions: clear stored CLI provider resume bindings on non-subagent `/reset` so the next turn starts a fresh provider-side CLI conversation instead of resuming old context. (#83448)
·Doctor: preserve legacy whole-agent Claude CLI intent by moving matching Anthropic model selections to model-scoped runtime policy before removing stale runtime pins. Fixes #83491.
·Discord/OpenAI: keep realtime Discord voice sessions hearing follow-up turns with OpenAI realtime and prebuffer assistant playback to avoid choppy starts. (#80505)
·LM Studio: resolve env-template API keys like `${LMSTUDIO_API_KEY}` through the standard SecretInput path instead of sending the raw template as the bearer token, and preserve header-auth and discovery-key precedence when the template is unset. Fixes #80495. (#80568)
·Discord/subagents: route the initial reply from thread-bound delegated sessions into the bound Discord thread instead of the parent channel. Fixes #83170. (#83172)
·Gateway/sessions: rotate failed agent sessions when their transcript file is missing instead of wedging per-channel lanes. Fixes #83488. (#83553)
·Agents: refresh final-delivery routing from fresh session state before declaring a no-send failure, keeping recovered runs on the normal durable delivery path. (#83835)
·Agents: guard final-delivery fresh session routing against mismatched logical sessions before reusing recovered delivery context. (#83928)
·Media: prevent image metadata probing from invoking external decoder delegates on unrecognized image bytes, and stop fallback chaining after real processing errors.
·Media: install Sharp with the root package and fall back to sips, Windows native imaging, ImageMagick, GraphicsMagick, or ffmpeg for image resizing/conversion when Sharp is unavailable. Fixes #83401.
·Telegram: deliver generated media completions back into forum topics by preserving topic IDs across requester-agent handoff. (#83556)
·Gateway: defer update-check startup until after readiness so package update checks no longer block sidecar-ready startup, while preserving update broadcasts and shutdown cleanup. (#83520)
·Telegram: keep `/btw` and read-only status commands from aborting active runs, and avoid retaining raw update payloads in timed-out spool tombstones. Refs #83272.
·Agents: log strict-agentic execution contract diagnostics only when the planning-only retry path actually triggers.
·Agents: stop embedded session takeover and session write-lock errors from consuming model fallbacks while preserving provider fallback metadata. Fixes #83510.
·Agents/video: hide `video_generate` reference-audio parameters unless a registered video provider supports audio inputs.
·Plugins: fall back to npm for official ClawHub updates when artifact downloads are unavailable, including beta-to-default fallback and dry-run version reporting.
·Plugins/xAI: echo PKCE challenge fields during OAuth authorization-code token exchange for xAI token-endpoint compatibility. (#83499)
·Codex app-server: hydrate current inbound image attachments before queued runs so Responses-backed agents receive Discord and other channel images as native vision input. Fixes #83466.
·Codex app-server: keep native code mode available without forcing code-mode-only so OpenClaw dynamic tool turns complete through the app-server tool bridge. Fixes #83109.
·Codex app-server: expose OpenClaw's sandbox-routed shell as `sandbox_exec`/`sandbox_process` for non-Docker sandbox backends so SSH sandbox agents keep a correctly routed shell path without shadowing Codex native shell. Fixes #80322.
·Release stability: recover stale session diagnostics and Codex OAuth fallback state so stuck runs and reused refresh tokens clear without blocking follow-up work. (#83503)
·Messages/TTS: apply TTS directives before message-tool sends reach core, gateway, or plugin delivery so opt-in message-tool rooms and proactive sends attach voice notes instead of leaking raw tags. Fixes #81598.
·Messages/Codex: keep Codex direct/source chats on message-tool visible delivery by default while documenting and testing `messages.visibleReplies: "automatic"` as the old-mode opt-out; channel wildcard model overrides now apply to direct chats before harness delivery defaults.
·Memory/QMD: keep archived session transcript hits visible after QMD export while preserving normal `.md` session ids that only resemble archive names. (#83518; fixes #83506)
·Codex app-server: preserve network access for sandboxed Codex code-mode turns when the OpenClaw sandbox allows outbound egress. Fixes #83347.
·Codex app-server: honor writable Docker bind mounts for sandboxed workspace-write turns while disabling native Code Mode when container-path aliases or read-only bind shadows cannot be represented safely host-side. Fixes #83737. (#83849)
·QA-Lab: keep the OTLP smoke decoder independent of removed OpenTelemetry generated-root internals.
·Messages: default group/channel visible replies to automatic final delivery again, keeping `message_tool` opt-in for ambient/shared rooms and tool-reliable models.
·CLI/TUI: force standalone `/exit` runs to terminate after `runTui` returns so onboarding-launched TUI children do not stay alive invisibly. (#83501)
·Agents/code mode: honor per-agent code-mode config in schema, runtime catalog activation, and model payload filtering. Fixes #83388.
·Agents/code mode: preserve agent, session, run, and channel context in `before_tool_call` hooks for top-level `exec`/`wait` dispatches. Fixes #83387.
·QQBot: shorten C2C typing indicators to a 10-second window renewed every 5 seconds, capped to keep a final passive-reply slot available. (#83469)
·Replies: keep final payload delivery after live preview updates so channels can finalize or send the completed answer instead of losing preview-only drafts. (#83468)
·Discord: deliver final replies in progress-mode preview streams instead of deduplicating the final visible message. (#83443)
·Providers/Xiaomi: replay MiMo Anthropic-compatible `reasoning_content` as provider-required thinking blocks even when OpenClaw thinking is disabled, fixing follow-up tool turns for `mimo-v2-flash`. Fixes #83407.
·Agents/exec approvals: forward approval-runtime credentials on agent-owned Gateway approval calls so approved async commands complete through the existing runtime path instead of stalling on unauthenticated follow-up calls.
·Gateway/skills: preflight remote macOS skill-bin refreshes with a WebSocket connectivity check so stale node sessions skip quickly instead of logging slow `system.which` timeout warnings.
·CLI/config: keep broken discovered plugins that are not referenced by active config from failing `openclaw config validate`, while preserving fatal errors for explicitly configured plugin entries.
·GitHub Copilot: drop unsafe native Responses reasoning replay items with non-replayable IDs before dispatch, preventing affected Copilot sessions from failing with `invalid_request_body`. Fixes #83220.
·Agents/Codex: fail closed when an explicitly requested Codex harness is not registered instead of silently trying configured model fallbacks. Fixes #83349.
·QA-Lab: make runtime tool coverage fail on missing required tool exercise instead of treating pass/pass parity envelope drift as missing coverage.
·Core/plugins: harden clawpatch-reported edge cases across gateway auth cleanup, Claude session id paths, plugin activation policy, apply-patch hunk handling, diagnostic redaction, and plugin metadata validation.
·UI: show reasoning choices as plain labels instead of leaking internal override wording in session and chat pickers.
·Mac app: avoid repeating the Configuration heading inside channel quick settings.
·Mac app: keep the Settings sidebar always visible and remove the redundant titlebar hide/show control.
·Mac app: normalize Settings pane content margins so pages share the same left and right rail.
·Mac app: prefer explicit private/Tailscale/LAN Gateway endpoints over SSH tunnels, preserve legacy loopback tunnel configs, persist transport choices, and show captured SSH stderr when tunneling really fails.
·Gateway/sessions: keep ACP/acpx and runtime child sessions visible in configured-only session lists when their owner or parent session belongs to a configured agent.
·Mac app: keep app-level menu commands and Dashboard failure states reachable when the remote Gateway is disconnected.
·Mac app: allow longer Gateway and Context errors to wrap in the menu instead of truncating the useful failure detail.
·Mac app: tighten remote Gateway fields in Settings so the Connection pane keeps readable labels and full action button text.
·Mac app: keep custom Settings card rows left-aligned and full-width so Discovery and status sections no longer appear centered or detached.
·Mac app: align Location permission controls to the same trailing column as the rest of Settings.
·Mac app: add Dashboard, Chat, Canvas, and Settings shortcuts to the Dock icon menu.
·Mac app: replace the Settings window's native split-view sidebar with an explicit layout so page content keeps its leading gutter when the sidebar is shown or hidden.
·Mac app: render channel quick config as aligned Settings rows and hide schema-only variants that cannot be edited safely from the quick pane.
·Gateway/webchat: hide internal runtime-context and other `display: false` transcript messages from Chat history and live message events. Fixes #83216.
·CLI/help: keep `gateway`, `doctor`, `status`, and `health` help registration out of action/runtime imports so subcommand `--help` stays lightweight in constrained terminals. Fixes #83228.
·CLI/help: show plugin-owned command help based on the active memory slot so LanceDB memory users see `ltm` instead of unavailable `memory` commands. Fixes #83745. (#83841)
·Cron/Discord: keep explicit announce runs in message-tool-only source-reply mode so scheduled agent turns post once instead of also echoing through automatic visible replies. Fixes #83261.
·Telegram: preserve forum-topic origin targets in inbound, audio-preflight, and skipped-message hook contexts so follow-up delivery stays bound to the originating topic. Fixes #83302.
·Telegram: retry HTTP 421 Misdirected Request send failures on a fresh fallback transport so transient edge-node routing errors no longer drop outbound replies. Fixes #48892. (#48908)
·Telegram: fail topic sends closed when Telegram reports `message thread not found` instead of retrying without `message_thread_id` into the base chat. Refs #83302.
·Config/subagents: remove ignored agent-model `timeoutMs` keys, keep subagent model config to primary/fallback selection, and clean shipped stale config through doctor. Fixes #83291.
·Mac app: align the Sessions settings pane with the standard Settings page gutter and row spacing.
·OpenAI/Codex: stop rejecting available `openai-codex` GPT-5.1, GPT-5.2, and GPT-5.3 model refs during config validation, while keeping removed Spark aliases suppressed. Fixes #83303.
·Plugins/xAI: complete OAuth-backed xAI login and sidecar auth fixes, including guarded loopback callback CORS handling, video generation polling/defaults, and native-host User-Agent attribution. (#83322)
·Codex app-server: preserve streamed native command output in mirrored transcripts and trajectory exports when final snapshots omit aggregated output. (#83200)
·Codex app-server: fail closed when chat or sender policy denies tools, disabling native code, app, environment, and user MCP surfaces for restricted turns. (#82374)
·Codex app-server: keep recent context-engine messages when oversized projected history is truncated, so short follow-ups in long channel sessions do not fall back to stale earlier turns. (#83127)
·Codex app-server: keep OpenClaw session spawning searchable while steering Codex-native delegation through native subagents, avoiding duplicate direct subagent surfaces. (#83329)
·Codex app-server: recover stale childless Codex-native subagent task mirrors during maintenance and allow their registry rows to be cancelled without an OpenClaw child session. (#82836)
·Feishu: return bound subagent delivery origins from session thread setup so Feishu subagent completions route back to the same DM or topic. (#83190)
·CLI/update: tailor post-update Gateway recovery hints by platform, showing systemd, LaunchAgent, Scheduled Task, or generic service-manager guidance instead of macOS-only recovery text. (#83096)
·Plugins: apply a default 15-second timeout to legacy `before_agent_start` hooks so hung plugin handlers no longer block agent startup. Fixes #48534. (#83136)
·Feishu: refresh inbound session delivery context for DM, group, and broadcast turns so later replies do not inherit stale WebChat routing. Fixes #78274.
·Agents/subagents: require the initial subagent registry save before reporting spawn accepted, returning a spawn error instead of losing an untracked run when the registry write fails. (#83146)
·QA-Lab/qa-channel: attach redacted agent tool-start traces to outbound `QaBusMessage` records so scenarios can assert actual tool use instead of relying only on reply text. Fixes #67637.
·QA-Lab: fail live runtime parity reports when assistant-message usage is missing, preventing `0 vs 0` live token rows from being reported as passing proof. Fixes #80411.
·QA-Lab: add a runtime token-efficiency sidecar report that classifies Codex savings separately from regressions and fails only positive Codex-over-Pi live token deltas above threshold. Fixes #81093.
·QA-Lab: fail Codex-backed OpenAI live runtime-pair runs before launching isolated workers when no portable Codex auth is available, while staging API-key fallbacks and configured Codex keys for isolated QA agents. Fixes #80412.
·QA-Lab: refresh parity gates, mock frontier fixtures, model scenarios, and workflow artifact lanes to compare GPT-5.5 against Claude Opus 4.7. Fixes #74262.
·QA-Lab: make mock parity dispatch provider-aware for source discovery and subagent scenarios so OpenAI and Anthropic lanes no longer share identical canned plans. Fixes #64879.
·QA-Lab: stop returning Control UI bearer tokens from unauthenticated bootstrap payloads and bind Docker harness ports to loopback-only host addresses. (#66355)
·Mac app: avoid a SwiftUI metadata crash when rendering the Cron Jobs settings pane.
·Agents/subagents: preserve run-mode keep subagent registry entries past the session sweep TTL, so kept subagent runs remain visible after cleanup completes. Fixes #83132. (#83168)
·Agents/OpenAI streams: yield via `setTimeout(0)` instead of `setImmediate` between bursty Responses chunks so abort timers can fire during the yield, keeping cancel-on-timeout responsive on hot streams. Refs #82462.
·Agents/Codex: keep legacy `oauthRef`-backed OAuth profiles usable while `openclaw doctor --fix` migrates them back to inline credentials, without creating new sidecar credentials. (#83312)
·Agents/Codex: load the selected provider owner alongside the Codex harness runtime so `openai-codex` models resolve when plugin allowlists scope runtime loading. Fixes #83380. (#83519)
·Telegram: fail stalled isolated-ingress handlers into tombstones and abort same-lane reply work before restarting, so later same-chat updates drain after a hung turn. Fixes #83272. (#83505)
·CLI/config: send SecretRef diagnostics to stderr so JSON command stdout remains parseable.
·CLI/doctor: seed Control UI allowed origins when migrating legacy non-loopback gateway bind host aliases like `0.0.0.0`. Fixes #83286.
·CLI/plugins: ship the bundled memory CLI as a package entry so package-installed `openclaw memory` commands register correctly.
·CLI/update: defer doctor-time plugin package installs during package swaps and seed post-core repair from the updated install registry, preventing duplicate reinstall failures.
·CLI/update: preserve old-parent-readable config metadata during legacy package handoffs, fall back only to official `@openclaw/*` npm plugin packages when ClawHub plugin artifacts are unavailable, and keep managed service package roots authoritative during updates.
·Feishu: detect SecretRef top-level credentials as a configured default account instead of treating object-backed app secrets as missing.
·Gateway/restart: keep ordinary unmanaged SIGUSR1/config restarts in-process instead of detach-spawning an orphaned child, preserving custom supervisor PID tracking while leaving update restarts on the fresh-process path. Fixes #65668.
·CLI/completion: resolve concrete PowerShell profile paths and reload commands during setup and doctor completion installation. Fixes #44296. (#83059)
·Telegram: keep isolated long polling below the hard `getUpdates` request guard so idle bot accounts with high `timeoutSeconds` do not false-disconnect and restart-loop. Fixes #83264.
·Providers/Google: preserve and recover Gemini 3 tool-call thought signatures during native replay so function-calling turns no longer fail with missing `thought_signature` 400s. Fixes #72879. (#80358)
·Telegram: skip transcript-only delivery mirrors and gateway-injected rows when resolving latest assistant text, preventing retained previews from replacing final replies with stale fragments. Fixes #83159. (#83362)
·Memory/QMD: keep lexical search on raw hyphenated queries while normalizing semantic QMD sub-searches, avoiding fallback to the builtin index for dashed identifiers and dates. Fixes #81328.
·Memory-core: distinguish sqlite-vec load failures from missing semantic vector embeddings in degraded `memory index` warnings, so vector recall diagnostics point at unresolved dimensions instead of blaming sqlite-vec when the store is ready. Fixes #75624. (#83056)
·Agents/subagents: preserve sandbox-peer controller ownership while routing completion announcements back to the originating run session, keeping subagent control and completion delivery scoped correctly. Fixes #80201. (#80242)
·Gateway: continue restarting remaining channels when one hot-reload channel restart fails, while still reporting aggregate reload failure and rolling back plugin pre-replace stops. Fixes #83054.
·Gateway/plugins: bind admin HTTP RPC dispatch to the accepting gateway instance so multi-gateway processes cannot execute plugin HTTP control-plane calls against another live gateway. Fixes #83486. (#83487)
·Telegram: keep hot-reload restarts from marking polling accounts manually stopped and restart isolated ingress cleanly after worker shutdown, preserving Telegram replies across config reloads. Fixes #83008. (#83410)
·Telegram/Ollama: pass current Telegram image attachments into native PI/Ollama vision turns so live photo prompts reach Ollama as native images. Fixes #83023. (#83516)
·Gateway/secrets: split the lightweight secrets runtime state and auth-store cache from the full secrets runtime and take a startup fast path when the gateway startup config has no SecretRef values, speeding up secrets startup while preserving cleanup and refresh semantics.
·Codex app-server: rotate oversized native Codex threads before resume and cap dynamic tool-result text entering native Codex sessions, preventing stale oversized context from surviving OpenClaw compaction. (#82981)
·Gateway/restart: drain pending replies and active chat runs during restart shutdown before sockets and channels close, aborting timed-out chat runs through the normal cleanup path. (#69121)
·Agents/Codex: use the Codex runtime context window for OpenAI-model preflight compaction and memory flush checks, so GPT-5.5 Codex sessions compact before hitting the smaller native context limit. Fixes #82982.
·QA-Lab: clean orphaned gateway temp roots when a suite parent exits and wait on gateway plus transport readiness after config restarts, reducing stale `qa-channel` noise from interrupted runs. Fixes #65506.
·QA-Lab: wake qa-bus long polls that arrive with stale future cursors after a bus restart, preserving reconnect readiness for harness clients. (#67142)
·QA-Lab: stage Multipass transfer scripts under OpenClaw's preferred temp root instead of raw OS temp paths, keeping the VM runner inside temp-path guardrails. (#64098)
·Agents/replies: keep surviving reply media and append a warning when other media references fail, so partial media normalization no longer drops failures silently.
·Config/models: accept `thinkingFormat: "together"` in model compat config so Together routes can opt into the Together-specific thinking response shape.
·Plugins/tokenjuice: bump the bundled tokenjuice runtime to 0.7.1, bringing Codex hook approval compatibility, pre-tool command wrapping fixes, and Rolldown/Vitest output compaction improvements into the OpenClaw plugin.
·Agents/OpenAI: stop post-processing GPT-5 final replies with hardcoded brevity caps, preserving full channel responses instead of appending synthetic ellipses, and log when strict-agentic GPT-5 execution activates. Fixes #82910.
·Mac app: refine the Settings General and Connection panes with cleaner status panels, card rows, and a single native titlebar sidebar toggle.
·Agents/media: deliver failed async image, music, and video generation completions directly when requester-session completion handoff fails, so channel users see provider errors instead of silent fallback stalls.
·Browser/CDP: keep loopback proxy bypass active across both `NO_PROXY` casings and redact home-relative Chrome MCP profile paths in attach-failure diagnostics.
·Agents/music: steer song, jingle, beat, anthem, and instrumental requests toward `music_generate` audio creation instead of lyric-only replies, and reserve `lyrics` for exact sung words.
·Codex app-server: record native Codex tool calls and results into trajectory artifacts so debug/trajectory exports capture the full Codex-native tool history, not just OpenClaw-bridged turns.
·Codex/app-server: keep bound conversation sessions on the owning agent runtime so native Codex control and follow-up turns do not fall back to the default agent client. Fixes #82954. (#82993)
·CLI/infer: run gateway model probes in fresh explicit sessions so one-shot provider checks do not inherit default agent transcript state. (#82861)
·Providers/Together: send video-generation requests to Together's v2 video API even when shared text-model config still points at the v1 base URL. (#82992)
·Browser CLI: preserve browser-level options on nested commands, skip option values during lazy command registration, and keep long-running wait/download/dialog hooks open for their advertised wait window.
·CLI/sessions: accept `openclaw sessions list` as an alias for `openclaw sessions`, matching other list-style commands. Fixes #81139. (#81163)
·Channels/stream previews: widen compact progress draft lines and cut prose at word boundaries while preserving command/path suffixes, with `streaming.progress.maxLineChars` for channel-specific tuning.
·CLI/plugins: have `openclaw plugins doctor` warn when a configured runtime needs a missing owner plugin, sharing the same install mapping as `openclaw doctor --fix`. Fixes #81326. (#81674)
·Agents/Codex: route OpenAI runs that resolve to `openai-codex` through the Codex provider and bootstrap OpenClaw's stored OAuth profile into the Codex harness when the harness owns transport, so `openai/*` model refs no longer fail with `No API key found for openai-codex` despite an existing Codex OAuth profile. (#82864)
·Agents/ACP: distinguish prompt-submitted and runtime-active child stalls from true interactive waits, including redacted proxy-env diagnostics for Codex ACP no-output runs. Fixes #44810.
·Agents/memory: explain that memory-triggered compaction exposes only `read` and append-only `write` when configured core tools are unavailable in `tools.allow` warnings. Fixes #82941.
·Agents/OpenAI: preserve deterministic tool payload ordering for prompt-cache reuse across OpenAI Responses and chat completions calls. (#82940)
·ACP/Codex: honor terminal ACP turn results so failed Codex/acpx runs are not recorded as successful after only progress text. Fixes #79522.
·Telegram: warn when a media group drops photos that fail to download, including albums where every photo is skipped. Fixes #55216. (#82987)
·Agents/diagnostics: treat repeated same-handle embedded-run cleanup as idempotent while preserving true replacement-handle mismatch diagnostics. Fixes #82959. (#82960)
·Agents/subagents: preserve high-priority `AGENTS.md` policy in bootstrap context when oversized files are trimmed, and warn agents to read the full policy file before relying on scoped rules. Fixes #82920. (#82921)
·Agents/skills: apply the full effective tool policy pipeline to inline `command-dispatch: tool` skill dispatch before owner-only filtering, preserving configured allow, deny, sandbox, sender, group, and subagent restrictions. (#78525)
·Codex: avoid spawning native hook relay subprocesses for post-tool/finalize events with no registered hook handlers while preserving pre-tool safety and approval relays. Fixes #76552. (#78004)
·Channel accounts: keep top-level default channel accounts visible when named accounts are added alongside default credential material, so mixed legacy/new account configs keep resolving `default` instead of silently dropping it.
·Agents/CLI: reject empty successful CLI subprocess replies as `empty_response` and keep them out of shared auth-profile health, so blank Claude CLI results no longer become green no-payload turns. Fixes #83231. (#83421)
·Codex/Telegram: synthesize native Codex tool progress from final turn snapshots so Telegram `/verbose` stays visible when command events arrive only at completion.
·Codex/Telegram: deliver Codex verbose tool summaries in direct message-tool-only turns while suppressing message-send and activity-log noise. (#83186)
·Mac app: make Channels settings open faster by deferring config-schema work, avoiding startup channel probes, caching decoded channel status rows, and showing only compact quick settings instead of the full generated channel schema.
·Control UI: include the Control UI and Gateway protocol versions in protocol-mismatch errors so stale app/dashboard pairings identify which side needs rebuilding or restarting.
·Gateway/protocol: restore Gateway WS protocol v4 and keep `message.action` room-event metadata on the existing `inboundTurnKind` wire field while preserving internal inbound-event classification.
·Agents/tools: prefer non-webchat session-key routes when the message tool has stale webchat context, so message-tool-only replies keep delivering to the originating channel. Fixes #82911. (#83004)
·Channels: keep direct-message last-route writes on isolated `per-channel-peer` sessions instead of contaminating the agent main session with channel delivery context. Fixes #36614.
·Mac app: move the Settings sidebar toggle into the native titlebar and tighten the General pane width.
·Mac app: keep visited Settings panes mounted so switching tabs no longer blanks and reloads their content.
·Mac app: make Config settings open from shallow schema lookups and load selected paths on demand instead of fetching and rendering the full generated config schema up front.
·Codex: sanitize inline image payloads before Codex app-server and OpenAI Responses replay, and clear poisoned Codex thread bindings after invalid image errors. Fixes #82878.
·Providers/GitHub Copilot: request identity-encoded Copilot API responses across token exchange, catalog, model calls, usage, and embeddings so compressed Business-account error payloads no longer reach JSON parsers as gzip bytes. Fixes #82871.
·Telegram: redact nested raw-update identifiers and user metadata before verbose raw update logging, preserving useful update/message ids without exposing chat, user, command, or profile details. (#82945)
·Telegram: preserve replied-to bot messages, captions, and media metadata in group reply chains so follow-up replies understand what the user is reacting to. (#82863)
·Providers/Together: update PI runtime packages to 0.74.1 and emit Together-style `reasoning.enabled`/`max_tokens` controls for reasoning-capable OpenAI-completions models.
·Agents/diagnostics: split slow embedded-run `attempt-dispatch` startup summaries into workspace, prompt, runtime-plan, and final dispatch subspans so traces identify the delayed setup phase. Fixes #82782. (#82783)
·Agents/Codex: flatten nested tool-result middleware blocks into bounded text so successful message sends are no longer replaced with `Tool output unavailable due to post-processing error`. Fixes #82912.
·CLI/media: accept HTTP(S) URLs in `openclaw infer image describe --file`, fetching remote images through the guarded media path instead of treating URLs as local files. Fixes #82837. (#82854)
·Agents/subagents: keep session-backed parent runs active when the child wait call times out before the child session has actually settled, so late subagent completions are reconciled instead of being lost. Fixes #82787.
·Control UI: advertise shared Gateway protocol constants in browser connect frames, fixing protocol mismatch handshakes after protocol constant drift. Fixes #82882.
·Gateway: add rollback protocol-mismatch diagnostics, including client protocol ranges in Gateway logs and deep status/doctor hints for stale client processes. Fixes #82841. (#82908)
·Agents/subagents: keep successful keep-mode completion payloads pending after final-delivery retry exhaustion, so requester recovery no longer loses final subagent results. Fixes #82583. (#82999)
·Gateway/auth: allow same-host trusted-proxy callers to use the documented local direct `gateway.auth.password` fallback after revisiting the #78684 fail-closed policy, while keeping token fallback rejected and forwarded-header requests on the trusted-proxy path. Fixes #82607. (#82953)
·Agents/subagents: wait for queued completion handoffs to reach the parent transcript before marking them announced, preventing busy parent runs from cleaning up before observing child results. Fixes #82913. (#83039)
·Agents/subagents: route group/channel subagent completions through message-tool-only handoffs when required and keep active-requester wake failures from dropping completion delivery. Fixes #82803.
·Memory-core: scan persisted memory source sessions on startup, comparing on-disk transcripts against the index and marking only missing/newer/resized files dirty for incremental sync. Fixes #82341. (#82341)
·Telegram: keep the top-level default account in the account list when named accounts or bindings are added alongside top-level credentials, preserving default polling while still letting named-only configs resolve to a single account. Fixes #82794. (#82794)
·CLI/models: reuse command-scoped plugin metadata across model listing, provider catalog, auth, and synthetic-auth checks, restoring fast `openclaw models` runs for plugin-heavy installs. Fixes #82881. (#83033)
·CLI/channels: show configured official external channels such as Discord in `openclaw channels list` when their plugin package is missing, including the install and doctor repair command instead of reporting no configured channels. Fixes #82813.
·Signal: preserve mixed-case group IDs through routing and session persistence so group auto-replies keep delivering after updates. Fixes #82827.
·Agents/tools: keep the `message` tool available in embedded runs when it is explicitly allowed through `tools.alsoAllow` or runtime tool allowlists, so channel plugins with custom reply delivery can still use configured message sends. Fixes #82833.
·WhatsApp: honor forced document delivery for outbound image, GIF, and video media so `forceDocument`/`asDocument` sends preserve original media bytes instead of using compressed media payloads. (#79272)
·WhatsApp: name outbound document attachments from their MIME type when no filename is provided, so PDF and CSV sends arrive as `file.pdf` and `file.csv` instead of an extensionless `file`.
·Process/diagnostics: report active lane blockers in lane wait warnings so `queueAhead=0` no longer hides commands waiting behind active work. Fixes #82791. (#82792)
·Process/diagnostics: stop counting the active processing turn as queued backlog in liveness warnings so transient max-only event-loop spikes do not surface as gateway warnings.
·Agents/replies: classify provider conversation-state rejections and return a clear message-channel error instead of auto-resetting or falling back to a generic runner failure. (#82616)
·Browser plugin: trust managed Chrome CDP diagnostics when launch HTTP probes race cold-start readiness, avoiding false startup failures. Fixes #82904. (#82986)
·Android: prompt before replacing a changed Gateway TLS thumbprint, showing the old and new SHA-256 fingerprints so users can accept expected certificate rotations instead of hard failing on pin mismatch. (#83077)
·CLI/status: render extra gateway-like service diagnostics as warning/info output instead of error output. Fixes #46930. (#82922)
·Agents/failover: classify Moonshot/Kimi exhausted-balance HTTP 429 payloads as billing instead of generic rate limits, preserving billing guidance and fallback behavior. Fixes #43447. (#83079)
·Plugin SDK: bundle `openclaw/plugin-sdk/zod` into the published package artifact and verify the packed zod subpath stays self-contained, so pnpm global installs can register plugins without a package-local `zod` symlink. Fixes #78398. (#78515)
·Providers/Google: drop compaction-truncated Gemini thought signatures before replay so malformed Base64 no longer aborts the next assistant turn. (#82995)
·Gateway/mobile: allow paired iOS and Android clients to refresh same-family OS metadata on authenticated reconnect instead of requiring a new approval. (#83490)
·WhatsApp: treat `upload-file` as a supported media send intent by lowering path/URL uploads through the channel's normal send-media transport. (#81883)
·iOS: end Live Activities when OpenClaw is connected, idle, or disconnected, and show compact attention states for approval-required reconnects. (#83597)
·Control UI: hide child nav items when collapsing the active sidebar group. Fixes #42167. (#42223)
·CI/proof: skip the real-behavior-proof gate for private org maintainers by minting a least-privilege (`members: read`) GitHub App token and checking active membership in the `maintainer` team, instead of treating `author_association=CONTRIBUTOR` as definitively external. (#83418)

v2026.5.19-alpha.1pre-release2026-05-20

openclaw 2026.5.19-alpha.1

GitHub ↗

Changes

·Agents: clarify that fixes should default to clean bounded refactors, lean internals, and explicit plugin SDK/API deprecation paths.
·Dependencies: update `@openclaw/proxyline` to 0.3.3.
·Dependencies: update Pi packages to 0.75.1 and raise the minimum supported Node.js 22 line to 22.19.
·Docker/Podman: add `OPENCLAW_IMAGE_APT_PACKAGES` as the runtime-neutral image build arg for extra apt packages while keeping `OPENCLAW_DOCKER_APT_PACKAGES` as a legacy fallback. (#62431)
·Gateway/ACPX: attribute startup probe, config, runtime, and resource-count costs in restart traces without changing readiness behavior. (#83300)
·Gateway: overlap startup logging and plugin-service startup with channel sidecars to reduce restart ready latency while preserving `/readyz` sidecar gating. (#83301)
·Plugins/admin-http-rpc: allow trusted admin HTTP RPC clients to start and wait for web QR login flows. (#83259)
·Mac app: redesign Settings pages with consistent card layouts, cached navigation, cleaner permissions/voice/skills/cron/exec/debug panes, and steadier spacing around the native sidebar.
·Mac app: refine Voice & Talk recognition-language and wake-phrase settings so they use the same compact card rows as the rest of Settings.
·Skills: rename the repo-local Codex closeout review skill and helper to `autoreview` while preserving the Codex-first fallback behavior.
·Skills: add a meme-maker skill for curated template search, local SVG/PNG rendering, Imgflip hosted rendering, and Know Your Meme provenance links.
·Skills CLI: allow `openclaw skills install` and `openclaw skills update` to target shared managed skills with `--global`. (#74466)
·Browser: surface pending and recently handled modal dialogs in snapshots, return `blockedByDialog` when an action opens a modal, and allow `browser dialog --dialog-id` to answer pending dialogs.
·Browser CLI: add `openclaw browser evaluate --timeout-ms` so long-running page functions can extend both the evaluate action and request timeout budgets. (#83447)
·Codex app-server: scope OpenClaw prompt guidance by runtime surface so native Codex keeps Codex-owned base/personality instructions while OpenClaw contributes only runtime context, delivery guidance, and explicitly scoped command hints. (#83454)
·Docker/Podman: add `OPENCLAW_IMAGE_PIP_PACKAGES` for opt-in Python package installation in local image builds. (#83771)
·Agents/tools: shorten built-in tool descriptions and schema hints across media, messaging, sessions, cron, Gateway, web, image/PDF, TTS, nodes, and plan tools while preserving routing guardrails.
·Skills: add node inspector debugging, fused diagram generation, and throwaway spike workflow skills.
·CLI/plugins: add `defineToolPlugin` plus `openclaw plugins build`, `validate`, and `init` for typed simple tool plugins with generated manifest metadata, optional tool declarations, and context factories.
·Agents/skills: tighten bundled skill prompts and metadata, quote skill descriptions, refresh current CLI/API guidance, and update embedded sherpa-onnx runtime downloads.
·Skills: update the Obsidian skill to target the official `obsidian` CLI and require its registered binary instead of the third-party `obsidian-cli`.
·Skills: add a Python debugging skill for pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.
·Codex: add `/codex plugins list`, `enable`, and `disable` for managing configured native Codex plugins from chat without editing config by hand.
·Plugins/messages: add presentation capability limits for channel renderers, adapt rich message controls before native rendering, and mark legacy `interactive`/Slack directive producer APIs as deprecated.
·Plugins/subagents: store channel delivery routes as canonical session metadata and deprecate ad hoc subagent hook delivery-origin fields in favor of core route projection.
·Proxy: support HTTPS managed forward-proxy endpoints and scoped `proxy.tls.caFile` CA trust for proxy endpoint TLS. (#79171)
·QA-Lab: add first-hour 20-turn and optional 100-turn runtime parity scenarios, with tier metadata for standard and soak QA gates. Fixes #80338; refs #80337.
·QA-Lab: add `openclaw qa suite --runtime-parity-tier` and wire the standard Codex-vs-Pi tier into release checks separately from optional/live-only/soak lanes. Fixes #80337.
·QA-Lab: add a live-only Codex Pi-shaped Read vocabulary canary so runtime parity catches native workspace-read prompt compatibility drift. (#80323)
·QA-Lab: add live-only harness self-health scenarios for plugin hook crashes, manifest contract errors, and WebChat direct-reply self-message routing. (#80323)
·QA-Lab: add runtime tool fixture scenarios and coverage reporting for Codex-native workspace tools, OpenClaw dynamic tools, and optional plugin-backed tools. Fixes #80173.
·QA-Lab: expose runtime tool fixture coverage through `openclaw qa coverage --tools`, with optional suite-summary evaluation for parity gate artifacts.
·QA-Lab: schedule a live-frontier Codex-vs-Pi runtime token-efficiency artifact lane in the all-lanes QA workflow. Fixes #80175.
·QA-Lab: hard-gate required OpenClaw dynamic runtime-tool drift in the standard Codex-vs-Pi tier with a blocking release-check verifier and publish the tool coverage report artifact. Fixes #80339; refs #80319.
·QA-Lab: add the personal-agent approval-denial scenario so the benchmark pack verifies denied local reads stop cleanly without tool progress or fixture leaks. (#83150)
·QA-Lab: extend the personal-agent benchmark pack with a local task followthrough scenario for proof-backed pending, blocked, and done status reporting.
·QA-Lab: add a report-only dreaming shadow-trial scenario so candidate memory promotion can be evaluated without mutating `MEMORY.md`.
·Gateway/performance: add `pnpm test:restart:gateway` benchmark tooling for repeated restart readiness, downtime, trace, and resource-slope evidence. (#83299)
·Android: switch Talk Mode to realtime Gateway relay voice sessions with streaming mic input, realtime audio playback, tool-result bridging, and on-screen transcripts. (#83130)
·Gateway/config: expose config lookup reload metadata so tools can distinguish restart-required, hot-reloadable, and no-op fields before applying config edits. Fixes #81409. (#81612)
·Telegram: add allowlisted native DM draft previews for transient tool progress while keeping final answers on the normal persistent delivery path. (#83622)
·QA-Lab: add a personal-agent share-safe diagnostics artifact scenario so support handoffs keep useful status while omitting raw personal content.
·QA-Lab: add a personal-agent no-fake-progress scenario so completion claims stay tied to local evidence instead of unsupported external progress. (#83824)

Fixes

·CLI: reject explicit port numbers above 65535 before they reach Gateway or Node bind paths. Fixes #83900. (#84008)
·Codex app-server: preserve plugin tool auth profiles when Codex owns model transport so OpenClaw dynamic tools can resolve their provider credentials. (#83603)
·Memory/search: scan the JS-side fallback vector path (used when the sqlite-vec index is unavailable or has a mismatched dimension) in bounded rowid batches and yield to the event loop between batches so large chunk tables can no longer pin the Node.js main thread for multi-second windows. Also keeps the SQL prepared statement rooted in a local so node:sqlite cannot finalize it mid-scan under heap pressure. Fixes #81172.
·Memory Wiki: preserve fs-safe diagnostics when bridge source page writes fail for non-symlink filesystem safety reasons, so directory collisions are reported with the underlying error code. (#83776)
·Telegram: keep forum topics from blocking sibling topic traffic by routing inbound serialization, media/text buffers, and account API queues on topic-aware lanes. (#83829)
·Telegram: keep queued forum-topic follow-up messages from inheriting superseded source abort signals, so later same-topic user turns can still run and reply after an active turn is replaced. (#83827)
·CLI/update: bypass npm freshness filters consistently during managed package and plugin installs so freshly published release plugins remain installable.
·CLI/update: guide root-owned npm install EACCES recovery by stopping the managed Gateway before manual package replacement, then reinstalling and restarting the service. Fixes #83747. (#83757)
·Twitch: register refreshing chat tokens with Twurple's chat intent so automatic token refresh keeps chat access available. (#83750)
·Agents/subagents: keep collect-mode announce queues batching unresolved-origin items with compatible same-route messages and resume collection after a true cross-channel drain when a later compatible batch remains. Fixes #83577.
·Skills: refresh existing session skill snapshots when watched skill roots change, so changed extra skill directories take effect without starting a new session. Fixes #83782. (#83800)
·Providers/Anthropic: preserve native image input for current Claude model rows when stale local catalog data marks them text-only. (#83756)
·Providers/DeepSeek: normalize MCP tool schemas with `anyOf`/`oneOf` unions before normal and compaction requests reach DeepSeek, preventing union-shaped parameters from being rejected. (#83766)
·Control UI: render live tool progress from session-scoped `session.tool` Gateway events so externally started runs show their tool cards in the active session. (#83734)
·Outbound: resolve send-capable channel plugins from the active runtime registry when the pinned startup registry only has setup metadata. (#83733)
·Control UI: keep the chat delete confirmation popover clamped inside the visible viewport on small screens. (#83804)
·Browser: enforce current-tab URL allowlist checks for `/act` evaluate/batch actions and `/highlight` routes while leaving tab-management actions unblocked. (#78523)
·CI: require real-behavior-proof verdict markers to come from the ClawSweeper GitHub App before accepting exact-head proof. (#83692)
·Models: show the effective OpenAI/Codex auth profile in `/models` provider headers instead of falling back to the OpenAI env-key label. (#83697)
·CLI: include active bundled loopback MCP tools in CLI system prompts and reset provider-side CLI sessions when that prompt-visible tool surface changes. (#83785)
·Browser: keep a profile `cdpPort` when its `cdpUrl` omits a port, while still letting explicitly written URL ports win. (#82166)
·Agents/image generation: allow distinct `image_generate` prompts to start separate session-backed background tasks while same-prompt retries still return the active task status. (#83614)
·Gateway/WebChat: honor configured `channels.webchat.textChunkLimit` and `chunkMode` overrides when chunking WebChat replies. (#83713)
·Control UI: stop the chat reading indicator from sticking after an assistant response finishes. (#83515)
·Skills: reject empty or whitespace-only skill names and descriptions during quick validation. (#27061)
·Sessions: skip trailing custom transcript entries when checking tail assistant replies so embedded CLI gap-fill does not duplicate canonical assistant output. (#83635)
·Memory Wiki: keep `wiki_lint` tool output path-safe by reporting vault-internal lint reports as relative paths in tool text and details while preserving absolute report paths for CLI/file callers. (#83439)
·Telegram: keep verbose tool progress visible without mirroring non-final progress into active session transcripts, preventing embedded provider replies from aborting mid-run. (#83631)
·Telegram: log successful outbound text and media deliveries with account, chat, message, operation, thread, reply, silent, and chunk metadata while keeping message bodies out of logs. Fixes #83196. (#83247)
·Cron: link isolated scheduled task runs to their stable cron session so task status and cleanup can follow the backing agent run. (#83606)
·Codex app-server: mark Codex-native subagent task mirrors terminal when blocked or failed spawn-agent calls arrive with stale initializing child state, preventing task registry entries from staying running. Fixes #83852. (#83945)
·CLI: enforce the documented Node.js 22.19 runtime floor in the source launcher.
·Release stability: repair broad-gate regressions in requester-agent completion handoff, QA-Lab mock spawn attribution, Slack monitor test isolation, plugin uninstall peer fixtures, and Node-floor launcher contract coverage.
·Agents/replies: persist queued follow-up user messages and assistant error stubs only once across model-fallback retries, preventing repeated provider rejections from corrupted same-role session transcripts. Fixes #83404. (#83417)
·Telegram: preserve reply-target context for bare mention replies on runtime-only turns so the model sees the replied-to message body. Fixes #83767. (#83953)
·Slack: persist delivered inbound message IDs and fail closed when same-channel thread replies lose their thread context, preventing delayed duplicate replies and accidental channel-root posts. Fixes #83521.
·Codex app-server: complete OpenClaw dynamic tool diagnostics at the request boundary so successful, failed, timed out, aborted, and blocked tool calls do not leave active tool state behind. Fixes #83474.
·Gateway/config: keep config writes from failing on unrelated unresolved auth-profile SecretRefs while preserving live auth-profile runtime snapshots.
·Gateway/sessions: clear stored CLI provider resume bindings on non-subagent `/reset` so the next turn starts a fresh provider-side CLI conversation instead of resuming old context. (#83448)
·Doctor: preserve legacy whole-agent Claude CLI intent by moving matching Anthropic model selections to model-scoped runtime policy before removing stale runtime pins. Fixes #83491.
·Discord/OpenAI: keep realtime Discord voice sessions hearing follow-up turns with OpenAI realtime and prebuffer assistant playback to avoid choppy starts. (#80505)
·LM Studio: resolve env-template API keys like `${LMSTUDIO_API_KEY}` through the standard SecretInput path instead of sending the raw template as the bearer token, and preserve header-auth and discovery-key precedence when the template is unset. Fixes #80495. (#80568)
·Discord/subagents: route the initial reply from thread-bound delegated sessions into the bound Discord thread instead of the parent channel. Fixes #83170. (#83172)
·Gateway/sessions: rotate failed agent sessions when their transcript file is missing instead of wedging per-channel lanes. Fixes #83488. (#83553)
·Agents: refresh final-delivery routing from fresh session state before declaring a no-send failure, keeping recovered runs on the normal durable delivery path. (#83835)
·Agents: guard final-delivery fresh session routing against mismatched logical sessions before reusing recovered delivery context. (#83928)
·Media: prevent image metadata probing from invoking external decoder delegates on unrecognized image bytes, and stop fallback chaining after real processing errors.
·Media: install Sharp with the root package and fall back to sips, Windows native imaging, ImageMagick, GraphicsMagick, or ffmpeg for image resizing/conversion when Sharp is unavailable. Fixes #83401.
·Telegram: deliver generated media completions back into forum topics by preserving topic IDs across requester-agent handoff. (#83556)
·Gateway: defer update-check startup until after readiness so package update checks no longer block sidecar-ready startup, while preserving update broadcasts and shutdown cleanup. (#83520)
·Telegram: keep `/btw` and read-only status commands from aborting active runs, and avoid retaining raw update payloads in timed-out spool tombstones. Refs #83272.
·Agents: log strict-agentic execution contract diagnostics only when the planning-only retry path actually triggers.
·Agents: stop embedded session takeover and session write-lock errors from consuming model fallbacks while preserving provider fallback metadata. Fixes #83510.
·Agents/video: hide `video_generate` reference-audio parameters unless a registered video provider supports audio inputs.
·Plugins: fall back to npm for official ClawHub updates when artifact downloads are unavailable, including beta-to-default fallback and dry-run version reporting.
·Plugins/xAI: echo PKCE challenge fields during OAuth authorization-code token exchange for xAI token-endpoint compatibility. (#83499)
·Codex app-server: hydrate current inbound image attachments before queued runs so Responses-backed agents receive Discord and other channel images as native vision input. Fixes #83466.
·Codex app-server: keep native code mode available without forcing code-mode-only so OpenClaw dynamic tool turns complete through the app-server tool bridge. Fixes #83109.
·Codex app-server: expose OpenClaw's sandbox-routed shell as `sandbox_exec`/`sandbox_process` for non-Docker sandbox backends so SSH sandbox agents keep a correctly routed shell path without shadowing Codex native shell. Fixes #80322.
·Release stability: recover stale session diagnostics and Codex OAuth fallback state so stuck runs and reused refresh tokens clear without blocking follow-up work. (#83503)
·Messages/TTS: apply TTS directives before message-tool sends reach core, gateway, or plugin delivery so opt-in message-tool rooms and proactive sends attach voice notes instead of leaking raw tags. Fixes #81598.
·Messages/Codex: keep Codex direct/source chats on message-tool visible delivery by default while documenting and testing `messages.visibleReplies: "automatic"` as the old-mode opt-out; channel wildcard model overrides now apply to direct chats before harness delivery defaults.
·Memory/QMD: keep archived session transcript hits visible after QMD export while preserving normal `.md` session ids that only resemble archive names. (#83518; fixes #83506)
·Codex app-server: preserve network access for sandboxed Codex code-mode turns when the OpenClaw sandbox allows outbound egress. Fixes #83347.
·Codex app-server: honor writable Docker bind mounts for sandboxed workspace-write turns while disabling native Code Mode when container-path aliases or read-only bind shadows cannot be represented safely host-side. Fixes #83737. (#83849)
·QA-Lab: keep the OTLP smoke decoder independent of removed OpenTelemetry generated-root internals.
·Messages: default group/channel visible replies to automatic final delivery again, keeping `message_tool` opt-in for ambient/shared rooms and tool-reliable models.
·CLI/TUI: force standalone `/exit` runs to terminate after `runTui` returns so onboarding-launched TUI children do not stay alive invisibly. (#83501)
·Agents/code mode: honor per-agent code-mode config in schema, runtime catalog activation, and model payload filtering. Fixes #83388.
·Agents/code mode: preserve agent, session, run, and channel context in `before_tool_call` hooks for top-level `exec`/`wait` dispatches. Fixes #83387.
·QQBot: shorten C2C typing indicators to a 10-second window renewed every 5 seconds, capped to keep a final passive-reply slot available. (#83469)
·Replies: keep final payload delivery after live preview updates so channels can finalize or send the completed answer instead of losing preview-only drafts. (#83468)
·Discord: deliver final replies in progress-mode preview streams instead of deduplicating the final visible message. (#83443)
·Providers/Xiaomi: replay MiMo Anthropic-compatible `reasoning_content` as provider-required thinking blocks even when OpenClaw thinking is disabled, fixing follow-up tool turns for `mimo-v2-flash`. Fixes #83407.
·Agents/exec approvals: forward approval-runtime credentials on agent-owned Gateway approval calls so approved async commands complete through the existing runtime path instead of stalling on unauthenticated follow-up calls.
·Gateway/skills: preflight remote macOS skill-bin refreshes with a WebSocket connectivity check so stale node sessions skip quickly instead of logging slow `system.which` timeout warnings.
·CLI/config: keep broken discovered plugins that are not referenced by active config from failing `openclaw config validate`, while preserving fatal errors for explicitly configured plugin entries.
·GitHub Copilot: drop unsafe native Responses reasoning replay items with non-replayable IDs before dispatch, preventing affected Copilot sessions from failing with `invalid_request_body`. Fixes #83220.
·Agents/Codex: fail closed when an explicitly requested Codex harness is not registered instead of silently trying configured model fallbacks. Fixes #83349.
·QA-Lab: make runtime tool coverage fail on missing required tool exercise instead of treating pass/pass parity envelope drift as missing coverage.
·Core/plugins: harden clawpatch-reported edge cases across gateway auth cleanup, Claude session id paths, plugin activation policy, apply-patch hunk handling, diagnostic redaction, and plugin metadata validation.
·UI: show reasoning choices as plain labels instead of leaking internal override wording in session and chat pickers.
·Mac app: avoid repeating the Configuration heading inside channel quick settings.
·Mac app: keep the Settings sidebar always visible and remove the redundant titlebar hide/show control.
·Mac app: normalize Settings pane content margins so pages share the same left and right rail.
·Mac app: prefer explicit private/Tailscale/LAN Gateway endpoints over SSH tunnels, preserve legacy loopback tunnel configs, persist transport choices, and show captured SSH stderr when tunneling really fails.
·Gateway/sessions: keep ACP/acpx and runtime child sessions visible in configured-only session lists when their owner or parent session belongs to a configured agent.
·Mac app: keep app-level menu commands and Dashboard failure states reachable when the remote Gateway is disconnected.
·Mac app: allow longer Gateway and Context errors to wrap in the menu instead of truncating the useful failure detail.
·Mac app: tighten remote Gateway fields in Settings so the Connection pane keeps readable labels and full action button text.
·Mac app: keep custom Settings card rows left-aligned and full-width so Discovery and status sections no longer appear centered or detached.
·Mac app: align Location permission controls to the same trailing column as the rest of Settings.
·Mac app: add Dashboard, Chat, Canvas, and Settings shortcuts to the Dock icon menu.
·Mac app: replace the Settings window's native split-view sidebar with an explicit layout so page content keeps its leading gutter when the sidebar is shown or hidden.
·Mac app: render channel quick config as aligned Settings rows and hide schema-only variants that cannot be edited safely from the quick pane.
·Gateway/webchat: hide internal runtime-context and other `display: false` transcript messages from Chat history and live message events. Fixes #83216.
·CLI/help: keep `gateway`, `doctor`, `status`, and `health` help registration out of action/runtime imports so subcommand `--help` stays lightweight in constrained terminals. Fixes #83228.
·CLI/help: show plugin-owned command help based on the active memory slot so LanceDB memory users see `ltm` instead of unavailable `memory` commands. Fixes #83745. (#83841)
·Cron/Discord: keep explicit announce runs in message-tool-only source-reply mode so scheduled agent turns post once instead of also echoing through automatic visible replies. Fixes #83261.
·Telegram: preserve forum-topic origin targets in inbound, audio-preflight, and skipped-message hook contexts so follow-up delivery stays bound to the originating topic. Fixes #83302.
·Telegram: retry HTTP 421 Misdirected Request send failures on a fresh fallback transport so transient edge-node routing errors no longer drop outbound replies. Fixes #48892. (#48908)
·Telegram: fail topic sends closed when Telegram reports `message thread not found` instead of retrying without `message_thread_id` into the base chat. Refs #83302.
·Config/subagents: remove ignored agent-model `timeoutMs` keys, keep subagent model config to primary/fallback selection, and clean shipped stale config through doctor. Fixes #83291.
·Mac app: align the Sessions settings pane with the standard Settings page gutter and row spacing.
·OpenAI/Codex: stop rejecting available `openai-codex` GPT-5.1, GPT-5.2, and GPT-5.3 model refs during config validation, while keeping removed Spark aliases suppressed. Fixes #83303.
·Plugins/xAI: complete OAuth-backed xAI login and sidecar auth fixes, including guarded loopback callback CORS handling, video generation polling/defaults, and native-host User-Agent attribution. (#83322)
·Codex app-server: preserve streamed native command output in mirrored transcripts and trajectory exports when final snapshots omit aggregated output. (#83200)
·Codex app-server: fail closed when chat or sender policy denies tools, disabling native code, app, environment, and user MCP surfaces for restricted turns. (#82374)
·Codex app-server: keep recent context-engine messages when oversized projected history is truncated, so short follow-ups in long channel sessions do not fall back to stale earlier turns. (#83127)
·Codex app-server: keep OpenClaw session spawning searchable while steering Codex-native delegation through native subagents, avoiding duplicate direct subagent surfaces. (#83329)
·Codex app-server: recover stale childless Codex-native subagent task mirrors during maintenance and allow their registry rows to be cancelled without an OpenClaw child session. (#82836)
·Feishu: return bound subagent delivery origins from session thread setup so Feishu subagent completions route back to the same DM or topic. (#83190)
·CLI/update: tailor post-update Gateway recovery hints by platform, showing systemd, LaunchAgent, Scheduled Task, or generic service-manager guidance instead of macOS-only recovery text. (#83096)
·Plugins: apply a default 15-second timeout to legacy `before_agent_start` hooks so hung plugin handlers no longer block agent startup. Fixes #48534. (#83136)
·Feishu: refresh inbound session delivery context for DM, group, and broadcast turns so later replies do not inherit stale WebChat routing. Fixes #78274.
·Agents/subagents: require the initial subagent registry save before reporting spawn accepted, returning a spawn error instead of losing an untracked run when the registry write fails. (#83146)
·QA-Lab/qa-channel: attach redacted agent tool-start traces to outbound `QaBusMessage` records so scenarios can assert actual tool use instead of relying only on reply text. Fixes #67637.
·QA-Lab: fail live runtime parity reports when assistant-message usage is missing, preventing `0 vs 0` live token rows from being reported as passing proof. Fixes #80411.
·QA-Lab: add a runtime token-efficiency sidecar report that classifies Codex savings separately from regressions and fails only positive Codex-over-Pi live token deltas above threshold. Fixes #81093.
·QA-Lab: fail Codex-backed OpenAI live runtime-pair runs before launching isolated workers when no portable Codex auth is available, while staging API-key fallbacks and configured Codex keys for isolated QA agents. Fixes #80412.
·QA-Lab: refresh parity gates, mock frontier fixtures, model scenarios, and workflow artifact lanes to compare GPT-5.5 against Claude Opus 4.7. Fixes #74262.
·QA-Lab: make mock parity dispatch provider-aware for source discovery and subagent scenarios so OpenAI and Anthropic lanes no longer share identical canned plans. Fixes #64879.
·QA-Lab: stop returning Control UI bearer tokens from unauthenticated bootstrap payloads and bind Docker harness ports to loopback-only host addresses. (#66355)
·Mac app: avoid a SwiftUI metadata crash when rendering the Cron Jobs settings pane.
·Agents/subagents: preserve run-mode keep subagent registry entries past the session sweep TTL, so kept subagent runs remain visible after cleanup completes. Fixes #83132. (#83168)
·Agents/OpenAI streams: yield via `setTimeout(0)` instead of `setImmediate` between bursty Responses chunks so abort timers can fire during the yield, keeping cancel-on-timeout responsive on hot streams. Refs #82462.
·Agents/Codex: keep legacy `oauthRef`-backed OAuth profiles usable while `openclaw doctor --fix` migrates them back to inline credentials, without creating new sidecar credentials. (#83312)
·Agents/Codex: load the selected provider owner alongside the Codex harness runtime so `openai-codex` models resolve when plugin allowlists scope runtime loading. Fixes #83380. (#83519)
·Telegram: fail stalled isolated-ingress handlers into tombstones and abort same-lane reply work before restarting, so later same-chat updates drain after a hung turn. Fixes #83272. (#83505)
·CLI/config: send SecretRef diagnostics to stderr so JSON command stdout remains parseable.
·CLI/doctor: seed Control UI allowed origins when migrating legacy non-loopback gateway bind host aliases like `0.0.0.0`. Fixes #83286.
·CLI/plugins: ship the bundled memory CLI as a package entry so package-installed `openclaw memory` commands register correctly.
·CLI/update: defer doctor-time plugin package installs during package swaps and seed post-core repair from the updated install registry, preventing duplicate reinstall failures.
·CLI/update: preserve old-parent-readable config metadata during legacy package handoffs, fall back only to official `@openclaw/*` npm plugin packages when ClawHub plugin artifacts are unavailable, and keep managed service package roots authoritative during updates.
·Feishu: detect SecretRef top-level credentials as a configured default account instead of treating object-backed app secrets as missing.
·Gateway/restart: keep ordinary unmanaged SIGUSR1/config restarts in-process instead of detach-spawning an orphaned child, preserving custom supervisor PID tracking while leaving update restarts on the fresh-process path. Fixes #65668.
·CLI/completion: resolve concrete PowerShell profile paths and reload commands during setup and doctor completion installation. Fixes #44296. (#83059)
·Telegram: keep isolated long polling below the hard `getUpdates` request guard so idle bot accounts with high `timeoutSeconds` do not false-disconnect and restart-loop. Fixes #83264.
·Providers/Google: preserve and recover Gemini 3 tool-call thought signatures during native replay so function-calling turns no longer fail with missing `thought_signature` 400s. Fixes #72879. (#80358)
·Telegram: skip transcript-only delivery mirrors and gateway-injected rows when resolving latest assistant text, preventing retained previews from replacing final replies with stale fragments. Fixes #83159. (#83362)
·Memory/QMD: keep lexical search on raw hyphenated queries while normalizing semantic QMD sub-searches, avoiding fallback to the builtin index for dashed identifiers and dates. Fixes #81328.
·Memory-core: distinguish sqlite-vec load failures from missing semantic vector embeddings in degraded `memory index` warnings, so vector recall diagnostics point at unresolved dimensions instead of blaming sqlite-vec when the store is ready. Fixes #75624. (#83056)
·Agents/subagents: preserve sandbox-peer controller ownership while routing completion announcements back to the originating run session, keeping subagent control and completion delivery scoped correctly. Fixes #80201. (#80242)
·Gateway: continue restarting remaining channels when one hot-reload channel restart fails, while still reporting aggregate reload failure and rolling back plugin pre-replace stops. Fixes #83054.
·Gateway/plugins: bind admin HTTP RPC dispatch to the accepting gateway instance so multi-gateway processes cannot execute plugin HTTP control-plane calls against another live gateway. Fixes #83486. (#83487)
·Telegram: keep hot-reload restarts from marking polling accounts manually stopped and restart isolated ingress cleanly after worker shutdown, preserving Telegram replies across config reloads. Fixes #83008. (#83410)
·Telegram/Ollama: pass current Telegram image attachments into native PI/Ollama vision turns so live photo prompts reach Ollama as native images. Fixes #83023. (#83516)
·Gateway/secrets: split the lightweight secrets runtime state and auth-store cache from the full secrets runtime and take a startup fast path when the gateway startup config has no SecretRef values, speeding up secrets startup while preserving cleanup and refresh semantics.
·Codex app-server: rotate oversized native Codex threads before resume and cap dynamic tool-result text entering native Codex sessions, preventing stale oversized context from surviving OpenClaw compaction. (#82981)
·Gateway/restart: drain pending replies and active chat runs during restart shutdown before sockets and channels close, aborting timed-out chat runs through the normal cleanup path. (#69121)
·Agents/Codex: use the Codex runtime context window for OpenAI-model preflight compaction and memory flush checks, so GPT-5.5 Codex sessions compact before hitting the smaller native context limit. Fixes #82982.
·QA-Lab: clean orphaned gateway temp roots when a suite parent exits and wait on gateway plus transport readiness after config restarts, reducing stale `qa-channel` noise from interrupted runs. Fixes #65506.
·QA-Lab: wake qa-bus long polls that arrive with stale future cursors after a bus restart, preserving reconnect readiness for harness clients. (#67142)
·QA-Lab: stage Multipass transfer scripts under OpenClaw's preferred temp root instead of raw OS temp paths, keeping the VM runner inside temp-path guardrails. (#64098)
·Agents/replies: keep surviving reply media and append a warning when other media references fail, so partial media normalization no longer drops failures silently.
·Config/models: accept `thinkingFormat: "together"` in model compat config so Together routes can opt into the Together-specific thinking response shape.
·Plugins/tokenjuice: bump the bundled tokenjuice runtime to 0.7.1, bringing Codex hook approval compatibility, pre-tool command wrapping fixes, and Rolldown/Vitest output compaction improvements into the OpenClaw plugin.
·Agents/OpenAI: stop post-processing GPT-5 final replies with hardcoded brevity caps, preserving full channel responses instead of appending synthetic ellipses, and log when strict-agentic GPT-5 execution activates. Fixes #82910.
·Mac app: refine the Settings General and Connection panes with cleaner status panels, card rows, and a single native titlebar sidebar toggle.
·Agents/media: deliver failed async image, music, and video generation completions directly when requester-session completion handoff fails, so channel users see provider errors instead of silent fallback stalls.
·Browser/CDP: keep loopback proxy bypass active across both `NO_PROXY` casings and redact home-relative Chrome MCP profile paths in attach-failure diagnostics.
·Agents/music: steer song, jingle, beat, anthem, and instrumental requests toward `music_generate` audio creation instead of lyric-only replies, and reserve `lyrics` for exact sung words.
·Codex app-server: record native Codex tool calls and results into trajectory artifacts so debug/trajectory exports capture the full Codex-native tool history, not just OpenClaw-bridged turns.
·Codex/app-server: keep bound conversation sessions on the owning agent runtime so native Codex control and follow-up turns do not fall back to the default agent client. Fixes #82954. (#82993)
·CLI/infer: run gateway model probes in fresh explicit sessions so one-shot provider checks do not inherit default agent transcript state. (#82861)
·Providers/Together: send video-generation requests to Together's v2 video API even when shared text-model config still points at the v1 base URL. (#82992)
·Browser CLI: preserve browser-level options on nested commands, skip option values during lazy command registration, and keep long-running wait/download/dialog hooks open for their advertised wait window.
·CLI/sessions: accept `openclaw sessions list` as an alias for `openclaw sessions`, matching other list-style commands. Fixes #81139. (#81163)
·Channels/stream previews: widen compact progress draft lines and cut prose at word boundaries while preserving command/path suffixes, with `streaming.progress.maxLineChars` for channel-specific tuning.
·CLI/plugins: have `openclaw plugins doctor` warn when a configured runtime needs a missing owner plugin, sharing the same install mapping as `openclaw doctor --fix`. Fixes #81326. (#81674)
·Agents/Codex: route OpenAI runs that resolve to `openai-codex` through the Codex provider and bootstrap OpenClaw's stored OAuth profile into the Codex harness when the harness owns transport, so `openai/*` model refs no longer fail with `No API key found for openai-codex` despite an existing Codex OAuth profile. (#82864)
·Agents/ACP: distinguish prompt-submitted and runtime-active child stalls from true interactive waits, including redacted proxy-env diagnostics for Codex ACP no-output runs. Fixes #44810.
·Agents/memory: explain that memory-triggered compaction exposes only `read` and append-only `write` when configured core tools are unavailable in `tools.allow` warnings. Fixes #82941.
·Agents/OpenAI: preserve deterministic tool payload ordering for prompt-cache reuse across OpenAI Responses and chat completions calls. (#82940)
·ACP/Codex: honor terminal ACP turn results so failed Codex/acpx runs are not recorded as successful after only progress text. Fixes #79522.
·Telegram: warn when a media group drops photos that fail to download, including albums where every photo is skipped. Fixes #55216. (#82987)
·Agents/diagnostics: treat repeated same-handle embedded-run cleanup as idempotent while preserving true replacement-handle mismatch diagnostics. Fixes #82959. (#82960)
·Agents/skills: apply the full effective tool policy pipeline to inline `command-dispatch: tool` skill dispatch before owner-only filtering, preserving configured allow, deny, sandbox, sender, group, and subagent restrictions. (#78525)
·Codex: avoid spawning native hook relay subprocesses for post-tool/finalize events with no registered hook handlers while preserving pre-tool safety and approval relays. Fixes #76552. (#78004)
·Channel accounts: keep top-level default channel accounts visible when named accounts are added alongside default credential material, so mixed legacy/new account configs keep resolving `default` instead of silently dropping it.
·Agents/CLI: reject empty successful CLI subprocess replies as `empty_response` and keep them out of shared auth-profile health, so blank Claude CLI results no longer become green no-payload turns. Fixes #83231. (#83421)
·Codex/Telegram: synthesize native Codex tool progress from final turn snapshots so Telegram `/verbose` stays visible when command events arrive only at completion.
·Codex/Telegram: deliver Codex verbose tool summaries in direct message-tool-only turns while suppressing message-send and activity-log noise. (#83186)
·Mac app: make Channels settings open faster by deferring config-schema work, avoiding startup channel probes, caching decoded channel status rows, and showing only compact quick settings instead of the full generated channel schema.
·Control UI: include the Control UI and Gateway protocol versions in protocol-mismatch errors so stale app/dashboard pairings identify which side needs rebuilding or restarting.
·Gateway/protocol: restore Gateway WS protocol v4 and keep `message.action` room-event metadata on the existing `inboundTurnKind` wire field while preserving internal inbound-event classification.
·Agents/tools: prefer non-webchat session-key routes when the message tool has stale webchat context, so message-tool-only replies keep delivering to the originating channel. Fixes #82911. (#83004)
·Channels: keep direct-message last-route writes on isolated `per-channel-peer` sessions instead of contaminating the agent main session with channel delivery context. Fixes #36614.
·Mac app: move the Settings sidebar toggle into the native titlebar and tighten the General pane width.
·Mac app: keep visited Settings panes mounted so switching tabs no longer blanks and reloads their content.
·Mac app: make Config settings open from shallow schema lookups and load selected paths on demand instead of fetching and rendering the full generated config schema up front.
·Codex: sanitize inline image payloads before Codex app-server and OpenAI Responses replay, and clear poisoned Codex thread bindings after invalid image errors. Fixes #82878.
·Providers/GitHub Copilot: request identity-encoded Copilot API responses across token exchange, catalog, model calls, usage, and embeddings so compressed Business-account error payloads no longer reach JSON parsers as gzip bytes. Fixes #82871.
·Telegram: redact nested raw-update identifiers and user metadata before verbose raw update logging, preserving useful update/message ids without exposing chat, user, command, or profile details. (#82945)
·Telegram: preserve replied-to bot messages, captions, and media metadata in group reply chains so follow-up replies understand what the user is reacting to. (#82863)
·Providers/Together: update PI runtime packages to 0.74.1 and emit Together-style `reasoning.enabled`/`max_tokens` controls for reasoning-capable OpenAI-completions models.
·Agents/diagnostics: split slow embedded-run `attempt-dispatch` startup summaries into workspace, prompt, runtime-plan, and final dispatch subspans so traces identify the delayed setup phase. Fixes #82782. (#82783)
·Agents/Codex: flatten nested tool-result middleware blocks into bounded text so successful message sends are no longer replaced with `Tool output unavailable due to post-processing error`. Fixes #82912.
·CLI/media: accept HTTP(S) URLs in `openclaw infer image describe --file`, fetching remote images through the guarded media path instead of treating URLs as local files. Fixes #82837. (#82854)
·Agents/subagents: keep session-backed parent runs active when the child wait call times out before the child session has actually settled, so late subagent completions are reconciled instead of being lost. Fixes #82787.
·Control UI: advertise shared Gateway protocol constants in browser connect frames, fixing protocol mismatch handshakes after protocol constant drift. Fixes #82882.
·Gateway: add rollback protocol-mismatch diagnostics, including client protocol ranges in Gateway logs and deep status/doctor hints for stale client processes. Fixes #82841. (#82908)
·Agents/subagents: keep successful keep-mode completion payloads pending after final-delivery retry exhaustion, so requester recovery no longer loses final subagent results. Fixes #82583. (#82999)
·Gateway/auth: allow same-host trusted-proxy callers to use the documented local direct `gateway.auth.password` fallback after revisiting the #78684 fail-closed policy, while keeping token fallback rejected and forwarded-header requests on the trusted-proxy path. Fixes #82607. (#82953)
·Agents/subagents: wait for queued completion handoffs to reach the parent transcript before marking them announced, preventing busy parent runs from cleaning up before observing child results. Fixes #82913. (#83039)
·Agents/subagents: route group/channel subagent completions through message-tool-only handoffs when required and keep active-requester wake failures from dropping completion delivery. Fixes #82803.
·Memory-core: scan persisted memory source sessions on startup, comparing on-disk transcripts against the index and marking only missing/newer/resized files dirty for incremental sync. Fixes #82341. (#82341)
·Telegram: keep the top-level default account in the account list when named accounts or bindings are added alongside top-level credentials, preserving default polling while still letting named-only configs resolve to a single account. Fixes #82794. (#82794)
·CLI/models: reuse command-scoped plugin metadata across model listing, provider catalog, auth, and synthetic-auth checks, restoring fast `openclaw models` runs for plugin-heavy installs. Fixes #82881. (#83033)
·CLI/channels: show configured official external channels such as Discord in `openclaw channels list` when their plugin package is missing, including the install and doctor repair command instead of reporting no configured channels. Fixes #82813.
·Signal: preserve mixed-case group IDs through routing and session persistence so group auto-replies keep delivering after updates. Fixes #82827.
·Agents/tools: keep the `message` tool available in embedded runs when it is explicitly allowed through `tools.alsoAllow` or runtime tool allowlists, so channel plugins with custom reply delivery can still use configured message sends. Fixes #82833.
·WhatsApp: honor forced document delivery for outbound image, GIF, and video media so `forceDocument`/`asDocument` sends preserve original media bytes instead of using compressed media payloads. (#79272)
·WhatsApp: name outbound document attachments from their MIME type when no filename is provided, so PDF and CSV sends arrive as `file.pdf` and `file.csv` instead of an extensionless `file`.
·Process/diagnostics: report active lane blockers in lane wait warnings so `queueAhead=0` no longer hides commands waiting behind active work. Fixes #82791. (#82792)
·Process/diagnostics: stop counting the active processing turn as queued backlog in liveness warnings so transient max-only event-loop spikes do not surface as gateway warnings.
·Agents/replies: classify provider conversation-state rejections and return a clear message-channel error instead of auto-resetting or falling back to a generic runner failure. (#82616)
·Browser plugin: trust managed Chrome CDP diagnostics when launch HTTP probes race cold-start readiness, avoiding false startup failures. Fixes #82904. (#82986)
·Android: prompt before replacing a changed Gateway TLS thumbprint, showing the old and new SHA-256 fingerprints so users can accept expected certificate rotations instead of hard failing on pin mismatch. (#83077)
·CLI/status: render extra gateway-like service diagnostics as warning/info output instead of error output. Fixes #46930. (#82922)
·Agents/failover: classify Moonshot/Kimi exhausted-balance HTTP 429 payloads as billing instead of generic rate limits, preserving billing guidance and fallback behavior. Fixes #43447. (#83079)
·Plugin SDK: bundle `openclaw/plugin-sdk/zod` into the published package artifact and verify the packed zod subpath stays self-contained, so pnpm global installs can register plugins without a package-local `zod` symlink. Fixes #78398. (#78515)
·Providers/Google: drop compaction-truncated Gemini thought signatures before replay so malformed Base64 no longer aborts the next assistant turn. (#82995)
·Gateway/mobile: allow paired iOS and Android clients to refresh same-family OS metadata on authenticated reconnect instead of requiring a new approval. (#83490)
·WhatsApp: treat `upload-file` as a supported media send intent by lowering path/URL uploads through the channel's normal send-media transport. (#81883)
·iOS: end Live Activities when OpenClaw is connected, idle, or disconnected, and show compact attention states for approval-required reconnects. (#83597)
·Control UI: hide child nav items when collapsing the active sidebar group. Fixes #42167. (#42223)
·CI/proof: skip the real-behavior-proof gate for private org maintainers by minting a least-privilege (`members: read`) GitHub App token and checking active membership in the `maintainer` team, instead of treating `author_association=CONTRIBUTOR` as definitively external. (#83418)

Release proof

·npm: https://www.npmjs.com/package/openclaw/v/2026.5.19-alpha.1
·registry tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.5.19-alpha.1.tgz
·integrity: `sha512-V7ECuM8Z9tGBTffZCLzni07RLzrUe8qJXng7Jb8CYXvggab6W3fuODMwb8nlqGB1dDhjy5Nd6gm31jhbqIn83A==`
·published: 2026-05-20T00:45:13.592Z
·release branch: `tideclaw/alpha/2026-05-19-2308Z`
·release SHA: `2812b4c6fee06d324731846c684cea8925618f65`
·full release validation: https://github.com/openclaw/openclaw/actions/runs/26131276755
·npm preflight: https://github.com/openclaw/openclaw/actions/runs/26131286126
·OpenClaw npm publish: https://github.com/openclaw/openclaw/actions/runs/26133693793
·plugin npm publish: https://github.com/openclaw/openclaw/actions/runs/26133461507

v2026.5.19-beta.1pre-release2026-05-18

openclaw 2026.5.19-beta.1

GitHub ↗

Changes

·Agents: clarify that fixes should default to clean bounded refactors, lean internals, and explicit plugin SDK/API deprecation paths.
·Dependencies: update `@openclaw/proxyline` to 0.3.3.
·Dependencies: update Pi packages to 0.75.1 and raise the minimum supported Node.js 22 line to 22.19.
·Docker/Podman: add `OPENCLAW_IMAGE_APT_PACKAGES` as the runtime-neutral image build arg for extra apt packages while keeping `OPENCLAW_DOCKER_APT_PACKAGES` as a legacy fallback. (#62431)
·Gateway/ACPX: attribute startup probe, config, runtime, and resource-count costs in restart traces without changing readiness behavior. (#83300)
·Gateway: overlap startup logging and plugin-service startup with channel sidecars to reduce restart ready latency while preserving `/readyz` sidecar gating. (#83301)
·Plugins/admin-http-rpc: allow trusted admin HTTP RPC clients to start and wait for web QR login flows. (#83259)
·Mac app: redesign Settings pages with consistent card layouts, cached navigation, cleaner permissions/voice/skills/cron/exec/debug panes, and steadier spacing around the native sidebar.
·Skills: rename the repo-local Codex closeout review skill and helper to `autoreview` while preserving the Codex-first fallback behavior.
·Skills: add a meme-maker skill for curated template search, local SVG/PNG rendering, Imgflip hosted rendering, and Know Your Meme provenance links.
·Skills CLI: allow `openclaw skills install` and `openclaw skills update` to target shared managed skills with `--global`. (#74466)
·Browser: surface pending and recently handled modal dialogs in snapshots, return `blockedByDialog` when an action opens a modal, and allow `browser dialog --dialog-id` to answer pending dialogs.
·Browser CLI: add `openclaw browser evaluate --timeout-ms` so long-running page functions can extend both the evaluate action and request timeout budgets. (#83447)
·Codex app-server: scope OpenClaw prompt guidance by runtime surface so native Codex keeps Codex-owned base/personality instructions while OpenClaw contributes only runtime context, delivery guidance, and explicitly scoped command hints. (#83454)
·Agents/tools: shorten built-in tool descriptions and schema hints across media, messaging, sessions, cron, Gateway, web, image/PDF, TTS, nodes, and plan tools while preserving routing guardrails.
·Skills: add node inspector debugging, fused diagram generation, and throwaway spike workflow skills.
·CLI/plugins: add `defineToolPlugin` plus `openclaw plugins build`, `validate`, and `init` for typed simple tool plugins with generated manifest metadata, optional tool declarations, and context factories.
·Agents/skills: tighten bundled skill prompts and metadata, quote skill descriptions, refresh current CLI/API guidance, and update embedded sherpa-onnx runtime downloads.
·Skills: update the Obsidian skill to target the official `obsidian` CLI and require its registered binary instead of the third-party `obsidian-cli`.
·Skills: add a Python debugging skill for pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.
·Plugins/messages: add presentation capability limits for channel renderers, adapt rich message controls before native rendering, and mark legacy `interactive`/Slack directive producer APIs as deprecated.
·Plugins/subagents: store channel delivery routes as canonical session metadata and deprecate ad hoc subagent hook delivery-origin fields in favor of core route projection.
·Proxy: support HTTPS managed forward-proxy endpoints and scoped `proxy.tls.caFile` CA trust for proxy endpoint TLS. (#79171)
·QA-Lab: add first-hour 20-turn and optional 100-turn runtime parity scenarios, with tier metadata for standard and soak QA gates. Fixes #80338; refs #80337.
·QA-Lab: add `openclaw qa suite --runtime-parity-tier` and wire the standard Codex-vs-Pi tier into release checks separately from optional/live-only/soak lanes. Fixes #80337.
·QA-Lab: add a live-only Codex Pi-shaped Read vocabulary canary so runtime parity catches native workspace-read prompt compatibility drift. (#80323)
·QA-Lab: add live-only harness self-health scenarios for plugin hook crashes, manifest contract errors, and WebChat direct-reply self-message routing. (#80323)
·QA-Lab: add runtime tool fixture scenarios and coverage reporting for Codex-native workspace tools, OpenClaw dynamic tools, and optional plugin-backed tools. Fixes #80173.
·QA-Lab: expose runtime tool fixture coverage through `openclaw qa coverage --tools`, with optional suite-summary evaluation for parity gate artifacts.
·QA-Lab: schedule a live-frontier Codex-vs-Pi runtime token-efficiency artifact lane in the all-lanes QA workflow. Fixes #80175.
·QA-Lab: hard-gate required OpenClaw dynamic runtime-tool drift in the standard Codex-vs-Pi tier with a blocking release-check verifier and publish the tool coverage report artifact. Fixes #80339; refs #80319.
·QA-Lab: add the personal-agent approval-denial scenario so the benchmark pack verifies denied local reads stop cleanly without tool progress or fixture leaks. (#83150)
·QA-Lab: extend the personal-agent benchmark pack with a local task followthrough scenario for proof-backed pending, blocked, and done status reporting.
·QA-Lab: add a report-only dreaming shadow-trial scenario so candidate memory promotion can be evaluated without mutating `MEMORY.md`.
·Gateway/performance: add `pnpm test:restart:gateway` benchmark tooling for repeated restart readiness, downtime, trace, and resource-slope evidence. (#83299)
·Android: switch Talk Mode to realtime Gateway relay voice sessions with streaming mic input, realtime audio playback, tool-result bridging, and on-screen transcripts. (#83130)
·Gateway/config: expose config lookup reload metadata so tools can distinguish restart-required, hot-reloadable, and no-op fields before applying config edits. Fixes #81409. (#81612)
·Telegram: add allowlisted native DM draft previews for transient tool progress while keeping final answers on the normal persistent delivery path. (#83622)
·QA-Lab: add a personal-agent share-safe diagnostics artifact scenario so support handoffs keep useful status while omitting raw personal content.

Fixes

·Memory/search: scan the JS-side fallback vector path (used when the sqlite-vec index is unavailable or has a mismatched dimension) in bounded rowid batches and yield to the event loop between batches so large chunk tables can no longer pin the Node.js main thread for multi-second windows. Also keeps the SQL prepared statement rooted in a local so node:sqlite cannot finalize it mid-scan under heap pressure. Fixes #81172.
·CLI/update: bypass npm freshness filters consistently during managed package and plugin installs so freshly published release plugins remain installable.
·Agents/subagents: keep collect-mode announce queues batching unresolved-origin items with compatible same-route messages and resume collection after a true cross-channel drain when a later compatible batch remains. Fixes #83577.
·Providers/Anthropic: preserve native image input for current Claude model rows when stale local catalog data marks them text-only. (#83756)
·Control UI: render live tool progress from session-scoped `session.tool` Gateway events so externally started runs show their tool cards in the active session. (#83734)
·Outbound: resolve send-capable channel plugins from the active runtime registry when the pinned startup registry only has setup metadata. (#83733)
·Browser: enforce current-tab URL allowlist checks for `/act` evaluate/batch actions and `/highlight` routes while leaving tab-management actions unblocked. (#78523)
·CI: require real-behavior-proof verdict markers to come from the ClawSweeper GitHub App before accepting exact-head proof. (#83692)
·Models: show the effective OpenAI/Codex auth profile in `/models` provider headers instead of falling back to the OpenAI env-key label. (#83697)
·Browser: keep a profile `cdpPort` when its `cdpUrl` omits a port, while still letting explicitly written URL ports win. (#82166)
·Agents/image generation: allow distinct `image_generate` prompts to start separate session-backed background tasks while same-prompt retries still return the active task status. (#83614)
·Gateway/WebChat: honor configured `channels.webchat.textChunkLimit` and `chunkMode` overrides when chunking WebChat replies. (#83713)
·Control UI: stop the chat reading indicator from sticking after an assistant response finishes. (#83515)
·Skills: reject empty or whitespace-only skill names and descriptions during quick validation. (#27061)
·Sessions: skip trailing custom transcript entries when checking tail assistant replies so embedded CLI gap-fill does not duplicate canonical assistant output. (#83635)
·Memory Wiki: keep `wiki_lint` tool output path-safe by reporting vault-internal lint reports as relative paths in tool text and details while preserving absolute report paths for CLI/file callers. (#83439)
·Telegram: keep verbose tool progress visible without mirroring non-final progress into active session transcripts, preventing embedded provider replies from aborting mid-run. (#83631)
·Telegram: log successful outbound text and media deliveries with account, chat, message, operation, thread, reply, silent, and chunk metadata while keeping message bodies out of logs. Fixes #83196. (#83247)
·Cron: link isolated scheduled task runs to their stable cron session so task status and cleanup can follow the backing agent run. (#83606)
·CLI: enforce the documented Node.js 22.19 runtime floor in the source launcher.
·Release stability: repair broad-gate regressions in requester-agent completion handoff, QA-Lab mock spawn attribution, Slack monitor test isolation, plugin uninstall peer fixtures, and Node-floor launcher contract coverage.
·Agents/replies: persist queued follow-up user messages and assistant error stubs only once across model-fallback retries, preventing repeated provider rejections from corrupted same-role session transcripts. Fixes #83404. (#83417)
·Slack: persist delivered inbound message IDs and fail closed when same-channel thread replies lose their thread context, preventing delayed duplicate replies and accidental channel-root posts. Fixes #83521.
·Codex app-server: complete OpenClaw dynamic tool diagnostics at the request boundary so successful, failed, timed out, aborted, and blocked tool calls do not leave active tool state behind. Fixes #83474.
·Gateway/config: keep config writes from failing on unrelated unresolved auth-profile SecretRefs while preserving live auth-profile runtime snapshots.
·Gateway/sessions: clear stored CLI provider resume bindings on non-subagent `/reset` so the next turn starts a fresh provider-side CLI conversation instead of resuming old context. (#83448)
·Doctor: preserve legacy whole-agent Claude CLI intent by moving matching Anthropic model selections to model-scoped runtime policy before removing stale runtime pins. Fixes #83491.
·Discord/OpenAI: keep realtime Discord voice sessions hearing follow-up turns with OpenAI realtime and prebuffer assistant playback to avoid choppy starts. (#80505)
·LM Studio: resolve env-template API keys like `${LMSTUDIO_API_KEY}` through the standard SecretInput path instead of sending the raw template as the bearer token, and preserve header-auth and discovery-key precedence when the template is unset. Fixes #80495. (#80568)
·Discord/subagents: route the initial reply from thread-bound delegated sessions into the bound Discord thread instead of the parent channel. Fixes #83170. (#83172)
·Gateway/sessions: rotate failed agent sessions when their transcript file is missing instead of wedging per-channel lanes. Fixes #83488. (#83553)
·Media: prevent image metadata probing from invoking external decoder delegates on unrecognized image bytes, and stop fallback chaining after real processing errors.
·Media: install Sharp with the root package and fall back to sips, Windows native imaging, ImageMagick, GraphicsMagick, or ffmpeg for image resizing/conversion when Sharp is unavailable. Fixes #83401.
·Telegram: deliver generated media completions back into forum topics by preserving topic IDs across requester-agent handoff. (#83556)
·Gateway: defer update-check startup until after readiness so package update checks no longer block sidecar-ready startup, while preserving update broadcasts and shutdown cleanup. (#83520)
·Telegram: keep `/btw` and read-only status commands from aborting active runs, and avoid retaining raw update payloads in timed-out spool tombstones. Refs #83272.
·Agents: log strict-agentic execution contract diagnostics only when the planning-only retry path actually triggers.
·Agents: stop embedded session takeover and session write-lock errors from consuming model fallbacks while preserving provider fallback metadata. Fixes #83510.
·Agents/video: hide `video_generate` reference-audio parameters unless a registered video provider supports audio inputs.
·Plugins: fall back to npm for official ClawHub updates when artifact downloads are unavailable, including beta-to-default fallback and dry-run version reporting.
·Plugins/xAI: echo PKCE challenge fields during OAuth authorization-code token exchange for xAI token-endpoint compatibility. (#83499)
·Codex app-server: hydrate current inbound image attachments before queued runs so Responses-backed agents receive Discord and other channel images as native vision input. Fixes #83466.
·Codex app-server: keep native code mode available without forcing code-mode-only so OpenClaw dynamic tool turns complete through the app-server tool bridge. Fixes #83109.
·Release stability: recover stale session diagnostics and Codex OAuth fallback state so stuck runs and reused refresh tokens clear without blocking follow-up work. (#83503)
·Messages/TTS: apply TTS directives before message-tool sends reach core, gateway, or plugin delivery so opt-in message-tool rooms and proactive sends attach voice notes instead of leaking raw tags. Fixes #81598.
·Messages/Codex: keep Codex direct/source chats on message-tool visible delivery by default while documenting and testing `messages.visibleReplies: "automatic"` as the old-mode opt-out; channel wildcard model overrides now apply to direct chats before harness delivery defaults.
·Memory/QMD: keep archived session transcript hits visible after QMD export while preserving normal `.md` session ids that only resemble archive names. (#83518; fixes #83506)
·Codex app-server: preserve network access for sandboxed Codex code-mode turns when the OpenClaw sandbox allows outbound egress. Fixes #83347.
·QA-Lab: keep the OTLP smoke decoder independent of removed OpenTelemetry generated-root internals.
·Messages: default group/channel visible replies to automatic final delivery again, keeping `message_tool` opt-in for ambient/shared rooms and tool-reliable models.
·CLI/TUI: force standalone `/exit` runs to terminate after `runTui` returns so onboarding-launched TUI children do not stay alive invisibly. (#83501)
·Agents/code mode: honor per-agent code-mode config in schema, runtime catalog activation, and model payload filtering. Fixes #83388.
·Agents/code mode: preserve agent, session, run, and channel context in `before_tool_call` hooks for top-level `exec`/`wait` dispatches. Fixes #83387.
·QQBot: shorten C2C typing indicators to a 10-second window renewed every 5 seconds, capped to keep a final passive-reply slot available. (#83469)
·Replies: keep final payload delivery after live preview updates so channels can finalize or send the completed answer instead of losing preview-only drafts. (#83468)
·Discord: deliver final replies in progress-mode preview streams instead of deduplicating the final visible message. (#83443)
·Providers/Xiaomi: replay MiMo Anthropic-compatible `reasoning_content` as provider-required thinking blocks even when OpenClaw thinking is disabled, fixing follow-up tool turns for `mimo-v2-flash`. Fixes #83407.
·Agents/exec approvals: forward approval-runtime credentials on agent-owned Gateway approval calls so approved async commands complete through the existing runtime path instead of stalling on unauthenticated follow-up calls.
·Gateway/skills: preflight remote macOS skill-bin refreshes with a WebSocket connectivity check so stale node sessions skip quickly instead of logging slow `system.which` timeout warnings.
·CLI/config: keep broken discovered plugins that are not referenced by active config from failing `openclaw config validate`, while preserving fatal errors for explicitly configured plugin entries.
·GitHub Copilot: drop unsafe native Responses reasoning replay items with non-replayable IDs before dispatch, preventing affected Copilot sessions from failing with `invalid_request_body`. Fixes #83220.
·Agents/Codex: fail closed when an explicitly requested Codex harness is not registered instead of silently trying configured model fallbacks. Fixes #83349.
·QA-Lab: make runtime tool coverage fail on missing required tool exercise instead of treating pass/pass parity envelope drift as missing coverage.
·Core/plugins: harden clawpatch-reported edge cases across gateway auth cleanup, Claude session id paths, plugin activation policy, apply-patch hunk handling, diagnostic redaction, and plugin metadata validation.
·UI: show reasoning choices as plain labels instead of leaking internal override wording in session and chat pickers.
·Mac app: avoid repeating the Configuration heading inside channel quick settings.
·Mac app: keep the Settings sidebar always visible and remove the redundant titlebar hide/show control.
·Mac app: normalize Settings pane content margins so pages share the same left and right rail.
·Mac app: prefer explicit private/Tailscale/LAN Gateway endpoints over SSH tunnels, preserve legacy loopback tunnel configs, persist transport choices, and show captured SSH stderr when tunneling really fails.
·Gateway/sessions: keep ACP/acpx and runtime child sessions visible in configured-only session lists when their owner or parent session belongs to a configured agent.
·Mac app: keep app-level menu commands and Dashboard failure states reachable when the remote Gateway is disconnected.
·Mac app: allow longer Gateway and Context errors to wrap in the menu instead of truncating the useful failure detail.
·Mac app: tighten remote Gateway fields in Settings so the Connection pane keeps readable labels and full action button text.
·Mac app: keep custom Settings card rows left-aligned and full-width so Discovery and status sections no longer appear centered or detached.
·Mac app: align Location permission controls to the same trailing column as the rest of Settings.
·Mac app: add Dashboard, Chat, Canvas, and Settings shortcuts to the Dock icon menu.
·Mac app: replace the Settings window's native split-view sidebar with an explicit layout so page content keeps its leading gutter when the sidebar is shown or hidden.
·Mac app: render channel quick config as aligned Settings rows and hide schema-only variants that cannot be edited safely from the quick pane.
·Gateway/webchat: hide internal runtime-context and other `display: false` transcript messages from Chat history and live message events. Fixes #83216.
·CLI/help: keep `gateway`, `doctor`, `status`, and `health` help registration out of action/runtime imports so subcommand `--help` stays lightweight in constrained terminals. Fixes #83228.
·Cron/Discord: keep explicit announce runs in message-tool-only source-reply mode so scheduled agent turns post once instead of also echoing through automatic visible replies. Fixes #83261.
·Telegram: preserve forum-topic origin targets in inbound, audio-preflight, and skipped-message hook contexts so follow-up delivery stays bound to the originating topic. Fixes #83302.
·Telegram: retry HTTP 421 Misdirected Request send failures on a fresh fallback transport so transient edge-node routing errors no longer drop outbound replies. Fixes #48892. (#48908)
·Telegram: fail topic sends closed when Telegram reports `message thread not found` instead of retrying without `message_thread_id` into the base chat. Refs #83302.
·Config/subagents: remove ignored agent-model `timeoutMs` keys, keep subagent model config to primary/fallback selection, and clean shipped stale config through doctor. Fixes #83291.
·Mac app: align the Sessions settings pane with the standard Settings page gutter and row spacing.
·OpenAI/Codex: stop rejecting available `openai-codex` GPT-5.1, GPT-5.2, and GPT-5.3 model refs during config validation, while keeping removed Spark aliases suppressed. Fixes #83303.
·Plugins/xAI: complete OAuth-backed xAI login and sidecar auth fixes, including guarded loopback callback CORS handling, video generation polling/defaults, and native-host User-Agent attribution. (#83322)
·Codex app-server: preserve streamed native command output in mirrored transcripts and trajectory exports when final snapshots omit aggregated output. (#83200)
·Codex app-server: fail closed when chat or sender policy denies tools, disabling native code, app, environment, and user MCP surfaces for restricted turns. (#82374)
·Codex app-server: keep recent context-engine messages when oversized projected history is truncated, so short follow-ups in long channel sessions do not fall back to stale earlier turns. (#83127)
·Codex app-server: keep OpenClaw session spawning searchable while steering Codex-native delegation through native subagents, avoiding duplicate direct subagent surfaces. (#83329)
·Codex app-server: recover stale childless Codex-native subagent task mirrors during maintenance and allow their registry rows to be cancelled without an OpenClaw child session. (#82836)
·Feishu: return bound subagent delivery origins from session thread setup so Feishu subagent completions route back to the same DM or topic. (#83190)
·CLI/update: tailor post-update Gateway recovery hints by platform, showing systemd, LaunchAgent, Scheduled Task, or generic service-manager guidance instead of macOS-only recovery text. (#83096)
·Plugins: apply a default 15-second timeout to legacy `before_agent_start` hooks so hung plugin handlers no longer block agent startup. Fixes #48534. (#83136)
·Feishu: refresh inbound session delivery context for DM, group, and broadcast turns so later replies do not inherit stale WebChat routing. Fixes #78274.
·Agents/subagents: require the initial subagent registry save before reporting spawn accepted, returning a spawn error instead of losing an untracked run when the registry write fails. (#83146)
·QA-Lab/qa-channel: attach redacted agent tool-start traces to outbound `QaBusMessage` records so scenarios can assert actual tool use instead of relying only on reply text. Fixes #67637.
·QA-Lab: fail live runtime parity reports when assistant-message usage is missing, preventing `0 vs 0` live token rows from being reported as passing proof. Fixes #80411.
·QA-Lab: add a runtime token-efficiency sidecar report that classifies Codex savings separately from regressions and fails only positive Codex-over-Pi live token deltas above threshold. Fixes #81093.
·QA-Lab: fail Codex-backed OpenAI live runtime-pair runs before launching isolated workers when no portable Codex auth is available, while staging API-key fallbacks and configured Codex keys for isolated QA agents. Fixes #80412.
·QA-Lab: refresh parity gates, mock frontier fixtures, model scenarios, and workflow artifact lanes to compare GPT-5.5 against Claude Opus 4.7. Fixes #74262.
·QA-Lab: make mock parity dispatch provider-aware for source discovery and subagent scenarios so OpenAI and Anthropic lanes no longer share identical canned plans. Fixes #64879.
·QA-Lab: stop returning Control UI bearer tokens from unauthenticated bootstrap payloads and bind Docker harness ports to loopback-only host addresses. (#66355)
·Mac app: avoid a SwiftUI metadata crash when rendering the Cron Jobs settings pane.
·Agents/subagents: preserve run-mode keep subagent registry entries past the session sweep TTL, so kept subagent runs remain visible after cleanup completes. Fixes #83132. (#83168)
·Agents/OpenAI streams: yield via `setTimeout(0)` instead of `setImmediate` between bursty Responses chunks so abort timers can fire during the yield, keeping cancel-on-timeout responsive on hot streams. Refs #82462.
·Agents/Codex: keep legacy `oauthRef`-backed OAuth profiles usable while `openclaw doctor --fix` migrates them back to inline credentials, without creating new sidecar credentials. (#83312)
·Agents/Codex: load the selected provider owner alongside the Codex harness runtime so `openai-codex` models resolve when plugin allowlists scope runtime loading. Fixes #83380. (#83519)
·Telegram: fail stalled isolated-ingress handlers into tombstones and abort same-lane reply work before restarting, so later same-chat updates drain after a hung turn. Fixes #83272. (#83505)
·CLI/config: send SecretRef diagnostics to stderr so JSON command stdout remains parseable.
·CLI/doctor: seed Control UI allowed origins when migrating legacy non-loopback gateway bind host aliases like `0.0.0.0`. Fixes #83286.
·CLI/plugins: ship the bundled memory CLI as a package entry so package-installed `openclaw memory` commands register correctly.
·CLI/update: defer doctor-time plugin package installs during package swaps and seed post-core repair from the updated install registry, preventing duplicate reinstall failures.
·CLI/update: preserve old-parent-readable config metadata during legacy package handoffs, fall back only to official `@openclaw/*` npm plugin packages when ClawHub plugin artifacts are unavailable, and keep managed service package roots authoritative during updates.
·Feishu: detect SecretRef top-level credentials as a configured default account instead of treating object-backed app secrets as missing.
·Gateway/restart: keep ordinary unmanaged SIGUSR1/config restarts in-process instead of detach-spawning an orphaned child, preserving custom supervisor PID tracking while leaving update restarts on the fresh-process path. Fixes #65668.
·CLI/completion: resolve concrete PowerShell profile paths and reload commands during setup and doctor completion installation. Fixes #44296. (#83059)
·Telegram: keep isolated long polling below the hard `getUpdates` request guard so idle bot accounts with high `timeoutSeconds` do not false-disconnect and restart-loop. Fixes #83264.
·Providers/Google: preserve and recover Gemini 3 tool-call thought signatures during native replay so function-calling turns no longer fail with missing `thought_signature` 400s. Fixes #72879. (#80358)
·Telegram: skip transcript-only delivery mirrors and gateway-injected rows when resolving latest assistant text, preventing retained previews from replacing final replies with stale fragments. Fixes #83159. (#83362)
·Memory/QMD: keep lexical search on raw hyphenated queries while normalizing semantic QMD sub-searches, avoiding fallback to the builtin index for dashed identifiers and dates. Fixes #81328.
·Memory-core: distinguish sqlite-vec load failures from missing semantic vector embeddings in degraded `memory index` warnings, so vector recall diagnostics point at unresolved dimensions instead of blaming sqlite-vec when the store is ready. Fixes #75624. (#83056)
·Agents/subagents: preserve sandbox-peer controller ownership while routing completion announcements back to the originating run session, keeping subagent control and completion delivery scoped correctly. Fixes #80201. (#80242)
·Gateway: continue restarting remaining channels when one hot-reload channel restart fails, while still reporting aggregate reload failure and rolling back plugin pre-replace stops. Fixes #83054.
·Gateway/plugins: bind admin HTTP RPC dispatch to the accepting gateway instance so multi-gateway processes cannot execute plugin HTTP control-plane calls against another live gateway. Fixes #83486. (#83487)
·Telegram: keep hot-reload restarts from marking polling accounts manually stopped and restart isolated ingress cleanly after worker shutdown, preserving Telegram replies across config reloads. Fixes #83008. (#83410)
·Telegram/Ollama: pass current Telegram image attachments into native PI/Ollama vision turns so live photo prompts reach Ollama as native images. Fixes #83023. (#83516)
·Gateway/secrets: split the lightweight secrets runtime state and auth-store cache from the full secrets runtime and take a startup fast path when the gateway startup config has no SecretRef values, speeding up secrets startup while preserving cleanup and refresh semantics.
·Codex app-server: rotate oversized native Codex threads before resume and cap dynamic tool-result text entering native Codex sessions, preventing stale oversized context from surviving OpenClaw compaction. (#82981)
·Gateway/restart: drain pending replies and active chat runs during restart shutdown before sockets and channels close, aborting timed-out chat runs through the normal cleanup path. (#69121)
·Agents/Codex: use the Codex runtime context window for OpenAI-model preflight compaction and memory flush checks, so GPT-5.5 Codex sessions compact before hitting the smaller native context limit. Fixes #82982.
·QA-Lab: clean orphaned gateway temp roots when a suite parent exits and wait on gateway plus transport readiness after config restarts, reducing stale `qa-channel` noise from interrupted runs. Fixes #65506.
·QA-Lab: wake qa-bus long polls that arrive with stale future cursors after a bus restart, preserving reconnect readiness for harness clients. (#67142)
·QA-Lab: stage Multipass transfer scripts under OpenClaw's preferred temp root instead of raw OS temp paths, keeping the VM runner inside temp-path guardrails. (#64098)
·Agents/replies: keep surviving reply media and append a warning when other media references fail, so partial media normalization no longer drops failures silently.
·Config/models: accept `thinkingFormat: "together"` in model compat config so Together routes can opt into the Together-specific thinking response shape.
·Plugins/tokenjuice: bump the bundled tokenjuice runtime to 0.7.1, bringing Codex hook approval compatibility, pre-tool command wrapping fixes, and Rolldown/Vitest output compaction improvements into the OpenClaw plugin.
·Agents/OpenAI: stop post-processing GPT-5 final replies with hardcoded brevity caps, preserving full channel responses instead of appending synthetic ellipses, and log when strict-agentic GPT-5 execution activates. Fixes #82910.
·Mac app: refine the Settings General and Connection panes with cleaner status panels, card rows, and a single native titlebar sidebar toggle.
·Agents/media: deliver failed async image, music, and video generation completions directly when requester-session completion handoff fails, so channel users see provider errors instead of silent fallback stalls.
·Browser/CDP: keep loopback proxy bypass active across both `NO_PROXY` casings and redact home-relative Chrome MCP profile paths in attach-failure diagnostics.
·Agents/music: steer song, jingle, beat, anthem, and instrumental requests toward `music_generate` audio creation instead of lyric-only replies, and reserve `lyrics` for exact sung words.
·Codex app-server: record native Codex tool calls and results into trajectory artifacts so debug/trajectory exports capture the full Codex-native tool history, not just OpenClaw-bridged turns.
·Codex/app-server: keep bound conversation sessions on the owning agent runtime so native Codex control and follow-up turns do not fall back to the default agent client. Fixes #82954. (#82993)
·CLI/infer: run gateway model probes in fresh explicit sessions so one-shot provider checks do not inherit default agent transcript state. (#82861)
·Providers/Together: send video-generation requests to Together's v2 video API even when shared text-model config still points at the v1 base URL. (#82992)
·Browser CLI: preserve browser-level options on nested commands, skip option values during lazy command registration, and keep long-running wait/download/dialog hooks open for their advertised wait window.
·CLI/sessions: accept `openclaw sessions list` as an alias for `openclaw sessions`, matching other list-style commands. Fixes #81139. (#81163)
·Channels/stream previews: widen compact progress draft lines and cut prose at word boundaries while preserving command/path suffixes, with `streaming.progress.maxLineChars` for channel-specific tuning.
·CLI/plugins: have `openclaw plugins doctor` warn when a configured runtime needs a missing owner plugin, sharing the same install mapping as `openclaw doctor --fix`. Fixes #81326. (#81674)
·Agents/Codex: route OpenAI runs that resolve to `openai-codex` through the Codex provider and bootstrap OpenClaw's stored OAuth profile into the Codex harness when the harness owns transport, so `openai/*` model refs no longer fail with `No API key found for openai-codex` despite an existing Codex OAuth profile. (#82864)
·Agents/ACP: distinguish prompt-submitted and runtime-active child stalls from true interactive waits, including redacted proxy-env diagnostics for Codex ACP no-output runs. Fixes #44810.
·Agents/memory: explain that memory-triggered compaction exposes only `read` and append-only `write` when configured core tools are unavailable in `tools.allow` warnings. Fixes #82941.
·Agents/OpenAI: preserve deterministic tool payload ordering for prompt-cache reuse across OpenAI Responses and chat completions calls. (#82940)
·ACP/Codex: honor terminal ACP turn results so failed Codex/acpx runs are not recorded as successful after only progress text. Fixes #79522.
·Telegram: warn when a media group drops photos that fail to download, including albums where every photo is skipped. Fixes #55216. (#82987)
·Agents/skills: apply the full effective tool policy pipeline to inline `command-dispatch: tool` skill dispatch before owner-only filtering, preserving configured allow, deny, sandbox, sender, group, and subagent restrictions. (#78525)
·Codex: avoid spawning native hook relay subprocesses for post-tool/finalize events with no registered hook handlers while preserving pre-tool safety and approval relays. Fixes #76552. (#78004)
·Channel accounts: keep top-level default channel accounts visible when named accounts are added alongside default credential material, so mixed legacy/new account configs keep resolving `default` instead of silently dropping it.
·Agents/CLI: reject empty successful CLI subprocess replies as `empty_response` and keep them out of shared auth-profile health, so blank Claude CLI results no longer become green no-payload turns. Fixes #83231. (#83421)
·Codex/Telegram: synthesize native Codex tool progress from final turn snapshots so Telegram `/verbose` stays visible when command events arrive only at completion.
·Codex/Telegram: deliver Codex verbose tool summaries in direct message-tool-only turns while suppressing message-send and activity-log noise. (#83186)
·Mac app: make Channels settings open faster by deferring config-schema work, avoiding startup channel probes, caching decoded channel status rows, and showing only compact quick settings instead of the full generated channel schema.
·Control UI: include the Control UI and Gateway protocol versions in protocol-mismatch errors so stale app/dashboard pairings identify which side needs rebuilding or restarting.
·Gateway/protocol: restore Gateway WS protocol v4 and keep `message.action` room-event metadata on the existing `inboundTurnKind` wire field while preserving internal inbound-event classification.
·Agents/tools: prefer non-webchat session-key routes when the message tool has stale webchat context, so message-tool-only replies keep delivering to the originating channel. Fixes #82911. (#83004)
·Channels: keep direct-message last-route writes on isolated `per-channel-peer` sessions instead of contaminating the agent main session with channel delivery context. Fixes #36614.
·Mac app: move the Settings sidebar toggle into the native titlebar and tighten the General pane width.
·Mac app: keep visited Settings panes mounted so switching tabs no longer blanks and reloads their content.
·Mac app: make Config settings open from shallow schema lookups and load selected paths on demand instead of fetching and rendering the full generated config schema up front.
·Codex: sanitize inline image payloads before Codex app-server and OpenAI Responses replay, and clear poisoned Codex thread bindings after invalid image errors. Fixes #82878.
·Providers/GitHub Copilot: request identity-encoded Copilot API responses across token exchange, catalog, model calls, usage, and embeddings so compressed Business-account error payloads no longer reach JSON parsers as gzip bytes. Fixes #82871.
·Telegram: redact nested raw-update identifiers and user metadata before verbose raw update logging, preserving useful update/message ids without exposing chat, user, command, or profile details. (#82945)
·Telegram: preserve replied-to bot messages, captions, and media metadata in group reply chains so follow-up replies understand what the user is reacting to. (#82863)
·Providers/Together: update PI runtime packages to 0.74.1 and emit Together-style `reasoning.enabled`/`max_tokens` controls for reasoning-capable OpenAI-completions models.
·Agents/diagnostics: split slow embedded-run `attempt-dispatch` startup summaries into workspace, prompt, runtime-plan, and final dispatch subspans so traces identify the delayed setup phase. Fixes #82782. (#82783)
·Agents/Codex: flatten nested tool-result middleware blocks into bounded text so successful message sends are no longer replaced with `Tool output unavailable due to post-processing error`. Fixes #82912.
·CLI/media: accept HTTP(S) URLs in `openclaw infer image describe --file`, fetching remote images through the guarded media path instead of treating URLs as local files. Fixes #82837. (#82854)
·Agents/subagents: keep session-backed parent runs active when the child wait call times out before the child session has actually settled, so late subagent completions are reconciled instead of being lost. Fixes #82787.
·Control UI: advertise shared Gateway protocol constants in browser connect frames, fixing protocol mismatch handshakes after protocol constant drift. Fixes #82882.
·Gateway: add rollback protocol-mismatch diagnostics, including client protocol ranges in Gateway logs and deep status/doctor hints for stale client processes. Fixes #82841. (#82908)
·Agents/subagents: keep successful keep-mode completion payloads pending after final-delivery retry exhaustion, so requester recovery no longer loses final subagent results. Fixes #82583. (#82999)
·Gateway/auth: allow same-host trusted-proxy callers to use the documented local direct `gateway.auth.password` fallback after revisiting the #78684 fail-closed policy, while keeping token fallback rejected and forwarded-header requests on the trusted-proxy path. Fixes #82607. (#82953)
·Agents/subagents: wait for queued completion handoffs to reach the parent transcript before marking them announced, preventing busy parent runs from cleaning up before observing child results. Fixes #82913. (#83039)
·Agents/subagents: route group/channel subagent completions through message-tool-only handoffs when required and keep active-requester wake failures from dropping completion delivery. Fixes #82803.
·Memory-core: scan persisted memory source sessions on startup, comparing on-disk transcripts against the index and marking only missing/newer/resized files dirty for incremental sync. Fixes #82341. (#82341)
·Telegram: keep the top-level default account in the account list when named accounts or bindings are added alongside top-level credentials, preserving default polling while still letting named-only configs resolve to a single account. Fixes #82794. (#82794)
·CLI/models: reuse command-scoped plugin metadata across model listing, provider catalog, auth, and synthetic-auth checks, restoring fast `openclaw models` runs for plugin-heavy installs. Fixes #82881. (#83033)
·CLI/channels: show configured official external channels such as Discord in `openclaw channels list` when their plugin package is missing, including the install and doctor repair command instead of reporting no configured channels. Fixes #82813.
·Signal: preserve mixed-case group IDs through routing and session persistence so group auto-replies keep delivering after updates. Fixes #82827.
·Agents/tools: keep the `message` tool available in embedded runs when it is explicitly allowed through `tools.alsoAllow` or runtime tool allowlists, so channel plugins with custom reply delivery can still use configured message sends. Fixes #82833.
·WhatsApp: honor forced document delivery for outbound image, GIF, and video media so `forceDocument`/`asDocument` sends preserve original media bytes instead of using compressed media payloads. (#79272)
·WhatsApp: name outbound document attachments from their MIME type when no filename is provided, so PDF and CSV sends arrive as `file.pdf` and `file.csv` instead of an extensionless `file`.
·Process/diagnostics: report active lane blockers in lane wait warnings so `queueAhead=0` no longer hides commands waiting behind active work. Fixes #82791. (#82792)
·Process/diagnostics: stop counting the active processing turn as queued backlog in liveness warnings so transient max-only event-loop spikes do not surface as gateway warnings.
·Agents/replies: classify provider conversation-state rejections and return a clear message-channel error instead of auto-resetting or falling back to a generic runner failure. (#82616)
·Browser plugin: trust managed Chrome CDP diagnostics when launch HTTP probes race cold-start readiness, avoiding false startup failures. Fixes #82904. (#82986)
·Android: prompt before replacing a changed Gateway TLS thumbprint, showing the old and new SHA-256 fingerprints so users can accept expected certificate rotations instead of hard failing on pin mismatch. (#83077)
·CLI/status: render extra gateway-like service diagnostics as warning/info output instead of error output. Fixes #46930. (#82922)
·Agents/failover: classify Moonshot/Kimi exhausted-balance HTTP 429 payloads as billing instead of generic rate limits, preserving billing guidance and fallback behavior. Fixes #43447. (#83079)
·Plugin SDK: bundle `openclaw/plugin-sdk/zod` into the published package artifact and verify the packed zod subpath stays self-contained, so pnpm global installs can register plugins without a package-local `zod` symlink. Fixes #78398. (#78515)
·Providers/Google: drop compaction-truncated Gemini thought signatures before replay so malformed Base64 no longer aborts the next assistant turn. (#82995)
·Gateway/mobile: allow paired iOS and Android clients to refresh same-family OS metadata on authenticated reconnect instead of requiring a new approval. (#83490)
·WhatsApp: treat `upload-file` as a supported media send intent by lowering path/URL uploads through the channel's normal send-media transport. (#81883)
·iOS: end Live Activities when OpenClaw is connected, idle, or disconnected, and show compact attention states for approval-required reconnects. (#83597)
·Control UI: hide child nav items when collapsing the active sidebar group. Fixes #42167. (#42223)
·CI/proof: skip the real-behavior-proof gate for private org maintainers by minting a least-privilege (`members: read`) GitHub App token and checking active membership in the `maintainer` team, instead of treating `author_association=CONTRIBUTOR` as definitively external. (#83418)

v2026.5.182026-05-18

openclaw 2026.5.18

GitHub ↗

Consolidated Since 2026.5.12

·Control UI and Mac app: faster Settings, cleaner chat/session controls, responsive logs, remote gateway setup, native Dashboard, improved pairing sheets, and more stable protocol negotiation.
·Realtime, voice, and mobile: Android Talk Mode moves to realtime Gateway relay voice sessions; Discord/OpenAI realtime follow-ups keep hearing turns; iOS/Mac permission, chat, and settings flows were polished.
·Telegram and Discord reliability: isolated Telegram polling/topic lanes, media/forum-topic delivery, `/stop` and `/btw` handling, progress drafts, final reply recovery, and Discord progress/final-message delivery were tightened.
·Codex/OpenAI runtime: app-server context projection, MCP projection, native tool progress, code-mode/network handling, OAuth fallback, stale-thread recovery, and transcript/trajectory fidelity were improved.
·Agents and subagents: queued follow-ups, manual-turn priority, subagent completion handoffs, session locks, context usage, fallback diagnostics, and final payload delivery were made more predictable.
·Plugins and SDK: typed tool-plugin helpers, plugin RPC metadata, install/update repair, externalized plugin recovery, manifest validation, and SDK packaging were hardened.
·Models/providers: xAI OAuth and media fixes, Anthropic/Claude CLI routing, OpenRouter/OpenAI-compatible reasoning replay, Gemini thought signatures, Ollama/Qwen/Together/Xiaomi/Copilot fixes, and local/custom provider guardrails landed.
·Gateway and update path: startup tracing, restart readiness, update-check deferral, service recovery hints, package-swap doctor repair, npm freshness bypasses, and Docker/package validation were improved.
·QA and release validation: personal-agent packs, Codex-vs-Pi parity, runtime tool coverage, Docker/package install/update lanes, and release evidence gates were expanded.
·Security and robustness: audit suppressions, gateway auth/log redaction, malformed JSON/base64/URL handling, SSRF/private-network guardrails, exec approval realpath binding, and Docker non-loopback fail-closed behavior were tightened.

Detailed 2026.5.18 Changes

·Agents: clarify that fixes should default to clean bounded refactors, lean internals, and explicit plugin SDK/API deprecation paths.
·Dependencies: update `@openclaw/proxyline` to 0.3.3.
·Dependencies: update Pi packages to 0.75.1 and raise the minimum supported Node.js 22 line to 22.19.
·Docker/Podman: add `OPENCLAW_IMAGE_APT_PACKAGES` as the runtime-neutral image build arg for extra apt packages while keeping `OPENCLAW_DOCKER_APT_PACKAGES` as a legacy fallback. (#62431)
·Gateway/ACPX: attribute startup probe, config, runtime, and resource-count costs in restart traces without changing readiness behavior. (#83300)
·Gateway: overlap startup logging and plugin-service startup with channel sidecars to reduce restart ready latency while preserving `/readyz` sidecar gating. (#83301)
·Plugins/admin-http-rpc: allow trusted admin HTTP RPC clients to start and wait for web QR login flows. (#83259)
·Mac app: redesign Settings pages with consistent card layouts, cached navigation, cleaner permissions/voice/skills/cron/exec/debug panes, and steadier spacing around the native sidebar.
·Skills: rename the repo-local Codex closeout review skill and helper to `autoreview` while preserving the Codex-first fallback behavior.
·Skills: add a meme-maker skill for curated template search, local SVG/PNG rendering, Imgflip hosted rendering, and Know Your Meme provenance links.
·Browser: surface pending and recently handled modal dialogs in snapshots, return `blockedByDialog` when an action opens a modal, and allow `browser dialog --dialog-id` to answer pending dialogs.
·Agents/tools: shorten built-in tool descriptions and schema hints across media, messaging, sessions, cron, Gateway, web, image/PDF, TTS, nodes, and plan tools while preserving routing guardrails.
·Skills: add node inspector debugging, fused diagram generation, and throwaway spike workflow skills.
·CLI/plugins: add `defineToolPlugin` plus `openclaw plugins build`, `validate`, and `init` for typed simple tool plugins with generated manifest metadata, optional tool declarations, and context factories.
·Agents/skills: tighten bundled skill prompts and metadata, quote skill descriptions, refresh current CLI/API guidance, and update embedded sherpa-onnx runtime downloads.
·Skills: update the Obsidian skill to target the official `obsidian` CLI and require its registered binary instead of the third-party `obsidian-cli`.
·Skills: add a Python debugging skill for pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.
·Plugins/messages: add presentation capability limits for channel renderers, adapt rich message controls before native rendering, and mark legacy `interactive`/Slack directive producer APIs as deprecated.
·Proxy: support HTTPS managed forward-proxy endpoints and scoped `proxy.tls.caFile` CA trust for proxy endpoint TLS. (#79171)
·QA-Lab: add first-hour 20-turn and optional 100-turn runtime parity scenarios, with tier metadata for standard and soak QA gates. Fixes #80338; refs #80337.
·QA-Lab: add `openclaw qa suite --runtime-parity-tier` and wire the standard Codex-vs-Pi tier into release checks separately from optional/live-only/soak lanes. Fixes #80337.
·QA-Lab: add a live-only Codex Pi-shaped Read vocabulary canary so runtime parity catches native workspace-read prompt compatibility drift. (#80323)
·QA-Lab: add live-only harness self-health scenarios for plugin hook crashes, manifest contract errors, and WebChat direct-reply self-message routing. (#80323)
·QA-Lab: add runtime tool fixture scenarios and coverage reporting for Codex-native workspace tools, OpenClaw dynamic tools, and optional plugin-backed tools. Fixes #80173.
·QA-Lab: expose runtime tool fixture coverage through `openclaw qa coverage --tools`, with optional suite-summary evaluation for parity gate artifacts.
·QA-Lab: schedule a live-frontier Codex-vs-Pi runtime token-efficiency artifact lane in the all-lanes QA workflow. Fixes #80175.
·QA-Lab: hard-gate required OpenClaw dynamic runtime-tool drift in the standard Codex-vs-Pi tier with a blocking release-check verifier and publish the tool coverage report artifact. Fixes #80339; refs #80319.
·QA-Lab: add the personal-agent approval-denial scenario so the benchmark pack verifies denied local reads stop cleanly without tool progress or fixture leaks. (#83150)
·QA-Lab: extend the personal-agent benchmark pack with a local task followthrough scenario for proof-backed pending, blocked, and done status reporting.
·Gateway/performance: add `pnpm test:restart:gateway` benchmark tooling for repeated restart readiness, downtime, trace, and resource-slope evidence. (#83299)
·Android: switch Talk Mode to realtime Gateway relay voice sessions with streaming mic input, realtime audio playback, tool-result bridging, and on-screen transcripts. (#83130)
·Discord/OpenAI: keep realtime Discord voice sessions hearing follow-up turns with OpenAI realtime and prebuffer assistant playback to avoid choppy starts. (#80505)
·Media: prevent image metadata probing from invoking external decoder delegates on unrecognized image bytes, and stop fallback chaining after real processing errors.
·Media: install Sharp with the root package and fall back to sips, Windows native imaging, ImageMagick, GraphicsMagick, or ffmpeg for image resizing/conversion when Sharp is unavailable. Fixes #83401.
·Telegram: deliver generated media completions back into forum topics by preserving topic IDs across requester-agent handoff. (#83556)
·Gateway: defer update-check startup until after readiness so package update checks no longer block sidecar-ready startup, while preserving update broadcasts and shutdown cleanup. (#83520)
·Telegram: keep `/btw` and read-only status commands from aborting active runs, and avoid retaining raw update payloads in timed-out spool tombstones. Refs #83272.
·Agents/video: hide `video_generate` reference-audio parameters unless a registered video provider supports audio inputs.
·Plugins/xAI: echo PKCE challenge fields during OAuth authorization-code token exchange for xAI token-endpoint compatibility. (#83499)
·Codex app-server: hydrate current inbound image attachments before queued runs so Responses-backed agents receive Discord and other channel images as native vision input. Fixes #83466.
·Codex app-server: keep native code mode available without forcing code-mode-only so OpenClaw dynamic tool turns complete through the app-server tool bridge. Fixes #83109.
·Release stability: recover stale session diagnostics and Codex OAuth fallback state so stuck runs and reused refresh tokens clear without blocking follow-up work. (#83503)
·Messages/TTS: apply TTS directives before message-tool sends reach core, gateway, or plugin delivery so opt-in message-tool rooms and proactive sends attach voice notes instead of leaking raw tags. Fixes #81598.
·Codex app-server: preserve network access for sandboxed Codex code-mode turns when the OpenClaw sandbox allows outbound egress. Fixes #83347.
·QA-Lab: keep the OTLP smoke decoder independent of removed OpenTelemetry generated-root internals.
·Messages: default group/channel visible replies to automatic final delivery again, keeping `message_tool` opt-in for ambient/shared rooms and tool-reliable models.
·CLI/TUI: force standalone `/exit` runs to terminate after `runTui` returns so onboarding-launched TUI children do not stay alive invisibly. (#83501)
·Agents/code mode: honor per-agent code-mode config in schema, runtime catalog activation, and model payload filtering. Fixes #83388.
·Agents/code mode: preserve agent, session, run, and channel context in `before_tool_call` hooks for top-level `exec`/`wait` dispatches. Fixes #83387.
·QQBot: shorten C2C typing indicators to a 10-second window renewed every 5 seconds, capped to keep a final passive-reply slot available. (#83469)
·Replies: keep final payload delivery after live preview updates so channels can finalize or send the completed answer instead of losing preview-only drafts. (#83468)
·Discord: deliver final replies in progress-mode preview streams instead of deduplicating the final visible message. (#83443)
·Providers/Xiaomi: replay MiMo Anthropic-compatible `reasoning_content` as provider-required thinking blocks even when OpenClaw thinking is disabled, fixing follow-up tool turns for `mimo-v2-flash`. Fixes #83407.
·Agents/exec approvals: forward approval-runtime credentials on agent-owned Gateway approval calls so approved async commands complete through the existing runtime path instead of stalling on unauthenticated follow-up calls.
·Gateway/skills: preflight remote macOS skill-bin refreshes with a WebSocket connectivity check so stale node sessions skip quickly instead of logging slow `system.which` timeout warnings.
·CLI/config: keep broken discovered plugins that are not referenced by active config from failing `openclaw config validate`, while preserving fatal errors for explicitly configured plugin entries.
·GitHub Copilot: drop unsafe native Responses reasoning replay items with non-replayable IDs before dispatch, preventing affected Copilot sessions from failing with `invalid_request_body`. Fixes #83220.
·Agents/Codex: fail closed when an explicitly requested Codex harness is not registered instead of silently trying configured model fallbacks. Fixes #83349.
·QA-Lab: make runtime tool coverage fail on missing required tool exercise instead of treating pass/pass parity envelope drift as missing coverage.
·Core/plugins: harden clawpatch-reported edge cases across gateway auth cleanup, Claude session id paths, plugin activation policy, apply-patch hunk handling, diagnostic redaction, and plugin metadata validation.
·UI: show reasoning choices as plain labels instead of leaking internal override wording in session and chat pickers.
·Mac app: avoid repeating the Configuration heading inside channel quick settings.
·Mac app: keep the Settings sidebar always visible and remove the redundant titlebar hide/show control.
·Mac app: prefer explicit private/Tailscale/LAN Gateway endpoints over SSH tunnels, preserve legacy loopback tunnel configs, persist transport choices, and show captured SSH stderr when tunneling really fails.
·Gateway/sessions: keep ACP/acpx and runtime child sessions visible in configured-only session lists when their owner or parent session belongs to a configured agent.
·Mac app: keep app-level menu commands and Dashboard failure states reachable when the remote Gateway is disconnected.
·Mac app: allow longer Gateway and Context errors to wrap in the menu instead of truncating the useful failure detail.
·Mac app: tighten remote Gateway fields in Settings so the Connection pane keeps readable labels and full action button text.
·Mac app: keep custom Settings card rows left-aligned and full-width so Discovery and status sections no longer appear centered or detached.
·Mac app: align Location permission controls to the same trailing column as the rest of Settings.
·Mac app: add Dashboard, Chat, Canvas, and Settings shortcuts to the Dock icon menu.
·Mac app: replace the Settings window's native split-view sidebar with an explicit layout so page content keeps its leading gutter when the sidebar is shown or hidden.
·Mac app: render channel quick config as aligned Settings rows and hide schema-only variants that cannot be edited safely from the quick pane.
·Gateway/webchat: hide internal runtime-context and other `display: false` transcript messages from Chat history and live message events. Fixes #83216.
·CLI/help: keep `gateway`, `doctor`, `status`, and `health` help registration out of action/runtime imports so subcommand `--help` stays lightweight in constrained terminals. Fixes #83228.
·Cron/Discord: keep explicit announce runs in message-tool-only source-reply mode so scheduled agent turns post once instead of also echoing through automatic visible replies. Fixes #83261.
·Telegram: preserve forum-topic origin targets in inbound, audio-preflight, and skipped-message hook contexts so follow-up delivery stays bound to the originating topic. Fixes #83302.
·Telegram: retry HTTP 421 Misdirected Request send failures on a fresh fallback transport so transient edge-node routing errors no longer drop outbound replies. Fixes #48892. (#48908)
·Telegram: fail topic sends closed when Telegram reports `message thread not found` instead of retrying without `message_thread_id` into the base chat. Refs #83302.
·Config/subagents: remove ignored agent-model `timeoutMs` keys, keep subagent model config to primary/fallback selection, and clean shipped stale config through doctor. Fixes #83291.
·Mac app: align the Sessions settings pane with the standard Settings page gutter and row spacing.
·OpenAI/Codex: stop rejecting available `openai-codex` GPT-5.1, GPT-5.2, and GPT-5.3 model refs during config validation, while keeping removed Spark aliases suppressed. Fixes #83303.
·Plugins/xAI: complete OAuth-backed xAI login and sidecar auth fixes, including guarded loopback callback CORS handling, video generation polling/defaults, and native-host User-Agent attribution. (#83322)
·Codex app-server: preserve streamed native command output in mirrored transcripts and trajectory exports when final snapshots omit aggregated output. (#83200)
·Codex app-server: fail closed when chat or sender policy denies tools, disabling native code, app, environment, and user MCP surfaces for restricted turns. (#82374)
·Codex app-server: keep recent context-engine messages when oversized projected history is truncated, so short follow-ups in long channel sessions do not fall back to stale earlier turns. (#83127)
·Codex app-server: keep OpenClaw session spawning searchable while steering Codex-native delegation through native subagents, avoiding duplicate direct subagent surfaces. (#83329)
·Codex app-server: recover stale childless Codex-native subagent task mirrors during maintenance and allow their registry rows to be cancelled without an OpenClaw child session. (#82836)
·Feishu: return bound subagent delivery origins from session thread setup so Feishu subagent completions route back to the same DM or topic. (#83190)
·CLI/update: tailor post-update Gateway recovery hints by platform, showing systemd, LaunchAgent, Scheduled Task, or generic service-manager guidance instead of macOS-only recovery text. (#83096)
·Plugins: apply a default 15-second timeout to legacy `before_agent_start` hooks so hung plugin handlers no longer block agent startup. Fixes #48534. (#83136)
·Feishu: refresh inbound session delivery context for DM, group, and broadcast turns so later replies do not inherit stale WebChat routing. Fixes #78274.
·Agents/subagents: require the initial subagent registry save before reporting spawn accepted, returning a spawn error instead of losing an untracked run when the registry write fails. (#83146)
·QA-Lab/qa-channel: attach redacted agent tool-start traces to outbound `QaBusMessage` records so scenarios can assert actual tool use instead of relying only on reply text. Fixes #67637.
·QA-Lab: fail live runtime parity reports when assistant-message usage is missing, preventing `0 vs 0` live token rows from being reported as passing proof. Fixes #80411.
·QA-Lab: add a runtime token-efficiency sidecar report that classifies Codex savings separately from regressions and fails only positive Codex-over-Pi live token deltas above threshold. Fixes #81093.
·QA-Lab: fail Codex-backed OpenAI live runtime-pair runs before launching isolated workers when no portable Codex auth is available, while staging API-key fallbacks and configured Codex keys for isolated QA agents. Fixes #80412.
·QA-Lab: refresh parity gates, mock frontier fixtures, model scenarios, and workflow artifact lanes to compare GPT-5.5 against Claude Opus 4.7. Fixes #74262.
·QA-Lab: make mock parity dispatch provider-aware for source discovery and subagent scenarios so OpenAI and Anthropic lanes no longer share identical canned plans. Fixes #64879.
·QA-Lab: stop returning Control UI bearer tokens from unauthenticated bootstrap payloads and bind Docker harness ports to loopback-only host addresses. (#66355)
·Mac app: avoid a SwiftUI metadata crash when rendering the Cron Jobs settings pane.
·Agents/subagents: preserve run-mode keep subagent registry entries past the session sweep TTL, so kept subagent runs remain visible after cleanup completes. Fixes #83132. (#83168)
·Agents/OpenAI streams: yield via `setTimeout(0)` instead of `setImmediate` between bursty Responses chunks so abort timers can fire during the yield, keeping cancel-on-timeout responsive on hot streams. Refs #82462.
·Agents/Codex: keep legacy `oauthRef`-backed OAuth profiles usable while `openclaw doctor --fix` migrates them back to inline credentials, without creating new sidecar credentials. (#83312)
·Agents/Codex: load the selected provider owner alongside the Codex harness runtime so `openai-codex` models resolve when plugin allowlists scope runtime loading. Fixes #83380. (#83519)
·Telegram: fail stalled isolated-ingress handlers into tombstones and abort same-lane reply work before restarting, so later same-chat updates drain after a hung turn. Fixes #83272. (#83505)
·CLI/config: send SecretRef diagnostics to stderr so JSON command stdout remains parseable.
·CLI/doctor: seed Control UI allowed origins when migrating legacy non-loopback gateway bind host aliases like `0.0.0.0`. Fixes #83286.
·CLI/plugins: ship the bundled memory CLI as a package entry so package-installed `openclaw memory` commands register correctly.
·CLI/update: defer doctor-time plugin package installs during package swaps and seed post-core repair from the updated install registry, preventing duplicate reinstall failures.
·CLI/update: preserve old-parent-readable config metadata during legacy package handoffs, fall back only to official `@openclaw/*` npm plugin packages when ClawHub plugin artifacts are unavailable, and keep managed service package roots authoritative during updates.
·Feishu: detect SecretRef top-level credentials as a configured default account instead of treating object-backed app secrets as missing.
·Gateway/restart: keep ordinary unmanaged SIGUSR1/config restarts in-process instead of detach-spawning an orphaned child, preserving custom supervisor PID tracking while leaving update restarts on the fresh-process path. Fixes #65668.
·CLI/completion: resolve concrete PowerShell profile paths and reload commands during setup and doctor completion installation. Fixes #44296. (#83059)
·Telegram: keep isolated long polling below the hard `getUpdates` request guard so idle bot accounts with high `timeoutSeconds` do not false-disconnect and restart-loop. Fixes #83264.
·Providers/Google: preserve and recover Gemini 3 tool-call thought signatures during native replay so function-calling turns no longer fail with missing `thought_signature` 400s. Fixes #72879. (#80358)
·Telegram: skip transcript-only delivery mirrors and gateway-injected rows when resolving latest assistant text, preventing retained previews from replacing final replies with stale fragments. Fixes #83159. (#83362)
·Memory/QMD: keep lexical search on raw hyphenated queries while normalizing semantic QMD sub-searches, avoiding fallback to the builtin index for dashed identifiers and dates. Fixes #81328.
·Memory-core: distinguish sqlite-vec load failures from missing semantic vector embeddings in degraded `memory index` warnings, so vector recall diagnostics point at unresolved dimensions instead of blaming sqlite-vec when the store is ready. Fixes #75624. (#83056)
·Agents/subagents: preserve sandbox-peer controller ownership while routing completion announcements back to the originating run session, keeping subagent control and completion delivery scoped correctly. Fixes #80201. (#80242)
·Gateway: continue restarting remaining channels when one hot-reload channel restart fails, while still reporting aggregate reload failure and rolling back plugin pre-replace stops. Fixes #83054.
·Telegram: keep hot-reload restarts from marking polling accounts manually stopped and restart isolated ingress cleanly after worker shutdown, preserving Telegram replies across config reloads. Fixes #83008. (#83410)
·Telegram/Ollama: pass current Telegram image attachments into native PI/Ollama vision turns so live photo prompts reach Ollama as native images. Fixes #83023. (#83516)
·Gateway/secrets: split the lightweight secrets runtime state and auth-store cache from the full secrets runtime and take a startup fast path when the gateway startup config has no SecretRef values, speeding up secrets startup while preserving cleanup and refresh semantics.
·Codex app-server: rotate oversized native Codex threads before resume and cap dynamic tool-result text entering native Codex sessions, preventing stale oversized context from surviving OpenClaw compaction. (#82981)
·Gateway/restart: drain pending replies and active chat runs during restart shutdown before sockets and channels close, aborting timed-out chat runs through the normal cleanup path. (#69121)
·Agents/Codex: use the Codex runtime context window for OpenAI-model preflight compaction and memory flush checks, so GPT-5.5 Codex sessions compact before hitting the smaller native context limit. Fixes #82982.
·QA-Lab: clean orphaned gateway temp roots when a suite parent exits and wait on gateway plus transport readiness after config restarts, reducing stale `qa-channel` noise from interrupted runs. Fixes #65506.
·QA-Lab: wake qa-bus long polls that arrive with stale future cursors after a bus restart, preserving reconnect readiness for harness clients. (#67142)
·QA-Lab: stage Multipass transfer scripts under OpenClaw's preferred temp root instead of raw OS temp paths, keeping the VM runner inside temp-path guardrails. (#64098)
·Agents/replies: keep surviving reply media and append a warning when other media references fail, so partial media normalization no longer drops failures silently.
·Config/models: accept `thinkingFormat: "together"` in model compat config so Together routes can opt into the Together-specific thinking response shape.
·Plugins/tokenjuice: bump the bundled tokenjuice runtime to 0.7.1, bringing Codex hook approval compatibility, pre-tool command wrapping fixes, and Rolldown/Vitest output compaction improvements into the OpenClaw plugin.
·Agents/OpenAI: stop post-processing GPT-5 final replies with hardcoded brevity caps, preserving full channel responses instead of appending synthetic ellipses, and log when strict-agentic GPT-5 execution activates. Fixes #82910.
·Mac app: refine the Settings General and Connection panes with cleaner status panels, card rows, and a single native titlebar sidebar toggle.
·Agents/media: deliver failed async image, music, and video generation completions directly when requester-session completion handoff fails, so channel users see provider errors instead of silent fallback stalls.
·Browser/CDP: keep loopback proxy bypass active across both `NO_PROXY` casings and redact home-relative Chrome MCP profile paths in attach-failure diagnostics.
·Agents/music: steer song, jingle, beat, anthem, and instrumental requests toward `music_generate` audio creation instead of lyric-only replies, and reserve `lyrics` for exact sung words.
·Codex app-server: record native Codex tool calls and results into trajectory artifacts so debug/trajectory exports capture the full Codex-native tool history, not just OpenClaw-bridged turns.
·Codex/app-server: keep bound conversation sessions on the owning agent runtime so native Codex control and follow-up turns do not fall back to the default agent client. Fixes #82954. (#82993)
·CLI/infer: run gateway model probes in fresh explicit sessions so one-shot provider checks do not inherit default agent transcript state. (#82861)
·Providers/Together: send video-generation requests to Together's v2 video API even when shared text-model config still points at the v1 base URL. (#82992)
·Browser CLI: preserve browser-level options on nested commands, skip option values during lazy command registration, and keep long-running wait/download/dialog hooks open for their advertised wait window.
·CLI/sessions: accept `openclaw sessions list` as an alias for `openclaw sessions`, matching other list-style commands. Fixes #81139. (#81163)
·Channels/stream previews: widen compact progress draft lines and cut prose at word boundaries while preserving command/path suffixes, with `streaming.progress.maxLineChars` for channel-specific tuning.
·CLI/plugins: have `openclaw plugins doctor` warn when a configured runtime needs a missing owner plugin, sharing the same install mapping as `openclaw doctor --fix`. Fixes #81326. (#81674)
·Agents/Codex: route OpenAI runs that resolve to `openai-codex` through the Codex provider and bootstrap OpenClaw's stored OAuth profile into the Codex harness when the harness owns transport, so `openai/*` model refs no longer fail with `No API key found for openai-codex` despite an existing Codex OAuth profile. (#82864)
·Agents/ACP: distinguish prompt-submitted and runtime-active child stalls from true interactive waits, including redacted proxy-env diagnostics for Codex ACP no-output runs. Fixes #44810.
·Agents/memory: explain that memory-triggered compaction exposes only `read` and append-only `write` when configured core tools are unavailable in `tools.allow` warnings. Fixes #82941.
·Agents/OpenAI: preserve deterministic tool payload ordering for prompt-cache reuse across OpenAI Responses and chat completions calls. (#82940)
·ACP/Codex: honor terminal ACP turn results so failed Codex/acpx runs are not recorded as successful after only progress text. Fixes #79522.
·Telegram: warn when a media group drops photos that fail to download, including albums where every photo is skipped. Fixes #55216. (#82987)
·Agents/skills: apply the full effective tool policy pipeline to inline `command-dispatch: tool` skill dispatch before owner-only filtering, preserving configured allow, deny, sandbox, sender, group, and subagent restrictions. (#78525)
·Codex: avoid spawning native hook relay subprocesses for post-tool/finalize events with no registered hook handlers while preserving pre-tool safety and approval relays. Fixes #76552. (#78004)
·Channel accounts: keep top-level default channel accounts visible when named accounts are added alongside default credential material, so mixed legacy/new account configs keep resolving `default` instead of silently dropping it.
·Agents/CLI: reject empty successful CLI subprocess replies as `empty_response` and keep them out of shared auth-profile health, so blank Claude CLI results no longer become green no-payload turns. Fixes #83231. (#83421)
·Codex/Telegram: synthesize native Codex tool progress from final turn snapshots so Telegram `/verbose` stays visible when command events arrive only at completion.
·Codex/Telegram: deliver Codex verbose tool summaries in direct message-tool-only turns while suppressing message-send and activity-log noise. (#83186)
·Mac app: make Channels settings open faster by deferring config-schema work, avoiding startup channel probes, caching decoded channel status rows, and showing only compact quick settings instead of the full generated channel schema.
·Control UI: include the Control UI and Gateway protocol versions in protocol-mismatch errors so stale app/dashboard pairings identify which side needs rebuilding or restarting.
·Gateway/protocol: restore Gateway WS protocol v4 and keep `message.action` room-event metadata on the existing `inboundTurnKind` wire field while preserving internal inbound-event classification.
·Agents/tools: prefer non-webchat session-key routes when the message tool has stale webchat context, so message-tool-only replies keep delivering to the originating channel. Fixes #82911. (#83004)
·Channels: keep direct-message last-route writes on isolated `per-channel-peer` sessions instead of contaminating the agent main session with channel delivery context. Fixes #36614.
·Mac app: move the Settings sidebar toggle into the native titlebar and tighten the General pane width.
·Mac app: keep visited Settings panes mounted so switching tabs no longer blanks and reloads their content.
·Mac app: make Config settings open from shallow schema lookups and load selected paths on demand instead of fetching and rendering the full generated config schema up front.
·Codex: sanitize inline image payloads before Codex app-server and OpenAI Responses replay, and clear poisoned Codex thread bindings after invalid image errors. Fixes #82878.
·Providers/GitHub Copilot: request identity-encoded Copilot API responses across token exchange, catalog, model calls, usage, and embeddings so compressed Business-account error payloads no longer reach JSON parsers as gzip bytes. Fixes #82871.
·Telegram: redact nested raw-update identifiers and user metadata before verbose raw update logging, preserving useful update/message ids without exposing chat, user, command, or profile details. (#82945)
·Telegram: preserve replied-to bot messages, captions, and media metadata in group reply chains so follow-up replies understand what the user is reacting to. (#82863)
·Providers/Together: update PI runtime packages to 0.74.1 and emit Together-style `reasoning.enabled`/`max_tokens` controls for reasoning-capable OpenAI-completions models.
·Agents/diagnostics: split slow embedded-run `attempt-dispatch` startup summaries into workspace, prompt, runtime-plan, and final dispatch subspans so traces identify the delayed setup phase. Fixes #82782. (#82783)
·Agents/Codex: flatten nested tool-result middleware blocks into bounded text so successful message sends are no longer replaced with `Tool output unavailable due to post-processing error`. Fixes #82912.
·CLI/media: accept HTTP(S) URLs in `openclaw infer image describe --file`, fetching remote images through the guarded media path instead of treating URLs as local files. Fixes #82837. (#82854)
·Agents/subagents: keep session-backed parent runs active when the child wait call times out before the child session has actually settled, so late subagent completions are reconciled instead of being lost. Fixes #82787.
·Control UI: advertise shared Gateway protocol constants in browser connect frames, fixing protocol mismatch handshakes after protocol constant drift. Fixes #82882.
·Gateway: add rollback protocol-mismatch diagnostics, including client protocol ranges in Gateway logs and deep status/doctor hints for stale client processes. Fixes #82841. (#82908)
·Agents/subagents: keep successful keep-mode completion payloads pending after final-delivery retry exhaustion, so requester recovery no longer loses final subagent results. Fixes #82583. (#82999)
·Gateway/auth: allow same-host trusted-proxy callers to use the documented local direct `gateway.auth.password` fallback after revisiting the #78684 fail-closed policy, while keeping token fallback rejected and forwarded-header requests on the trusted-proxy path. Fixes #82607. (#82953)
·Agents/subagents: wait for queued completion handoffs to reach the parent transcript before marking them announced, preventing busy parent runs from cleaning up before observing child results. Fixes #82913. (#83039)
·Agents/subagents: route group/channel subagent completions through message-tool-only handoffs when required and keep active-requester wake failures from dropping completion delivery. Fixes #82803.
·Memory-core: scan persisted memory source sessions on startup, comparing on-disk transcripts against the index and marking only missing/newer/resized files dirty for incremental sync. Fixes #82341. (#82341)
·Telegram: keep the top-level default account in the account list when named accounts or bindings are added alongside top-level credentials, preserving default polling while still letting named-only configs resolve to a single account. Fixes #82794. (#82794)
·CLI/models: reuse command-scoped plugin metadata across model listing, provider catalog, auth, and synthetic-auth checks, restoring fast `openclaw models` runs for plugin-heavy installs. Fixes #82881. (#83033)
·CLI/channels: show configured official external channels such as Discord in `openclaw channels list` when their plugin package is missing, including the install and doctor repair command instead of reporting no configured channels. Fixes #82813.
·Signal: preserve mixed-case group IDs through routing and session persistence so group auto-replies keep delivering after updates. Fixes #82827.
·Agents/tools: keep the `message` tool available in embedded runs when it is explicitly allowed through `tools.alsoAllow` or runtime tool allowlists, so channel plugins with custom reply delivery can still use configured message sends. Fixes #82833.
·WhatsApp: honor forced document delivery for outbound image, GIF, and video media so `forceDocument`/`asDocument` sends preserve original media bytes instead of using compressed media payloads. (#79272)
·WhatsApp: name outbound document attachments from their MIME type when no filename is provided, so PDF and CSV sends arrive as `file.pdf` and `file.csv` instead of an extensionless `file`.
·Process/diagnostics: report active lane blockers in lane wait warnings so `queueAhead=0` no longer hides commands waiting behind active work. Fixes #82791. (#82792)
·Process/diagnostics: stop counting the active processing turn as queued backlog in liveness warnings so transient max-only event-loop spikes do not surface as gateway warnings.
·Agents/replies: classify provider conversation-state rejections and return a clear message-channel error instead of auto-resetting or falling back to a generic runner failure. (#82616)
·Browser plugin: trust managed Chrome CDP diagnostics when launch HTTP probes race cold-start readiness, avoiding false startup failures. Fixes #82904. (#82986)
·Android: prompt before replacing a changed Gateway TLS thumbprint, showing the old and new SHA-256 fingerprints so users can accept expected certificate rotations instead of hard failing on pin mismatch. (#83077)
·CLI/status: render extra gateway-like service diagnostics as warning/info output instead of error output. Fixes #46930. (#82922)
·Agents/failover: classify Moonshot/Kimi exhausted-balance HTTP 429 payloads as billing instead of generic rate limits, preserving billing guidance and fallback behavior. Fixes #43447. (#83079)
·Plugin SDK: bundle `openclaw/plugin-sdk/zod` into the published package artifact and verify the packed zod subpath stays self-contained, so pnpm global installs can register plugins without a package-local `zod` symlink. Fixes #78398. (#78515)
·Providers/Google: drop compaction-truncated Gemini thought signatures before replay so malformed Base64 no longer aborts the next assistant turn. (#82995)

v2026.5.18-beta.1pre-release2026-05-18

openclaw 2026.5.18-beta.1

GitHub ↗

Changes

·Agents: clarify that fixes should default to clean bounded refactors, lean internals, and explicit plugin SDK/API deprecation paths.
·Dependencies: update `@openclaw/proxyline` to 0.3.3.
·Dependencies: update Pi packages to 0.75.1 and raise the minimum supported Node.js 22 line to 22.19.
·Docker/Podman: add `OPENCLAW_IMAGE_APT_PACKAGES` as the runtime-neutral image build arg for extra apt packages while keeping `OPENCLAW_DOCKER_APT_PACKAGES` as a legacy fallback. (#62431)
·Gateway/ACPX: attribute startup probe, config, runtime, and resource-count costs in restart traces without changing readiness behavior. (#83300)
·Gateway: overlap startup logging and plugin-service startup with channel sidecars to reduce restart ready latency while preserving `/readyz` sidecar gating. (#83301)
·Plugins/admin-http-rpc: allow trusted admin HTTP RPC clients to start and wait for web QR login flows. (#83259)
·Mac app: redesign Settings pages with consistent card layouts, cached navigation, cleaner permissions/voice/skills/cron/exec/debug panes, and steadier spacing around the native sidebar.
·Skills: rename the repo-local Codex closeout review skill and helper to `autoreview` while preserving the Codex-first fallback behavior.
·Skills: add a meme-maker skill for curated template search, local SVG/PNG rendering, Imgflip hosted rendering, and Know Your Meme provenance links.
·Browser: surface pending and recently handled modal dialogs in snapshots, return `blockedByDialog` when an action opens a modal, and allow `browser dialog --dialog-id` to answer pending dialogs.
·Agents/tools: shorten built-in tool descriptions and schema hints across media, messaging, sessions, cron, Gateway, web, image/PDF, TTS, nodes, and plan tools while preserving routing guardrails.
·Skills: add node inspector debugging, fused diagram generation, and throwaway spike workflow skills.
·CLI/plugins: add `defineToolPlugin` plus `openclaw plugins build`, `validate`, and `init` for typed simple tool plugins with generated manifest metadata, optional tool declarations, and context factories.
·Agents/skills: tighten bundled skill prompts and metadata, quote skill descriptions, refresh current CLI/API guidance, and update embedded sherpa-onnx runtime downloads.
·Skills: update the Obsidian skill to target the official `obsidian` CLI and require its registered binary instead of the third-party `obsidian-cli`.
·Skills: add a Python debugging skill for pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.
·Plugins/messages: add presentation capability limits for channel renderers, adapt rich message controls before native rendering, and mark legacy `interactive`/Slack directive producer APIs as deprecated.
·Proxy: support HTTPS managed forward-proxy endpoints and scoped `proxy.tls.caFile` CA trust for proxy endpoint TLS. (#79171)
·QA-Lab: add first-hour 20-turn and optional 100-turn runtime parity scenarios, with tier metadata for standard and soak QA gates. Fixes #80338; refs #80337.
·QA-Lab: add `openclaw qa suite --runtime-parity-tier` and wire the standard Codex-vs-Pi tier into release checks separately from optional/live-only/soak lanes. Fixes #80337.
·QA-Lab: add a live-only Codex Pi-shaped Read vocabulary canary so runtime parity catches native workspace-read prompt compatibility drift. (#80323)
·QA-Lab: add live-only harness self-health scenarios for plugin hook crashes, manifest contract errors, and WebChat direct-reply self-message routing. (#80323)
·QA-Lab: add runtime tool fixture scenarios and coverage reporting for Codex-native workspace tools, OpenClaw dynamic tools, and optional plugin-backed tools. Fixes #80173.
·QA-Lab: expose runtime tool fixture coverage through `openclaw qa coverage --tools`, with optional suite-summary evaluation for parity gate artifacts.
·QA-Lab: schedule a live-frontier Codex-vs-Pi runtime token-efficiency artifact lane in the all-lanes QA workflow. Fixes #80175.
·QA-Lab: hard-gate required OpenClaw dynamic runtime-tool drift in the standard Codex-vs-Pi tier with a blocking release-check verifier and publish the tool coverage report artifact. Fixes #80339; refs #80319.
·QA-Lab: add the personal-agent approval-denial scenario so the benchmark pack verifies denied local reads stop cleanly without tool progress or fixture leaks. (#83150)
·QA-Lab: extend the personal-agent benchmark pack with a local task followthrough scenario for proof-backed pending, blocked, and done status reporting.
·Gateway/performance: add `pnpm test:restart:gateway` benchmark tooling for repeated restart readiness, downtime, trace, and resource-slope evidence. (#83299)
·Android: switch Talk Mode to realtime Gateway relay voice sessions with streaming mic input, realtime audio playback, tool-result bridging, and on-screen transcripts. (#83130)

Fixes

·Discord/OpenAI: keep realtime Discord voice sessions hearing follow-up turns with OpenAI realtime and prebuffer assistant playback to avoid choppy starts. (#80505)
·Media: prevent image metadata probing from invoking external decoder delegates on unrecognized image bytes, and stop fallback chaining after real processing errors.
·Media: install Sharp with the root package and fall back to sips, Windows native imaging, ImageMagick, GraphicsMagick, or ffmpeg for image resizing/conversion when Sharp is unavailable. Fixes #83401.
·Telegram: deliver generated media completions back into forum topics by preserving topic IDs across requester-agent handoff. (#83556)
·Gateway: defer update-check startup until after readiness so package update checks no longer block sidecar-ready startup, while preserving update broadcasts and shutdown cleanup. (#83520)
·Telegram: keep `/btw` and read-only status commands from aborting active runs, and avoid retaining raw update payloads in timed-out spool tombstones. Refs #83272.
·Agents/video: hide `video_generate` reference-audio parameters unless a registered video provider supports audio inputs.
·Plugins/xAI: echo PKCE challenge fields during OAuth authorization-code token exchange for xAI token-endpoint compatibility. (#83499)
·Codex app-server: hydrate current inbound image attachments before queued runs so Responses-backed agents receive Discord and other channel images as native vision input. Fixes #83466.
·Codex app-server: keep native code mode available without forcing code-mode-only so OpenClaw dynamic tool turns complete through the app-server tool bridge. Fixes #83109.
·Release stability: recover stale session diagnostics and Codex OAuth fallback state so stuck runs and reused refresh tokens clear without blocking follow-up work. (#83503)
·Messages/TTS: apply TTS directives before message-tool sends reach core, gateway, or plugin delivery so opt-in message-tool rooms and proactive sends attach voice notes instead of leaking raw tags. Fixes #81598.
·Codex app-server: preserve network access for sandboxed Codex code-mode turns when the OpenClaw sandbox allows outbound egress. Fixes #83347.
·QA-Lab: keep the OTLP smoke decoder independent of removed OpenTelemetry generated-root internals.
·Messages: default group/channel visible replies to automatic final delivery again, keeping `message_tool` opt-in for ambient/shared rooms and tool-reliable models.
·CLI/TUI: force standalone `/exit` runs to terminate after `runTui` returns so onboarding-launched TUI children do not stay alive invisibly. (#83501)
·Agents/code mode: honor per-agent code-mode config in schema, runtime catalog activation, and model payload filtering. Fixes #83388.
·Agents/code mode: preserve agent, session, run, and channel context in `before_tool_call` hooks for top-level `exec`/`wait` dispatches. Fixes #83387.
·QQBot: shorten C2C typing indicators to a 10-second window renewed every 5 seconds, capped to keep a final passive-reply slot available. (#83469)
·Replies: keep final payload delivery after live preview updates so channels can finalize or send the completed answer instead of losing preview-only drafts. (#83468)
·Discord: deliver final replies in progress-mode preview streams instead of deduplicating the final visible message. (#83443)
·Providers/Xiaomi: replay MiMo Anthropic-compatible `reasoning_content` as provider-required thinking blocks even when OpenClaw thinking is disabled, fixing follow-up tool turns for `mimo-v2-flash`. Fixes #83407.
·Agents/exec approvals: forward approval-runtime credentials on agent-owned Gateway approval calls so approved async commands complete through the existing runtime path instead of stalling on unauthenticated follow-up calls.
·Gateway/skills: preflight remote macOS skill-bin refreshes with a WebSocket connectivity check so stale node sessions skip quickly instead of logging slow `system.which` timeout warnings.
·CLI/config: keep broken discovered plugins that are not referenced by active config from failing `openclaw config validate`, while preserving fatal errors for explicitly configured plugin entries.
·GitHub Copilot: drop unsafe native Responses reasoning replay items with non-replayable IDs before dispatch, preventing affected Copilot sessions from failing with `invalid_request_body`. Fixes #83220.
·Agents/Codex: fail closed when an explicitly requested Codex harness is not registered instead of silently trying configured model fallbacks. Fixes #83349.
·QA-Lab: make runtime tool coverage fail on missing required tool exercise instead of treating pass/pass parity envelope drift as missing coverage.
·Core/plugins: harden clawpatch-reported edge cases across gateway auth cleanup, Claude session id paths, plugin activation policy, apply-patch hunk handling, diagnostic redaction, and plugin metadata validation.
·UI: show reasoning choices as plain labels instead of leaking internal override wording in session and chat pickers.
·Mac app: avoid repeating the Configuration heading inside channel quick settings.
·Mac app: keep the Settings sidebar always visible and remove the redundant titlebar hide/show control.
·Mac app: prefer explicit private/Tailscale/LAN Gateway endpoints over SSH tunnels, preserve legacy loopback tunnel configs, persist transport choices, and show captured SSH stderr when tunneling really fails.
·Gateway/sessions: keep ACP/acpx and runtime child sessions visible in configured-only session lists when their owner or parent session belongs to a configured agent.
·Mac app: keep app-level menu commands and Dashboard failure states reachable when the remote Gateway is disconnected.
·Mac app: allow longer Gateway and Context errors to wrap in the menu instead of truncating the useful failure detail.
·Mac app: tighten remote Gateway fields in Settings so the Connection pane keeps readable labels and full action button text.
·Mac app: keep custom Settings card rows left-aligned and full-width so Discovery and status sections no longer appear centered or detached.
·Mac app: align Location permission controls to the same trailing column as the rest of Settings.
·Mac app: add Dashboard, Chat, Canvas, and Settings shortcuts to the Dock icon menu.
·Mac app: replace the Settings window's native split-view sidebar with an explicit layout so page content keeps its leading gutter when the sidebar is shown or hidden.
·Mac app: render channel quick config as aligned Settings rows and hide schema-only variants that cannot be edited safely from the quick pane.
·Gateway/webchat: hide internal runtime-context and other `display: false` transcript messages from Chat history and live message events. Fixes #83216.
·CLI/help: keep `gateway`, `doctor`, `status`, and `health` help registration out of action/runtime imports so subcommand `--help` stays lightweight in constrained terminals. Fixes #83228.
·Cron/Discord: keep explicit announce runs in message-tool-only source-reply mode so scheduled agent turns post once instead of also echoing through automatic visible replies. Fixes #83261.
·Telegram: preserve forum-topic origin targets in inbound, audio-preflight, and skipped-message hook contexts so follow-up delivery stays bound to the originating topic. Fixes #83302.
·Telegram: retry HTTP 421 Misdirected Request send failures on a fresh fallback transport so transient edge-node routing errors no longer drop outbound replies. Fixes #48892. (#48908)
·Telegram: fail topic sends closed when Telegram reports `message thread not found` instead of retrying without `message_thread_id` into the base chat. Refs #83302.
·Config/subagents: remove ignored agent-model `timeoutMs` keys, keep subagent model config to primary/fallback selection, and clean shipped stale config through doctor. Fixes #83291.
·Mac app: align the Sessions settings pane with the standard Settings page gutter and row spacing.
·OpenAI/Codex: stop rejecting available `openai-codex` GPT-5.1, GPT-5.2, and GPT-5.3 model refs during config validation, while keeping removed Spark aliases suppressed. Fixes #83303.
·Plugins/xAI: complete OAuth-backed xAI login and sidecar auth fixes, including guarded loopback callback CORS handling, video generation polling/defaults, and native-host User-Agent attribution. (#83322)
·Codex app-server: preserve streamed native command output in mirrored transcripts and trajectory exports when final snapshots omit aggregated output. (#83200)
·Codex app-server: fail closed when chat or sender policy denies tools, disabling native code, app, environment, and user MCP surfaces for restricted turns. (#82374)
·Codex app-server: keep recent context-engine messages when oversized projected history is truncated, so short follow-ups in long channel sessions do not fall back to stale earlier turns. (#83127)
·Codex app-server: keep OpenClaw session spawning searchable while steering Codex-native delegation through native subagents, avoiding duplicate direct subagent surfaces. (#83329)
·Codex app-server: recover stale childless Codex-native subagent task mirrors during maintenance and allow their registry rows to be cancelled without an OpenClaw child session. (#82836)
·Feishu: return bound subagent delivery origins from session thread setup so Feishu subagent completions route back to the same DM or topic. (#83190)
·CLI/update: tailor post-update Gateway recovery hints by platform, showing systemd, LaunchAgent, Scheduled Task, or generic service-manager guidance instead of macOS-only recovery text. (#83096)
·Plugins: apply a default 15-second timeout to legacy `before_agent_start` hooks so hung plugin handlers no longer block agent startup. Fixes #48534. (#83136)
·Feishu: refresh inbound session delivery context for DM, group, and broadcast turns so later replies do not inherit stale WebChat routing. Fixes #78274.
·Agents/subagents: require the initial subagent registry save before reporting spawn accepted, returning a spawn error instead of losing an untracked run when the registry write fails. (#83146)
·QA-Lab/qa-channel: attach redacted agent tool-start traces to outbound `QaBusMessage` records so scenarios can assert actual tool use instead of relying only on reply text. Fixes #67637.
·QA-Lab: fail live runtime parity reports when assistant-message usage is missing, preventing `0 vs 0` live token rows from being reported as passing proof. Fixes #80411.
·QA-Lab: add a runtime token-efficiency sidecar report that classifies Codex savings separately from regressions and fails only positive Codex-over-Pi live token deltas above threshold. Fixes #81093.
·QA-Lab: fail Codex-backed OpenAI live runtime-pair runs before launching isolated workers when no portable Codex auth is available, while staging API-key fallbacks and configured Codex keys for isolated QA agents. Fixes #80412.
·QA-Lab: refresh parity gates, mock frontier fixtures, model scenarios, and workflow artifact lanes to compare GPT-5.5 against Claude Opus 4.7. Fixes #74262.
·QA-Lab: make mock parity dispatch provider-aware for source discovery and subagent scenarios so OpenAI and Anthropic lanes no longer share identical canned plans. Fixes #64879.
·QA-Lab: stop returning Control UI bearer tokens from unauthenticated bootstrap payloads and bind Docker harness ports to loopback-only host addresses. (#66355)
·Mac app: avoid a SwiftUI metadata crash when rendering the Cron Jobs settings pane.
·Agents/subagents: preserve run-mode keep subagent registry entries past the session sweep TTL, so kept subagent runs remain visible after cleanup completes. Fixes #83132. (#83168)
·Agents/OpenAI streams: yield via `setTimeout(0)` instead of `setImmediate` between bursty Responses chunks so abort timers can fire during the yield, keeping cancel-on-timeout responsive on hot streams. Refs #82462.
·Agents/Codex: keep legacy `oauthRef`-backed OAuth profiles usable while `openclaw doctor --fix` migrates them back to inline credentials, without creating new sidecar credentials. (#83312)
·Agents/Codex: load the selected provider owner alongside the Codex harness runtime so `openai-codex` models resolve when plugin allowlists scope runtime loading. Fixes #83380. (#83519)
·Telegram: fail stalled isolated-ingress handlers into tombstones and abort same-lane reply work before restarting, so later same-chat updates drain after a hung turn. Fixes #83272. (#83505)
·CLI/config: send SecretRef diagnostics to stderr so JSON command stdout remains parseable.
·CLI/doctor: seed Control UI allowed origins when migrating legacy non-loopback gateway bind host aliases like `0.0.0.0`. Fixes #83286.
·CLI/plugins: ship the bundled memory CLI as a package entry so package-installed `openclaw memory` commands register correctly.
·CLI/update: defer doctor-time plugin package installs during package swaps and seed post-core repair from the updated install registry, preventing duplicate reinstall failures.
·CLI/update: preserve old-parent-readable config metadata during legacy package handoffs, fall back only to official `@openclaw/*` npm plugin packages when ClawHub plugin artifacts are unavailable, and keep managed service package roots authoritative during updates.
·Feishu: detect SecretRef top-level credentials as a configured default account instead of treating object-backed app secrets as missing.
·Gateway/restart: keep ordinary unmanaged SIGUSR1/config restarts in-process instead of detach-spawning an orphaned child, preserving custom supervisor PID tracking while leaving update restarts on the fresh-process path. Fixes #65668.
·CLI/completion: resolve concrete PowerShell profile paths and reload commands during setup and doctor completion installation. Fixes #44296. (#83059)
·Telegram: keep isolated long polling below the hard `getUpdates` request guard so idle bot accounts with high `timeoutSeconds` do not false-disconnect and restart-loop. Fixes #83264.
·Providers/Google: preserve and recover Gemini 3 tool-call thought signatures during native replay so function-calling turns no longer fail with missing `thought_signature` 400s. Fixes #72879. (#80358)
·Telegram: skip transcript-only delivery mirrors and gateway-injected rows when resolving latest assistant text, preventing retained previews from replacing final replies with stale fragments. Fixes #83159. (#83362)
·Memory/QMD: keep lexical search on raw hyphenated queries while normalizing semantic QMD sub-searches, avoiding fallback to the builtin index for dashed identifiers and dates. Fixes #81328.
·Memory-core: distinguish sqlite-vec load failures from missing semantic vector embeddings in degraded `memory index` warnings, so vector recall diagnostics point at unresolved dimensions instead of blaming sqlite-vec when the store is ready. Fixes #75624. (#83056)
·Agents/subagents: preserve sandbox-peer controller ownership while routing completion announcements back to the originating run session, keeping subagent control and completion delivery scoped correctly. Fixes #80201. (#80242)
·Gateway: continue restarting remaining channels when one hot-reload channel restart fails, while still reporting aggregate reload failure and rolling back plugin pre-replace stops. Fixes #83054.
·Telegram: keep hot-reload restarts from marking polling accounts manually stopped and restart isolated ingress cleanly after worker shutdown, preserving Telegram replies across config reloads. Fixes #83008. (#83410)
·Telegram/Ollama: pass current Telegram image attachments into native PI/Ollama vision turns so live photo prompts reach Ollama as native images. Fixes #83023. (#83516)
·Gateway/secrets: split the lightweight secrets runtime state and auth-store cache from the full secrets runtime and take a startup fast path when the gateway startup config has no SecretRef values, speeding up secrets startup while preserving cleanup and refresh semantics.
·Codex app-server: rotate oversized native Codex threads before resume and cap dynamic tool-result text entering native Codex sessions, preventing stale oversized context from surviving OpenClaw compaction. (#82981)
·Gateway/restart: drain pending replies and active chat runs during restart shutdown before sockets and channels close, aborting timed-out chat runs through the normal cleanup path. (#69121)
·Agents/Codex: use the Codex runtime context window for OpenAI-model preflight compaction and memory flush checks, so GPT-5.5 Codex sessions compact before hitting the smaller native context limit. Fixes #82982.
·QA-Lab: clean orphaned gateway temp roots when a suite parent exits and wait on gateway plus transport readiness after config restarts, reducing stale `qa-channel` noise from interrupted runs. Fixes #65506.
·QA-Lab: wake qa-bus long polls that arrive with stale future cursors after a bus restart, preserving reconnect readiness for harness clients. (#67142)
·QA-Lab: stage Multipass transfer scripts under OpenClaw's preferred temp root instead of raw OS temp paths, keeping the VM runner inside temp-path guardrails. (#64098)
·Agents/replies: keep surviving reply media and append a warning when other media references fail, so partial media normalization no longer drops failures silently.
·Config/models: accept `thinkingFormat: "together"` in model compat config so Together routes can opt into the Together-specific thinking response shape.
·Plugins/tokenjuice: bump the bundled tokenjuice runtime to 0.7.1, bringing Codex hook approval compatibility, pre-tool command wrapping fixes, and Rolldown/Vitest output compaction improvements into the OpenClaw plugin.
·Agents/OpenAI: stop post-processing GPT-5 final replies with hardcoded brevity caps, preserving full channel responses instead of appending synthetic ellipses, and log when strict-agentic GPT-5 execution activates. Fixes #82910.
·Mac app: refine the Settings General and Connection panes with cleaner status panels, card rows, and a single native titlebar sidebar toggle.
·Agents/media: deliver failed async image, music, and video generation completions directly when requester-session completion handoff fails, so channel users see provider errors instead of silent fallback stalls.
·Browser/CDP: keep loopback proxy bypass active across both `NO_PROXY` casings and redact home-relative Chrome MCP profile paths in attach-failure diagnostics.
·Agents/music: steer song, jingle, beat, anthem, and instrumental requests toward `music_generate` audio creation instead of lyric-only replies, and reserve `lyrics` for exact sung words.
·Codex app-server: record native Codex tool calls and results into trajectory artifacts so debug/trajectory exports capture the full Codex-native tool history, not just OpenClaw-bridged turns.
·Codex/app-server: keep bound conversation sessions on the owning agent runtime so native Codex control and follow-up turns do not fall back to the default agent client. Fixes #82954. (#82993)
·CLI/infer: run gateway model probes in fresh explicit sessions so one-shot provider checks do not inherit default agent transcript state. (#82861)
·Providers/Together: send video-generation requests to Together's v2 video API even when shared text-model config still points at the v1 base URL. (#82992)
·Browser CLI: preserve browser-level options on nested commands, skip option values during lazy command registration, and keep long-running wait/download/dialog hooks open for their advertised wait window.
·CLI/sessions: accept `openclaw sessions list` as an alias for `openclaw sessions`, matching other list-style commands. Fixes #81139. (#81163)
·Channels/stream previews: widen compact progress draft lines and cut prose at word boundaries while preserving command/path suffixes, with `streaming.progress.maxLineChars` for channel-specific tuning.
·CLI/plugins: have `openclaw plugins doctor` warn when a configured runtime needs a missing owner plugin, sharing the same install mapping as `openclaw doctor --fix`. Fixes #81326. (#81674)
·Agents/Codex: route OpenAI runs that resolve to `openai-codex` through the Codex provider and bootstrap OpenClaw's stored OAuth profile into the Codex harness when the harness owns transport, so `openai/*` model refs no longer fail with `No API key found for openai-codex` despite an existing Codex OAuth profile. (#82864)
·Agents/ACP: distinguish prompt-submitted and runtime-active child stalls from true interactive waits, including redacted proxy-env diagnostics for Codex ACP no-output runs. Fixes #44810.
·Agents/memory: explain that memory-triggered compaction exposes only `read` and append-only `write` when configured core tools are unavailable in `tools.allow` warnings. Fixes #82941.
·Agents/OpenAI: preserve deterministic tool payload ordering for prompt-cache reuse across OpenAI Responses and chat completions calls. (#82940)
·ACP/Codex: honor terminal ACP turn results so failed Codex/acpx runs are not recorded as successful after only progress text. Fixes #79522.
·Telegram: warn when a media group drops photos that fail to download, including albums where every photo is skipped. Fixes #55216. (#82987)
·Agents/skills: apply the full effective tool policy pipeline to inline `command-dispatch: tool` skill dispatch before owner-only filtering, preserving configured allow, deny, sandbox, sender, group, and subagent restrictions. (#78525)
·Codex: avoid spawning native hook relay subprocesses for post-tool/finalize events with no registered hook handlers while preserving pre-tool safety and approval relays. Fixes #76552. (#78004)
·Channel accounts: keep top-level default channel accounts visible when named accounts are added alongside default credential material, so mixed legacy/new account configs keep resolving `default` instead of silently dropping it.
·Agents/CLI: reject empty successful CLI subprocess replies as `empty_response` and keep them out of shared auth-profile health, so blank Claude CLI results no longer become green no-payload turns. Fixes #83231. (#83421)
·Codex/Telegram: synthesize native Codex tool progress from final turn snapshots so Telegram `/verbose` stays visible when command events arrive only at completion.
·Codex/Telegram: deliver Codex verbose tool summaries in direct message-tool-only turns while suppressing message-send and activity-log noise. (#83186)
·Mac app: make Channels settings open faster by deferring config-schema work, avoiding startup channel probes, caching decoded channel status rows, and showing only compact quick settings instead of the full generated channel schema.
·Control UI: include the Control UI and Gateway protocol versions in protocol-mismatch errors so stale app/dashboard pairings identify which side needs rebuilding or restarting.
·Gateway/protocol: restore Gateway WS protocol v4 and keep `message.action` room-event metadata on the existing `inboundTurnKind` wire field while preserving internal inbound-event classification.
·Agents/tools: prefer non-webchat session-key routes when the message tool has stale webchat context, so message-tool-only replies keep delivering to the originating channel. Fixes #82911. (#83004)
·Channels: keep direct-message last-route writes on isolated `per-channel-peer` sessions instead of contaminating the agent main session with channel delivery context. Fixes #36614.
·Mac app: move the Settings sidebar toggle into the native titlebar and tighten the General pane width.
·Mac app: keep visited Settings panes mounted so switching tabs no longer blanks and reloads their content.
·Mac app: make Config settings open from shallow schema lookups and load selected paths on demand instead of fetching and rendering the full generated config schema up front.
·Codex: sanitize inline image payloads before Codex app-server and OpenAI Responses replay, and clear poisoned Codex thread bindings after invalid image errors. Fixes #82878.
·Providers/GitHub Copilot: request identity-encoded Copilot API responses across token exchange, catalog, model calls, usage, and embeddings so compressed Business-account error payloads no longer reach JSON parsers as gzip bytes. Fixes #82871.
·Telegram: redact nested raw-update identifiers and user metadata before verbose raw update logging, preserving useful update/message ids without exposing chat, user, command, or profile details. (#82945)
·Telegram: preserve replied-to bot messages, captions, and media metadata in group reply chains so follow-up replies understand what the user is reacting to. (#82863)
·Providers/Together: update PI runtime packages to 0.74.1 and emit Together-style `reasoning.enabled`/`max_tokens` controls for reasoning-capable OpenAI-completions models.
·Agents/diagnostics: split slow embedded-run `attempt-dispatch` startup summaries into workspace, prompt, runtime-plan, and final dispatch subspans so traces identify the delayed setup phase. Fixes #82782. (#82783)
·Agents/Codex: flatten nested tool-result middleware blocks into bounded text so successful message sends are no longer replaced with `Tool output unavailable due to post-processing error`. Fixes #82912.
·CLI/media: accept HTTP(S) URLs in `openclaw infer image describe --file`, fetching remote images through the guarded media path instead of treating URLs as local files. Fixes #82837. (#82854)
·Agents/subagents: keep session-backed parent runs active when the child wait call times out before the child session has actually settled, so late subagent completions are reconciled instead of being lost. Fixes #82787.
·Control UI: advertise shared Gateway protocol constants in browser connect frames, fixing protocol mismatch handshakes after protocol constant drift. Fixes #82882.
·Gateway: add rollback protocol-mismatch diagnostics, including client protocol ranges in Gateway logs and deep status/doctor hints for stale client processes. Fixes #82841. (#82908)
·Agents/subagents: keep successful keep-mode completion payloads pending after final-delivery retry exhaustion, so requester recovery no longer loses final subagent results. Fixes #82583. (#82999)
·Gateway/auth: allow same-host trusted-proxy callers to use the documented local direct `gateway.auth.password` fallback after revisiting the #78684 fail-closed policy, while keeping token fallback rejected and forwarded-header requests on the trusted-proxy path. Fixes #82607. (#82953)
·Agents/subagents: wait for queued completion handoffs to reach the parent transcript before marking them announced, preventing busy parent runs from cleaning up before observing child results. Fixes #82913. (#83039)
·Agents/subagents: route group/channel subagent completions through message-tool-only handoffs when required and keep active-requester wake failures from dropping completion delivery. Fixes #82803.
·Memory-core: scan persisted memory source sessions on startup, comparing on-disk transcripts against the index and marking only missing/newer/resized files dirty for incremental sync. Fixes #82341. (#82341)
·Telegram: keep the top-level default account in the account list when named accounts or bindings are added alongside top-level credentials, preserving default polling while still letting named-only configs resolve to a single account. Fixes #82794. (#82794)
·CLI/models: reuse command-scoped plugin metadata across model listing, provider catalog, auth, and synthetic-auth checks, restoring fast `openclaw models` runs for plugin-heavy installs. Fixes #82881. (#83033)
·CLI/channels: show configured official external channels such as Discord in `openclaw channels list` when their plugin package is missing, including the install and doctor repair command instead of reporting no configured channels. Fixes #82813.
·Signal: preserve mixed-case group IDs through routing and session persistence so group auto-replies keep delivering after updates. Fixes #82827.
·Agents/tools: keep the `message` tool available in embedded runs when it is explicitly allowed through `tools.alsoAllow` or runtime tool allowlists, so channel plugins with custom reply delivery can still use configured message sends. Fixes #82833.
·WhatsApp: honor forced document delivery for outbound image, GIF, and video media so `forceDocument`/`asDocument` sends preserve original media bytes instead of using compressed media payloads. (#79272)
·WhatsApp: name outbound document attachments from their MIME type when no filename is provided, so PDF and CSV sends arrive as `file.pdf` and `file.csv` instead of an extensionless `file`.
·Process/diagnostics: report active lane blockers in lane wait warnings so `queueAhead=0` no longer hides commands waiting behind active work. Fixes #82791. (#82792)
·Process/diagnostics: stop counting the active processing turn as queued backlog in liveness warnings so transient max-only event-loop spikes do not surface as gateway warnings.
·Agents/replies: classify provider conversation-state rejections and return a clear message-channel error instead of auto-resetting or falling back to a generic runner failure. (#82616)
·Browser plugin: trust managed Chrome CDP diagnostics when launch HTTP probes race cold-start readiness, avoiding false startup failures. Fixes #82904. (#82986)
·Android: prompt before replacing a changed Gateway TLS thumbprint, showing the old and new SHA-256 fingerprints so users can accept expected certificate rotations instead of hard failing on pin mismatch. (#83077)
·CLI/status: render extra gateway-like service diagnostics as warning/info output instead of error output. Fixes #46930. (#82922)
·Agents/failover: classify Moonshot/Kimi exhausted-balance HTTP 429 payloads as billing instead of generic rate limits, preserving billing guidance and fallback behavior. Fixes #43447. (#83079)
·Plugin SDK: bundle `openclaw/plugin-sdk/zod` into the published package artifact and verify the packed zod subpath stays self-contained, so pnpm global installs can register plugins without a package-local `zod` symlink. Fixes #78398. (#78515)
·Providers/Google: drop compaction-truncated Gemini thought signatures before replay so malformed Base64 no longer aborts the next assistant turn. (#82995)

v2026.5.16-beta.7pre-release2026-05-18

openclaw 2026.5.16-beta.7

GitHub ↗

Changes

·Dependencies: update `@openclaw/proxyline` to 0.3.3.
·Dependencies: update Pi packages to 0.75.1 and raise the minimum supported Node.js 22 line to 22.19.
·Docker/Podman: add `OPENCLAW_IMAGE_APT_PACKAGES` as the runtime-neutral image build arg for extra apt packages while keeping `OPENCLAW_DOCKER_APT_PACKAGES` as a legacy fallback. (#62431)
·Gateway/ACPX: attribute startup probe, config, runtime, and resource-count costs in restart traces without changing readiness behavior. (#83300)
·Gateway: overlap startup logging and plugin-service startup with channel sidecars to reduce restart ready latency while preserving `/readyz` sidecar gating. (#83301)
·Mac app: redesign Settings pages with consistent card layouts, cached navigation, cleaner permissions/voice/skills/cron/exec/debug panes, and steadier spacing around the native sidebar.
·Skills: rename the repo-local Codex closeout review skill and helper to `autoreview` while preserving the Codex-first fallback behavior.
·Skills: add a meme-maker skill for curated template search, local SVG/PNG rendering, Imgflip hosted rendering, and Know Your Meme provenance links.
·Browser: surface pending and recently handled modal dialogs in snapshots, return `blockedByDialog` when an action opens a modal, and allow `browser dialog --dialog-id` to answer pending dialogs.
·Agents/tools: shorten built-in tool descriptions and schema hints across media, messaging, sessions, cron, Gateway, web, image/PDF, TTS, nodes, and plan tools while preserving routing guardrails.
·Skills: add node inspector debugging, fused diagram generation, and throwaway spike workflow skills.
·CLI/plugins: add `defineToolPlugin` plus `openclaw plugins build`, `validate`, and `init` for typed simple tool plugins with generated manifest metadata, optional tool declarations, and context factories.
·Agents/skills: tighten bundled skill prompts and metadata, quote skill descriptions, refresh current CLI/API guidance, and update embedded sherpa-onnx runtime downloads.
·Skills: update the Obsidian skill to target the official `obsidian` CLI and require its registered binary instead of the third-party `obsidian-cli`.
·Skills: add a Python debugging skill for pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.
·Plugins/messages: add presentation capability limits for channel renderers, adapt rich message controls before native rendering, and mark legacy `interactive`/Slack directive producer APIs as deprecated.
·Proxy: support HTTPS managed forward-proxy endpoints and scoped `proxy.tls.caFile` CA trust for proxy endpoint TLS. (#79171)
·QA-Lab: add first-hour 20-turn and optional 100-turn runtime parity scenarios, with tier metadata for standard and soak QA gates. Fixes #80338; refs #80337.
·QA-Lab: add `openclaw qa suite --runtime-parity-tier` and wire the standard Codex-vs-Pi tier into release checks separately from optional/live-only/soak lanes. Fixes #80337.
·QA-Lab: add a live-only Codex Pi-shaped Read vocabulary canary so runtime parity catches native workspace-read prompt compatibility drift. (#80323)
·QA-Lab: add live-only harness self-health scenarios for plugin hook crashes, manifest contract errors, and WebChat direct-reply self-message routing. (#80323)
·QA-Lab: add runtime tool fixture scenarios and coverage reporting for Codex-native workspace tools, OpenClaw dynamic tools, and optional plugin-backed tools. Fixes #80173.
·QA-Lab: expose runtime tool fixture coverage through `openclaw qa coverage --tools`, with optional suite-summary evaluation for parity gate artifacts.
·QA-Lab: schedule a live-frontier Codex-vs-Pi runtime token-efficiency artifact lane in the all-lanes QA workflow. Fixes #80175.
·QA-Lab: hard-gate required OpenClaw dynamic runtime-tool drift in the standard Codex-vs-Pi tier with a blocking release-check verifier and publish the tool coverage report artifact. Fixes #80339; refs #80319.
·QA-Lab: add the personal-agent approval-denial scenario so the benchmark pack verifies denied local reads stop cleanly without tool progress or fixture leaks. (#83150)
·QA-Lab: extend the personal-agent benchmark pack with a local task followthrough scenario for proof-backed pending, blocked, and done status reporting.

Fixes

·Agents/code mode: preserve agent, session, run, and channel context in `before_tool_call` hooks for top-level `exec`/`wait` dispatches. Fixes #83387.
·Replies: keep final payload delivery after live preview updates so channels can finalize or send the completed answer instead of losing preview-only drafts. (#83468)
·Providers/Xiaomi: replay MiMo Anthropic-compatible `reasoning_content` as provider-required thinking blocks even when OpenClaw thinking is disabled, fixing follow-up tool turns for `mimo-v2-flash`. Fixes #83407.
·Agents/exec approvals: forward approval-runtime credentials on agent-owned Gateway approval calls so approved async commands complete through the existing runtime path instead of stalling on unauthenticated follow-up calls.
·Gateway/skills: preflight remote macOS skill-bin refreshes with a WebSocket connectivity check so stale node sessions skip quickly instead of logging slow `system.which` timeout warnings.
·CLI/config: keep broken discovered plugins that are not referenced by active config from failing `openclaw config validate`, while preserving fatal errors for explicitly configured plugin entries.
·GitHub Copilot: drop unsafe native Responses reasoning replay items with non-replayable IDs before dispatch, preventing affected Copilot sessions from failing with `invalid_request_body`. Fixes #83220.
·Agents/Codex: fail closed when an explicitly requested Codex harness is not registered instead of silently trying configured model fallbacks. Fixes #83349.
·QA-Lab: make runtime tool coverage fail on missing required tool exercise instead of treating pass/pass parity envelope drift as missing coverage.
·Core/plugins: harden clawpatch-reported edge cases across gateway auth cleanup, Claude session id paths, plugin activation policy, apply-patch hunk handling, diagnostic redaction, and plugin metadata validation.
·Mac app: prefer explicit private/Tailscale/LAN Gateway endpoints over SSH tunnels, preserve legacy loopback tunnel configs, persist transport choices, and show captured SSH stderr when tunneling really fails.
·Gateway/sessions: keep ACP/acpx and runtime child sessions visible in configured-only session lists when their owner or parent session belongs to a configured agent.
·Mac app: keep app-level menu commands and Dashboard failure states reachable when the remote Gateway is disconnected, and keep the Settings sidebar toggle in the leading titlebar area.
·Mac app: allow longer Gateway and Context errors to wrap in the menu instead of truncating the useful failure detail.
·Mac app: tighten remote Gateway fields in Settings so the Connection pane keeps readable labels and full action button text.
·Mac app: keep custom Settings card rows left-aligned and full-width so Discovery and status sections no longer appear centered or detached.
·Mac app: align Location permission controls to the same trailing column as the rest of Settings.
·Gateway/webchat: hide internal runtime-context and other `display: false` transcript messages from Chat history and live message events. Fixes #83216.
·CLI/help: keep `gateway`, `doctor`, `status`, and `health` help registration out of action/runtime imports so subcommand `--help` stays lightweight in constrained terminals. Fixes #83228.
·Cron/Discord: keep explicit announce runs in message-tool-only source-reply mode so scheduled agent turns post once instead of also echoing through automatic visible replies. Fixes #83261.
·Telegram: preserve forum-topic origin targets in inbound, audio-preflight, and skipped-message hook contexts so follow-up delivery stays bound to the originating topic. Fixes #83302.
·Telegram: retry HTTP 421 Misdirected Request send failures on a fresh fallback transport so transient edge-node routing errors no longer drop outbound replies. Fixes #48892. (#48908)
·Telegram: fail topic sends closed when Telegram reports `message thread not found` instead of retrying without `message_thread_id` into the base chat. Refs #83302.
·Config/subagents: remove ignored agent-model `timeoutMs` keys, keep subagent model config to primary/fallback selection, and clean shipped stale config through doctor. Fixes #83291.
·Mac app: align the Sessions settings pane with the standard Settings page gutter and row spacing.
·OpenAI/Codex: stop rejecting available `openai-codex` GPT-5.1, GPT-5.2, and GPT-5.3 model refs during config validation, while keeping removed Spark aliases suppressed. Fixes #83303.
·Plugins/xAI: complete OAuth-backed xAI login and sidecar auth fixes, including guarded loopback callback CORS handling, video generation polling/defaults, and native-host User-Agent attribution. (#83322)
·Codex app-server: preserve streamed native command output in mirrored transcripts and trajectory exports when final snapshots omit aggregated output. (#83200)
·Codex app-server: fail closed when chat or sender policy denies tools, disabling native code, app, environment, and user MCP surfaces for restricted turns. (#82374)
·Codex app-server: keep recent context-engine messages when oversized projected history is truncated, so short follow-ups in long channel sessions do not fall back to stale earlier turns. (#83127)
·Codex app-server: keep OpenClaw session spawning searchable while steering Codex-native delegation through native subagents, avoiding duplicate direct subagent surfaces. (#83329)
·Codex app-server: recover stale childless Codex-native subagent task mirrors during maintenance and allow their registry rows to be cancelled without an OpenClaw child session. (#82836)
·Feishu: return bound subagent delivery origins from session thread setup so Feishu subagent completions route back to the same DM or topic. (#83190)
·CLI/update: tailor post-update Gateway recovery hints by platform, showing systemd, LaunchAgent, Scheduled Task, or generic service-manager guidance instead of macOS-only recovery text. (#83096)
·Plugins: apply a default 15-second timeout to legacy `before_agent_start` hooks so hung plugin handlers no longer block agent startup. Fixes #48534. (#83136)
·Feishu: refresh inbound session delivery context for DM, group, and broadcast turns so later replies do not inherit stale WebChat routing. Fixes #78274.
·Agents/subagents: require the initial subagent registry save before reporting spawn accepted, returning a spawn error instead of losing an untracked run when the registry write fails. (#83146)
·QA-Lab/qa-channel: attach redacted agent tool-start traces to outbound `QaBusMessage` records so scenarios can assert actual tool use instead of relying only on reply text. Fixes #67637.
·QA-Lab: fail live runtime parity reports when assistant-message usage is missing, preventing `0 vs 0` live token rows from being reported as passing proof. Fixes #80411.
·QA-Lab: add a runtime token-efficiency sidecar report that classifies Codex savings separately from regressions and fails only positive Codex-over-Pi live token deltas above threshold. Fixes #81093.
·QA-Lab: fail Codex-backed OpenAI live runtime-pair runs before launching isolated workers when no portable Codex auth is available, while staging API-key fallbacks and configured Codex keys for isolated QA agents. Fixes #80412.
·QA-Lab: refresh parity gates, mock frontier fixtures, model scenarios, and workflow artifact lanes to compare GPT-5.5 against Claude Opus 4.7. Fixes #74262.
·QA-Lab: make mock parity dispatch provider-aware for source discovery and subagent scenarios so OpenAI and Anthropic lanes no longer share identical canned plans. Fixes #64879.
·QA-Lab: stop returning Control UI bearer tokens from unauthenticated bootstrap payloads and bind Docker harness ports to loopback-only host addresses. (#66355)
·Mac app: avoid a SwiftUI metadata crash when rendering the Cron Jobs settings pane.
·Agents/subagents: preserve run-mode keep subagent registry entries past the session sweep TTL, so kept subagent runs remain visible after cleanup completes. Fixes #83132. (#83168)
·Agents/OpenAI streams: yield via `setTimeout(0)` instead of `setImmediate` between bursty Responses chunks so abort timers can fire during the yield, keeping cancel-on-timeout responsive on hot streams. Refs #82462.
·Agents/Codex: keep legacy `oauthRef`-backed OAuth profiles usable while `openclaw doctor --fix` migrates them back to inline credentials, without creating new sidecar credentials. (#83312)
·CLI/config: send SecretRef diagnostics to stderr so JSON command stdout remains parseable.
·CLI/doctor: seed Control UI allowed origins when migrating legacy non-loopback gateway bind host aliases like `0.0.0.0`. Fixes #83286.
·CLI/plugins: ship the bundled memory CLI as a package entry so package-installed `openclaw memory` commands register correctly.
·CLI/update: defer doctor-time plugin package installs during package swaps and seed post-core repair from the updated install registry, preventing duplicate reinstall failures.
·CLI/update: preserve old-parent-readable config metadata during legacy package handoffs, fall back only to official `@openclaw/*` npm plugin packages when ClawHub plugin artifacts are unavailable, and keep managed service package roots authoritative during updates.
·Feishu: detect SecretRef top-level credentials as a configured default account instead of treating object-backed app secrets as missing.
·Gateway/restart: keep ordinary unmanaged SIGUSR1/config restarts in-process instead of detach-spawning an orphaned child, preserving custom supervisor PID tracking while leaving update restarts on the fresh-process path. Fixes #65668.
·CLI/completion: resolve concrete PowerShell profile paths and reload commands during setup and doctor completion installation. Fixes #44296. (#83059)
·Telegram: keep isolated long polling below the hard `getUpdates` request guard so idle bot accounts with high `timeoutSeconds` do not false-disconnect and restart-loop. Fixes #83264.
·Providers/Google: preserve and recover Gemini 3 tool-call thought signatures during native replay so function-calling turns no longer fail with missing `thought_signature` 400s. Fixes #72879. (#80358)
·Telegram: skip transcript-only delivery mirrors and gateway-injected rows when resolving latest assistant text, preventing retained previews from replacing final replies with stale fragments. Fixes #83159. (#83362)
·Memory/QMD: keep lexical search on raw hyphenated queries while normalizing semantic QMD sub-searches, avoiding fallback to the builtin index for dashed identifiers and dates. Fixes #81328.
·Memory-core: distinguish sqlite-vec load failures from missing semantic vector embeddings in degraded `memory index` warnings, so vector recall diagnostics point at unresolved dimensions instead of blaming sqlite-vec when the store is ready. Fixes #75624. (#83056)
·Agents/subagents: preserve sandbox-peer controller ownership while routing completion announcements back to the originating run session, keeping subagent control and completion delivery scoped correctly. Fixes #80201. (#80242)
·Gateway: continue restarting remaining channels when one hot-reload channel restart fails, while still reporting aggregate reload failure and rolling back plugin pre-replace stops. Fixes #83054.
·Telegram: keep hot-reload restarts from marking polling accounts manually stopped and restart isolated ingress cleanly after worker shutdown, preserving Telegram replies across config reloads. Fixes #83008. (#83410)
·Gateway/secrets: split the lightweight secrets runtime state and auth-store cache from the full secrets runtime and take a startup fast path when the gateway startup config has no SecretRef values, speeding up secrets startup while preserving cleanup and refresh semantics.
·Codex app-server: rotate oversized native Codex threads before resume and cap dynamic tool-result text entering native Codex sessions, preventing stale oversized context from surviving OpenClaw compaction. (#82981)
·Gateway/restart: drain pending replies and active chat runs during restart shutdown before sockets and channels close, aborting timed-out chat runs through the normal cleanup path. (#69121)
·Agents/Codex: use the Codex runtime context window for OpenAI-model preflight compaction and memory flush checks, so GPT-5.5 Codex sessions compact before hitting the smaller native context limit. Fixes #82982.
·QA-Lab: clean orphaned gateway temp roots when a suite parent exits and wait on gateway plus transport readiness after config restarts, reducing stale `qa-channel` noise from interrupted runs. Fixes #65506.
·QA-Lab: wake qa-bus long polls that arrive with stale future cursors after a bus restart, preserving reconnect readiness for harness clients. (#67142)
·QA-Lab: stage Multipass transfer scripts under OpenClaw's preferred temp root instead of raw OS temp paths, keeping the VM runner inside temp-path guardrails. (#64098)
·Agents/replies: keep surviving reply media and append a warning when other media references fail, so partial media normalization no longer drops failures silently.
·Config/models: accept `thinkingFormat: "together"` in model compat config so Together routes can opt into the Together-specific thinking response shape.
·Plugins/tokenjuice: bump the bundled tokenjuice runtime to 0.7.1, bringing Codex hook approval compatibility, pre-tool command wrapping fixes, and Rolldown/Vitest output compaction improvements into the OpenClaw plugin.
·Agents/OpenAI: stop post-processing GPT-5 final replies with hardcoded brevity caps, preserving full channel responses instead of appending synthetic ellipses, and log when strict-agentic GPT-5 execution activates. Fixes #82910.
·Mac app: refine the Settings General and Connection panes with cleaner status panels, card rows, and a single native titlebar sidebar toggle.
·Agents/media: deliver failed async image, music, and video generation completions directly when requester-session completion handoff fails, so channel users see provider errors instead of silent fallback stalls.
·Browser/CDP: keep loopback proxy bypass active across both `NO_PROXY` casings and redact home-relative Chrome MCP profile paths in attach-failure diagnostics.
·Agents/music: steer song, jingle, beat, anthem, and instrumental requests toward `music_generate` audio creation instead of lyric-only replies, and reserve `lyrics` for exact sung words.
·Codex app-server: record native Codex tool calls and results into trajectory artifacts so debug/trajectory exports capture the full Codex-native tool history, not just OpenClaw-bridged turns.
·Codex/app-server: keep bound conversation sessions on the owning agent runtime so native Codex control and follow-up turns do not fall back to the default agent client. Fixes #82954. (#82993)
·CLI/infer: run gateway model probes in fresh explicit sessions so one-shot provider checks do not inherit default agent transcript state. (#82861)
·Providers/Together: send video-generation requests to Together's v2 video API even when shared text-model config still points at the v1 base URL. (#82992)
·Browser CLI: preserve browser-level options on nested commands, skip option values during lazy command registration, and keep long-running wait/download/dialog hooks open for their advertised wait window.
·CLI/sessions: accept `openclaw sessions list` as an alias for `openclaw sessions`, matching other list-style commands. Fixes #81139. (#81163)
·Channels/stream previews: widen compact progress draft lines and cut prose at word boundaries while preserving command/path suffixes, with `streaming.progress.maxLineChars` for channel-specific tuning.
·CLI/plugins: have `openclaw plugins doctor` warn when a configured runtime needs a missing owner plugin, sharing the same install mapping as `openclaw doctor --fix`. Fixes #81326. (#81674)
·Agents/Codex: route OpenAI runs that resolve to `openai-codex` through the Codex provider and bootstrap OpenClaw's stored OAuth profile into the Codex harness when the harness owns transport, so `openai/*` model refs no longer fail with `No API key found for openai-codex` despite an existing Codex OAuth profile. (#82864)
·Agents/ACP: distinguish prompt-submitted and runtime-active child stalls from true interactive waits, including redacted proxy-env diagnostics for Codex ACP no-output runs. Fixes #44810.
·Agents/memory: explain that memory-triggered compaction exposes only `read` and append-only `write` when configured core tools are unavailable in `tools.allow` warnings. Fixes #82941.
·Agents/OpenAI: preserve deterministic tool payload ordering for prompt-cache reuse across OpenAI Responses and chat completions calls. (#82940)
·ACP/Codex: honor terminal ACP turn results so failed Codex/acpx runs are not recorded as successful after only progress text. Fixes #79522.
·Telegram: warn when a media group drops photos that fail to download, including albums where every photo is skipped. Fixes #55216. (#82987)
·Agents/skills: apply the full effective tool policy pipeline to inline `command-dispatch: tool` skill dispatch before owner-only filtering, preserving configured allow, deny, sandbox, sender, group, and subagent restrictions. (#78525)
·Codex: avoid spawning native hook relay subprocesses for post-tool/finalize events with no registered hook handlers while preserving pre-tool safety and approval relays. Fixes #76552. (#78004)
·Channel accounts: keep top-level default channel accounts visible when named accounts are added alongside default credential material, so mixed legacy/new account configs keep resolving `default` instead of silently dropping it.
·Codex/Telegram: synthesize native Codex tool progress from final turn snapshots so Telegram `/verbose` stays visible when command events arrive only at completion.
·Codex/Telegram: deliver Codex verbose tool summaries in direct message-tool-only turns while suppressing message-send and activity-log noise. (#83186)
·Mac app: make Channels settings open faster by deferring config-schema work, avoiding startup channel probes, caching decoded channel status rows, and showing only compact quick settings instead of the full generated channel schema.
·Control UI: include the Control UI and Gateway protocol versions in protocol-mismatch errors so stale app/dashboard pairings identify which side needs rebuilding or restarting.
·Gateway/protocol: restore Gateway WS protocol v4 and keep `message.action` room-event metadata on the existing `inboundTurnKind` wire field while preserving internal inbound-event classification.
·Agents/tools: prefer non-webchat session-key routes when the message tool has stale webchat context, so message-tool-only replies keep delivering to the originating channel. Fixes #82911. (#83004)
·Channels: keep direct-message last-route writes on isolated `per-channel-peer` sessions instead of contaminating the agent main session with channel delivery context. Fixes #36614.
·Mac app: move the Settings sidebar toggle into the native titlebar and tighten the General pane width.
·Mac app: keep visited Settings panes mounted so switching tabs no longer blanks and reloads their content.
·Mac app: make Config settings open from shallow schema lookups and load selected paths on demand instead of fetching and rendering the full generated config schema up front.
·Codex: sanitize inline image payloads before Codex app-server and OpenAI Responses replay, and clear poisoned Codex thread bindings after invalid image errors. Fixes #82878.
·Providers/GitHub Copilot: request identity-encoded Copilot API responses across token exchange, catalog, model calls, usage, and embeddings so compressed Business-account error payloads no longer reach JSON parsers as gzip bytes. Fixes #82871.
·Telegram: redact nested raw-update identifiers and user metadata before verbose raw update logging, preserving useful update/message ids without exposing chat, user, command, or profile details. (#82945)
·Telegram: preserve replied-to bot messages, captions, and media metadata in group reply chains so follow-up replies understand what the user is reacting to. (#82863)
·Providers/Together: update PI runtime packages to 0.74.1 and emit Together-style `reasoning.enabled`/`max_tokens` controls for reasoning-capable OpenAI-completions models.
·Agents/diagnostics: split slow embedded-run `attempt-dispatch` startup summaries into workspace, prompt, runtime-plan, and final dispatch subspans so traces identify the delayed setup phase. Fixes #82782. (#82783)
·Agents/Codex: flatten nested tool-result middleware blocks into bounded text so successful message sends are no longer replaced with `Tool output unavailable due to post-processing error`. Fixes #82912.
·CLI/media: accept HTTP(S) URLs in `openclaw infer image describe --file`, fetching remote images through the guarded media path instead of treating URLs as local files. Fixes #82837. (#82854)
·Agents/subagents: keep session-backed parent runs active when the child wait call times out before the child session has actually settled, so late subagent completions are reconciled instead of being lost. Fixes #82787.
·Control UI: advertise shared Gateway protocol constants in browser connect frames, fixing protocol mismatch handshakes after protocol constant drift. Fixes #82882.
·Gateway: add rollback protocol-mismatch diagnostics, including client protocol ranges in Gateway logs and deep status/doctor hints for stale client processes. Fixes #82841. (#82908)
·Agents/subagents: keep successful keep-mode completion payloads pending after final-delivery retry exhaustion, so requester recovery no longer loses final subagent results. Fixes #82583. (#82999)
·Gateway/auth: allow same-host trusted-proxy callers to use the documented local direct `gateway.auth.password` fallback after revisiting the #78684 fail-closed policy, while keeping token fallback rejected and forwarded-header requests on the trusted-proxy path. Fixes #82607. (#82953)
·Agents/subagents: wait for queued completion handoffs to reach the parent transcript before marking them announced, preventing busy parent runs from cleaning up before observing child results. Fixes #82913. (#83039)
·Agents/subagents: route group/channel subagent completions through message-tool-only handoffs when required and keep active-requester wake failures from dropping completion delivery. Fixes #82803.
·Memory-core: scan persisted memory source sessions on startup, comparing on-disk transcripts against the index and marking only missing/newer/resized files dirty for incremental sync. Fixes #82341. (#82341)
·Telegram: keep the top-level default account in the account list when named accounts or bindings are added alongside top-level credentials, preserving default polling while still letting named-only configs resolve to a single account. Fixes #82794. (#82794)
·CLI/models: reuse command-scoped plugin metadata across model listing, provider catalog, auth, and synthetic-auth checks, restoring fast `openclaw models` runs for plugin-heavy installs. Fixes #82881. (#83033)
·CLI/channels: show configured official external channels such as Discord in `openclaw channels list` when their plugin package is missing, including the install and doctor repair command instead of reporting no configured channels. Fixes #82813.
·Signal: preserve mixed-case group IDs through routing and session persistence so group auto-replies keep delivering after updates. Fixes #82827.
·Agents/tools: keep the `message` tool available in embedded runs when it is explicitly allowed through `tools.alsoAllow` or runtime tool allowlists, so channel plugins with custom reply delivery can still use configured message sends. Fixes #82833.
·WhatsApp: honor forced document delivery for outbound image, GIF, and video media so `forceDocument`/`asDocument` sends preserve original media bytes instead of using compressed media payloads. (#79272)
·WhatsApp: name outbound document attachments from their MIME type when no filename is provided, so PDF and CSV sends arrive as `file.pdf` and `file.csv` instead of an extensionless `file`.
·Process/diagnostics: report active lane blockers in lane wait warnings so `queueAhead=0` no longer hides commands waiting behind active work. Fixes #82791. (#82792)
·Process/diagnostics: stop counting the active processing turn as queued backlog in liveness warnings so transient max-only event-loop spikes do not surface as gateway warnings.
·Agents/replies: classify provider conversation-state rejections and return a clear message-channel error instead of auto-resetting or falling back to a generic runner failure. (#82616)
·Browser plugin: trust managed Chrome CDP diagnostics when launch HTTP probes race cold-start readiness, avoiding false startup failures. Fixes #82904. (#82986)
·Android: prompt before replacing a changed Gateway TLS thumbprint, showing the old and new SHA-256 fingerprints so users can accept expected certificate rotations instead of hard failing on pin mismatch. (#83077)
·CLI/status: render extra gateway-like service diagnostics as warning/info output instead of error output. Fixes #46930. (#82922)
·Agents/failover: classify Moonshot/Kimi exhausted-balance HTTP 429 payloads as billing instead of generic rate limits, preserving billing guidance and fallback behavior. Fixes #43447. (#83079)
·Plugin SDK: bundle `openclaw/plugin-sdk/zod` into the published package artifact and verify the packed zod subpath stays self-contained, so pnpm global installs can register plugins without a package-local `zod` symlink. Fixes #78398. (#78515)
·Providers/Google: drop compaction-truncated Gemini thought signatures before replay so malformed Base64 no longer aborts the next assistant turn. (#82995)

v2026.5.16-beta.6pre-release2026-05-18

openclaw 2026.5.16-beta.6

GitHub ↗

Changes

·Mac app: redesign Settings pages with consistent card layouts, cached navigation, cleaner permissions/voice/skills/cron/exec/debug panes, and steadier spacing around the native sidebar.
·Skills: rename the repo-local Codex closeout review skill and helper to `autoreview` while preserving the Codex-first fallback behavior.
·Skills: add a meme-maker skill for curated template search, local SVG/PNG rendering, Imgflip hosted rendering, and Know Your Meme provenance links.
·Browser: surface pending and recently handled modal dialogs in snapshots, return `blockedByDialog` when an action opens a modal, and allow `browser dialog --dialog-id` to answer pending dialogs.
·Agents/tools: shorten built-in tool descriptions and schema hints across media, messaging, sessions, cron, Gateway, web, image/PDF, TTS, nodes, and plan tools while preserving routing guardrails.
·Skills: add node inspector debugging, fused diagram generation, and throwaway spike workflow skills.
·CLI/plugins: add `defineToolPlugin` plus `openclaw plugins build`, `validate`, and `init` for typed simple tool plugins with generated manifest metadata, optional tool declarations, and context factories.
·Agents/skills: tighten bundled skill prompts and metadata, quote skill descriptions, refresh current CLI/API guidance, and update embedded sherpa-onnx runtime downloads.
·Skills: update the Obsidian skill to target the official `obsidian` CLI and require its registered binary instead of the third-party `obsidian-cli`.
·Skills: add a Python debugging skill for pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.
·Plugins/messages: add presentation capability limits for channel renderers, adapt rich message controls before native rendering, and mark legacy `interactive`/Slack directive producer APIs as deprecated.
·Proxy: support HTTPS managed forward-proxy endpoints and scoped `proxy.tls.caFile` CA trust for proxy endpoint TLS. (#79171)
·QA-Lab: add first-hour 20-turn and optional 100-turn runtime parity scenarios, with tier metadata for standard and soak QA gates. Fixes #80338; refs #80337.
·QA-Lab: add `openclaw qa suite --runtime-parity-tier` and wire the standard Codex-vs-Pi tier into release checks separately from optional/live-only/soak lanes. Fixes #80337.
·QA-Lab: add a live-only Codex Pi-shaped Read vocabulary canary so runtime parity catches native workspace-read prompt compatibility drift. (#80323)
·QA-Lab: add live-only harness self-health scenarios for plugin hook crashes, manifest contract errors, and WebChat direct-reply self-message routing. (#80323)
·QA-Lab: add runtime tool fixture scenarios and coverage reporting for Codex-native workspace tools, OpenClaw dynamic tools, and optional plugin-backed tools. Fixes #80173.
·QA-Lab: expose runtime tool fixture coverage through `openclaw qa coverage --tools`, with optional suite-summary evaluation for parity gate artifacts.
·QA-Lab: add the personal-agent approval-denial scenario so the benchmark pack verifies denied local reads stop cleanly without tool progress or fixture leaks. (#83150)

Fixes

·Mac app: keep app-level menu commands and Dashboard failure states reachable when the remote Gateway is disconnected, and keep the Settings sidebar toggle in the leading titlebar area.
·Gateway/webchat: hide internal runtime-context and other `display: false` transcript messages from Chat history and live message events. Fixes #83216.
·Mac app: align the Sessions settings pane with the standard Settings page gutter and row spacing.
·OpenAI/Codex: stop rejecting available `openai-codex` GPT-5.1, GPT-5.2, and GPT-5.3 model refs during config validation, while keeping removed Spark aliases suppressed. Fixes #83303.
·Codex app-server: preserve streamed native command output in mirrored transcripts and trajectory exports when final snapshots omit aggregated output. (#83200)
·Codex app-server: fail closed when chat or sender policy denies tools, disabling native code, app, environment, and user MCP surfaces for restricted turns. (#82374)
·Codex app-server: keep recent context-engine messages when oversized projected history is truncated, so short follow-ups in long channel sessions do not fall back to stale earlier turns. (#83127)
·Feishu: return bound subagent delivery origins from session thread setup so Feishu subagent completions route back to the same DM or topic. (#83190)
·CLI/update: tailor post-update Gateway recovery hints by platform, showing systemd, LaunchAgent, Scheduled Task, or generic service-manager guidance instead of macOS-only recovery text. (#83096)
·Plugins: apply a default 15-second timeout to legacy `before_agent_start` hooks so hung plugin handlers no longer block agent startup. Fixes #48534. (#83136)
·Feishu: refresh inbound session delivery context for DM, group, and broadcast turns so later replies do not inherit stale WebChat routing. Fixes #78274.
·Agents/subagents: require the initial subagent registry save before reporting spawn accepted, returning a spawn error instead of losing an untracked run when the registry write fails. (#83146)
·QA-Lab/qa-channel: attach redacted agent tool-start traces to outbound `QaBusMessage` records so scenarios can assert actual tool use instead of relying only on reply text. Fixes #67637.
·QA-Lab: fail live runtime parity reports when assistant-message usage is missing, preventing `0 vs 0` live token rows from being reported as passing proof. Fixes #80411.
·QA-Lab: fail Codex-backed OpenAI live runtime-pair runs before launching isolated workers when no portable Codex auth is available, while staging API-key fallbacks and configured Codex keys for isolated QA agents. Fixes #80412.
·QA-Lab: refresh parity gates, mock frontier fixtures, model scenarios, and workflow artifact lanes to compare GPT-5.5 against Claude Opus 4.7. Fixes #74262.
·QA-Lab: make mock parity dispatch provider-aware for source discovery and subagent scenarios so OpenAI and Anthropic lanes no longer share identical canned plans. Fixes #64879.
·QA-Lab: stop returning Control UI bearer tokens from unauthenticated bootstrap payloads and bind Docker harness ports to loopback-only host addresses. (#66355)
·Mac app: avoid a SwiftUI metadata crash when rendering the Cron Jobs settings pane.
·Agents/subagents: preserve run-mode keep subagent registry entries past the session sweep TTL, so kept subagent runs remain visible after cleanup completes. Fixes #83132. (#83168)
·Agents/OpenAI streams: yield via `setTimeout(0)` instead of `setImmediate` between bursty Responses chunks so abort timers can fire during the yield, keeping cancel-on-timeout responsive on hot streams. Refs #82462.
·Agents/Codex: keep legacy `oauthRef`-backed OAuth profiles usable while `openclaw doctor --fix` migrates them back to inline credentials, without creating new sidecar credentials. (#83312)
·CLI/config: send SecretRef diagnostics to stderr so JSON command stdout remains parseable.
·CLI/plugins: ship the bundled memory CLI as a package entry so package-installed `openclaw memory` commands register correctly.
·CLI/update: defer doctor-time plugin package installs during package swaps and seed post-core repair from the updated install registry, preventing duplicate reinstall failures.
·Feishu: detect SecretRef top-level credentials as a configured default account instead of treating object-backed app secrets as missing.
·Gateway/restart: keep ordinary unmanaged SIGUSR1/config restarts in-process instead of detach-spawning an orphaned child, preserving custom supervisor PID tracking while leaving update restarts on the fresh-process path. Fixes #65668.
·CLI/completion: resolve concrete PowerShell profile paths and reload commands during setup and doctor completion installation. Fixes #44296. (#83059)
·Telegram: keep isolated long polling below the hard `getUpdates` request guard so idle bot accounts with high `timeoutSeconds` do not false-disconnect and restart-loop. Fixes #83264.
·Providers/Google: preserve and recover Gemini 3 tool-call thought signatures during native replay so function-calling turns no longer fail with missing `thought_signature` 400s. Fixes #72879. (#80358)
·Memory/QMD: keep lexical search on raw hyphenated queries while normalizing semantic QMD sub-searches, avoiding fallback to the builtin index for dashed identifiers and dates. Fixes #81328.
·Memory-core: distinguish sqlite-vec load failures from missing semantic vector embeddings in degraded `memory index` warnings, so vector recall diagnostics point at unresolved dimensions instead of blaming sqlite-vec when the store is ready. Fixes #75624. (#83056)
·Agents/subagents: preserve sandbox-peer controller ownership while routing completion announcements back to the originating run session, keeping subagent control and completion delivery scoped correctly. Fixes #80201. (#80242)
·Gateway: continue restarting remaining channels when one hot-reload channel restart fails, while still reporting aggregate reload failure and rolling back plugin pre-replace stops. Fixes #83054.
·Gateway/secrets: split the lightweight secrets runtime state and auth-store cache from the full secrets runtime and take a startup fast path when the gateway startup config has no SecretRef values, speeding up secrets startup while preserving cleanup and refresh semantics.
·Codex app-server: rotate oversized native Codex threads before resume and cap dynamic tool-result text entering native Codex sessions, preventing stale oversized context from surviving OpenClaw compaction. (#82981)
·Gateway/restart: drain pending replies and active chat runs during restart shutdown before sockets and channels close, aborting timed-out chat runs through the normal cleanup path. (#69121)
·Agents/Codex: use the Codex runtime context window for OpenAI-model preflight compaction and memory flush checks, so GPT-5.5 Codex sessions compact before hitting the smaller native context limit. Fixes #82982.
·QA-Lab: clean orphaned gateway temp roots when a suite parent exits and wait on gateway plus transport readiness after config restarts, reducing stale `qa-channel` noise from interrupted runs. Fixes #65506.
·QA-Lab: wake qa-bus long polls that arrive with stale future cursors after a bus restart, preserving reconnect readiness for harness clients. (#67142)
·QA-Lab: stage Multipass transfer scripts under OpenClaw's preferred temp root instead of raw OS temp paths, keeping the VM runner inside temp-path guardrails. (#64098)
·Agents/replies: keep surviving reply media and append a warning when other media references fail, so partial media normalization no longer drops failures silently.
·Config/models: accept `thinkingFormat: "together"` in model compat config so Together routes can opt into the Together-specific thinking response shape.
·Plugins/tokenjuice: bump the bundled tokenjuice runtime to 0.7.1, bringing Codex hook approval compatibility, pre-tool command wrapping fixes, and Rolldown/Vitest output compaction improvements into the OpenClaw plugin.
·Agents/OpenAI: stop post-processing GPT-5 final replies with hardcoded brevity caps, preserving full channel responses instead of appending synthetic ellipses, and log when strict-agentic GPT-5 execution activates. Fixes #82910.
·Mac app: refine the Settings General and Connection panes with cleaner status panels, card rows, and a single native titlebar sidebar toggle.
·Agents/media: deliver failed async image, music, and video generation completions directly when requester-session completion handoff fails, so channel users see provider errors instead of silent fallback stalls.
·Agents/music: steer song, jingle, beat, anthem, and instrumental requests toward `music_generate` audio creation instead of lyric-only replies, and reserve `lyrics` for exact sung words.
·Codex app-server: record native Codex tool calls and results into trajectory artifacts so debug/trajectory exports capture the full Codex-native tool history, not just OpenClaw-bridged turns.
·Codex/app-server: keep bound conversation sessions on the owning agent runtime so native Codex control and follow-up turns do not fall back to the default agent client. Fixes #82954. (#82993)
·CLI/infer: run gateway model probes in fresh explicit sessions so one-shot provider checks do not inherit default agent transcript state. (#82861)
·Providers/Together: send video-generation requests to Together's v2 video API even when shared text-model config still points at the v1 base URL. (#82992)
·Browser CLI: preserve browser-level options on nested commands, skip option values during lazy command registration, and keep long-running wait/download/dialog hooks open for their advertised wait window.
·CLI/sessions: accept `openclaw sessions list` as an alias for `openclaw sessions`, matching other list-style commands. Fixes #81139. (#81163)
·Channels/stream previews: widen compact progress draft lines and cut prose at word boundaries while preserving command/path suffixes, with `streaming.progress.maxLineChars` for channel-specific tuning.
·CLI/plugins: have `openclaw plugins doctor` warn when a configured runtime needs a missing owner plugin, sharing the same install mapping as `openclaw doctor --fix`. Fixes #81326. (#81674)
·Agents/Codex: route OpenAI runs that resolve to `openai-codex` through the Codex provider and bootstrap OpenClaw's stored OAuth profile into the Codex harness when the harness owns transport, so `openai/*` model refs no longer fail with `No API key found for openai-codex` despite an existing Codex OAuth profile. (#82864)
·Agents/ACP: distinguish prompt-submitted and runtime-active child stalls from true interactive waits, including redacted proxy-env diagnostics for Codex ACP no-output runs. Fixes #44810.
·Agents/memory: explain that memory-triggered compaction exposes only `read` and append-only `write` when configured core tools are unavailable in `tools.allow` warnings. Fixes #82941.
·Agents/OpenAI: preserve deterministic tool payload ordering for prompt-cache reuse across OpenAI Responses and chat completions calls. (#82940)
·ACP/Codex: honor terminal ACP turn results so failed Codex/acpx runs are not recorded as successful after only progress text. Fixes #79522.
·Telegram: warn when a media group drops photos that fail to download, including albums where every photo is skipped. Fixes #55216. (#82987)
·Agents/skills: apply the full effective tool policy pipeline to inline `command-dispatch: tool` skill dispatch before owner-only filtering, preserving configured allow, deny, sandbox, sender, group, and subagent restrictions. (#78525)
·Codex: avoid spawning native hook relay subprocesses for post-tool/finalize events with no registered hook handlers while preserving pre-tool safety and approval relays. Fixes #76552. (#78004)
·Channel accounts: keep top-level default channel accounts visible when named accounts are added alongside default credential material, so mixed legacy/new account configs keep resolving `default` instead of silently dropping it.
·Codex/Telegram: synthesize native Codex tool progress from final turn snapshots so Telegram `/verbose` stays visible when command events arrive only at completion.
·Codex/Telegram: deliver Codex verbose tool summaries in direct message-tool-only turns while suppressing message-send and activity-log noise. (#83186)
·Mac app: make Channels settings open faster by deferring config-schema work, avoiding startup channel probes, caching decoded channel status rows, and showing only compact quick settings instead of the full generated channel schema.
·Control UI: include the Control UI and Gateway protocol versions in protocol-mismatch errors so stale app/dashboard pairings identify which side needs rebuilding or restarting.
·Gateway/protocol: restore Gateway WS protocol v4 and keep `message.action` room-event metadata on the existing `inboundTurnKind` wire field while preserving internal inbound-event classification.
·Agents/tools: prefer non-webchat session-key routes when the message tool has stale webchat context, so message-tool-only replies keep delivering to the originating channel. Fixes #82911. (#83004)
·Channels: keep direct-message last-route writes on isolated `per-channel-peer` sessions instead of contaminating the agent main session with channel delivery context. Fixes #36614.
·Mac app: move the Settings sidebar toggle into the native titlebar and tighten the General pane width.
·Mac app: keep visited Settings panes mounted so switching tabs no longer blanks and reloads their content.
·Mac app: make Config settings open from shallow schema lookups and load selected paths on demand instead of fetching and rendering the full generated config schema up front.
·Codex: sanitize inline image payloads before Codex app-server and OpenAI Responses replay, and clear poisoned Codex thread bindings after invalid image errors. Fixes #82878.
·Providers/GitHub Copilot: request identity-encoded Copilot API responses across token exchange, catalog, model calls, usage, and embeddings so compressed Business-account error payloads no longer reach JSON parsers as gzip bytes. Fixes #82871.
·Telegram: preserve replied-to bot messages, captions, and media metadata in group reply chains so follow-up replies understand what the user is reacting to. (#82863)
·Providers/Together: update PI runtime packages to 0.74.1 and emit Together-style `reasoning.enabled`/`max_tokens` controls for reasoning-capable OpenAI-completions models.
·Agents/diagnostics: split slow embedded-run `attempt-dispatch` startup summaries into workspace, prompt, runtime-plan, and final dispatch subspans so traces identify the delayed setup phase. Fixes #82782. (#82783)
·Agents/Codex: flatten nested tool-result middleware blocks into bounded text so successful message sends are no longer replaced with `Tool output unavailable due to post-processing error`. Fixes #82912.
·CLI/media: accept HTTP(S) URLs in `openclaw infer image describe --file`, fetching remote images through the guarded media path instead of treating URLs as local files. Fixes #82837. (#82854)
·Agents/subagents: keep session-backed parent runs active when the child wait call times out before the child session has actually settled, so late subagent completions are reconciled instead of being lost. Fixes #82787.
·Control UI: advertise shared Gateway protocol constants in browser connect frames, fixing protocol mismatch handshakes after protocol constant drift. Fixes #82882.
·Gateway: add rollback protocol-mismatch diagnostics, including client protocol ranges in Gateway logs and deep status/doctor hints for stale client processes. Fixes #82841. (#82908)
·Agents/subagents: keep successful keep-mode completion payloads pending after final-delivery retry exhaustion, so requester recovery no longer loses final subagent results. Fixes #82583. (#82999)
·Gateway/auth: allow same-host trusted-proxy callers to use the documented local direct `gateway.auth.password` fallback after revisiting the #78684 fail-closed policy, while keeping token fallback rejected and forwarded-header requests on the trusted-proxy path. Fixes #82607. (#82953)
·Agents/subagents: wait for queued completion handoffs to reach the parent transcript before marking them announced, preventing busy parent runs from cleaning up before observing child results. Fixes #82913. (#83039)
·Agents/subagents: route group/channel subagent completions through message-tool-only handoffs when required and keep active-requester wake failures from dropping completion delivery. Fixes #82803.
·Memory-core: scan persisted memory source sessions on startup, comparing on-disk transcripts against the index and marking only missing/newer/resized files dirty for incremental sync. Fixes #82341. (#82341)
·Telegram: keep the top-level default account in the account list when named accounts or bindings are added alongside top-level credentials, preserving default polling while still letting named-only configs resolve to a single account. Fixes #82794. (#82794)
·CLI/models: reuse command-scoped plugin metadata across model listing, provider catalog, auth, and synthetic-auth checks, restoring fast `openclaw models` runs for plugin-heavy installs. Fixes #82881. (#83033)
·CLI/channels: show configured official external channels such as Discord in `openclaw channels list` when their plugin package is missing, including the install and doctor repair command instead of reporting no configured channels. Fixes #82813.
·Signal: preserve mixed-case group IDs through routing and session persistence so group auto-replies keep delivering after updates. Fixes #82827.
·Agents/tools: keep the `message` tool available in embedded runs when it is explicitly allowed through `tools.alsoAllow` or runtime tool allowlists, so channel plugins with custom reply delivery can still use configured message sends. Fixes #82833.
·WhatsApp: honor forced document delivery for outbound image, GIF, and video media so `forceDocument`/`asDocument` sends preserve original media bytes instead of using compressed media payloads. (#79272)
·WhatsApp: name outbound document attachments from their MIME type when no filename is provided, so PDF and CSV sends arrive as `file.pdf` and `file.csv` instead of an extensionless `file`.
·Process/diagnostics: report active lane blockers in lane wait warnings so `queueAhead=0` no longer hides commands waiting behind active work. Fixes #82791. (#82792)
·Process/diagnostics: stop counting the active processing turn as queued backlog in liveness warnings so transient max-only event-loop spikes do not surface as gateway warnings.
·Agents/replies: classify provider conversation-state rejections and return a clear message-channel error instead of auto-resetting or falling back to a generic runner failure. (#82616)
·Browser plugin: trust managed Chrome CDP diagnostics when launch HTTP probes race cold-start readiness, avoiding false startup failures. Fixes #82904. (#82986)
·Android: prompt before replacing a changed Gateway TLS thumbprint, showing the old and new SHA-256 fingerprints so users can accept expected certificate rotations instead of hard failing on pin mismatch. (#83077)
·CLI/status: render extra gateway-like service diagnostics as warning/info output instead of error output. Fixes #46930. (#82922)
·Agents/failover: classify Moonshot/Kimi exhausted-balance HTTP 429 payloads as billing instead of generic rate limits, preserving billing guidance and fallback behavior. Fixes #43447. (#83079)
·Plugin SDK: bundle `openclaw/plugin-sdk/zod` into the published package artifact and verify the packed zod subpath stays self-contained, so pnpm global installs can register plugins without a package-local `zod` symlink. Fixes #78398. (#78515)
·Providers/Google: drop compaction-truncated Gemini thought signatures before replay so malformed Base64 no longer aborts the next assistant turn. (#82995)

v2026.5.16-beta.5pre-release2026-05-17

openclaw 2026.5.16-beta.5

GitHub ↗

Changes

·Mac app: redesign Settings pages with consistent card layouts, cached navigation, cleaner permissions/voice/skills/cron/exec/debug panes, and steadier spacing around the native sidebar.
·Skills: rename the repo-local Codex closeout review skill and helper to `autoreview` while preserving the Codex-first fallback behavior.
·Skills: add a meme-maker skill for curated template search, local SVG/PNG rendering, Imgflip hosted rendering, and Know Your Meme provenance links.
·Agents/tools: shorten built-in tool descriptions and schema hints across media, messaging, sessions, cron, Gateway, web, image/PDF, TTS, nodes, and plan tools while preserving routing guardrails.
·Skills: add node inspector debugging, fused diagram generation, and throwaway spike workflow skills.
·CLI/plugins: add `defineToolPlugin` plus `openclaw plugins build`, `validate`, and `init` for typed simple tool plugins with generated manifest metadata, optional tool declarations, and context factories.
·Agents/skills: tighten bundled skill prompts and metadata, quote skill descriptions, refresh current CLI/API guidance, and update embedded sherpa-onnx runtime downloads.
·Skills: update the Obsidian skill to target the official `obsidian` CLI and require its registered binary instead of the third-party `obsidian-cli`.
·Skills: add a Python debugging skill for pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.
·Plugins/messages: add presentation capability limits for channel renderers, adapt rich message controls before native rendering, and mark legacy `interactive`/Slack directive producer APIs as deprecated.
·Proxy: support HTTPS managed forward-proxy endpoints and scoped `proxy.tls.caFile` CA trust for proxy endpoint TLS. (#79171)
·QA-Lab: add first-hour 20-turn and optional 100-turn runtime parity scenarios, with tier metadata for standard and soak QA gates. Fixes #80338; refs #80337.
·QA-Lab: add `openclaw qa suite --runtime-parity-tier` and wire the standard Codex-vs-Pi tier into release checks separately from optional/live-only/soak lanes. Fixes #80337.
·QA-Lab: add a live-only Codex Pi-shaped Read vocabulary canary so runtime parity catches native workspace-read prompt compatibility drift. (#80323)
·QA-Lab: add live-only harness self-health scenarios for plugin hook crashes, manifest contract errors, and WebChat direct-reply self-message routing. (#80323)
·QA-Lab: add runtime tool fixture scenarios and coverage reporting for Codex-native workspace tools, OpenClaw dynamic tools, and optional plugin-backed tools. Fixes #80173.
·QA-Lab: expose runtime tool fixture coverage through `openclaw qa coverage --tools`, with optional suite-summary evaluation for parity gate artifacts.
·QA-Lab: add the personal-agent approval-denial scenario so the benchmark pack verifies denied local reads stop cleanly without tool progress or fixture leaks. (#83150)

Fixes

·CLI/update: tailor post-update Gateway recovery hints by platform, showing systemd, LaunchAgent, Scheduled Task, or generic service-manager guidance instead of macOS-only recovery text. (#83096)
·Plugins: apply a default 15-second timeout to legacy `before_agent_start` hooks so hung plugin handlers no longer block agent startup. Fixes #48534. (#83136)
·Feishu: refresh inbound session delivery context for DM, group, and broadcast turns so later replies do not inherit stale WebChat routing. Fixes #78274.
·QA-Lab/qa-channel: attach redacted agent tool-start traces to outbound `QaBusMessage` records so scenarios can assert actual tool use instead of relying only on reply text. Fixes #67637.
·QA-Lab: fail live runtime parity reports when assistant-message usage is missing, preventing `0 vs 0` live token rows from being reported as passing proof. Fixes #80411.
·QA-Lab: fail Codex-backed OpenAI live runtime-pair runs before launching isolated workers when no portable Codex auth is available, while staging API-key fallbacks and configured Codex keys for isolated QA agents. Fixes #80412.
·QA-Lab: refresh parity gates, mock frontier fixtures, model scenarios, and workflow artifact lanes to compare GPT-5.5 against Claude Opus 4.7. Fixes #74262.
·QA-Lab: make mock parity dispatch provider-aware for source discovery and subagent scenarios so OpenAI and Anthropic lanes no longer share identical canned plans. Fixes #64879.
·QA-Lab: stop returning Control UI bearer tokens from unauthenticated bootstrap payloads and bind Docker harness ports to loopback-only host addresses. (#66355)
·Mac app: avoid a SwiftUI metadata crash when rendering the Cron Jobs settings pane.
·Agents/OpenAI streams: yield via `setTimeout(0)` instead of `setImmediate` between bursty Responses chunks so abort timers can fire during the yield, keeping cancel-on-timeout responsive on hot streams. Refs #82462.
·CLI/config: send SecretRef diagnostics to stderr so JSON command stdout remains parseable.
·CLI/plugins: ship the bundled memory CLI as a package entry so package-installed `openclaw memory` commands register correctly.
·CLI/update: defer doctor-time plugin package installs during package swaps and seed post-core repair from the updated install registry, preventing duplicate reinstall failures.
·Feishu: detect SecretRef top-level credentials as a configured default account instead of treating object-backed app secrets as missing.
·CLI/completion: resolve concrete PowerShell profile paths and reload commands during setup and doctor completion installation. Fixes #44296. (#83059)
·Providers/Google: preserve and recover Gemini 3 tool-call thought signatures during native replay so function-calling turns no longer fail with missing `thought_signature` 400s. Fixes #72879. (#80358)
·Memory-core: distinguish sqlite-vec load failures from missing semantic vector embeddings in degraded `memory index` warnings, so vector recall diagnostics point at unresolved dimensions instead of blaming sqlite-vec when the store is ready. Fixes #75624. (#83056)
·Agents/subagents: preserve sandbox-peer controller ownership while routing completion announcements back to the originating run session, keeping subagent control and completion delivery scoped correctly. Fixes #80201. (#80242)
·Gateway: continue restarting remaining channels when one hot-reload channel restart fails, while still reporting aggregate reload failure and rolling back plugin pre-replace stops. Fixes #83054.
·Gateway/secrets: split the lightweight secrets runtime state and auth-store cache from the full secrets runtime and take a startup fast path when the gateway startup config has no SecretRef values, speeding up secrets startup while preserving cleanup and refresh semantics.
·Codex app-server: rotate oversized native Codex threads before resume and cap dynamic tool-result text entering native Codex sessions, preventing stale oversized context from surviving OpenClaw compaction. (#82981)
·Gateway/restart: drain pending replies and active chat runs during restart shutdown before sockets and channels close, aborting timed-out chat runs through the normal cleanup path. (#69121)
·Agents/Codex: use the Codex runtime context window for OpenAI-model preflight compaction and memory flush checks, so GPT-5.5 Codex sessions compact before hitting the smaller native context limit. Fixes #82982.
·QA-Lab: clean orphaned gateway temp roots when a suite parent exits and wait on gateway plus transport readiness after config restarts, reducing stale `qa-channel` noise from interrupted runs. Fixes #65506.
·QA-Lab: wake qa-bus long polls that arrive with stale future cursors after a bus restart, preserving reconnect readiness for harness clients. (#67142)
·QA-Lab: stage Multipass transfer scripts under OpenClaw's preferred temp root instead of raw OS temp paths, keeping the VM runner inside temp-path guardrails. (#64098)
·Agents/replies: keep surviving reply media and append a warning when other media references fail, so partial media normalization no longer drops failures silently.
·Config/models: accept `thinkingFormat: "together"` in model compat config so Together routes can opt into the Together-specific thinking response shape.
·Plugins/tokenjuice: bump the bundled tokenjuice runtime to 0.7.1, bringing Codex hook approval compatibility, pre-tool command wrapping fixes, and Rolldown/Vitest output compaction improvements into the OpenClaw plugin.
·Agents/OpenAI: stop post-processing GPT-5 final replies with hardcoded brevity caps, preserving full channel responses instead of appending synthetic ellipses, and log when strict-agentic GPT-5 execution activates. Fixes #82910.
·Mac app: refine the Settings General and Connection panes with cleaner status panels, card rows, and a single native titlebar sidebar toggle.
·Agents/media: deliver failed async image, music, and video generation completions directly when requester-session completion handoff fails, so channel users see provider errors instead of silent fallback stalls.
·Agents/music: steer song, jingle, beat, anthem, and instrumental requests toward `music_generate` audio creation instead of lyric-only replies, and reserve `lyrics` for exact sung words.
·Codex app-server: record native Codex tool calls and results into trajectory artifacts so debug/trajectory exports capture the full Codex-native tool history, not just OpenClaw-bridged turns.
·Codex/app-server: keep bound conversation sessions on the owning agent runtime so native Codex control and follow-up turns do not fall back to the default agent client. Fixes #82954. (#82993)
·CLI/infer: run gateway model probes in fresh explicit sessions so one-shot provider checks do not inherit default agent transcript state. (#82861)
·Providers/Together: send video-generation requests to Together's v2 video API even when shared text-model config still points at the v1 base URL. (#82992)
·Browser CLI: preserve browser-level options on nested commands, skip option values during lazy command registration, and keep long-running wait/download/dialog hooks open for their advertised wait window.
·CLI/sessions: accept `openclaw sessions list` as an alias for `openclaw sessions`, matching other list-style commands. Fixes #81139. (#81163)
·Channels/stream previews: widen compact progress draft lines and cut prose at word boundaries while preserving command/path suffixes, with `streaming.progress.maxLineChars` for channel-specific tuning.
·CLI/plugins: have `openclaw plugins doctor` warn when a configured runtime needs a missing owner plugin, sharing the same install mapping as `openclaw doctor --fix`. Fixes #81326. (#81674)
·Agents/Codex: route OpenAI runs that resolve to `openai-codex` through the Codex provider and bootstrap OpenClaw's stored OAuth profile into the Codex harness when the harness owns transport, so `openai/*` model refs no longer fail with `No API key found for openai-codex` despite an existing Codex OAuth profile. (#82864)
·Agents/ACP: distinguish prompt-submitted and runtime-active child stalls from true interactive waits, including redacted proxy-env diagnostics for Codex ACP no-output runs. Fixes #44810.
·Agents/memory: explain that memory-triggered compaction exposes only `read` and append-only `write` when configured core tools are unavailable in `tools.allow` warnings. Fixes #82941.
·Agents/OpenAI: preserve deterministic tool payload ordering for prompt-cache reuse across OpenAI Responses and chat completions calls. (#82940)
·ACP/Codex: honor terminal ACP turn results so failed Codex/acpx runs are not recorded as successful after only progress text. Fixes #79522.
·Telegram: warn when a media group drops photos that fail to download, including albums where every photo is skipped. Fixes #55216. (#82987)
·Agents/skills: apply the full effective tool policy pipeline to inline `command-dispatch: tool` skill dispatch before owner-only filtering, preserving configured allow, deny, sandbox, sender, group, and subagent restrictions. (#78525)
·Codex: avoid spawning native hook relay subprocesses for post-tool/finalize events with no registered hook handlers while preserving pre-tool safety and approval relays. Fixes #76552. (#78004)
·Channel accounts: keep top-level default channel accounts visible when named accounts are added alongside default credential material, so mixed legacy/new account configs keep resolving `default` instead of silently dropping it.
·Codex/Telegram: synthesize native Codex tool progress from final turn snapshots so Telegram `/verbose` stays visible when command events arrive only at completion.
·Mac app: make Channels settings open faster by deferring config-schema work, avoiding startup channel probes, caching decoded channel status rows, and showing only compact quick settings instead of the full generated channel schema.
·Control UI: include the Control UI and Gateway protocol versions in protocol-mismatch errors so stale app/dashboard pairings identify which side needs rebuilding or restarting.
·Gateway/protocol: restore Gateway WS protocol v4 and keep `message.action` room-event metadata on the existing `inboundTurnKind` wire field while preserving internal inbound-event classification.
·Agents/tools: prefer non-webchat session-key routes when the message tool has stale webchat context, so message-tool-only replies keep delivering to the originating channel. Fixes #82911. (#83004)
·Channels: keep direct-message last-route writes on isolated `per-channel-peer` sessions instead of contaminating the agent main session with channel delivery context. Fixes #36614.
·Mac app: move the Settings sidebar toggle into the native titlebar and tighten the General pane width.
·Mac app: keep visited Settings panes mounted so switching tabs no longer blanks and reloads their content.
·Mac app: make Config settings open from shallow schema lookups and load selected paths on demand instead of fetching and rendering the full generated config schema up front.
·Codex: sanitize inline image payloads before Codex app-server and OpenAI Responses replay, and clear poisoned Codex thread bindings after invalid image errors. Fixes #82878.
·Providers/GitHub Copilot: request identity-encoded Copilot API responses across token exchange, catalog, model calls, usage, and embeddings so compressed Business-account error payloads no longer reach JSON parsers as gzip bytes. Fixes #82871.
·Telegram: preserve replied-to bot messages, captions, and media metadata in group reply chains so follow-up replies understand what the user is reacting to. (#82863)
·Providers/Together: update PI runtime packages to 0.74.1 and emit Together-style `reasoning.enabled`/`max_tokens` controls for reasoning-capable OpenAI-completions models.
·Agents/diagnostics: split slow embedded-run `attempt-dispatch` startup summaries into workspace, prompt, runtime-plan, and final dispatch subspans so traces identify the delayed setup phase. Fixes #82782. (#82783)
·Agents/Codex: flatten nested tool-result middleware blocks into bounded text so successful message sends are no longer replaced with `Tool output unavailable due to post-processing error`. Fixes #82912.
·CLI/media: accept HTTP(S) URLs in `openclaw infer image describe --file`, fetching remote images through the guarded media path instead of treating URLs as local files. Fixes #82837. (#82854)
·Agents/subagents: keep session-backed parent runs active when the child wait call times out before the child session has actually settled, so late subagent completions are reconciled instead of being lost. Fixes #82787.
·Control UI: advertise shared Gateway protocol constants in browser connect frames, fixing protocol mismatch handshakes after protocol constant drift. Fixes #82882.
·Gateway: add rollback protocol-mismatch diagnostics, including client protocol ranges in Gateway logs and deep status/doctor hints for stale client processes. Fixes #82841. (#82908)
·Agents/subagents: keep successful keep-mode completion payloads pending after final-delivery retry exhaustion, so requester recovery no longer loses final subagent results. Fixes #82583. (#82999)
·Gateway/auth: allow same-host trusted-proxy callers to use the documented local direct `gateway.auth.password` fallback after revisiting the #78684 fail-closed policy, while keeping token fallback rejected and forwarded-header requests on the trusted-proxy path. Fixes #82607. (#82953)
·Agents/subagents: wait for queued completion handoffs to reach the parent transcript before marking them announced, preventing busy parent runs from cleaning up before observing child results. Fixes #82913. (#83039)
·Agents/subagents: route group/channel subagent completions through message-tool-only handoffs when required and keep active-requester wake failures from dropping completion delivery. Fixes #82803.
·Memory-core: scan persisted memory source sessions on startup, comparing on-disk transcripts against the index and marking only missing/newer/resized files dirty for incremental sync. Fixes #82341. (#82341)
·Telegram: keep the top-level default account in the account list when named accounts or bindings are added alongside top-level credentials, preserving default polling while still letting named-only configs resolve to a single account. Fixes #82794. (#82794)
·CLI/models: reuse command-scoped plugin metadata across model listing, provider catalog, auth, and synthetic-auth checks, restoring fast `openclaw models` runs for plugin-heavy installs. Fixes #82881. (#83033)
·CLI/channels: show configured official external channels such as Discord in `openclaw channels list` when their plugin package is missing, including the install and doctor repair command instead of reporting no configured channels. Fixes #82813.
·Signal: preserve mixed-case group IDs through routing and session persistence so group auto-replies keep delivering after updates. Fixes #82827.
·Agents/tools: keep the `message` tool available in embedded runs when it is explicitly allowed through `tools.alsoAllow` or runtime tool allowlists, so channel plugins with custom reply delivery can still use configured message sends. Fixes #82833.
·WhatsApp: honor forced document delivery for outbound image, GIF, and video media so `forceDocument`/`asDocument` sends preserve original media bytes instead of using compressed media payloads. (#79272)
·WhatsApp: name outbound document attachments from their MIME type when no filename is provided, so PDF and CSV sends arrive as `file.pdf` and `file.csv` instead of an extensionless `file`.
·Process/diagnostics: report active lane blockers in lane wait warnings so `queueAhead=0` no longer hides commands waiting behind active work. Fixes #82791. (#82792)
·Process/diagnostics: stop counting the active processing turn as queued backlog in liveness warnings so transient max-only event-loop spikes do not surface as gateway warnings.
·Agents/replies: classify provider conversation-state rejections and return a clear message-channel error instead of auto-resetting or falling back to a generic runner failure. (#82616)
·Browser plugin: trust managed Chrome CDP diagnostics when launch HTTP probes race cold-start readiness, avoiding false startup failures. Fixes #82904. (#82986)
·Android: prompt before replacing a changed Gateway TLS thumbprint, showing the old and new SHA-256 fingerprints so users can accept expected certificate rotations instead of hard failing on pin mismatch. (#83077)
·CLI/status: render extra gateway-like service diagnostics as warning/info output instead of error output. Fixes #46930. (#82922)
·Agents/failover: classify Moonshot/Kimi exhausted-balance HTTP 429 payloads as billing instead of generic rate limits, preserving billing guidance and fallback behavior. Fixes #43447. (#83079)
·Plugin SDK: bundle `openclaw/plugin-sdk/zod` into the published package artifact and verify the packed zod subpath stays self-contained, so pnpm global installs can register plugins without a package-local `zod` symlink. Fixes #78398. (#78515)

v2026.5.16-beta.4pre-release2026-05-17

openclaw 2026.5.16-beta.4

GitHub ↗

Changes

·Security/audit: add `security.audit.suppressions` for intentionally accepted audit findings, keeping suppressed matches out of the active summary while preserving them in JSON output with an active suppression notice. (#76949)
·Agents/subagents: label delegated task and subagent completion handoffs as ready for parent review, and tell requester agents to review/verify results before calling them done. (#78985)
·Providers/media: add fal and OpenRouter music-generation providers for the shared `music_generate` tool, including fal MiniMax/ACE/Stable Audio endpoints and OpenRouter Lyria audio output.
·Maintainer tooling: warn before running JS package commands on raw Crabbox AWS boxes, pointing maintainers to Actions hydration or Blacksmith Testbox for CI-like proof.
·Control UI: show provider quota usage in the Overview card and Chat header, and recover stale Chat in-progress state after missed terminal events. (#82647)
·Mac app remote setup can now be preconfigured from `openclaw-mac configure-remote`, skips onboarding when config is already complete, supports direct LAN/Tailnet gateway URLs, allows private same-origin Control UI loads, and owns the SSH tunnel process when SSH is selected.
·Providers/xAI: add xAI Grok OAuth login for SuperGrok subscribers, letting `xai/*` models and xAI media/tool providers authenticate without `XAI_API_KEY`.
·CLI/cron: add `openclaw cron run --wait` with timeout and poll interval controls, plus exact `cron.runs --run-id` filtering so automation can block on one queued manual run. (#81929)
·Maintainer tooling: route Crabbox skill defaults through the repo brokered AWS config, leaving Blacksmith Testbox as an explicit opt-in instead of the broad-proof default.
·CLI/onboarding: localize the setup wizard and bundled channel setup flows for English, Simplified Chinese, and Traditional Chinese. (#80645)
·Agents/skills: cache hydrated `resolvedSkills` across warm gateway turns while keying reuse by the redacted effective config, reducing redundant skill snapshot rebuilds without crossing config-gated skill boundaries. (#81451)
·Group chat: add core inbound event classification with opt-in `messages.groupChat.unmentionedInbound: "room_event"`, so always-on unmentioned room chatter can run as quiet context and speak visibly only via the message tool. (#81317)
·Codex/context engines: bind thread-bootstrap projection epochs to Codex app-server threads, carry redacted tool-result context into fresh threads, and rotate backend threads when projection state changes. (#82351)
·Agents/media: run `image_generate` through the shared async media-generation task lifecycle in session-backed chats, with task status, duplicate guarding, and message-tool completion delivery matching music/video.
·Gateway: add opt-in restart trace logs for restart signal, active-work drain, close, next-start, ready, and memory spans. (#82396)
·Gateway/performance: split startup benchmark HTTP-listen timing from full gateway-ready timing and add post-bind plugin and sidecar diagnostics to restart-readiness traces. (#82603)
·QA-Lab: add a deterministic local personal-agent scenario pack covering reminders, threaded replies, scoped memory recall, redaction, and safe tool followthrough. (#78219)
·QA-Lab: add `--pack personal-agent` for `openclaw qa suite` so maintainers can run the accepted personal-agent scenario pack by selector. (#82760)
·QA-Lab: add a private Codex-vs-Pi runtime parity axis with runtime-pair suite runs, parity reports, and release-check wiring. (#80238)
·Slack: add Slack assistant thread lifecycle support with assistant view manifest entries, suggested prompts, thread-scoped assistant sessions, and Slack-provided assistant context. Fixes #80787.

Fixes

·Agents/subagents: route group/channel subagent completions through message-tool-only handoffs when required and keep active-requester wake failures from dropping completion delivery. Fixes #82803.
·Memory-core: scan persisted memory source sessions on startup, comparing on-disk transcripts against the index and marking only missing/newer/resized files dirty for incremental sync. Fixes #82341. (#82341)
·Telegram: keep the top-level default account in the account list when named accounts or bindings are added alongside top-level credentials, preserving default polling while still letting named-only configs resolve to a single account. Fixes #82794. (#82794)
·WhatsApp: honor forced document delivery for outbound image, GIF, and video media so `forceDocument`/`asDocument` sends preserve original media bytes instead of using compressed media payloads. (#79272)
·Gateway/usage: refresh large session usage summaries in the background and reuse durable transcript metadata so `sessions.usage` no longer blocks Gateway requests on full transcript rescans. Fixes #82773. (#82778)
·TUI: restore the submitted draft when chat is busy instead of clearing it or queueing another run. Fixes #45326. (#82774)
·Browser plugin: redact attach-details from Chrome MCP diagnostics and keep raw Chrome launch error output around long enough to surface in user reports without leaking sensitive paths.
·System prompts: clarify MEMORY guidance over generic TTS hints in the embedded speech-core/system-prompt scaffolding so agents prefer memory-store usage over speech defaults. Fixes #81930.
·Agents/auth: include the checked credential source in missing API key errors, so users can see which env var, profile, or config path to fix. Fixes #82785.
·Providers/GitHub Copilot: hash Responses replay item ids with sha256 instead of a weak 32-bit hash and build same-provider Copilot tool-call ids distinctly, so concurrent tool-call replays no longer collide and reject follow-up turns.
·Agents/replay: normalize malformed assistant replay content before transport conversion while preserving empty-stop replay repair, so bad provider history no longer crashes with non-iterable content. Fixes #43795. (#82748)
·Gateway/macOS: write LaunchAgent stdout under `~/Library/Logs/openclaw`, suppress stderr, and attach stdin to `/dev/null` so launchd startup avoids symlinked state-dir log failures and silent module-evaluation hangs. Fixes #40207 and #46153.
·CLI/configure: let model-only section setup enter provider auth directly instead of first asking where the Gateway runs, unblocking OAuth/token setup in terminals where that unrelated prompt is unresponsive. Fixes #39223.
·Providers/Anthropic-messages: extract `reasoning_content` from `thinking` blocks during assistant replay so proxy providers that route through the Anthropic-messages transport preserve reasoning context across tool-call follow-up turns.
·Agents/GitHub Copilot: normalize replayed Responses tool-call IDs before dispatch so resumed sessions with historical overlong tool IDs continue instead of failing Copilot schema validation. (#82750)
·CLI/web: resolve provider-scoped web search/fetch SecretRefs for `infer web ... --provider ...` while leaving unrelated plugin secrets untouched. Fixes #82621.
·Providers/Anthropic Vertex: resolve installed provider public surfaces from package-local `dist/`, restoring `anthropic-vertex/*` model calls after plugin externalization. Fixes #82781.
·Gateway/exec approvals: bind path-shaped allowlists, safe-bin trust, skill auto-allow, Allow Always persistence, and approval audit metadata to the executable realpath so symlinked binaries cannot keep approvals after retargeting. Fixes #45595.
·Mac app: let menu gateway/session error text wrap across a few lines and stop rebuilding dynamic Context/Gateway menu rows while the menu is open, reducing flicker.
·Mac app: make device pairing approval sheets friendlier, with concise Mac/device copy, shortened identifiers, friendly scope labels, and Approve as the primary action.
·Providers/Qwen: honor session thinking level for `qwen-chat-template` payloads so `/think off` disables nested llama.cpp chat-template thinking controls. Fixes #82768.
·Feishu/wiki: reject numeric wiki space IDs before creating Lark clients and keep numeric-looking IDs documented as quoted opaque strings, preventing JavaScript precision loss in knowledge base calls. Fixes #45301. (#82769)
·Control UI: simplify Talk settings to Voice, Model, and Sensitivity defaults, with provider, transport, exact VAD, and timing controls behind Advanced.
·Telegram: let catch-all mention patterns match captionless group photos, so media-only group messages reach the agent when the group is intentionally configured to respond to all messages. Fixes #44833. (#82756)
·Gateway/pairing: reject forged loopback Control UI origins from non-local proxy paths, and keep mobile pairing setup on Tailscale bind mode pointing users to Tailscale Serve/Funnel instead of cleartext tailnet WebSockets.
·Telegram/Gateway: persist isolated polling offsets only after main-thread dispatch and preserve gateway caller scopes for Telegram message actions, fixing consumed-but-unrouted polling updates and recursive CLI send scope approvals. Fixes #82277. (#82705)
·Memory-core: abort timed-out embedding provider calls so remote embedding HTTP requests do not continue running after memory query or indexing timeouts. Fixes #82732.
·Channels/stream previews: contain rejected background draft-stream flushes so preview send failures do not surface as fatal unhandled rejections. Fixes #82712. (#82713)
·Codex/app-server: keep shared native app-server clients isolated per agent runtime key so starting one agent no longer closes another agent's active Codex turn. Fixes #82758.
·Providers/OpenAI Codex: include base `gpt-5.5` and `gpt-5.4` reasoning metadata in the bundled Codex catalog so `/think xhigh` remains available for those models. Fixes #82744.
·Providers/OpenAI Codex: keep the native hook relay as the final Codex app-server thread config patch so hook-backed approvals stay enabled even when lower-priority config disables hooks.
·Providers/MiniMax: declare CN endpoint auth aliases in the plugin manifest so `minimax-cn` and `minimax-portal-cn` reuse the correct base auth profiles instead of falling back to unrelated models after 401s. Fixes #63823.
·Secrets/audit: treat `$VAR` auth-profile values as env SecretRefs and stop reporting env-ref credentials as plaintext, including mixed `keyRef` plus env-ref profile states. Fixes #53998.
·Agents/model fallback: suppress fallback notices when the active OpenAI Codex runtime reports the same canonical OpenAI model.
·Agents/music generation: remove model-controlled request timeouts, default internal provider requests to five minutes, and keep configured timeouts at a 120-second floor.
·Agents/media generation: stop logging delivered failure summaries as missing message-tool delivery when no generated media was expected.
·Agents/sessions: prioritize manual user turns ahead of queued cron and maintenance work in the same session lane, so visible follow-ups no longer wait behind background runs. Fixes #82764. (#82765)
·Agents/edit tool: honor `file_path` and related path aliases when resolving edit-recovery targets, so post-write errors no longer surface false edit failures after the file actually changed. Fixes #81909.
·QQBot: treat only explicit truthy `QQBOT_DEBUG` values as enabling debug logs, so false-like values such as `0` no longer expose debug output. Fixes #82644. (#82697)
·Agents/session_status: resolve implicit no-arg status lookups against the live run session, so `/think` changes report the current thinking level instead of stale sandbox state. Fixes #82669. (#82696)
·Discord: keep progress drafts visible for message-tool-only guild replies under the default coding tool profile. Fixes #82747.
·Discord: keep unmentioned room-event history until a visible Discord send succeeds, so quiet ambient context does not disappear before message-tool delivery. (#82573)
·CLI/setup: order the model/auth provider picker as OpenAI, Anthropic, xAI, Google, then the remaining providers alphabetically.
·Diagnostics/usage/voice-call: treat explicit zero and non-finite limits as empty results and reject invalid voice-call numeric CLI flags. Fixes #82646, #82650, #82651, and #82653. (#82679)
·CLI/config: avoid redundant startup config/plugin checks for the guided `openclaw config` flow and show progress while source checkout CLI artifacts build or load.
·Config/Mac app: accept `gateway.remote.remotePort` in core config validation so Mac SSH remote setup stays compatible with the CLI.
·Gateway/diagnostics: add opt-in critical memory pressure stability snapshots with gateway logs, V8 heap, cgroup, active-resource, and redacted large session-file evidence. Fixes #82518.
·Doctor/Gateway: avoid treating unrelated macOS LaunchAgents as legacy gateways just because their environment values mention old checkout paths.
·Gateway/heartbeat: defer heartbeat runs while the target reply operation is queued or active, preventing heartbeat prompts from interleaving with WebChat responses before the streaming lane starts. Fixes #82722.
·CLI/setup: collapse raw gateway config keys in existing-config summaries into friendly `Model` and `Gateway` rows.
·CLI/config: show concise human config-write output with an indented backup path instead of printing checksum-heavy overwrite audit details by default.
·CLI/docs: call the canonical lowercase docs MCP search tool and surface MCP errors instead of returning empty search results. Fixes #82702. (#82704)
·QA-Lab: add gateway log sentinels for plugin hook failures, Codex app-server stalls/timeouts, cron allowlist drift, live quota blockers, and direct-reply self-message transcripts so harness proof fails on self-health regressions. (#80323)
·QA-Lab: ignore heartbeat-only operational transcripts when capturing runtime parity cells so background checks cannot replace the scenario reply. (#80323)
·QA-Lab: pin threaded-memory parity runs to `memory-core`, keep bundled plugin resolution enabled for QA commands, and retry transient session-store lock reads. (#72045)
·QA-Lab/qa-channel: keep mock memory ranking, inbound media notes, and opened-file realpath checks stable for mock OpenAI qa-channel runs. (#66826)
·Gateway/exec approvals: wait for accepted async approval follow-up runs instead of direct-fallback sending duplicate completions when retries use different nonce keys. Fixes #82711. (#82717)
·Agents/subagents: mark completed subagent handoffs as ready for parent review so requester agents verify results and continue required follow-up work before reporting done. (#82724)
·QA-Lab: validate Capture saved views loaded from browser storage so malformed local state cannot poison Capture inspector filters or layout controls. (#77722)
·Agents/performance: reuse prepared plugin manifest metadata across local CLI turns, model catalog normalization, auth lookups, and tool capability checks, restoring fast pre-provider startup for plugin-heavy installs.
·CLI/config: add `--dry-run` support to `openclaw config unset`, with `--json` output and allow-exec validation parity with `config set`/`config patch` dry-run handling. (#81895)
·CLI/infer: resolve command SecretRefs before local provider-backed capability runs, so web search/fetch and other local infer commands can use plugin-scoped credential refs. Fixes #82621. (#82798)
·Memory-core: retry disabled dreaming cron cleanup until cron is available after startup, so persisted managed dreaming jobs are removed after restart. Fixes #82383. (#82389)
·Providers/xAI: keep retired Grok 3, Grok 4 Fast, Grok 4.1 Fast, and Grok Code slugs out of model pickers while preserving compatibility resolution for existing configs.
·Providers/xAI: replace the retired `grok-imagine-image-pro` image model with `grok-imagine-image-quality` in the bundled image-generation provider and docs. (#81399)
·Providers/OAuth: let browser-hosted identity provider pages read successful localhost callback responses, preventing xAI Grok OAuth from showing a false connection failure after OpenClaw completes login.
·Gateway/security: reject malformed HTTP and WebSocket request targets with the existing auth failure response instead of letting invalid URL parsing crash the Gateway. Fixes GHSA-6hc3-f4rg-377m.
·Browser/CDP: redact credential-bearing Chrome MCP and managed Chrome launch diagnostics, and require exact loopback entries before treating `NO_PROXY` as already covering local CDP proxy bypasses.
·Gateway/diagnostics: redact credential-bearing gateway target URLs and client diagnostics while preserving raw connection URLs for programmatic use, so connect-failure logs no longer surface embedded tokens.
·Gateway/auth: honor `OPENCLAW_GATEWAY_TOKEN` as the remote interactive fallback when no remote token is configured, keeping remote TUI setup aligned with documented auth precedence.
·Providers/xAI: continue polling video generations while xAI reports in-flight jobs as `pending`, so Grok video requests no longer fail before the final `done` response. (#82610)
·Logs: redact raw Basic auth and named security headers from `logs.tail` output before returning lines to read-scoped clients. Fixes #66832.
·CLI/gateway: emit structured JSON for gateway transport close/timeout failures when `--json` is requested by health, gateway health, and devices list commands. Fixes #79108.
·Telegram: normalize announce group targets via a new `resolveSessionTarget` channel hook so scheduled announcements resolve consistently against the same Telegram session conversation registry as inbound turns. Fixes #81229.
·QA/RTT: let `pnpm rtt` lease Convex-backed Telegram credentials while preserving RTT sample counts, sample timeouts, and result stats on the RTT harness path.
·Discord: bind delayed gateway `identify` retries to the originating socket generation so retries triggered after a reconnect do not identify against a fresh socket. Fixes #82225.
·ACP/control plane: refresh cached runtime handles when agent config changes so ACP sessions stop using stale runtimes after `agents.defaults` edits. Fixes #82237.
·Gateway/sessions: scope session data lookups by agent id so multi-agent gateway state cannot cross-leak session records across configured agents. (#81386)
·Gateway/restart: mark active main sessions as restart-aborted before forced restarts so startup recovery can resume interrupted turns instead of leaving them stranded as running. Fixes #82433. (#82772)
·Agents/media: require generated music/video completion agents to use the message tool for visible delivery and stop merging generated image attachments into message-tool-only source reply mirrors, avoiding direct fallback posts that can duplicate media the model already sent.
·Agents/media: accept generated media attachments on internal completion events and report delivery-loss failures as errors, so completed background music/video tasks do not disappear after provider success.
·Matrix/approvals: release in-flight reaction bindings when the channel approval handler stops mid-delivery, preventing stale approval targets after restart. Fixes #82485. (#82482)
·Matrix/E2EE: stop requesting MSC4222 `state_after` sync responses so homeservers with incomplete state-after data do not leave fresh encrypted rooms without outbound room encryptors. Fixes #82515.
·TUI: update the displayed model in real time when an auto-fallback resolution swaps in a different model mid-turn, so the status line reflects the actual model handling the run. Fixes #82296.
·Gateway/sessions: estimate context usage from local/OpenAI-compatible transcripts when provider usage telemetry is missing, so status no longer shows empty usage for real local-model sessions. Fixes #73990. (#82317)
·Update/installers: override npm `min-release-age` quarantine for OpenClaw-managed package installs, so `openclaw update`, plugin updates, and hosted installer scripts can install the requested latest release immediately.
·Agents/sessions: preserve fresh post-compaction token snapshots across stale usage updates, preventing repeated auto-compaction after every message. Fixes #82576. (#82578)
·Agents/replies: preserve active inbound reply context at the LLM boundary so Discord referenced-message turns do not answer from stale session history. Fixes #82608. (#82801)
·Agents/OpenAI Responses: log redacted diagnostics for detail-less `response.failed` events while preserving failed response ids, so operators can correlate provider-side failures. Fixes #82558.
·Agents/OpenRouter: strip non-replayable Anthropic/xAI reasoning provenance tags from follow-up requests, preventing poisoned thinking signatures from breaking second turns. Fixes #82335. (#82380)
·Providers/xAI: send configurable reasoning effort only for Grok 4.3, preserving xAI's default low reasoning while omitting unsupported controls for Grok 4.20 reasoning models. (#81227)
·Image generation: raise Google, OpenRouter, and xAI hosted provider default timeouts to 180 seconds so slow hosted image requests have more time to complete. (#75337)
·Agents/auth: redact OAuth refresh failure causes against in-memory, attempted, and reloaded credentials before generic token masking while ensuring failed ACP dispatch cleanup closes initialized runtimes.
·Google/Gemini CLI OAuth: add provider-owned refresh support for `google-gemini-cli` so expired Gemini CLI tokens refresh in OpenClaw instead of falling through to the generic unknown-provider path. Fixes #42541.
·Agents/Anthropic transport: replay `reasoning_content` from compatible thinking blocks for Xiaomi/MiMo-style Anthropic Messages routes, preventing follow-up turns from losing required reasoning context. Fixes #81261.
·Telegram: cache successful startup bot identity by account and token fingerprint for up to 24 hours, so restarts can skip redundant `getMe` probes during Telegram API slow periods without permanently pinning renamed bots. Refs #82525.
·Telegram: keep streamed text replies in place when delayed TTS audio arrives, sending the audio as a follow-up instead of deleting the preview. Fixes #82570. (#82820)
·Gateway/sessions: discard stale metadata when recreating dead main session rows, so replacement sessions do not inherit old labels or transcript paths.
·Codex app-server: mark native context compaction completion events as successful, preventing false "Compaction incomplete" notices after successful Codex-managed compaction. Fixes #82470. (#81593)
·Codex app-server: keep long-running turns alive while current-turn approvals, user input, dynamic tools, and notifications make progress, and carry that progress into the outer run timeout. (#82601)
·Gateway/channels: hand off traced channel account startup outside the startup diagnostic phase so long-lived channel tasks do not keep liveness warnings pinned to channel startup. Refs #82398.
·Gateway/restart: queue restart and shutdown signals received while the gateway startup loop is still returning its server handle, so startup-time restarts are not dropped during update churn. (#82660)
·Gateway/restart: carry operator restart intent reasons into macOS LaunchAgent restart traces, so cascade diagnostics identify `gateway.restart` instead of a bare SIGTERM.
·GitHub Copilot: route device-login requests through the plugin SSRF guard with a GitHub-only policy.
·Group/channel replies: keep message-tool-preferred final replies private when the agent misses the message tool, and log suppressed payload metadata in the gateway debug log for quieter diagnosis.
·Gateway/WebChat: route image attachments through a configured vision-capable `imageModel` plan before inlining images, and carry that image-model fallback chain through runtime retries. (#82524)
·macOS app: open the Dashboard in a native WebKit window with standard macOS traffic-light controls, keep the Dock icon visible by default, and reuse the app's connected gateway auth for automatic Control UI login.
·WebChat: show progress while manual `/compact` is running by streaming a session operation event to subscribed Control UI clients. Fixes #82407.
·Codex app-server: limit canonical OpenAI Codex app-server attribution rewrites to local transcript and trajectory records, leaving runtime/tool routing on the selected OpenAI model metadata so OpenAI API-key backup profiles keep their billing path.
·Codex app-server: hide native tool-search control tools from dynamic tool exposure while preserving the message tool.
·Android/chat: make bare and markdown URLs in chat messages tappable by preserving Compose URL annotations in rendered markdown. Fixes #82187. (#82392)
·Plugins/doctor: migrate legacy top-level plugin `tools` declarations into `contracts.tools`, so `openclaw doctor --fix` repairs local plugins for the manifest tool contract. (#81112)
·Slack: guide agents to use stable `<@USER_ID>` mention tokens from context instead of plain `@name` text, so user mentions link and notify correctly. Fixes #82090. (#82152)
·Auth: serialize provider login writes through the auth-profile lock for OpenAI Codex, Anthropic, Cloudflare AI Gateway, GitHub Copilot, and z.ai, preserving upsert semantics so a live Gateway cannot overwrite freshly refreshed OAuth credentials with an expired in-memory snapshot.
·Auth/Codex: remove runtime support for `oauthRef` sidecar-backed OAuth profiles and add a doctor repair that migrates affected Codex profiles back to inline `auth-profiles.json` credentials. (#82777)
·Slack: keep DM thread replies on the main direct-message session instead of routing them to invisible thread-scoped sessions. Refs #82390. (#82418)
·Auth/macOS: avoid creating the OAuth profile master key in Keychain automatically, falling back to the file-backed secret key so headless agents do not trigger a Keychain prompt.
·Codex app-server: release raw assistant completions when `turn/completed` is missing while keeping commentary/status items as progress, preventing completed Codex runs from hanging until timeout. Fixes #82343. (#82403)
·Codex app-server: keep a bounded terminal guard after post-tool raw assistant completions so missing `turn/completed` events fail fast instead of leaving embedded runs stuck. Fixes #82775. (#82816)
·Agents/sessions: remove the transient `*.bak-<pid>-<ts>` backup written by `repairSessionFileIfNeeded` once the atomic replace succeeds, so a stuck session with a persistently malformed JSONL line no longer accumulates one snapshot per repair invocation. Fixes #80960. (#80969)
·CLI/status: show plain empty-state messages instead of empty Channels and Sessions tables when no channels or sessions exist.
·CLI/dashboard: probe Gateway readiness before handing out the dashboard URL, prompting to start or install the managed service when the Gateway is stopped and printing recovery commands instead of opening a dead browser tab.
·CLI/dashboard: treat Gateway `device identity required` probes as proof that the dashboard listener is reachable, so `openclaw dashboard` can still open the Control UI.
·CLI: hide decorative startup and status emoji on terminals that are unlikely to render them correctly, keeping semantic message and identity emoji intact.
·CLI/gateway: recover the Linux user systemd bus environment when `openclaw dashboard` starts the Gateway from stripped desktop shells such as VNC terminals.
·Gateway/WebSocket: log expected startup `1013 gateway starting` retry closes at debug instead of warn while preserving WARN for unexpected pre-connect failures. Fixes #76361. (#82457)
·Providers/Xiaomi: strip synthetic empty array `items` from MiMo tool schemas while preserving typed array items, avoiding strict OpenAI-compatible schema rejection.
·Telegram: send the transcript-backed full final answer after progress-mode tool drafts when the dispatcher final payload is an ellipsis-truncated snapshot. Fixes #82409.
·Providers/Ollama: omit truthy native `think` payloads for models marked non-reasoning while preserving supported thinking models and explicit `think: false`. (#82445)
·Update/channels: preserve pre-update channel config through package-swap doctor and post-core plugin repair so externalized channel upgrades do not drop configured chat channels. Fixes #82533.
·CLI/context engines: bootstrap and finalize non-legacy context engines for CLI turns while preserving transcript snapshots and deferred maintenance ownership. (#81869)
·Telegram: persist polling updates through restart replay so queued same-topic messages resume in order instead of losing context after a gateway restart. (#82256)
·Gateway/Gmail: abort in-flight Gmail watcher startup and hot-reload restarts before shutdown so reloads cannot spawn `gog serve` after the Gateway is closing.
·Agents/Codex: fall back to the embedded PI runner when OpenAI's implicit Codex harness preference cannot find a registered Codex plugin, preventing OpenAI-compatible gateway requests from failing with an unregistered harness error. Fixes #82437.
·Agents/OpenAI: honor `openai-codex:*` entries placed ahead of API-key backups in `auth.order.openai` for explicit OpenAI PI runs, and accept `models auth login --provider openai-codex --device-code` for headless sign-in. Fixes #82521. (#82605)
·CLI/channels: install missing externalized same-id channel plugins during `channels add --channel <id>`, so recovery for WhatsApp and other externalized stock channels does not require a separate `plugins enable` step. Fixes #82533.
·MCP plugin tools: forward host MCP `tools/call` `AbortSignal` through `createPluginToolsMcpHandlers().callTool` into plugin `tool.execute`, so host cancellation actually cancels in-flight plugin tool calls instead of letting them run to completion. Fixes #82424. (#82443)
·Agents/sandbox: honor explicit Docker sandbox env variables with credential-looking names during container creation, and recreate affected sandbox containers when the effective env policy changes. Fixes #82695. (#82763)
·Plugins: accept deprecated `api.on("deactivate")` registrations as a dated compatibility alias for `gateway_stop`, so external plugin cleanup handlers run on Gateway shutdown while authors get migration guidance.
·Plugins: resolve bundled entry, dist-runtime, package-state, and public artifact paths from packaged roots, so bundled plugin probes and hardlinked public surfaces no longer fall back to source files or fail during restart. Fixes #78462. Fixes #75797. Refs #76865.
·Media: ignore image MIME and filename hints when bytes sniff as generic containers, so zip/octet-stream payloads mislabeled as images do not become local image media or keep image file extensions when staged.
·Update/doctor: avoid materializing `groupAllowFrom` for channel schemas that reject it, so package-swap doctor repairs do not fail on externalized Slack configs.
·Gateway/media: prevent image filenames from overriding generic non-image byte sniffing, so zip/octet-stream payloads mislabeled as images are offloaded or rejected before they become inline image attachments.
·Plugins/web search: downgrade stale optional provider installs to warnings so Gateway and doctor repair paths keep running after startup provider selection. Refs #82313.
·Telegram/Gateway: route targeted Telegram `/stop@bot` messages onto the control lane without cached bot metadata and match gateway stop requests across raw/canonical session aliases. (#82298)
·MS Teams/media: sniff inline `data:image/*` attachment bytes before staging them, skipping payloads that are not actually images.
·WebChat/media: require trusted local-media provenance before preserving local audio reply paths for display, so untrusted audio-looking paths go through normal staging and read-policy checks.
·WebChat: trust local Auto-TTS audio on block-streamed replies, including ACP-dispatched tails, so synthesized browser audio renders instead of being silently dropped. Fixes #82628. (#82701)
·Agents/tool media: preserve trusted local-media provenance when merging generated tool attachments into final reply payloads, so trusted audio/media survives outbound display normalization.
·Anthropic/Claude CLI: write model-scoped `claude-cli` runtime policy when reusing local Claude CLI auth, so upgraded Telegram and Dashboard gateway turns keep using the CLI backend instead of falling through to Anthropic API billing. Fixes #82344.
·Update: let package-swap `doctor --fix` persist core config repairs while plugin schemas are still converging, preventing update failures on externalized channel configs.
·Update: carry plugin-validation bypasses into config mutation pre-write reads, so package update doctor repairs can finish while externalized plugin schemas are converging.
·Update/doctor: keep plugin-validation bypasses on the top-level `$include` config write path, so package repair can update included plugin config files without flattening them into the root config.
·Agents/subagents: warn and continue completion announce cleanup when lifecycle cleanup fails, preventing ended subagent runs from becoming silent ghosts. Fixes #82306.
·Telegram: let authorized text `/stop` commands use the fast-abort path before queued agent work, so active turns stop immediately instead of processing the abort after the turn finishes; foreign-bot `/stop@otherbot` mentions now stay on the regular topic lane instead of being routed into our control lane. Fixes #82162.
·Sessions: drop persisted entries with invalid session ids and strip malformed transcript file metadata before hydrating session runtime state.
·Auth/device: normalize malformed persisted device-auth token metadata before returning or preserving token entries.
·Pairing: skip malformed persisted pending pairing requests before approving valid channel pairing codes.
·Commitments: strip malformed optional reminder scope metadata from persisted commitments before matching pending follow-ups.
·Config persistence: normalize malformed auth profile credential fields/state, skip JSON-valid garbage transcript checkpoint rows, and let `openclaw doctor --fix` remove unrepairable cron job rows.
·Cron: skip persisted job rows with malformed schedule or payload shapes in memory, leaving the store for `openclaw doctor --fix` instead of hydrating them into runtime state.
·Cron: keep legacy string schedules and blank system-event jobs available for runtime repair/skip handling instead of dropping them as malformed persisted rows.
·Cron: reject empty scheduled main/isolated payloads before persisting jobs, keeping runtime stores compatible with malformed-row hardening.
·Task persistence: drop malformed array/scalar requester-origin JSON from task and task-flow SQLite sidecars instead of restoring it as delivery metadata.
·Agents/timeouts: clarify model idle-timeout errors and docs so provider `timeoutSeconds` is shown as bounded by the whole agent/run timeout ceiling.
·Agents/OpenAI streams: yield cooperatively while processing bursty Completions and Responses chunks, keeping aborts, channel liveness timers, and startup heartbeats responsive under noisy model output. Refs #82462.
·Media/images: avoid broad model/plugin discovery while preparing image requests, preventing Windows event-loop stalls that could block Telegram polling. Fixes #82338. (#82799)
·Release tooling: align the published launcher Node floor, `npm start`, package script checks, sharded lint locking, Vitest root project coverage, and plugin-SDK declaration build cache metadata so release/package validation does not silently skip or ship stale surfaces.
·Cron/agents: honor configured subagent model fallbacks for isolated scheduled runs and forward that fallback policy into embedded agent timeout failover. Fixes #74985.
·Codex app-server/MCP: scope user MCP servers to specific OpenClaw agent ids through an optional `mcp.servers.<name>.codex.agents` list and accept `codex.defaultToolsApprovalMode` (`auto`/`prompt`/`approve`) for native Codex approval defaults; OpenClaw strips the `codex` block before handing `mcp_servers` config to Codex. (#82180)
·Agents/OpenAI Responses: clamp `input_tokens - cached_tokens` at zero and reconstruct `totalTokens` from input + output + cached components so Responses-API streams report consistent usage when providers under-report `input_tokens` relative to `cached_tokens`.
·Agents: mark adapter-caught tool execution failures as error tool results in embedded Pi sessions, so models can retry recoverable edit failures instead of seeing a successful tool result. Fixes #81546. (#81564)
·Plugins: reject malformed `package.json` `openclaw.extensions` metadata during install, discovery, and post-update payload smoke instead of silently dropping invalid entries.
·Plugins: reject package metadata records whose `package.json` resolves outside the plugin root instead of trusting persisted or reconstructed registry snapshots.
·Plugins: ignore malformed persisted package channel/install metadata instead of crashing catalog reconstruction or leaking invalid install hints.
·Plugin releases: reject package `files` negations that would omit advertised package-local runtime entries from npm plugin tarballs.
·Media/files: sniff `input_file` bytes before trusting declared MIME headers, rejecting spoofed image or zip payloads before they become agent-visible text.
·Plugins/dependencies: scrub stale managed-root `openclaw` ownership metadata without deleting a linked active host package, preventing plugin installs from downgrading npm-global hosts. Fixes #79462.
·Gateway/update: keep shutdown hook-runner imports on a stable dist entry and ship a legacy chunk alias so package swaps do not strand running gateways on missing shutdown chunks. Fixes #81819.
·Config persistence: ignore malformed array/scalar auth profile, cron job state, and session store entries instead of hydrating them into numeric profile ids, crashed cron rows, or invalid session records.
·Config persistence: strip malformed pending final-delivery session fields on load so replay/recovery paths skip poisoned reply metadata instead of crashing on raw objects.
·Config persistence: strip malformed plugin extension state and promoted session-slot ownership on load so corrupted session rows do not leak poisoned plugin metadata into replay/projection paths.
·Gateway/sessions: ignore malformed compaction checkpoint rows during session projection so corrupted stores do not crash session list/describe responses or show bogus checkpoint counts.
·Gateway/sessions: keep reachable transcript history when imported tree transcripts reference missing or legacy parent rows, preventing session history reads from going empty after a partial import.
·Trajectory export: report incomplete transcript parent chains and stop cyclic branch walks so malformed imports cannot hang `/export-trajectory`.
·Session replay: skip malformed user/assistant-shaped transcript rows during silent session resets instead of copying invalid entries into the fresh transcript.
·Backup verify: report malformed archive manifests with a stable error instead of leaking raw JSON parser details.
·Session export: report skipped malformed transcript JSONL rows instead of silently omitting them from exported HTML archives.
·Providers: reject malformed successful Runway, BytePlus, and Ollama embedding responses with provider-owned errors instead of raw parser/type failures, silent bad vectors, or long bogus polling.
·Providers/images: reject malformed successful OpenAI-compatible, OpenAI, Google, fal, and OpenRouter image responses with provider-owned errors instead of raw shape failures, silent invalid base64 skips, or empty image results.
·Providers/videos: reject malformed successful xAI, OpenRouter, and fal video create, poll, and result responses with provider-owned errors instead of raw parser failures or long bogus polling.
·Providers/videos: let selected-model capability overlays clear inherited `providerOptions`, so fallback skips models that explicitly accept no provider-specific options instead of forwarding unsupported knobs.
·TTS/providers: honor preferred provider aliases when routing model override directives, so alias-selected speech providers receive unqualified `[[tts:*]]` overrides.
·Providers/audio: reject malformed successful OpenAI-compatible, ElevenLabs, and Deepgram speech responses with provider-owned errors instead of raw parser failures, wrong-shaped transcripts, or JSON/text bodies treated as audio.
·Providers/embeddings: reject malformed successful OpenAI-compatible, Google Gemini, and Amazon Bedrock embedding responses instead of silently returning empty or coerced vectors.
·Providers/catalogs: reject malformed successful LM Studio, GitHub Copilot, DeepInfra, Vercel AI Gateway, and Kilocode model-list responses with provider-owned errors instead of raw parser/type failures or silent fallback catalogs.
·Providers/polling: reject array, null, or scalar successful operation status responses with provider-owned malformed JSON errors instead of waiting until timeout.
·ACPX/Codex: reap plugin-local Codex ACP adapter orphans on startup after wrapper crashes while keeping direct adapter commands out of launch-lease injection. Fixes #82364. (#82459)
·Agents/model fallback: periodically probe the configured primary for auto-pinned fallback sessions, announce fallback/recovery transitions, and clear the pin when it recovers, preventing sessions from staying on a fallback model indefinitely. Fixes #82544.
·Telegram: send presentation-only payloads by rendering fallback text and inline buttons instead of treating them as empty. Fixes #82404. (#82449)
·Providers/Kimi: preserve Kimi Coding `reasoning_content` replay and backfill assistant tool-call placeholders when thinking is enabled, so `kimi-for-coding` follow-up tool turns no longer fail after prior tool use. Fixes #82161.
·Providers/search tools: reject malformed successful xAI, Gemini, and Kimi web/code search responses with provider-owned errors instead of silent `No response` payloads or ungrounded fallback state.
·Trajectory export: skip and report malformed session/runtime JSONL rows in `manifest.json` instead of letting wrong-shaped session rows crash support bundle export.
·Voice calls: persist rejected inbound-call replay keys so duplicate carrier webhook retries stay ignored after a Gateway restart.
·Config/doctor: copy fallback-enabled channel `allowFrom` entries into explicit `groupAllowFrom` allowlists during `openclaw doctor --fix`, preserving current group access without adding runtime fallback-transition flags.
·Config/doctor: replace source-only official Brave and Slack plugin installs from trusted catalog metadata during `openclaw doctor --fix`, unblocking externalized stock plugin recovery after upgrade. (#82425)
·Config/memory: warn instead of rejecting configs that select the official external `memory-lancedb` slot before the plugin is installed, with an explicit no-persistent-memory startup warning and install hint. Fixes #82428. (#82438)
·Agents/bootstrap: ignore stale completed root `BOOTSTRAP.md` context after workspace setup cleanup fails, preventing channel agent turns from treating it as a directory. (#82463)
·Update/doctor: re-enable the Codex plugin during `openclaw doctor --fix` when configured OpenAI agent models require the Codex runtime, preventing upgraded configs from failing with an unregistered Codex harness. Fixes #82368. (#82502)
·Configure: show one OpenAI provider entry with ChatGPT/Codex sign-in and API key choices, and keep browsed Codex models in the saved `/model` picker allowlist.
·Agents/model fallback: preserve auto fallback chains across deferred config reloads when session fallback provenance survives but `modelOverrideSource` is missing. Fixes #81982.
·Hooks: raise bounded gateway lifecycle hook wait budgets to 5 seconds for shutdown and 10 seconds for pre-restart, giving short restart notification handlers time to finish before shutdown continues. (#82273)
·Plugin releases: require external package compatibility metadata in the npm plugin publish plan, matching the ClawHub package contract before packages ship.
·Agents/OpenAI-compatible: honor per-model `max_completion_tokens`/`max_tokens` params in embedded OpenAI-completions runs so high-token Kimi-style routes keep their configured completion cap. Fixes #82230.
·Agents/local: install a local gateway request scope around trusted `openclaw agent --local` runs, so subagent completion announces can use in-process gateway dispatch without crashing. Fixes #82140.
·Cron: keep failed isolated-agent runs from marking successful result delivery when only the failure notification was delivered. Fixes #72985.
·Discord: validate message-read results before normalizing channel history and report unexpected payloads with a Discord boundary error instead of `map is not a function`. Fixes #82252.
·Agents/runtime: apply `agents.defaults.models["provider/*"].agentRuntime` as provider-wide model runtime policy while preserving exact model runtime precedence. Fixes #82243.
·Model picker: show the effective Codex runtime first for official OpenAI routes while keeping Pi available as an alternate and preserving Pi-first custom OpenAI-compatible providers. Fixes #82269.
·Agents/auto-reply: restrict `NO_REPLY` prompt guidance to automatic group/channel replies, remove legacy silent-reply rewrites, and suppress accidental direct-chat silent tokens instead of delivering fallback text. Fixes #82254.
·Telegram: retain a longer partial-stream preview when a final callback only carries an ellipsis-truncated snapshot, preventing the visible answer and transcript mirror from being replaced by the short preview. Fixes #82239.
·Telegram/active-memory: run blocking memory recall through the Telegram provider for direct-message turns even when the hook context carries the raw chat id, preventing embedded recall from launching against an invalid numeric channel. Fixes #82177.
·Control UI/WebChat: keep optimistic image messages from embedding large inline `data:` previews and preserve image-only user turns in chat history, avoiding browser stack overflows when sending image attachments. Fixes #82182.
·Agents/media: preserve message-tool-only delivery for generated music and video completion handoffs, so group/channel completions do not finish without posting the generated attachment.
·Telegram: drain queued outbound deliveries after polling reconnect confirms fresh `getUpdates` activity, so stale-socket and network recovery do not leave failed replies stranded. Fixes #50040. Refs #82175.
·Gateway/model auth: abort active provider runs when saved auth is removed through the Gateway control plane, refresh live runtime auth snapshots, and surface `stopReason: "auth-revoked"` to clients. Fixes #81987. (#82346)
·Codex app-server: keep the raw tool-output idle watchdog armed after `custom_tool_call_output` notifications, so post-tool stream silence fails fast instead of waiting for the terminal idle timeout. Fixes #82274. (#82378)
·Codex app-server: enforce OpenClaw `before_tool_call` policy for Codex-native app-server shell and approval paths, preventing native tool execution from bypassing plugin policy. Fixes #82372. (#82496)
·Telegram: mark isolated polling ingress unhealthy when a spooled inbound backlog stalls while Bot API polling still succeeds, so gateway/channel health no longer stays green after Telegram DM processing wedges. Fixes #82175.
·Telegram: drop expired approval callbacks from isolated polling after approval id expiry so stale inline-button updates do not retry forever across restarts. Fixes #82347. (#82455)
·Agents: strip Gemini/Gemma `<final>` tags with attributes or self-closing syntax from delivered replies, including strict final-tag streaming enforcement. Fixes #65867.
·macOS/update: disarm legacy `ai.openclaw.update.*` LaunchAgents when `openclaw update` starts from one, preventing KeepAlive relaunch loops that repeatedly restart the Gateway and replay update continuations. Fixes #82167.
·Agents/replay: strip internal runtime-context metadata and `NO_REPLY` sentinels from provider replay and pending final-delivery recovery so restart and heartbeat resumes do not feed control text back to the model. Fixes #76629.
·Agents/replay: skip malformed transcript tail rows when deduping embedded assistant gap-fill, preventing truncated JSONL from duplicating the final assistant reply during replay recovery.
·LINE: acknowledge signed webhook events before agent processing so slow model replies do not cause LINE `request_timeout` delivery failures. Fixes #65375.
·LINE: stop cron recovery from inferring lowercased LINE recipients from canonical session keys, so long-running task replies do not silently retry undeliverable push targets. Fixes #81628. (#81704)
·TTS: preserve channel-derived voice-note delivery for `/tts audio` replies even when the provider output is not natively voice-compatible. (#82174)
·Codex app-server: preserve inbound sender metadata and source-channel provenance on mirrored user prompts, including failure snapshots, so channel history keeps the original sender identity. (#82184)
·Codex app-server: yield projector work to the event loop between embedded-run notifications while preserving pre-turn rate-limit capture, reducing gateway stalls from account and MCP status notifications. Fixes #81936. (#82333)
·Plugins/web search: start the configured web_search provider plugin during gateway startup, including auto-enabled external providers behind allowlists. Fixes #82313. (#82376)
·Codex account/status: treat metadata-only rate-limit buckets as returned but empty so `/codex status` and `/codex account` report `none returned` instead of counting phantom limits.
·Codex/Lossless: keep Codex explicit compaction on native app-server threads while allowing Lossless through the context-engine slot; `openclaw doctor --fix` now migrates legacy `compaction.provider: "lossless-claw"` config to `plugins.slots.contextEngine`.
·Cron/doctor: report scheduled jobs with explicit `payload.model` overrides, including provider namespace counts and default-model mismatches, so stale cron model pins are visible during auth or billing investigations. Fixes #82151.
·Codex app-server: keep the short turn-completion idle watchdog armed after the last non-assistant current-turn item completes, so a quiet Codex app-server releases the OpenClaw session lane before the outer attempt timeout. Fixes #82171. (#82172)
·Providers/OpenRouter: stop adding empty DeepSeek V4 `reasoning_content` placeholders to assistant tool-call replay messages and strip empty replay artifacts before follow-up Chat Completions requests, so `openrouter/deepseek/deepseek-v4-pro` no longer fails after tool use. Fixes #82150. (#82158)
·OpenAI-compatible providers: honor streaming-usage compatibility metadata when deciding whether to send `stream_options.include_usage`, while keeping bundled Volcengine routes opted in to Ark streaming usage. Refs #44845. (#82181)
·Gateway/approvals: treat `turnSourceTo` as optional in `canBridgeNoDeviceChatApprovalFromBackend`, matching the existing optional handling of `turnSourceAccountId` and `turnSourceThreadId`. Channels without a recipient concept (webchat, control-ui) leave `turnSourceTo` null on both the approval snapshot and the replay params, so the prior required-string check rejected every backend replay with `APPROVAL_CLIENT_MISMATCH`. Cross-channel replay is still gated by the required `turnSourceChannel` and `sessionKey` checks. Fixes #82132. (#82136)
·OC Path: add `openclaw path set --dry-run --diff` so addressed edits can be reviewed as a unified diff before writing.
·Cron: load runtime plugins before isolated cron model and delivery resolution so external channels can be selected for scheduled runs. (#82111)
·Cron: mirror successful direct scheduled deliveries into the resolved destination session transcript while preserving isolated-delivery awareness policy. (#80786)
·Cron: preserve rotated transcript identity after session-bound scheduled runs compact, so `sessionTarget: "current"` keeps the next user message on the same conversation. Fixes #82164.
·Twitch: keep gateway accounts running until shutdown instead of treating successful monitor startup as a clean channel exit, preventing immediate auto-restart loops. Fixes #60071. (#81853)
·Agents/auto-reply: honor `agents.defaults.silentReply` and per-surface group silent-reply policy when generic agent-run failure fallbacks decide whether to send visible fallback text. Fixes #82060. (#82086)
·Discord: render channel topic context as structured untrusted metadata in reply prompts and stop duplicating inbound message bodies or exposing raw `EXTERNAL_UNTRUSTED_CONTENT` envelopes. Fixes #82168.
·Codex app-server: arm the short idle watchdog as soon as Codex accepts a turn, so accepted turns with no current-turn progress release the OpenClaw session lane before the outer model timeout. Fixes #82129.
·Agents/replies: also strip `<function_response>` workflow output when it becomes visible after an adjacent stripped tool-call XML block, closing the remaining sanitizer leak from #47444.
·Control UI/WebChat: focus the composer when users click the visible input chrome and restore larger, labeled desktop composer controls while preserving compact mobile taps. Fixes #45656.
·Discord: suppress generated link embeds on outbound messages by default so agent-sent URLs stay as plain links unless `channels.discord.suppressEmbeds` is disabled.
·System events: keep owner downgrades in structured metadata while rendering queued prompt text as plain `System:` lines, preserving least-privilege wakeups without prompt-visible trust labels. (#82067)
·Gateway/agents: abort active embedded runs when diagnostics detect a stale native tool call, preventing nested agent sessions from staying deadlocked through restart recovery. Fixes #81976. (#82369)
·Slack: default outbound bot link unfurls off so agent-sent URLs no longer expand into inline previews unless `channels.slack.unfurlLinks` is enabled. (#82123)
·Slack: keep finalized draft-preview replies visible when a later same-turn tool warning is delivered normally instead of clearing the edited answer. Fixes #81903. (#81979)
·Providers/Xiaomi: preserve MiMo `reasoning_content` on multi-turn tool-call replay, including custom Xiaomi-compatible proxy routes, so follow-up turns no longer fail with `400 Param Incorrect`. Fixes #81419. (#81589)
·Slack/plugins: route plugin-owned modal `view_submission` and `view_closed` events through Slack interactive handlers before compacting the agent-visible system event, so plugins can persist full submitted form state while the transcript stays compact. Fixes #82102.
·Providers/Xiaomi: promote legacy MiMo V2 reasoning-only final answers to visible text, including Xiaomi-compatible proxy routes, so `mimo-v2-pro` and `mimo-v2-omni` replies no longer appear blank when the answer arrives in `reasoning_content`. Fixes #60261. (#60304)
·Providers: preserve required `reasoning_content` replay for Kimi K2.6/K2 thinking and MiMo V2.6 OpenAI-compatible tool-call follow-up turns while keeping the stock OpenAI/Qwen strip path intact. Fixes #82139.
·Memory search: stop using chokidar write-stability polling for memory and QMD watchers so large Markdown extraPath trees no longer build up regular file descriptors; changed files now settle through the existing debounced sync queue. Fixes #77327 and #78224. (#81802)
·Message tool: rename the Discord channel-create schema field exposed to models from `type` to `channelType`, avoiding NVIDIA NIM JSON Schema parser failures while still accepting legacy `type` tool calls. (#78920)
·Feishu: send CardKit streaming cards as delivered deltas and retry failed updates, preventing duplicated or dropped streamed text. Fixes #82417. (#82419)
·WhatsApp: accept `group:`-prefixed group JIDs for outbound targets so `whatsapp:group:<jid>@g.us` resolves to the canonical group JID.
·Gateway/Gmail: stop queued post-ready Gmail sidecars before hot reload and abort stale Tailscale setup, so cancelled watcher restarts cannot rewrite an old public hook target or report abort-killed commands as success. (#82395)

v2026.5.16-beta.3pre-release2026-05-16

openclaw 2026.5.16-beta.3

GitHub ↗

Changes

·Providers/xAI: add xAI Grok OAuth login for SuperGrok subscribers, letting `xai/*` models and xAI media/tool providers authenticate without `XAI_API_KEY`.
·CLI/cron: add `openclaw cron run --wait` with timeout and poll interval controls, plus exact `cron.runs --run-id` filtering so automation can block on one queued manual run. (#81929)
·Maintainer tooling: route Crabbox skill defaults through the repo brokered AWS config, leaving Blacksmith Testbox as an explicit opt-in instead of the broad-proof default.
·CLI/onboarding: localize the setup wizard and bundled channel setup flows for English, Simplified Chinese, and Traditional Chinese. (#80645)
·Agents/skills: cache hydrated `resolvedSkills` across warm gateway turns while keying reuse by the redacted effective config, reducing redundant skill snapshot rebuilds without crossing config-gated skill boundaries. (#81451)
·Telegram/group chat: add opt-in `messages.groupChat.ambientTurns: "room_event"` handling so always-on ambient chatter can run as quiet room context and speak visibly only via the message tool. (#81317)
·Codex/context engines: bind thread-bootstrap projection epochs to Codex app-server threads, carry redacted tool-result context into fresh threads, and rotate backend threads when projection state changes. (#82351)
·Gateway: add opt-in restart trace logs for restart signal, active-work drain, close, next-start, ready, and memory spans. (#82396)
·Gateway/performance: split startup benchmark HTTP-listen timing from full gateway-ready timing and add post-bind plugin and sidecar diagnostics to restart-readiness traces. (#82603)

Fixes

·Gateway/diagnostics: redact credential-bearing gateway target URLs and client diagnostics while preserving raw connection URLs for programmatic use, so connect-failure logs no longer surface embedded tokens.
·Telegram: normalize announce group targets via a new `resolveSessionTarget` channel hook so scheduled announcements resolve consistently against the same Telegram session conversation registry as inbound turns. Fixes #81229.
·Discord: bind delayed gateway `identify` retries to the originating socket generation so retries triggered after a reconnect do not identify against a fresh socket. Fixes #82225.
·ACP/control plane: refresh cached runtime handles when agent config changes so ACP sessions stop using stale runtimes after `agents.defaults` edits. Fixes #82237.
·Gateway/sessions: scope session data lookups by agent id so multi-agent gateway state cannot cross-leak session records across configured agents. (#81386)
·Agents/media: accept generated media attachments on internal completion events and report delivery-loss failures as errors, so completed background music/video tasks do not disappear after provider success.
·Matrix/approvals: release in-flight reaction bindings when the channel approval handler stops mid-delivery, preventing stale approval targets after restart. Fixes #82485. (#82482)
·Matrix/E2EE: stop requesting MSC4222 `state_after` sync responses so homeservers with incomplete state-after data do not leave fresh encrypted rooms without outbound room encryptors. Fixes #82515.
·TUI: update the displayed model in real time when an auto-fallback resolution swaps in a different model mid-turn, so the status line reflects the actual model handling the run. Fixes #82296.
·Gateway/sessions: estimate context usage from local/OpenAI-compatible transcripts when provider usage telemetry is missing, so status no longer shows empty usage for real local-model sessions. Fixes #73990. (#82317)
·Update/installers: override npm `min-release-age` quarantine for OpenClaw-managed package installs, so `openclaw update`, plugin updates, and hosted installer scripts can install the requested latest release immediately.
·Agents/sessions: preserve fresh post-compaction token snapshots across stale usage updates, preventing repeated auto-compaction after every message. Fixes #82576. (#82578)
·Agents/OpenAI Responses: log redacted diagnostics for detail-less `response.failed` events while preserving failed response ids, so operators can correlate provider-side failures. Fixes #82558.
·Agents/auth: redact OAuth refresh failure causes against in-memory, attempted, and reloaded credentials before generic token masking while ensuring failed ACP dispatch cleanup closes initialized runtimes.
·Telegram: cache successful startup bot identity by account and token fingerprint for up to 24 hours, so restarts can skip redundant `getMe` probes during Telegram API slow periods without permanently pinning renamed bots. Refs #82525.
·Gateway/sessions: discard stale metadata when recreating dead main session rows, so replacement sessions do not inherit old labels or transcript paths.
·Codex app-server: mark native context compaction completion events as successful, preventing false "Compaction incomplete" notices after successful Codex-managed compaction. Fixes #82470. (#81593)
·Codex app-server: keep long-running turns alive while current-turn approvals, user input, dynamic tools, and notifications make progress, and carry that progress into the outer run timeout. (#82601)
·Gateway/channels: hand off traced channel account startup outside the startup diagnostic phase so long-lived channel tasks do not keep liveness warnings pinned to channel startup. Refs #82398.
·Gateway/restart: queue restart and shutdown signals received while the gateway startup loop is still returning its server handle, so startup-time restarts are not dropped during update churn. (#82660)
·GitHub Copilot: route device-login requests through the plugin SSRF guard with a GitHub-only policy.
·Group/channel replies: keep message-tool-preferred final replies private when the agent misses the message tool, and log suppressed payload metadata in the gateway debug log for quieter diagnosis.
·Gateway/WebChat: route image attachments through a configured vision-capable `imageModel` plan before inlining images, and carry that image-model fallback chain through runtime retries. (#82524)
·WebChat: show progress while manual `/compact` is running by streaming a session operation event to subscribed Control UI clients. Fixes #82407.
·Codex app-server: limit canonical OpenAI Codex app-server attribution rewrites to local transcript and trajectory records, leaving runtime/tool routing on the selected OpenAI model metadata so OpenAI API-key backup profiles keep their billing path.
·Codex app-server: hide native tool-search control tools from dynamic tool exposure while preserving the message tool.
·Android/chat: make bare and markdown URLs in chat messages tappable by preserving Compose URL annotations in rendered markdown. Fixes #82187. (#82392)
·Plugins/doctor: migrate legacy top-level plugin `tools` declarations into `contracts.tools`, so `openclaw doctor --fix` repairs local plugins for the manifest tool contract. (#81112)
·Slack: guide agents to use stable `<@USER_ID>` mention tokens from context instead of plain `@name` text, so user mentions link and notify correctly. Fixes #82090. (#82152)
·Auth: serialize provider login writes through the auth-profile lock for OpenAI Codex, Anthropic, Cloudflare AI Gateway, GitHub Copilot, and z.ai, preserving upsert semantics so a live Gateway cannot overwrite freshly refreshed OAuth credentials with an expired in-memory snapshot.
·Slack: keep DM thread replies on the main direct-message session instead of routing them to invisible thread-scoped sessions. Refs #82390. (#82418)
·Auth/macOS: avoid creating the OAuth profile master key in Keychain automatically, falling back to the file-backed secret key so headless agents do not trigger a Keychain prompt.
·Codex app-server: release raw assistant completions when `turn/completed` is missing while keeping commentary/status items as progress, preventing completed Codex runs from hanging until timeout. Fixes #82343. (#82403)
·Agents/sessions: remove the transient `*.bak-<pid>-<ts>` backup written by `repairSessionFileIfNeeded` once the atomic replace succeeds, so a stuck session with a persistently malformed JSONL line no longer accumulates one snapshot per repair invocation. Fixes #80960. (#80969)
·CLI/status: show plain empty-state messages instead of empty Channels and Sessions tables when no channels or sessions exist.
·CLI/dashboard: probe Gateway readiness before handing out the dashboard URL, prompting to start or install the managed service when the Gateway is stopped and printing recovery commands instead of opening a dead browser tab.
·CLI/dashboard: treat Gateway `device identity required` probes as proof that the dashboard listener is reachable, so `openclaw dashboard` can still open the Control UI.
·CLI: hide decorative startup and status emoji on terminals that are unlikely to render them correctly, keeping semantic message and identity emoji intact.
·CLI/gateway: recover the Linux user systemd bus environment when `openclaw dashboard` starts the Gateway from stripped desktop shells such as VNC terminals.
·Gateway/WebSocket: log expected startup `1013 gateway starting` retry closes at debug instead of warn while preserving WARN for unexpected pre-connect failures. Fixes #76361. (#82457)
·Providers/Xiaomi: strip synthetic empty array `items` from MiMo tool schemas while preserving typed array items, avoiding strict OpenAI-compatible schema rejection.
·Telegram: send the transcript-backed full final answer after progress-mode tool drafts when the dispatcher final payload is an ellipsis-truncated snapshot. Fixes #82409.
·Providers/Ollama: omit truthy native `think` payloads for models marked non-reasoning while preserving supported thinking models and explicit `think: false`. (#82445)
·Update/channels: preserve pre-update channel config through package-swap doctor and post-core plugin repair so externalized channel upgrades do not drop configured chat channels. Fixes #82533.
·CLI/context engines: bootstrap and finalize non-legacy context engines for CLI turns while preserving transcript snapshots and deferred maintenance ownership. (#81869)
·Telegram: persist polling updates through restart replay so queued same-topic messages resume in order instead of losing context after a gateway restart. (#82256)
·Gateway/Gmail: abort in-flight Gmail watcher startup and hot-reload restarts before shutdown so reloads cannot spawn `gog serve` after the Gateway is closing.
·Agents/Codex: fall back to the embedded PI runner when OpenAI's implicit Codex harness preference cannot find a registered Codex plugin, preventing OpenAI-compatible gateway requests from failing with an unregistered harness error. Fixes #82437.
·Agents/OpenAI: honor `openai-codex:*` entries placed ahead of API-key backups in `auth.order.openai` for explicit OpenAI PI runs, and accept `models auth login --provider openai-codex --device-code` for headless sign-in. Fixes #82521. (#82605)
·CLI/channels: install missing externalized same-id channel plugins during `channels add --channel <id>`, so recovery for WhatsApp and other externalized stock channels does not require a separate `plugins enable` step. Fixes #82533.
·MCP plugin tools: forward host MCP `tools/call` `AbortSignal` through `createPluginToolsMcpHandlers().callTool` into plugin `tool.execute`, so host cancellation actually cancels in-flight plugin tool calls instead of letting them run to completion. Fixes #82424. (#82443)
·Plugins: accept deprecated `api.on("deactivate")` registrations as a dated compatibility alias for `gateway_stop`, so external plugin cleanup handlers run on Gateway shutdown while authors get migration guidance.
·Media: ignore image MIME and filename hints when bytes sniff as generic containers, so zip/octet-stream payloads mislabeled as images do not become local image media or keep image file extensions when staged.
·Update/doctor: avoid materializing `groupAllowFrom` for channel schemas that reject it, so package-swap doctor repairs do not fail on externalized Slack configs.
·Gateway/media: prevent image filenames from overriding generic non-image byte sniffing, so zip/octet-stream payloads mislabeled as images are offloaded or rejected before they become inline image attachments.
·Plugins/web search: downgrade stale optional provider installs to warnings so Gateway and doctor repair paths keep running after startup provider selection. Refs #82313.
·Telegram/Gateway: route targeted Telegram `/stop@bot` messages onto the control lane without cached bot metadata and match gateway stop requests across raw/canonical session aliases. (#82298)
·MS Teams/media: sniff inline `data:image/*` attachment bytes before staging them, skipping payloads that are not actually images.
·WebChat/media: require trusted local-media provenance before preserving local audio reply paths for display, so untrusted audio-looking paths go through normal staging and read-policy checks.
·Agents/tool media: preserve trusted local-media provenance when merging generated tool attachments into final reply payloads, so trusted audio/media survives outbound display normalization.
·Anthropic/Claude CLI: write model-scoped `claude-cli` runtime policy when reusing local Claude CLI auth, so upgraded Telegram and Dashboard gateway turns keep using the CLI backend instead of falling through to Anthropic API billing. Fixes #82344.
·Update: let package-swap `doctor --fix` persist core config repairs while plugin schemas are still converging, preventing update failures on externalized channel configs.
·Update: carry plugin-validation bypasses into config mutation pre-write reads, so package update doctor repairs can finish while externalized plugin schemas are converging.
·Update/doctor: keep plugin-validation bypasses on the top-level `$include` config write path, so package repair can update included plugin config files without flattening them into the root config.
·Agents/subagents: warn and continue completion announce cleanup when lifecycle cleanup fails, preventing ended subagent runs from becoming silent ghosts. Fixes #82306.
·Telegram: let authorized text `/stop` commands use the fast-abort path before queued agent work, so active turns stop immediately instead of processing the abort after the turn finishes; foreign-bot `/stop@otherbot` mentions now stay on the regular topic lane instead of being routed into our control lane. Fixes #82162.
·Sessions: drop persisted entries with invalid session ids and strip malformed transcript file metadata before hydrating session runtime state.
·Auth/device: normalize malformed persisted device-auth token metadata before returning or preserving token entries.
·Pairing: skip malformed persisted pending pairing requests before approving valid channel pairing codes.
·Commitments: strip malformed optional reminder scope metadata from persisted commitments before matching pending follow-ups.
·Config persistence: normalize malformed auth profile credential fields/state, skip JSON-valid garbage transcript checkpoint rows, and let `openclaw doctor --fix` remove unrepairable cron job rows.
·Cron: skip persisted job rows with malformed schedule or payload shapes in memory, leaving the store for `openclaw doctor --fix` instead of hydrating them into runtime state.
·Cron: keep legacy string schedules and blank system-event jobs available for runtime repair/skip handling instead of dropping them as malformed persisted rows.
·Cron: reject empty scheduled main/isolated payloads before persisting jobs, keeping runtime stores compatible with malformed-row hardening.
·Task persistence: drop malformed array/scalar requester-origin JSON from task and task-flow SQLite sidecars instead of restoring it as delivery metadata.
·Agents/timeouts: clarify model idle-timeout errors and docs so provider `timeoutSeconds` is shown as bounded by the whole agent/run timeout ceiling.
·Agents/OpenAI streams: yield cooperatively while processing bursty Completions and Responses chunks, keeping aborts, channel liveness timers, and startup heartbeats responsive under noisy model output. Refs #82462.
·Release tooling: align the published launcher Node floor, `npm start`, package script checks, sharded lint locking, Vitest root project coverage, and plugin-SDK declaration build cache metadata so release/package validation does not silently skip or ship stale surfaces.
·Cron/agents: honor configured subagent model fallbacks for isolated scheduled runs and forward that fallback policy into embedded agent timeout failover. Fixes #74985.
·Codex app-server/MCP: scope user MCP servers to specific OpenClaw agent ids through an optional `mcp.servers.<name>.codex.agents` list and accept `codex.defaultToolsApprovalMode` (`auto`/`prompt`/`approve`) for native Codex approval defaults; OpenClaw strips the `codex` block before handing `mcp_servers` config to Codex. (#82180)
·Agents/OpenAI Responses: clamp `input_tokens - cached_tokens` at zero and reconstruct `totalTokens` from input + output + cached components so Responses-API streams report consistent usage when providers under-report `input_tokens` relative to `cached_tokens`.
·Agents: mark adapter-caught tool execution failures as error tool results in embedded Pi sessions, so models can retry recoverable edit failures instead of seeing a successful tool result. Fixes #81546. (#81564)
·Plugins: reject malformed `package.json` `openclaw.extensions` metadata during install, discovery, and post-update payload smoke instead of silently dropping invalid entries.
·Plugins: reject package metadata records whose `package.json` resolves outside the plugin root instead of trusting persisted or reconstructed registry snapshots.
·Plugins: ignore malformed persisted package channel/install metadata instead of crashing catalog reconstruction or leaking invalid install hints.
·Plugin releases: reject package `files` negations that would omit advertised package-local runtime entries from npm plugin tarballs.
·Media/files: sniff `input_file` bytes before trusting declared MIME headers, rejecting spoofed image or zip payloads before they become agent-visible text.
·Plugins/dependencies: scrub stale managed-root `openclaw` ownership metadata without deleting a linked active host package, preventing plugin installs from downgrading npm-global hosts. Fixes #79462.
·Gateway/update: keep shutdown hook-runner imports on a stable dist entry and ship a legacy chunk alias so package swaps do not strand running gateways on missing shutdown chunks. Fixes #81819.
·Config persistence: ignore malformed array/scalar auth profile, cron job state, and session store entries instead of hydrating them into numeric profile ids, crashed cron rows, or invalid session records.
·Config persistence: strip malformed pending final-delivery session fields on load so replay/recovery paths skip poisoned reply metadata instead of crashing on raw objects.
·Config persistence: strip malformed plugin extension state and promoted session-slot ownership on load so corrupted session rows do not leak poisoned plugin metadata into replay/projection paths.
·Gateway/sessions: ignore malformed compaction checkpoint rows during session projection so corrupted stores do not crash session list/describe responses or show bogus checkpoint counts.
·Gateway/sessions: keep reachable transcript history when imported tree transcripts reference missing or legacy parent rows, preventing session history reads from going empty after a partial import.
·Trajectory export: report incomplete transcript parent chains and stop cyclic branch walks so malformed imports cannot hang `/export-trajectory`.
·Session replay: skip malformed user/assistant-shaped transcript rows during silent session resets instead of copying invalid entries into the fresh transcript.
·Backup verify: report malformed archive manifests with a stable error instead of leaking raw JSON parser details.
·Session export: report skipped malformed transcript JSONL rows instead of silently omitting them from exported HTML archives.
·Providers: reject malformed successful Runway, BytePlus, and Ollama embedding responses with provider-owned errors instead of raw parser/type failures, silent bad vectors, or long bogus polling.
·Providers/images: reject malformed successful OpenAI-compatible, OpenAI, Google, fal, and OpenRouter image responses with provider-owned errors instead of raw shape failures, silent invalid base64 skips, or empty image results.
·Providers/videos: reject malformed successful xAI, OpenRouter, and fal video create, poll, and result responses with provider-owned errors instead of raw parser failures or long bogus polling.
·Providers/videos: let selected-model capability overlays clear inherited `providerOptions`, so fallback skips models that explicitly accept no provider-specific options instead of forwarding unsupported knobs.
·TTS/providers: honor preferred provider aliases when routing model override directives, so alias-selected speech providers receive unqualified `[[tts:*]]` overrides.
·Providers/audio: reject malformed successful OpenAI-compatible, ElevenLabs, and Deepgram speech responses with provider-owned errors instead of raw parser failures, wrong-shaped transcripts, or JSON/text bodies treated as audio.
·Providers/embeddings: reject malformed successful OpenAI-compatible, Google Gemini, and Amazon Bedrock embedding responses instead of silently returning empty or coerced vectors.
·Providers/catalogs: reject malformed successful LM Studio, GitHub Copilot, DeepInfra, Vercel AI Gateway, and Kilocode model-list responses with provider-owned errors instead of raw parser/type failures or silent fallback catalogs.
·Providers/polling: reject array, null, or scalar successful operation status responses with provider-owned malformed JSON errors instead of waiting until timeout.
·ACPX/Codex: reap plugin-local Codex ACP adapter orphans on startup after wrapper crashes while keeping direct adapter commands out of launch-lease injection. Fixes #82364. (#82459)
·Telegram: send presentation-only payloads by rendering fallback text and inline buttons instead of treating them as empty. Fixes #82404. (#82449)
·Providers/Kimi: preserve Kimi Coding `reasoning_content` replay and backfill assistant tool-call placeholders when thinking is enabled, so `kimi-for-coding` follow-up tool turns no longer fail after prior tool use. Fixes #82161.
·Providers/search tools: reject malformed successful xAI, Gemini, and Kimi web/code search responses with provider-owned errors instead of silent `No response` payloads or ungrounded fallback state.
·Trajectory export: skip and report malformed session/runtime JSONL rows in `manifest.json` instead of letting wrong-shaped session rows crash support bundle export.
·Voice calls: persist rejected inbound-call replay keys so duplicate carrier webhook retries stay ignored after a Gateway restart.
·Config/doctor: copy fallback-enabled channel `allowFrom` entries into explicit `groupAllowFrom` allowlists during `openclaw doctor --fix`, preserving current group access without adding runtime fallback-transition flags.
·Config/doctor: replace source-only official Brave and Slack plugin installs from trusted catalog metadata during `openclaw doctor --fix`, unblocking externalized stock plugin recovery after upgrade. (#82425)
·Config/memory: warn instead of rejecting configs that select the official external `memory-lancedb` slot before the plugin is installed, with an explicit no-persistent-memory startup warning and install hint. Fixes #82428. (#82438)
·Agents/bootstrap: ignore stale completed root `BOOTSTRAP.md` context after workspace setup cleanup fails, preventing channel agent turns from treating it as a directory. (#82463)
·Update/doctor: re-enable the Codex plugin during `openclaw doctor --fix` when configured OpenAI agent models require the Codex runtime, preventing upgraded configs from failing with an unregistered Codex harness. Fixes #82368. (#82502)
·Configure: show one OpenAI provider entry with ChatGPT/Codex sign-in and API key choices, and keep browsed Codex models in the saved `/model` picker allowlist.
·Agents/model fallback: preserve auto fallback chains across deferred config reloads when session fallback provenance survives but `modelOverrideSource` is missing. Fixes #81982.
·Hooks: raise bounded gateway lifecycle hook wait budgets to 5 seconds for shutdown and 10 seconds for pre-restart, giving short restart notification handlers time to finish before shutdown continues. (#82273)
·Plugin releases: require external package compatibility metadata in the npm plugin publish plan, matching the ClawHub package contract before packages ship.
·Agents/OpenAI-compatible: honor per-model `max_completion_tokens`/`max_tokens` params in embedded OpenAI-completions runs so high-token Kimi-style routes keep their configured completion cap. Fixes #82230.
·Agents/local: install a local gateway request scope around trusted `openclaw agent --local` runs, so subagent completion announces can use in-process gateway dispatch without crashing. Fixes #82140.
·Cron: keep failed isolated-agent runs from marking successful result delivery when only the failure notification was delivered. Fixes #72985.
·Discord: validate message-read results before normalizing channel history and report unexpected payloads with a Discord boundary error instead of `map is not a function`. Fixes #82252.
·Agents/runtime: apply `agents.defaults.models["provider/*"].agentRuntime` as provider-wide model runtime policy while preserving exact model runtime precedence. Fixes #82243.
·Model picker: show the effective Codex runtime first for official OpenAI routes while keeping Pi available as an alternate and preserving Pi-first custom OpenAI-compatible providers. Fixes #82269.
·Agents/auto-reply: restrict `NO_REPLY` prompt guidance to automatic group/channel replies, remove legacy silent-reply rewrites, and suppress accidental direct-chat silent tokens instead of delivering fallback text. Fixes #82254.
·Telegram: retain a longer partial-stream preview when a final callback only carries an ellipsis-truncated snapshot, preventing the visible answer and transcript mirror from being replaced by the short preview. Fixes #82239.
·Telegram/active-memory: run blocking memory recall through the Telegram provider for direct-message turns even when the hook context carries the raw chat id, preventing embedded recall from launching against an invalid numeric channel. Fixes #82177.
·Control UI/WebChat: keep optimistic image messages from embedding large inline `data:` previews and preserve image-only user turns in chat history, avoiding browser stack overflows when sending image attachments. Fixes #82182.
·Agents/media: preserve message-tool-only delivery for generated music and video completion handoffs, so group/channel completions do not finish without posting the generated attachment.
·Telegram: drain queued outbound deliveries after polling reconnect confirms fresh `getUpdates` activity, so stale-socket and network recovery do not leave failed replies stranded. Fixes #50040. Refs #82175.
·Gateway/model auth: abort active provider runs when saved auth is removed through the Gateway control plane, refresh live runtime auth snapshots, and surface `stopReason: "auth-revoked"` to clients. Fixes #81987. (#82346)
·Codex app-server: keep the raw tool-output idle watchdog armed after `custom_tool_call_output` notifications, so post-tool stream silence fails fast instead of waiting for the terminal idle timeout. Fixes #82274. (#82378)
·Codex app-server: enforce OpenClaw `before_tool_call` policy for Codex-native app-server shell and approval paths, preventing native tool execution from bypassing plugin policy. Fixes #82372. (#82496)
·Telegram: mark isolated polling ingress unhealthy when a spooled inbound backlog stalls while Bot API polling still succeeds, so gateway/channel health no longer stays green after Telegram DM processing wedges. Fixes #82175.
·Telegram: drop expired approval callbacks from isolated polling after approval id expiry so stale inline-button updates do not retry forever across restarts. Fixes #82347. (#82455)
·Agents: strip Gemini/Gemma `<final>` tags with attributes or self-closing syntax from delivered replies, including strict final-tag streaming enforcement. Fixes #65867.
·macOS/update: disarm legacy `ai.openclaw.update.*` LaunchAgents when `openclaw update` starts from one, preventing KeepAlive relaunch loops that repeatedly restart the Gateway and replay update continuations. Fixes #82167.
·Agents/replay: strip internal runtime-context metadata and `NO_REPLY` sentinels from provider replay and pending final-delivery recovery so restart and heartbeat resumes do not feed control text back to the model. Fixes #76629.
·Agents/replay: skip malformed transcript tail rows when deduping embedded assistant gap-fill, preventing truncated JSONL from duplicating the final assistant reply during replay recovery.
·LINE: acknowledge signed webhook events before agent processing so slow model replies do not cause LINE `request_timeout` delivery failures. Fixes #65375.
·LINE: stop cron recovery from inferring lowercased LINE recipients from canonical session keys, so long-running task replies do not silently retry undeliverable push targets. Fixes #81628. (#81704)
·TTS: preserve channel-derived voice-note delivery for `/tts audio` replies even when the provider output is not natively voice-compatible. (#82174)
·Codex app-server: preserve inbound sender metadata and source-channel provenance on mirrored user prompts, including failure snapshots, so channel history keeps the original sender identity. (#82184)
·Codex app-server: yield projector work to the event loop between embedded-run notifications while preserving pre-turn rate-limit capture, reducing gateway stalls from account and MCP status notifications. Fixes #81936. (#82333)
·Plugins/web search: start the configured web_search provider plugin during gateway startup, including auto-enabled external providers behind allowlists. Fixes #82313. (#82376)
·Codex account/status: treat metadata-only rate-limit buckets as returned but empty so `/codex status` and `/codex account` report `none returned` instead of counting phantom limits.
·Codex/Lossless: keep Codex explicit compaction on native app-server threads while allowing Lossless through the context-engine slot; `openclaw doctor --fix` now migrates legacy `compaction.provider: "lossless-claw"` config to `plugins.slots.contextEngine`.
·Cron/doctor: report scheduled jobs with explicit `payload.model` overrides, including provider namespace counts and default-model mismatches, so stale cron model pins are visible during auth or billing investigations. Fixes #82151.
·Codex app-server: keep the short turn-completion idle watchdog armed after the last non-assistant current-turn item completes, so a quiet Codex app-server releases the OpenClaw session lane before the outer attempt timeout. Fixes #82171. (#82172)
·Providers/OpenRouter: stop adding empty DeepSeek V4 `reasoning_content` placeholders to assistant tool-call replay messages and strip empty replay artifacts before follow-up Chat Completions requests, so `openrouter/deepseek/deepseek-v4-pro` no longer fails after tool use. Fixes #82150. (#82158)
·OpenAI-compatible providers: honor streaming-usage compatibility metadata when deciding whether to send `stream_options.include_usage`, while keeping bundled Volcengine routes opted in to Ark streaming usage. Refs #44845. (#82181)
·Gateway/approvals: treat `turnSourceTo` as optional in `canBridgeNoDeviceChatApprovalFromBackend`, matching the existing optional handling of `turnSourceAccountId` and `turnSourceThreadId`. Channels without a recipient concept (webchat, control-ui) leave `turnSourceTo` null on both the approval snapshot and the replay params, so the prior required-string check rejected every backend replay with `APPROVAL_CLIENT_MISMATCH`. Cross-channel replay is still gated by the required `turnSourceChannel` and `sessionKey` checks. Fixes #82132. (#82136)
·OC Path: add `openclaw path set --dry-run --diff` so addressed edits can be reviewed as a unified diff before writing.
·Cron: load runtime plugins before isolated cron model and delivery resolution so external channels can be selected for scheduled runs. (#82111)
·Cron: mirror successful direct scheduled deliveries into the resolved destination session transcript while preserving isolated-delivery awareness policy. (#80786)
·Cron: preserve rotated transcript identity after session-bound scheduled runs compact, so `sessionTarget: "current"` keeps the next user message on the same conversation. Fixes #82164.
·Twitch: keep gateway accounts running until shutdown instead of treating successful monitor startup as a clean channel exit, preventing immediate auto-restart loops. Fixes #60071. (#81853)
·Agents/auto-reply: honor `agents.defaults.silentReply` and per-surface group silent-reply policy when generic agent-run failure fallbacks decide whether to send visible fallback text. Fixes #82060. (#82086)
·Discord: render channel topic context as structured untrusted metadata in reply prompts and stop duplicating inbound message bodies or exposing raw `EXTERNAL_UNTRUSTED_CONTENT` envelopes. Fixes #82168.
·Codex app-server: arm the short idle watchdog as soon as Codex accepts a turn, so accepted turns with no current-turn progress release the OpenClaw session lane before the outer model timeout. Fixes #82129.
·Agents/replies: also strip `<function_response>` workflow output when it becomes visible after an adjacent stripped tool-call XML block, closing the remaining sanitizer leak from #47444.
·Control UI/WebChat: focus the composer when users click the visible input chrome and restore larger, labeled desktop composer controls while preserving compact mobile taps. Fixes #45656.
·Discord: suppress generated link embeds on outbound messages by default so agent-sent URLs stay as plain links unless `channels.discord.suppressEmbeds` is disabled.
·System events: keep owner downgrades in structured metadata while rendering queued prompt text as plain `System:` lines, preserving least-privilege wakeups without prompt-visible trust labels. (#82067)
·Gateway/agents: abort active embedded runs when diagnostics detect a stale native tool call, preventing nested agent sessions from staying deadlocked through restart recovery. Fixes #81976. (#82369)
·Slack: default outbound bot link unfurls off so agent-sent URLs no longer expand into inline previews unless `channels.slack.unfurlLinks` is enabled. (#82123)
·Slack: keep finalized draft-preview replies visible when a later same-turn tool warning is delivered normally instead of clearing the edited answer. Fixes #81903. (#81979)
·Providers/Xiaomi: preserve MiMo `reasoning_content` on multi-turn tool-call replay, including custom Xiaomi-compatible proxy routes, so follow-up turns no longer fail with `400 Param Incorrect`. Fixes #81419. (#81589)
·Slack/plugins: route plugin-owned modal `view_submission` and `view_closed` events through Slack interactive handlers before compacting the agent-visible system event, so plugins can persist full submitted form state while the transcript stays compact. Fixes #82102.
·Providers/Xiaomi: promote legacy MiMo V2 reasoning-only final answers to visible text, including Xiaomi-compatible proxy routes, so `mimo-v2-pro` and `mimo-v2-omni` replies no longer appear blank when the answer arrives in `reasoning_content`. Fixes #60261. (#60304)
·Providers: preserve required `reasoning_content` replay for Kimi K2.6/K2 thinking and MiMo V2.6 OpenAI-compatible tool-call follow-up turns while keeping the stock OpenAI/Qwen strip path intact. Fixes #82139.
·Memory search: stop using chokidar write-stability polling for memory and QMD watchers so large Markdown extraPath trees no longer build up regular file descriptors; changed files now settle through the existing debounced sync queue. Fixes #77327 and #78224. (#81802)
·Message tool: rename the Discord channel-create schema field exposed to models from `type` to `channelType`, avoiding NVIDIA NIM JSON Schema parser failures while still accepting legacy `type` tool calls. (#78920)
·Feishu: send CardKit streaming cards as delivered deltas and retry failed updates, preventing duplicated or dropped streamed text. Fixes #82417. (#82419)
·Gateway/Gmail: stop queued post-ready Gmail sidecars before hot reload and abort stale Tailscale setup, so cancelled watcher restarts cannot rewrite an old public hook target or report abort-killed commands as success. (#82395)

v2026.5.16-beta.2pre-release2026-05-16

openclaw 2026.5.16-beta.2

GitHub ↗

Changes

·Providers/xAI: add xAI Grok OAuth login for SuperGrok subscribers, letting `xai/*` models and xAI media/tool providers authenticate without `XAI_API_KEY`.
·CLI/cron: add `openclaw cron run --wait` with timeout and poll interval controls, plus exact `cron.runs --run-id` filtering so automation can block on one queued manual run. (#81929)
·Maintainer tooling: route Crabbox skill defaults through the repo brokered AWS config, leaving Blacksmith Testbox as an explicit opt-in instead of the broad-proof default.
·CLI/onboarding: localize the setup wizard and bundled channel setup flows for English, Simplified Chinese, and Traditional Chinese. (#80645)
·Agents/skills: cache hydrated `resolvedSkills` across warm gateway turns while keying reuse by the redacted effective config, reducing redundant skill snapshot rebuilds without crossing config-gated skill boundaries. (#81451)
·Telegram/group chat: add opt-in `messages.groupChat.ambientTurns: "room_event"` handling so always-on ambient chatter can run as quiet room context and speak visibly only via the message tool. (#81317)
·Codex/context engines: bind thread-bootstrap projection epochs to Codex app-server threads, carry redacted tool-result context into fresh threads, and rotate backend threads when projection state changes. (#82351)

Fixes

·Telegram: persist polling updates through restart replay so queued same-topic messages resume in order instead of losing context after a gateway restart. (#82256)
·Gateway/Gmail: abort in-flight Gmail watcher startup and hot-reload restarts before shutdown so reloads cannot spawn `gog serve` after the Gateway is closing.
·MCP plugin tools: forward host MCP `tools/call` `AbortSignal` through `createPluginToolsMcpHandlers().callTool` into plugin `tool.execute`, so host cancellation actually cancels in-flight plugin tool calls instead of letting them run to completion. Fixes #82424. (#82443)
·Media: ignore image MIME and filename hints when bytes sniff as generic containers, so zip/octet-stream payloads mislabeled as images do not become local image media or keep image file extensions when staged.
·Update/doctor: avoid materializing `groupAllowFrom` for channel schemas that reject it, so package-swap doctor repairs do not fail on externalized Slack configs.
·Gateway/media: prevent image filenames from overriding generic non-image byte sniffing, so zip/octet-stream payloads mislabeled as images are offloaded or rejected before they become inline image attachments.
·Plugins/web search: downgrade stale optional provider installs to warnings so Gateway and doctor repair paths keep running after startup provider selection. Refs #82313.
·Telegram/Gateway: route targeted Telegram `/stop@bot` messages onto the control lane without cached bot metadata and match gateway stop requests across raw/canonical session aliases. (#82298)
·MS Teams/media: sniff inline `data:image/*` attachment bytes before staging them, skipping payloads that are not actually images.
·Update: let package-swap `doctor --fix` persist core config repairs while plugin schemas are still converging, preventing update failures on externalized channel configs.
·Update: carry plugin-validation bypasses into config mutation pre-write reads, so package update doctor repairs can finish while externalized plugin schemas are converging.
·Update/doctor: keep plugin-validation bypasses on the top-level `$include` config write path, so package repair can update included plugin config files without flattening them into the root config.
·Agents/subagents: warn and continue completion announce cleanup when lifecycle cleanup fails, preventing ended subagent runs from becoming silent ghosts. Fixes #82306.
·Telegram: let authorized text `/stop` commands use the fast-abort path before queued agent work, so active turns stop immediately instead of processing the abort after the turn finishes; foreign-bot `/stop@otherbot` mentions now stay on the regular topic lane instead of being routed into our control lane. Fixes #82162.
·Sessions: drop persisted entries with invalid session ids and strip malformed transcript file metadata before hydrating session runtime state.
·Auth/device: normalize malformed persisted device-auth token metadata before returning or preserving token entries.
·Pairing: skip malformed persisted pending pairing requests before approving valid channel pairing codes.
·Commitments: strip malformed optional reminder scope metadata from persisted commitments before matching pending follow-ups.
·Config persistence: normalize malformed auth profile credential fields/state, skip JSON-valid garbage transcript checkpoint rows, and let `openclaw doctor --fix` remove unrepairable cron job rows.
·Cron: skip persisted job rows with malformed schedule or payload shapes in memory, leaving the store for `openclaw doctor --fix` instead of hydrating them into runtime state.
·Cron: reject empty scheduled main/isolated payloads before persisting jobs, keeping runtime stores compatible with malformed-row hardening.
·Task persistence: drop malformed array/scalar requester-origin JSON from task and task-flow SQLite sidecars instead of restoring it as delivery metadata.
·Agents/timeouts: clarify model idle-timeout errors and docs so provider `timeoutSeconds` is shown as bounded by the whole agent/run timeout ceiling.
·Release tooling: align the published launcher Node floor, `npm start`, package script checks, sharded lint locking, Vitest root project coverage, and plugin-SDK declaration build cache metadata so release/package validation does not silently skip or ship stale surfaces.
·Cron/agents: honor configured subagent model fallbacks for isolated scheduled runs and forward that fallback policy into embedded agent timeout failover. Fixes #74985.
·Codex app-server/MCP: scope user MCP servers to specific OpenClaw agent ids through an optional `mcp.servers.<name>.codex.agents` list and accept `codex.defaultToolsApprovalMode` (`auto`/`prompt`/`approve`) for native Codex approval defaults; OpenClaw strips the `codex` block before handing `mcp_servers` config to Codex. (#82180)
·Agents/OpenAI Responses: clamp `input_tokens - cached_tokens` at zero and reconstruct `totalTokens` from input + output + cached components so Responses-API streams report consistent usage when providers under-report `input_tokens` relative to `cached_tokens`.
·Agents: mark adapter-caught tool execution failures as error tool results in embedded Pi sessions, so models can retry recoverable edit failures instead of seeing a successful tool result. Fixes #81546. (#81564)
·Plugins: reject malformed `package.json` `openclaw.extensions` metadata during install, discovery, and post-update payload smoke instead of silently dropping invalid entries.
·Plugins: reject package metadata records whose `package.json` resolves outside the plugin root instead of trusting persisted or reconstructed registry snapshots.
·Plugins: ignore malformed persisted package channel/install metadata instead of crashing catalog reconstruction or leaking invalid install hints.
·Plugin releases: reject package `files` negations that would omit advertised package-local runtime entries from npm plugin tarballs.
·Media/files: sniff `input_file` bytes before trusting declared MIME headers, rejecting spoofed image or zip payloads before they become agent-visible text.
·Plugins/dependencies: scrub stale managed-root `openclaw` ownership metadata without deleting a linked active host package, preventing plugin installs from downgrading npm-global hosts. Fixes #79462.
·Gateway/update: keep shutdown hook-runner imports on a stable dist entry and ship a legacy chunk alias so package swaps do not strand running gateways on missing shutdown chunks. Fixes #81819.
·Config persistence: ignore malformed array/scalar auth profile, cron job state, and session store entries instead of hydrating them into numeric profile ids, crashed cron rows, or invalid session records.
·Config persistence: strip malformed pending final-delivery session fields on load so replay/recovery paths skip poisoned reply metadata instead of crashing on raw objects.
·Config persistence: strip malformed plugin extension state and promoted session-slot ownership on load so corrupted session rows do not leak poisoned plugin metadata into replay/projection paths.
·Gateway/sessions: ignore malformed compaction checkpoint rows during session projection so corrupted stores do not crash session list/describe responses or show bogus checkpoint counts.
·Gateway/sessions: keep reachable transcript history when imported tree transcripts reference missing or legacy parent rows, preventing session history reads from going empty after a partial import.
·Providers: reject malformed successful Runway, BytePlus, and Ollama embedding responses with provider-owned errors instead of raw parser/type failures, silent bad vectors, or long bogus polling.
·Providers/images: reject malformed successful OpenAI-compatible, OpenAI, Google, fal, and OpenRouter image responses with provider-owned errors instead of raw shape failures, silent invalid base64 skips, or empty image results.
·Providers/videos: reject malformed successful xAI, OpenRouter, and fal video create, poll, and result responses with provider-owned errors instead of raw parser failures or long bogus polling.
·Providers/audio: reject malformed successful OpenAI-compatible, ElevenLabs, and Deepgram speech responses with provider-owned errors instead of raw parser failures, wrong-shaped transcripts, or JSON/text bodies treated as audio.
·Providers/embeddings: reject malformed successful OpenAI-compatible, Google Gemini, and Amazon Bedrock embedding responses instead of silently returning empty or coerced vectors.
·Providers/catalogs: reject malformed successful LM Studio, GitHub Copilot, DeepInfra, Vercel AI Gateway, and Kilocode model-list responses with provider-owned errors instead of raw parser/type failures or silent fallback catalogs.
·Providers/polling: reject array, null, or scalar successful operation status responses with provider-owned malformed JSON errors instead of waiting until timeout.
·ACPX/Codex: reap plugin-local Codex ACP adapter orphans on startup after wrapper crashes while keeping direct adapter commands out of launch-lease injection. Fixes #82364. (#82459)
·Telegram: send presentation-only payloads by rendering fallback text and inline buttons instead of treating them as empty. Fixes #82404. (#82449)
·Trajectory export: skip and report malformed session/runtime JSONL rows in `manifest.json` instead of letting wrong-shaped session rows crash support bundle export.
·Voice calls: persist rejected inbound-call replay keys so duplicate carrier webhook retries stay ignored after a Gateway restart.
·Config/doctor: copy fallback-enabled channel `allowFrom` entries into explicit `groupAllowFrom` allowlists during `openclaw doctor --fix`, preserving current group access without adding runtime fallback-transition flags.
·Config/doctor: replace source-only official Brave and Slack plugin installs from trusted catalog metadata during `openclaw doctor --fix`, unblocking externalized stock plugin recovery after upgrade. (#82425)
·Agents/bootstrap: ignore stale completed root `BOOTSTRAP.md` context after workspace setup cleanup fails, preventing channel agent turns from treating it as a directory. (#82463)
·Update/doctor: re-enable the Codex plugin during `openclaw doctor --fix` when configured OpenAI agent models require the Codex runtime, preventing upgraded configs from failing with an unregistered Codex harness. Fixes #82368. (#82502)
·Configure: show one OpenAI provider entry with ChatGPT/Codex sign-in and API key choices, and keep browsed Codex models in the saved `/model` picker allowlist.
·Agents/model fallback: preserve auto fallback chains across deferred config reloads when session fallback provenance survives but `modelOverrideSource` is missing. Fixes #81982.
·Hooks: raise bounded gateway lifecycle hook wait budgets to 5 seconds for shutdown and 10 seconds for pre-restart, giving short restart notification handlers time to finish before shutdown continues. (#82273)
·Plugin releases: require external package compatibility metadata in the npm plugin publish plan, matching the ClawHub package contract before packages ship.
·Agents/OpenAI-compatible: honor per-model `max_completion_tokens`/`max_tokens` params in embedded OpenAI-completions runs so high-token Kimi-style routes keep their configured completion cap. Fixes #82230.
·Agents/local: install a local gateway request scope around trusted `openclaw agent --local` runs, so subagent completion announces can use in-process gateway dispatch without crashing. Fixes #82140.
·Cron: keep failed isolated-agent runs from marking successful result delivery when only the failure notification was delivered. Fixes #72985.
·Discord: validate message-read results before normalizing channel history and report unexpected payloads with a Discord boundary error instead of `map is not a function`. Fixes #82252.
·Agents/runtime: apply `agents.defaults.models["provider/*"].agentRuntime` as provider-wide model runtime policy while preserving exact model runtime precedence. Fixes #82243.
·Agents/auto-reply: restrict `NO_REPLY` prompt guidance to automatic group/channel replies, remove legacy silent-reply rewrites, and suppress accidental direct-chat silent tokens instead of delivering fallback text. Fixes #82254.
·Telegram: retain a longer partial-stream preview when a final callback only carries an ellipsis-truncated snapshot, preventing the visible answer and transcript mirror from being replaced by the short preview. Fixes #82239.
·Telegram/active-memory: run blocking memory recall through the Telegram provider for direct-message turns even when the hook context carries the raw chat id, preventing embedded recall from launching against an invalid numeric channel. Fixes #82177.
·Control UI/WebChat: keep optimistic image messages from embedding large inline `data:` previews and preserve image-only user turns in chat history, avoiding browser stack overflows when sending image attachments. Fixes #82182.
·Agents/media: preserve message-tool-only delivery for generated music and video completion handoffs, so group/channel completions do not finish without posting the generated attachment.
·Telegram: drain queued outbound deliveries after polling reconnect confirms fresh `getUpdates` activity, so stale-socket and network recovery do not leave failed replies stranded. Fixes #50040. Refs #82175.
·Gateway/model auth: abort active provider runs when saved auth is removed through the Gateway control plane, refresh live runtime auth snapshots, and surface `stopReason: "auth-revoked"` to clients. Fixes #81987. (#82346)
·Codex app-server: keep the raw tool-output idle watchdog armed after `custom_tool_call_output` notifications, so post-tool stream silence fails fast instead of waiting for the terminal idle timeout. Fixes #82274. (#82378)
·Codex app-server: enforce OpenClaw `before_tool_call` policy for Codex-native app-server shell and approval paths, preventing native tool execution from bypassing plugin policy. Fixes #82372. (#82496)
·Telegram: mark isolated polling ingress unhealthy when a spooled inbound backlog stalls while Bot API polling still succeeds, so gateway/channel health no longer stays green after Telegram DM processing wedges. Fixes #82175.
·Telegram: drop expired approval callbacks from isolated polling after approval id expiry so stale inline-button updates do not retry forever across restarts. Fixes #82347. (#82455)
·Agents: strip Gemini/Gemma `<final>` tags with attributes or self-closing syntax from delivered replies, including strict final-tag streaming enforcement. Fixes #65867.
·macOS/update: disarm legacy `ai.openclaw.update.*` LaunchAgents when `openclaw update` starts from one, preventing KeepAlive relaunch loops that repeatedly restart the Gateway and replay update continuations. Fixes #82167.
·Agents/replay: strip internal runtime-context metadata and `NO_REPLY` sentinels from provider replay and pending final-delivery recovery so restart and heartbeat resumes do not feed control text back to the model. Fixes #76629.
·Agents/replay: skip malformed transcript tail rows when deduping embedded assistant gap-fill, preventing truncated JSONL from duplicating the final assistant reply during replay recovery.
·LINE: acknowledge signed webhook events before agent processing so slow model replies do not cause LINE `request_timeout` delivery failures. Fixes #65375.
·LINE: stop cron recovery from inferring lowercased LINE recipients from canonical session keys, so long-running task replies do not silently retry undeliverable push targets. Fixes #81628. (#81704)
·TTS: preserve channel-derived voice-note delivery for `/tts audio` replies even when the provider output is not natively voice-compatible. (#82174)
·Codex app-server: preserve inbound sender metadata and source-channel provenance on mirrored user prompts, including failure snapshots, so channel history keeps the original sender identity. (#82184)
·Codex app-server: yield projector work to the event loop between embedded-run notifications while preserving pre-turn rate-limit capture, reducing gateway stalls from account and MCP status notifications. Fixes #81936. (#82333)
·Plugins/web search: start the configured web_search provider plugin during gateway startup, including auto-enabled external providers behind allowlists. Fixes #82313. (#82376)
·Codex account/status: treat metadata-only rate-limit buckets as returned but empty so `/codex status` and `/codex account` report `none returned` instead of counting phantom limits.
·Codex/Lossless: keep Codex explicit compaction on native app-server threads while allowing Lossless through the context-engine slot; `openclaw doctor --fix` now migrates legacy `compaction.provider: "lossless-claw"` config to `plugins.slots.contextEngine`.
·Cron/doctor: report scheduled jobs with explicit `payload.model` overrides, including provider namespace counts and default-model mismatches, so stale cron model pins are visible during auth or billing investigations. Fixes #82151.
·Codex app-server: keep the short turn-completion idle watchdog armed after the last non-assistant current-turn item completes, so a quiet Codex app-server releases the OpenClaw session lane before the outer attempt timeout. Fixes #82171. (#82172)
·Providers/OpenRouter: stop adding empty DeepSeek V4 `reasoning_content` placeholders to assistant tool-call replay messages and strip empty replay artifacts before follow-up Chat Completions requests, so `openrouter/deepseek/deepseek-v4-pro` no longer fails after tool use. Fixes #82150. (#82158)
·OpenAI-compatible providers: honor streaming-usage compatibility metadata when deciding whether to send `stream_options.include_usage`, while keeping bundled Volcengine routes opted in to Ark streaming usage. Refs #44845. (#82181)
·Gateway/approvals: treat `turnSourceTo` as optional in `canBridgeNoDeviceChatApprovalFromBackend`, matching the existing optional handling of `turnSourceAccountId` and `turnSourceThreadId`. Channels without a recipient concept (webchat, control-ui) leave `turnSourceTo` null on both the approval snapshot and the replay params, so the prior required-string check rejected every backend replay with `APPROVAL_CLIENT_MISMATCH`. Cross-channel replay is still gated by the required `turnSourceChannel` and `sessionKey` checks. Fixes #82132. (#82136)
·OC Path: add `openclaw path set --dry-run --diff` so addressed edits can be reviewed as a unified diff before writing.
·Cron: load runtime plugins before isolated cron model and delivery resolution so external channels can be selected for scheduled runs. (#82111)
·Cron: mirror successful direct scheduled deliveries into the resolved destination session transcript while preserving isolated-delivery awareness policy. (#80786)
·Cron: preserve rotated transcript identity after session-bound scheduled runs compact, so `sessionTarget: "current"` keeps the next user message on the same conversation. Fixes #82164.
·Twitch: keep gateway accounts running until shutdown instead of treating successful monitor startup as a clean channel exit, preventing immediate auto-restart loops. Fixes #60071. (#81853)
·Agents/auto-reply: honor `agents.defaults.silentReply` and per-surface group silent-reply policy when generic agent-run failure fallbacks decide whether to send visible fallback text. Fixes #82060. (#82086)
·Discord: render channel topic context as structured untrusted metadata in reply prompts and stop duplicating inbound message bodies or exposing raw `EXTERNAL_UNTRUSTED_CONTENT` envelopes. Fixes #82168.
·Codex app-server: arm the short idle watchdog as soon as Codex accepts a turn, so accepted turns with no current-turn progress release the OpenClaw session lane before the outer model timeout. Fixes #82129.
·Agents/replies: also strip `<function_response>` workflow output when it becomes visible after an adjacent stripped tool-call XML block, closing the remaining sanitizer leak from #47444.
·Control UI/WebChat: focus the composer when users click the visible input chrome and restore larger, labeled desktop composer controls while preserving compact mobile taps. Fixes #45656.
·Discord: suppress generated link embeds on outbound messages by default so agent-sent URLs stay as plain links unless `channels.discord.suppressEmbeds` is disabled.
·System events: keep owner downgrades in structured metadata while rendering queued prompt text as plain `System:` lines, preserving least-privilege wakeups without prompt-visible trust labels. (#82067)
·Gateway/agents: abort active embedded runs when diagnostics detect a stale native tool call, preventing nested agent sessions from staying deadlocked through restart recovery. Fixes #81976. (#82369)
·Slack: default outbound bot link unfurls off so agent-sent URLs no longer expand into inline previews unless `channels.slack.unfurlLinks` is enabled. (#82123)
·Slack: keep finalized draft-preview replies visible when a later same-turn tool warning is delivered normally instead of clearing the edited answer. Fixes #81903. (#81979)
·Providers/Xiaomi: preserve MiMo `reasoning_content` on multi-turn tool-call replay, including custom Xiaomi-compatible proxy routes, so follow-up turns no longer fail with `400 Param Incorrect`. Fixes #81419. (#81589)
·Slack/plugins: route plugin-owned modal `view_submission` and `view_closed` events through Slack interactive handlers before compacting the agent-visible system event, so plugins can persist full submitted form state while the transcript stays compact. Fixes #82102.
·Providers/Xiaomi: promote legacy MiMo V2 reasoning-only final answers to visible text, including Xiaomi-compatible proxy routes, so `mimo-v2-pro` and `mimo-v2-omni` replies no longer appear blank when the answer arrives in `reasoning_content`. Fixes #60261. (#60304)
·Providers: preserve required `reasoning_content` replay for Kimi K2.6/K2 thinking and MiMo V2.6 OpenAI-compatible tool-call follow-up turns while keeping the stock OpenAI/Qwen strip path intact. Fixes #82139.
·Memory search: stop using chokidar write-stability polling for memory and QMD watchers so large Markdown extraPath trees no longer build up regular file descriptors; changed files now settle through the existing debounced sync queue. Fixes #77327 and #78224. (#81802)
·Message tool: rename the Discord channel-create schema field exposed to models from `type` to `channelType`, avoiding NVIDIA NIM JSON Schema parser failures while still accepting legacy `type` tool calls. (#78920)
·Feishu: send CardKit streaming cards as delivered deltas and retry failed updates, preventing duplicated or dropped streamed text. Fixes #82417. (#82419)
·Gateway/Gmail: stop queued post-ready Gmail sidecars before hot reload and abort stale Tailscale setup, so cancelled watcher restarts cannot rewrite an old public hook target or report abort-killed commands as success. (#82395)

v2026.5.16-beta.1pre-release2026-05-16

openclaw 2026.5.16-beta.1

GitHub ↗

Changes

·Maintainer tooling: route Crabbox skill defaults through the repo brokered AWS config, leaving Blacksmith Testbox as an explicit opt-in instead of the broad-proof default.
·CLI/onboarding: localize the setup wizard and bundled channel setup flows for English, Simplified Chinese, and Traditional Chinese. (#80645)
·Agents/skills: cache hydrated `resolvedSkills` across warm gateway turns while keying reuse by the redacted effective config, reducing redundant skill snapshot rebuilds without crossing config-gated skill boundaries. (#81451)
·Telegram/group chat: add opt-in `messages.groupChat.ambientTurns: "room_event"` handling so always-on ambient chatter can run as quiet room context and speak visibly only via the message tool. (#81317)

Fixes

·Release tooling: align the published launcher Node floor, `npm start`, package script checks, sharded lint locking, Vitest root project coverage, and plugin-SDK declaration build cache metadata so release/package validation does not silently skip or ship stale surfaces.
·Cron/agents: honor configured subagent model fallbacks for isolated scheduled runs and forward that fallback policy into embedded agent timeout failover. Fixes #74985.
·Codex app-server/MCP: scope user MCP servers to specific OpenClaw agent ids through an optional `mcp.servers.<name>.codex.agents` list and accept `codex.defaultToolsApprovalMode` (`auto`/`prompt`/`approve`) for native Codex approval defaults; OpenClaw strips the `codex` block before handing `mcp_servers` config to Codex. (#82180)
·Agents/OpenAI Responses: clamp `input_tokens - cached_tokens` at zero and reconstruct `totalTokens` from input + output + cached components so Responses-API streams report consistent usage when providers under-report `input_tokens` relative to `cached_tokens`.
·Plugins: reject malformed `package.json` `openclaw.extensions` metadata during install, discovery, and post-update payload smoke instead of silently dropping invalid entries.
·Media/files: sniff `input_file` bytes before trusting declared MIME headers, rejecting spoofed image or zip payloads before they become agent-visible text.
·Config persistence: ignore malformed array/scalar auth profile, cron job state, and session store entries instead of hydrating them into numeric profile ids, crashed cron rows, or invalid session records.
·Providers: reject malformed successful Runway, BytePlus, and Ollama embedding responses with provider-owned errors instead of raw parser/type failures, silent bad vectors, or long bogus polling.
·Trajectory export: skip and report malformed session/runtime JSONL rows in `manifest.json` instead of letting wrong-shaped session rows crash support bundle export.
·Config/doctor: copy fallback-enabled channel `allowFrom` entries into explicit `groupAllowFrom` allowlists during `openclaw doctor --fix`, preserving current group access without adding runtime fallback-transition flags.
·Hooks: raise bounded gateway lifecycle hook wait budgets to 5 seconds for shutdown and 10 seconds for pre-restart, giving short restart notification handlers time to finish before shutdown continues. (#82273)
·Plugin releases: require external package compatibility metadata in the npm plugin publish plan, matching the ClawHub package contract before packages ship.
·Agents/OpenAI-compatible: honor per-model `max_completion_tokens`/`max_tokens` params in embedded OpenAI-completions runs so high-token Kimi-style routes keep their configured completion cap. Fixes #82230.
·Agents/local: install a local gateway request scope around trusted `openclaw agent --local` runs, so subagent completion announces can use in-process gateway dispatch without crashing. Fixes #82140.
·Cron: keep failed isolated-agent runs from marking successful result delivery when only the failure notification was delivered. Fixes #72985.
·Discord: validate message-read results before normalizing channel history and report unexpected payloads with a Discord boundary error instead of `map is not a function`. Fixes #82252.
·Agents/runtime: apply `agents.defaults.models["provider/*"].agentRuntime` as provider-wide model runtime policy while preserving exact model runtime precedence. Fixes #82243.
·Agents/auto-reply: restrict `NO_REPLY` prompt guidance to automatic group/channel replies, remove legacy silent-reply rewrites, and suppress accidental direct-chat silent tokens instead of delivering fallback text. Fixes #82254.
·Telegram: retain a longer partial-stream preview when a final callback only carries an ellipsis-truncated snapshot, preventing the visible answer and transcript mirror from being replaced by the short preview. Fixes #82239.
·Telegram/active-memory: run blocking memory recall through the Telegram provider for direct-message turns even when the hook context carries the raw chat id, preventing embedded recall from launching against an invalid numeric channel. Fixes #82177.
·Control UI/WebChat: keep optimistic image messages from embedding large inline `data:` previews and preserve image-only user turns in chat history, avoiding browser stack overflows when sending image attachments. Fixes #82182.
·Agents/media: preserve message-tool-only delivery for generated music and video completion handoffs, so group/channel completions do not finish without posting the generated attachment.
·Telegram: drain queued outbound deliveries after polling reconnect confirms fresh `getUpdates` activity, so stale-socket and network recovery do not leave failed replies stranded. Fixes #50040. Refs #82175.
·Telegram: mark isolated polling ingress unhealthy when a spooled inbound backlog stalls while Bot API polling still succeeds, so gateway/channel health no longer stays green after Telegram DM processing wedges. Fixes #82175.
·Agents: strip Gemini/Gemma `<final>` tags with attributes or self-closing syntax from delivered replies, including strict final-tag streaming enforcement. Fixes #65867.
·macOS/update: disarm legacy `ai.openclaw.update.*` LaunchAgents when `openclaw update` starts from one, preventing KeepAlive relaunch loops that repeatedly restart the Gateway and replay update continuations. Fixes #82167.
·Agents/replay: strip internal runtime-context metadata and `NO_REPLY` sentinels from provider replay and pending final-delivery recovery so restart and heartbeat resumes do not feed control text back to the model. Fixes #76629.
·LINE: acknowledge signed webhook events before agent processing so slow model replies do not cause LINE `request_timeout` delivery failures. Fixes #65375.
·LINE: stop cron recovery from inferring lowercased LINE recipients from canonical session keys, so long-running task replies do not silently retry undeliverable push targets. Fixes #81628. (#81704)
·TTS: preserve channel-derived voice-note delivery for `/tts audio` replies even when the provider output is not natively voice-compatible. (#82174)
·Codex app-server: preserve inbound sender metadata and source-channel provenance on mirrored user prompts, including failure snapshots, so channel history keeps the original sender identity. (#82184)
·Codex account/status: treat metadata-only rate-limit buckets as returned but empty so `/codex status` and `/codex account` report `none returned` instead of counting phantom limits.
·Codex/Lossless: keep Codex explicit compaction on native app-server threads while allowing Lossless through the context-engine slot; `openclaw doctor --fix` now migrates legacy `compaction.provider: "lossless-claw"` config to `plugins.slots.contextEngine`.
·Cron/doctor: report scheduled jobs with explicit `payload.model` overrides, including provider namespace counts and default-model mismatches, so stale cron model pins are visible during auth or billing investigations. Fixes #82151.
·Codex app-server: keep the short turn-completion idle watchdog armed after the last non-assistant current-turn item completes, so a quiet Codex app-server releases the OpenClaw session lane before the outer attempt timeout. Fixes #82171. (#82172)
·Providers/OpenRouter: stop adding empty DeepSeek V4 `reasoning_content` placeholders to assistant tool-call replay messages and strip empty replay artifacts before follow-up Chat Completions requests, so `openrouter/deepseek/deepseek-v4-pro` no longer fails after tool use. Fixes #82150. (#82158)
·OpenAI-compatible providers: honor streaming-usage compatibility metadata when deciding whether to send `stream_options.include_usage`, while keeping bundled Volcengine routes opted in to Ark streaming usage. Refs #44845. (#82181)
·Gateway/approvals: treat `turnSourceTo` as optional in `canBridgeNoDeviceChatApprovalFromBackend`, matching the existing optional handling of `turnSourceAccountId` and `turnSourceThreadId`. Channels without a recipient concept (webchat, control-ui) leave `turnSourceTo` null on both the approval snapshot and the replay params, so the prior required-string check rejected every backend replay with `APPROVAL_CLIENT_MISMATCH`. Cross-channel replay is still gated by the required `turnSourceChannel` and `sessionKey` checks. Fixes #82132. (#82136)
·Cron: load runtime plugins before isolated cron model and delivery resolution so external channels can be selected for scheduled runs. (#82111)
·Cron: mirror successful direct scheduled deliveries into the resolved destination session transcript while preserving isolated-delivery awareness policy. (#80786)
·Cron: preserve rotated transcript identity after session-bound scheduled runs compact, so `sessionTarget: "current"` keeps the next user message on the same conversation. Fixes #82164.
·Twitch: keep gateway accounts running until shutdown instead of treating successful monitor startup as a clean channel exit, preventing immediate auto-restart loops. Fixes #60071. (#81853)
·Agents/auto-reply: honor `agents.defaults.silentReply` and per-surface group silent-reply policy when generic agent-run failure fallbacks decide whether to send visible fallback text. Fixes #82060. (#82086)
·Discord: render channel topic context as structured untrusted metadata in reply prompts and stop duplicating inbound message bodies or exposing raw `EXTERNAL_UNTRUSTED_CONTENT` envelopes. Fixes #82168.
·Codex app-server: arm the short idle watchdog as soon as Codex accepts a turn, so accepted turns with no current-turn progress release the OpenClaw session lane before the outer model timeout. Fixes #82129.
·Agents/replies: also strip `<function_response>` workflow output when it becomes visible after an adjacent stripped tool-call XML block, closing the remaining sanitizer leak from #47444.
·Control UI/WebChat: focus the composer when users click the visible input chrome and restore larger, labeled desktop composer controls while preserving compact mobile taps. Fixes #45656.
·Discord: suppress generated link embeds on outbound messages by default so agent-sent URLs stay as plain links unless `channels.discord.suppressEmbeds` is disabled.
·System events: keep owner downgrades in structured metadata while rendering queued prompt text as plain `System:` lines, preserving least-privilege wakeups without prompt-visible trust labels. (#82067)
·Slack: default outbound bot link unfurls off so agent-sent URLs no longer expand into inline previews unless `channels.slack.unfurlLinks` is enabled. (#82123)
·Slack: keep finalized draft-preview replies visible when a later same-turn tool warning is delivered normally instead of clearing the edited answer. Fixes #81903. (#81979)
·Providers/Xiaomi: preserve MiMo `reasoning_content` on multi-turn tool-call replay, including custom Xiaomi-compatible proxy routes, so follow-up turns no longer fail with `400 Param Incorrect`. Fixes #81419. (#81589)
·Slack/plugins: route plugin-owned modal `view_submission` and `view_closed` events through Slack interactive handlers before compacting the agent-visible system event, so plugins can persist full submitted form state while the transcript stays compact. Fixes #82102.
·Providers/Xiaomi: promote legacy MiMo V2 reasoning-only final answers to visible text, including Xiaomi-compatible proxy routes, so `mimo-v2-pro` and `mimo-v2-omni` replies no longer appear blank when the answer arrives in `reasoning_content`. Fixes #60261. (#60304)
·Providers: preserve required `reasoning_content` replay for Kimi K2.6/K2 thinking and MiMo V2.6 OpenAI-compatible tool-call follow-up turns while keeping the stock OpenAI/Qwen strip path intact. Fixes #82139.
·Memory search: stop using chokidar write-stability polling for memory and QMD watchers so large Markdown extraPath trees no longer build up regular file descriptors; changed files now settle through the existing debounced sync queue. Fixes #77327 and #78224. (#81802)
·Message tool: rename the Discord channel-create schema field exposed to models from `type` to `channelType`, avoiding NVIDIA NIM JSON Schema parser failures while still accepting legacy `type` tool calls. (#78920)

v2026.5.14-beta.2pre-release2026-05-15

openclaw 2026.5.14-beta.2

GitHub ↗

Changes

·Channels/SDK: add normalized command turn facts to channel turn construction and expose command-turn helpers for plugin inbound contexts.
·Agents/config: support per-agent bootstrap profile overrides for `contextInjection`, `bootstrapMaxChars`, and `bootstrapTotalMaxChars`, inheriting from `agents.defaults` when omitted. Fixes #69966.
·Dependencies: route root ambient Node proxy agents through `@openclaw/proxyline` and drop root `proxy-agent`, `https-proxy-agent`, and `minimatch` dependencies.
·Canvas: lazy-load HTTP host, hosted media resolver, CLI implementation, and tool runtime modules so Gateway startup only pays Canvas implementation cost on first use. (#82001)
·Control UI/i18n: add a `pnpm ui:i18n:report` baseline report for hardcoded-copy focus areas and locale fallback metadata. (#81320)
·Maintainer tooling: add a repo-local `codex-review` skill for Codex closeout reviews, including local dirty-work and PR-branch review helpers that rerun until no accepted/actionable findings remain and avoid unsupported inline prompts with `--base`.
·Maintainer tooling: fail CI when pull requests add package patch files or pnpm patched dependencies, preserving the upstream-and-bump dependency workflow.
·Codex app-server: stream commentary preambles into editable channel progress drafts without promoting them to final answers.
·Codex migration: remove the bundled `codex-cli` backend and repair legacy `codex-cli/*` model refs to the Codex app-server route on `openai/*`.
·Gateway/startup: add owner-level startup trace attribution for auth, plugin loading, lookup counts, and plugin sidecar services. (#81738)
·Plugins/hooks: expose the resolved effective `contextTokenBudget` plus source/reference metadata on `llm_output` and sanitized `model_call_*` hook events/contexts so plugin cost and context-health alerts can use agent-level context caps. Fixes #64327.
·Channels/status reactions: wire `StatusReactionController` into WhatsApp message turns (queued → thinking → tool → done/error lifecycle, on par with Telegram and Discord), add `deploy`/`build`/`concierge` emoji categories with tool-token routing, and replace the status reaction defaults with self-explanatory emoji (🧠 thinking, 🛠️ tool, 💻 coding, 🌐 web, ⏳ stallSoft, ⚠️ stallHard, ✅ done, ❌ error, 🗜️ compacting) so stall and lifecycle reactions read as status indicators instead of emotional commentary. Fixes #59077. (#80612)
·Control UI: add a browser-local Text size setting in Appearance and Quick Settings, scaling chat and dense UI text while keeping inputs above the mobile Safari focus-zoom threshold. Fixes #8547.
·Docs: add a dedicated ds4 provider page with local DeepSeek V4 Flash config, on-demand startup, context sizing, and live verification steps.
·Release validation: add a package-installed Docker user-journey lane that verifies onboarding, mocked model setup, external plugin install/uninstall, ClickClack outbound/inbound messaging, Gateway restart survival, and doctor.
·Release validation: add package-installed Docker lanes for real TTY onboarding, media and memory persistence, published-package upgrade journeys, and local marketplace plugin install/update/uninstall coverage.
·Maintainers: add a Clawdtributor skill for Discrawl-backed contributor PR triage, live status checks, and compact review formatting.
·Telegram: support Mini App `web_app` buttons in generic message presentation payloads, allowing `openclaw message send --presentation` to render Telegram Web App inline buttons for private chats. (#81356)
·Scripts: add `OPENCLAW_HEAVY_CHECK_LOCK_SCOPE=worktree` so high-capacity local worktrees can use independent heavy-check locks while shared locks remain the default. Fixes #80729. (#80734)
·Agents/subagents: deliver native `sessions_spawn` tasks in the child session's first visible `[Subagent Task]` message instead of hiding the task in the sub-agent system prompt, keeping delegation auditable without duplicating tokens. Fixes #78592.
·Messages/queue: make mid-turn prompts steer active runs by default via `/queue steer`, preserve `/queue followup` and `/queue collect` for users who want messages to queue by default, and make `/steer` continue as a normal prompt when steering is unavailable. (#77023)
·Voice Call/Telnyx: add realtime media-streaming call support for conversational voice calls. (#81024)
·Dependencies: add release dependency evidence reports, npm advisory gating, and PR dependency-change awareness so maintainers can review dependency risk before and during releases.
·Gateway: expose optional `isHeartbeat` metadata on agent event payloads so clients can distinguish scheduled heartbeat runs from ordinary chat runs. (#80610)
·Agents: add `agents.defaults.runRetries` and `agents.list[].runRetries` config for embedded Pi runner retry loop limits. (#80661)
·Codex: add node-backed Codex CLI session listing and binding so an OpenClaw conversation can continue an existing Codex CLI session running on a paired node.

Fixes

·Models/providers: trust the exact configured custom/local provider `baseUrl` origin for guarded model HTTP requests, so loopback, LAN, tailnet, and private DNS endpoints work without broad private-network access while different ports and metadata/link-local pivots remain blocked. Fixes #80732. (#80751)
·Bind shell script operands after combined options [AI]. (#81882)
·fix(canvas): validate snapshot response formats [AI]. (#81881)
·Constrain provider catalog entry paths [AI]. (#81884)
·Require canonical node platform IDs [AI]. (#81880)
·Agents/Azure OpenAI Responses: default unset Azure OpenAI API versions to `preview` so `/openai/v1/responses` calls use Azure's current Responses API route. (#82026)
·Control UI/WebChat: compact the desktop chat header controls into a single aligned row so the session, model, thinking, and action controls no longer waste vertical space.
·Agents: retry empty final turns for generic `anthropic-messages` providers instead of limiting non-visible recovery to Kimi, so custom/proxied Anthropic-compatible routes can recover with a visible answer. Addresses #46080.
·Agents/replies: strip workflow `<function_response>` scaffolding from user-visible sanitizer paths so raw tool output does not leak into chat history, transcript mirrors, or channel replies. Fixes #47444.
·Agents/media: deliver generated image, music, and video results through structured attachments, keep message-tool-only Codex completions on the message tool, and fail completion handoff when expected media is not actually sent.
·Diagnostics/Codex: recover stalled embedded Codex app-server runs after the shorter default stalled-run window so queued turns resume sooner.
·Control UI: rotate browser service-worker caches per build so updated Gateways are less likely to keep serving stale dashboard bundles that trigger protocol mismatch errors.
·Gateway/protocol: lazy-compile protocol validators on first use instead of compiling every AJV schema during cold import, reducing startup CPU and RSS. (#82064)
·Discord: report unresolved configured bot-token SecretRefs during startup instead of treating the account as unconfigured. (#82009)
·CLI/config: preserve numeric-looking object keys such as Discord guild IDs during `config patch` recursive merges. (#81999)
·Gateway/OpenAI-compatible HTTP: forward `response_format` from `/v1/chat/completions` requests through agent stream params to upstream Chat Completions and Responses transports, restoring structured-output support. Fixes #82003. (#82004)
·Control UI/WebChat: let sidebar markdown code-block Copy buttons use the same delegated clipboard handler as chat messages. (#58709)
·Discord/streaming: only mark partial draft previews delivered after final edit or fallback delivery succeeds, so failed finalization cleanup removes stale truncated drafts instead of leaving them as the visible reply. Fixes #82035.
·macOS/Gateway: surface leftover `ai.openclaw.update.*` launchd updater jobs in `openclaw gateway status --deep` and doctor so post-update launchd loops point at the stale job cleanup. Fixes #81859.
·macOS/screen snapshots: reject malformed `screen.snapshot` params before capture, bound base64 results against the projected `node.invoke.result` frame, and preserve stable caller-facing errors for oversized payloads and capture failures. Fixes #68181.
·Config/doctor: rotate capped `.clobbered.*` repair snapshots by artifact timestamp so repeated repairs keep the newest forensic copy instead of preserving only the first capped set. (#82012)
·Telegram: initialize the bot before isolated polling drains spooled updates so default isolated polling no longer retries every update with `Bot not initialized` and stalls replies. Fixes #81973. (#81975)
·Telegram: apply method-aware Bot API request timeouts to direct message/action clients so `openclaw message delete --channel telegram` no longer waits on grammY's 500-second default when the API request wedges. Fixes #81908.
·Cron: treat attempt dispatch and assembled context as execution-start milestones so isolated agent jobs that have reached backend dispatch are governed by their configured job timeout instead of the 60s pre-execution watchdog. Fixes #81368. (#81871)
·Doctor/auth: warn about stale per-agent OAuth auth profile shadows and let `openclaw doctor --fix` remove the local shadow so agents inherit the fresher main-agent credential.
·Status/channels: show configured channels whose plugin setup failed to load as `plugin load failed: dependency tree corrupted; run openclaw doctor --fix` instead of silently dropping them from `openclaw status`.
·Status/update: show pending or failed update restart handoffs in `openclaw status` and make `openclaw update` print explicit gateway restart verified, skipped, or failed guidance.
·QA/update: add an E2E corrupt plugin dependency lane that verifies `status --all` guidance, `doctor --fix` cleanup, and channel status recovery.
·Discord/channels: make `openclaw channels list --all` prefer reachable Gateway runtime account status and mark configured-but-unavailable credentials, avoiding false `not configured` output when Discord is running from service-only env. Fixes #79343.
·WhatsApp: mark text slash commands as command turns so authorized group command replies stay visible under message-tool-only group reply mode. (#81972)
·Providers/OpenCode Go: stop sending unsupported reasoning parameters to Kimi K2.5/K2.6, avoiding OpenCode Go payload-validation failures while preserving DeepSeek V4 reasoning support.
·Installer: handle noninteractive git installs from moving refs without tag-fetch conflicts, while keeping immutable refs on frozen lockfile installs. (#81875)
·Codex app-server: inject native client factories per run and compaction attempt instead of using module-scope test state, avoiding temporal-dead-zone reads during cyclic startup. (#81148)
·Plugin skills: replace generated Windows plugin-skill directories before publishing the current skill link, avoiding repeated `EINVAL` warnings from stale non-symlink entries. Fixes #81432. (#81446)
·Channels/config: treat channel entries with only `enabled: true` as configured state so plugin-backed channels can auto-enable from an explicit on switch. Fixes #81323. (#81331)
·CLI/update: add an update finalization path for externally swapped core runtimes, running update-time doctor repair and plugin convergence from post-doctor config and install-record state before reporting completion.
·CLI/update: refresh config after package-update doctor repairs before post-update plugin sync, avoiding stale-hash conflicts during package upgrade journeys.
·macOS/Gateway: hand managed LaunchAgent package self-updates to the post-exit CLI path and report handoff failures through the update restart sentinel instead of leaving agent-invoked updates pending. Fixes #81894. (#81945)
·Agents/WebChat: stop a successful assistant turn whose stale `errorMessage` matches a billing, auth, or rate-limit pattern from rotating profiles, falling back, or surfacing a hard `FailoverError` unless the current attempt has a real failover failure. (#70900)
·Control UI/usage: remove the duplicated inner Usage page heading so the shared dashboard header is the only page title.
·Control UI/WebChat: keep mobile PWA composer controls above the iOS home indicator when standalone safe-area insets under-report. Fixes #77408.
·Control UI/logs: make the Gateway Logs stream height responsive to the viewport with a minimum height floor, so larger screens can show substantially more log lines without collapsing on shorter viewports. (#53916)
·ACP/Codex: surface redacted Codex wrapper stderr for generic ACP internal failures and preserve safe Codex model/provider routing in isolated `CODEX_HOME`, making `sessions_spawn(runtime="acp", agentId="codex")` failures actionable. Fixes #80079. (#80718)
·Agents/trace: mark execution traces as fallback-used when merged fallback attempts prove a primary model failed before the winning attempt, keeping `/trace raw` and agent JSON telemetry consistent. Addresses fallback telemetry in #81213.
·ACP: treat rejected timeout config options as best-effort hints so ACP turns continue with adapters that do not support `session/set_config_option` timeout keys. Fixes #81250. (#81603)
·Cron/Codex: default exact-command scheduled agent turns to lightweight bootstrap context so automation runs the command before loading workspace identity or memory context.
·Codex cron: disable native Codex project-doc loading for lightweight app-server cron turns so scheduled jobs avoid project-doc injection after OpenClaw suppresses bootstrap context. (#81822)
·Codex plugin/Gateway: strip unpaired UTF-16 surrogates from Codex app-server JSON-RPC payloads and let stale reply-work recovery abort stalled reply runs, preventing malformed media turns from wedging gateway lanes.
·Codex app server: force OAuth refresh requests to perform a real token refresh instead of reusing unchanged inherited auth-profile tokens after refresh failures. (#80738)
·Control UI/WebChat: render `/tts audio` replies as playable audio attachments through the assistant-media ticket path, with structured-audio compatibility for older live payloads. (#81722)
·Bind gateway approval access to requester metadata [AI]. (#81380)
·Telegram: let isolated polling drain independent topics, DMs, and status/control commands concurrently while preserving same-lane order. (#81849)
·Telegram: derive readable plain-text retries from HTML fallback sends so parse failures show `label (url)` links instead of raw anchors. (#81764)
·Ollama/Doctor: copy explicit native Ollama `contextWindow` or `maxTokens` provider/model budgets into `params.num_ctx` during `openclaw doctor --fix`, preserving large-context configs after native Ollama stopped inferring per-request `num_ctx`. Fixes #81878. (#81928)
·Discord: honor `threadName` on `message send` to existing threads by renaming the thread after successful delivery, and warn when the rename cannot be applied. Fixes #81836. (#81933)
·Build: keep externalized Slack, OpenShell sandbox, and Anthropic Vertex runtime dependency declarations out of the root dist artifact build.
·ClawHub: include Amazon Bedrock and Bedrock Mantle provider packages in the published registry metadata so the externalized providers are discoverable from ClawHub as well as npm.
·Codex account/status: hide empty rate-limit buckets and show server-reported usage-limit blocks without calling them available.
·Auto-reply/Claude CLI: bridge CLI-runtime assistant text-delta agent events into the chat reasoning preview through `onReasoningStream`, mirroring the existing assistant-text (#76914) and tool-event (#80046) bridges and adding gating so non-CLI runtimes are unaffected.
·Mantis: keep QA evidence in Actions artifacts only and stop publishing evidence files to Git-backed artifact branches.
·CLI/migrate: handle delayed Codex plugin marketplace responses so warnings, next-steps, and conflict states render with ⚠️ glyphs and post-install migration retries the marketplace fetch instead of silently skipping plugin items. (#81625)
·Channels/Weixin: bump the bundled `@tencent-weixin/openclaw-weixin` external entry to `2.4.3` (from `2.4.1`) so onboarding and `openclaw channels add` install the current Tencent Weixin (personal WeChat) plugin release. (#81730)
·CLI: lazy-load model, plugin, and device runtime helpers and keep channel option help on generated startup metadata or generic fallback text so parent/help output renders without importing those runtime paths.
·CLI: route `plugins list --json` through the parsed command fast path and cover it in response budgets so plugin JSON inventory avoids full CLI registration work.
·Control UI/Overview: render recent session rows through the shared session display resolver so label/displayName priority, key-equivalent labels, and channel fallbacks stay consistent with the chat selector. (#50696)
·Gateway/network: keep OpenClaw-installed undici dispatchers on HTTP/1.1 and treat destroyed HTTP/2 session errors as recoverable network teardown, preventing `ERR_HTTP2_INVALID_SESSION` from crashing active gateway turns. Fixes #81627. (#81838)
·Memory/daily-files: widen the daily-memory file matcher used by Dreaming, rem-backfill, rem-harness, the doctor sweep, and short-term promotion so `memory/YYYY-MM-DD-<slug>.md` files written by the bundled session-memory hook (and any future slugged variants) are discovered alongside the date-only `memory/YYYY-MM-DD.md` shape. Date extraction still uses the leading `YYYY-MM-DD` capture group, so per-day ingestion/promotion semantics are unchanged for existing date-only files; slugged files now flow through the same paths instead of being silently skipped. Fixes #69536.
·macOS/Gateway: fail managed LaunchAgent stop and restart when the configured gateway port remains busy after cleanup instead of reporting success while a listener survives. Fixes #73132.
·Telegram: reuse the sticky IPv4 Bot API transport for periodic getMe health checks, so IPv4-working hosts with broken IPv6 egress stop logging repeated probe timeouts. Fixes #76852. (#76856)
·Telegram: ship the isolated polling worker at the root dist path used by the bundled worker loader, avoiding startup failures looking for `dist/telegram-ingress-worker.runtime.js`.
·Control UI/Gateway: stop stale token-mismatch reconnect loops when no trusted device-token retry is available, and cap rendered chat history by raw tool-output size so dashboard auth/history work cannot keep degrading channel sockets. Fixes #72139.
·Memory/daily-files: prioritize the canonical `memory/YYYY-MM-DD.md` daily note before same-day slugged session captures during capped live ingestion and historical seeding, preserving existing daily-note behavior when slugged files exist.
·Gateway/OpenAI-compatible HTTP: parse shared JSON endpoint paths without trusting malformed Host headers, avoiding 500s before `/v1/chat/completions`, `/v1/responses`, and `/v1/embeddings` request handling.
·Telegram: resolve plugin native commands with the active runtime config so commands like `/codex ...` stay on the native command path.
·Voice-call webhooks: parse webhook and realtime upgrade paths without trusting malformed Host headers, avoiding 500s before provider signature checks or path rejection.
·Media store: reject malformed redirect `Location` headers as media-download failures instead of letting URL parsing escape the async response callback.
·ClickClack: skip malformed realtime websocket frames instead of stopping the channel monitor on a single bad JSON event.
·Browser tool: treat malformed node proxy `payloadJSON` responses as browser proxy failures instead of leaking raw JSON parser errors.
·Gateway HTTP: match models, session kill, and session history route paths without trusting malformed Host headers, avoiding pre-auth 500s on those endpoints.
·Google Meet/Codex: report malformed node proxy `payloadJSON` responses with plugin-owned errors instead of leaking raw JSON parser failures.
·Debug proxy: reject malformed relative-form proxy targets with a controlled 400 response instead of letting URL parsing escape the request handler.
·File transfer: reject malformed inline `file_write` base64 before computing hashes or invoking paired nodes, avoiding Node's lenient base64 decoder.
·QA channel: skip malformed inline inbound attachment base64 instead of staging silently corrupted media for agent turns.
·Microsoft Teams: reject malformed inline HTML image base64 padding instead of decoding corrupted `data:` image attachments.
·Voice-call realtime: ignore malformed provider media-frame base64 before forwarding audio into bridge and transcription paths.
·QQBot: reject malformed stored cron payload base64 before JSON decoding structured reminder data.
·Telnyx voice-call: use the raw `client_state` fallback when webhook state is malformed base64 instead of using silently corrupted decoded text.
·Google Meet: report malformed node-host params JSON with plugin-owned errors instead of leaking raw JSON parser failures.
·CLI/export-trajectory: report malformed encoded request JSON with a stable CLI error instead of leaking raw parser output.
·ComfyUI: report malformed workflow API JSON responses with owned errors instead of leaking raw parser failures.
·DeepInfra video: report malformed successful API JSON responses with provider-owned errors instead of leaking raw parser failures.
·Brave Search: report malformed web and LLM-context API JSON with provider-owned errors instead of leaking raw parser failures.
·xAI tools: report malformed web search, X search, and code execution JSON with provider-owned errors instead of leaking raw parser failures.
·Nextcloud Talk: report malformed room-info and bot-admin JSON with channel-owned errors instead of leaking raw parser failures.
·Microsoft Teams: report malformed Graph and delegated OAuth JSON with channel-owned errors instead of leaking raw parser failures.
·Google Chat: report malformed Chat API and certificate JSON with channel-owned errors instead of leaking raw parser failures.
·Firecrawl: report malformed search and scrape API JSON with provider-owned errors instead of leaking raw parser failures.
·Tavily: report malformed search and extract API JSON with provider-owned errors instead of leaking raw parser failures.
·Perplexity: report malformed Search API and chat completion JSON with provider-owned errors instead of leaking raw parser failures.
·Exa: report malformed search API JSON with a provider-owned error instead of leaking raw parser failures.
·Memory host SDK: report malformed remote JSON with caller-scoped errors for POST and batch file upload responses instead of leaking raw parser failures.
·Media providers: report malformed operation-poll and audio-transcription JSON with provider-owned errors instead of leaking raw parser failures.
·MiniMax, Gemini, Kimi, and Ollama web search: report malformed API JSON with provider-owned errors instead of leaking raw parser failures.
·Twilio voice-call: report malformed successful API JSON responses with provider-owned errors instead of leaking raw parser failures.
·Voice-call provider APIs: report malformed successful guarded JSON responses with provider-prefixed errors instead of leaking raw parser failures.
·Realtime transcription: report malformed provider websocket JSON frames with owned parser errors instead of leaking raw `SyntaxError` objects.
·Microsoft Foundry: report malformed Azure CLI token JSON with owned auth errors instead of leaking raw parser failures.
·Gateway/model pricing: report malformed external pricing catalog JSON with source-owned errors instead of leaking raw parser failures.
·QA Lab: report malformed model-catalog subprocess JSON with an owned error and ignore invalid catalog rows.
·Google Meet: report malformed browser-control status JSON with plugin-owned errors instead of leaking raw parser failures.
·Google provider: report malformed SSE stream JSON with provider-owned errors instead of leaking raw parser failures.
·Node host: report malformed built-in invoke `paramsJSON` with stable invalid-request errors instead of leaking raw parser failures.
·Amazon Bedrock embeddings: report malformed provider response JSON with provider-owned errors instead of leaking raw parser failures.
·QQBot: report malformed access-token JSON with provider-owned errors instead of leaking raw parser failures.
·OpenAI embeddings: report malformed batch output JSONL with provider-owned errors instead of leaking raw parser failures.
·Synology Chat: report malformed JSON webhook payloads with stable channel-owned parser errors.
·Mattermost: report malformed interaction callback JSON with stable channel-owned parser errors.
·Twilio voice-call: report malformed media stream WebSocket JSON with an owned parser error instead of logging raw parser failures.
·Tlon/Urbit: report malformed SSE event JSON with an owned parser error instead of logging raw parser failures.
·Signal: return a stable installer error when GitHub release metadata is malformed JSON.
·ClawHub: report malformed successful marketplace JSON responses with owned errors instead of leaking raw parser failures.
·Provider usage: report malformed successful usage JSON responses with stable provider errors instead of leaking raw parser failures.
·Tlon/Urbit: report malformed scry response JSON with owned errors instead of leaking raw parser failures.
·LM Studio: report malformed model list and model load JSON with owned errors instead of leaking raw parser failures.
·Matrix: ignore malformed percent-encoding in optional location URI parameters instead of letting a bad `geo:` event abort inbound message handling.
·Web search: auto-detect Brave through its legacy `tools.web.search.apiKey` compatibility fallback while keeping doctor migration to `plugins.entries.brave.config.webSearch.apiKey` as the canonical repair, so allowlisted isolated cron runs do not report `web_search` unavailable before migration. Fixes #81538.
·Plugins: memoize repeated in-process plugin metadata snapshots and keep vanished managed-install residue from forcing full derived discovery, reducing gateway/status startup scans under large plugin sets. Fixes #81143 and #79806. (#81570)
·CLI/plugins: route lazy plugin command-registration chatter to stderr only during JSON-output command registration, keeping plugin-backed `--json` stdout parseable without changing parse-only or pass-through `--json` behavior. Fixes #81535. (#81536)
·Plugins: treat git plugin install refs as refs instead of checkout flags, so option-like selectors fail checkout instead of silently installing the default branch. Fixes #79898. (#79901)
·Doctor/memory: stop warning that no memory plugin is active when an enabled alternate memory plugin explicitly owns the memory slot, while preserving the warning for missing or disabled slot entries. Fixes #78540. (#78557)
·Plugins: keep process-local plugin metadata snapshot memo freshness tied to the cached registry snapshot so policy-stale derived plugin metadata edits invalidate the memo instead of returning stale owners or command aliases. (#81064)
·Plugins: discover provider plugins from `setup.providers[].envVars` credentials during provider discovery while keeping the deprecated `providerAuthEnvVars` fallback. (#81542)
·Docs/Codex harness: clarify that per-agent `CODEX_HOME` isolates `~/.codex` while inherited `HOME` intentionally keeps `.agents` discovery and subprocess user-home state available.
·CLI/plugins: keep bare plugin and parent-command help on the lightweight path, avoiding plugin registry discovery before rendering help.
·Auth: reclaim dead-owner stale file locks before retrying locked writes, so crashed OAuth refreshes no longer wedge `auth-profiles.json` until manual cleanup.
·CLI tables: preserve muted/color styling on wrapped continuation lines after multiline cells, keeping `openclaw plugins list` descriptions readable.
·Process execution: collapse case-insensitive duplicate child environment keys on Windows so caller-provided overrides such as `PATH` cannot be shadowed by host `Path`.
·Browser CLI: request the existing `operator.admin` gateway scope explicitly for browser control commands, avoiding unnecessary scope-upgrade approval loops. Fixes #81555. (#81716)
·Web: honor explicitly configured global `web_search` providers during provider ownership resolution while keeping sandboxed `web_fetch` limited to bundled providers.
·Plugins/doctor: repair configured legacy npm declaration stubs by reinstalling their npm packages into the managed plugin root instead of loading workspace `node_modules`, and warn when discovery sees those stubs. Fixes #79632.
·Channels: keep configured third-party channel plugins visible in `openclaw channels list` when their manifest declares `channels` but has not added `channelConfigs` metadata yet. Fixes #81334. (#81340)
·Agents: skip bootstrap file and hook preload work on completed `continuation-skip` turns when no workspace bootstrap is pending, reducing isolated-agent prep latency without changing first-turn bootstrap behavior. Fixes #81548.
·Config: validate JSON dry-runs against plugin-owned channel schemas, so external channel fields are not rejected by stale bundled schemas. Fixes #77887. (#81504)
·iOS: restore first-use Contacts, Calendar, and Reminders permission prompts and add Privacy & Access status/actions in Settings.
·Canvas: return not found for malformed percent-encoded Canvas/A2UI/document asset paths and keep decoded parent traversal blocked before path normalization.
·Telegram: allow trusted local Bot API media files whose filenames start with dots instead of falling back to remote download.
·Agents/Codex app-server: remap injected context files under dot-dot-prefixed workspace directories when a run switches to an effective sandbox workspace.
·Control UI/i18n: use the installed workspace pi runtime for locale refreshes, update the fallback package pin, and skip scheduled refreshes with invalid provider credentials instead of failing main.
·CI/performance: authenticate the clawgrit report repository remote during both checkout and publish so performance report pushes do not fail after benchmarks complete.
·Hooks: load workspace-relative legacy hook modules from dot-dot-prefixed directories without treating the filename prefix as parent traversal.
·Plugins: preserve installed package metadata and persisted registry freshness checks for plugin package paths under dot-dot-prefixed directories.
·Agents: allow dot-dot-prefixed filenames such as `..note.txt` through sandbox FS bridge, remote sandbox reads, and apply_patch summaries without mistaking the name for parent traversal.
·CLI/migrate: hide per-item source/plugin hints on non-conflicting Codex skill and plugin selection prompts, keeping the hint text reserved for rows that actually need attention.
·Codex harness: treat high-confidence app-server OAuth refresh invalidation as a terminal auth-profile failure, stopping repeated raw token-refresh errors without turning entitlement or usage-limit payloads into re-auth prompts.
·CLI/migrate: humanize Codex conflict-status messaging across the migrate UI so selection prompts and plan/result rows say "Codex skill already installed in workspace" instead of surfacing internal `MIGRATION_REASON_*` codes.
·CLI/migrate: render migrate result rows with distinct glyphs for manual-review (🔍) and archive (📖) items instead of the misleading "skipped" and "migrated" checkmarks, so users can see which entries still need attention versus which were filed away.
·CLI/migrate: split Codex migrate output into separate preview and result phases so the Before plan and After result render through clack with independently tunable copy.
·Codex app-server: project bundle and user MCP servers into Codex threads, rotate threads when an MCP server is disabled, scope bundle MCP injection to bundled servers, and resend user MCP config on resume so MCP changes take effect mid-session without restarting the agent. (#81551)
·Codex migration: invoke the managed Codex binary instead of a stale system `codex` for source-config migration plans, so users running the bundled Codex runtime get plan output that matches the binary the gateway will actually use. (#81582)
·Subagents/maintenance: preserve pending subagent registry sessions during session-store cleanup, pruning, and disk-budget enforcement so in-flight subagent runs are not deleted by background maintenance before they complete. (#81498)
·Control UI/chat: reconcile terminal and reconnect run cleanup with cached session activity, stale compaction/fallback indicators, and a compact composer run-status chip so completed or interrupted turns do not leave Stop active. Fixes #76874 and #64220; refs #71630.
·Maintainer tooling: clarify which pnpm test/check commands are safe locally versus inside Codex worktrees, routing linked-worktree gates through node wrappers and Crabbox/Testbox.
·Auto-reply: preserve same-key ordering when debounced inbound work falls back to immediate flushes, so follow-up turns cannot overtake an active buffered flush.
·Telegram/WhatsApp: keep Telegram same-chat replies ordered behind active no-delay turns without blocking WhatsApp follow-up message dispatch.
·Codex migration: avoid duplicate cached plugin bundle warnings when app-server plugin inventory is available.
·Agents: suppress aborted embedded assistant partials, reasoning text, reply directives, and stale prior replies before user-facing delivery while preserving clean timeout/error payloads. Fixes #48241.
·Agents: allow dot-dot-prefixed filenames such as `..file.txt` inside workspace and sandbox path policy while still rejecting real parent traversal.
·Native image input: detect Windows drive image paths in plain prompts so `C:\...\screenshot.png` references are not missed.
·Media: normalize Windows-style filename hints before staging attachments, remote media, audio transcodes, and saved-media display names, so POSIX hosts do not preserve drive or directory text in generated filenames.
·Media references: resolve first-level inbound media files whose IDs start with dots instead of treating names like `..photo.png` as parent traversal.
·iOS/chat: resize PhotosPicker image attachments to capped JPEGs before staging and sending, stripping source metadata and keeping oversized camera photos under the chat upload budget. Fixes #68524.
·Control UI: keep shared form, config, and usage text-entry controls at 16px on touch-primary devices while preserving chat composer input sizing, so iOS Safari no longer auto-zooms focused fields. Fixes #64651; carries forward #64673.
·Agents/trajectory: make the trajectory flush cleanup timeout configurable with `OPENCLAW_TRAJECTORY_FLUSH_TIMEOUT_MS`, preserving the 10s default while slower stores drain. Refs #75839.
·Skills: load ClawHub and local-manager skill-directory symlinks from managed `~/.openclaw/skills` and personal `~/.agents/skills` roots while keeping workspace, extra, bundled, and per-skill `SKILL.md` containment fail-closed. Fixes #44051. Refs #59219.
·Config: return the canonical persisted config from `config.set`, `config.apply`, and `config.patch` responses after write-time shaping. Fixes #77455.
·Codex auth: accept OAuth profiles backed by `oauthRef` during runtime auth selection, so official Codex OAuth logins are used by app-server agent runs. (#81633)
·Telegram: release stopped polling leases after the gateway stop grace so in-process restarts can reuse the same bot token without weakening active duplicate-poller protection. Fixes #81507. (#81890)
·ACP: preserve redacted numeric JSON-RPC `RequestError` details in runtime failure text, so backend diagnostics are visible instead of only `Internal error`. Fixes #81126. (#81188)
·Agents: cache unchanged PI model discovery stores and model lookups, reducing repeated model-resolution startup latency under large model configs. Fixes #78851.
·Onboarding: carry returned Codex plugin migration config through the OpenAI model wizard so accepted plugin migrations are saved with the final config write.
·Security/Windows ACL audit: classify Anonymous Logon, Guests, Interactive, Local, and Network SIDs as world-equivalent principals so broadly writable paths stay critical instead of being downgraded to group-writable. Fixes #74350. (#74383)
·Media-understanding: retry transient remote attachment fetch failures before audio or vision processing, so Discord voice notes are not lost after one network/CDN blip. Fixes #74316.
·Control UI: order timestamped live stream and tool items before untimestamped history fallbacks, keeping chat history in visible time order. Fixes #80759. (#81016)
·ClawHub: cancel stalled archive body reads for skill, package, and ClawPack downloads instead of leaving installs hanging after headers arrive. Fixes #52073. Refs #80006.
·macOS/Chat: render persisted assistant provider failures from `errorMessage` in refreshed chat history while keeping stale non-error provider details hidden. (#65689)
·Control UI/config: discard stale redacted placeholders from form-mode config saves while preserving restorable saved secrets, so unrelated settings changes no longer submit `__OPENCLAW_REDACTED__` as real data. Fixes #60917.
·OpenAI plugin: clarify remote Codex OAuth login copy so tunneled users know sign-in may finish automatically before they paste the redirect URL. (#81301)
·SGLang: preserve replayed reasoning history for OpenAI-compatible chat completions, keeping thinking-capable local models from losing prior reasoning turns. (#81091)
·Plugins/install: derive managed peer dependency pins from npm's lockfile planner instead of recursively scanning `node_modules`, while keeping OpenClaw host peers out of managed root ownership and preserving active root-managed runtimes.
·Control UI/WebChat: keep short assistant replies clear of in-bubble copy/open action buttons by applying the existing reserved action spacing in the grouped chat renderer. Fixes #79509. (#81244)
·Codex harness: make the live test wrapper portable to Windows and defer locked temp cleanup so native Windows and WSL2 live runs complete.
·Link understanding: fetch page content through the SSRF guard before running configured CLI summarizers, preventing curl/wget-style link fetchers from reaching private redirect or DNS-rebound targets.
·fix: harden safe-bin argument validation [AI]. (#80999)
·Codex/status: align `/codex status` rate-limit wording with `/status` by showing remaining quota and compact reset durations instead of used quota and raw ISO timestamps.
·Mattermost: log a structured `mattermost no-visible-reply` diagnostic when a substantive (non-reasoning) final reply payload reaches `deliverMattermostReplyPayload` but the underlying `deliverTextOrMediaReply` returns `"empty"` — previously the run completed with a misleading `delivered reply to <channel>` log even though no Mattermost API send happened, masking silent completions in channel/thread contexts. No behavior change; the diagnostic surfaces the failure so operators can detect it instead of seeing the agent appear to go silent. Fixes #80501.
·Telegram: limit concurrent startup `getMe` probes across multi-account bots so large Telegram configs do not fan out all account probes at once during gateway startup. Refs #80695. (#80986)
·fix(config): reject auto-managed meta.lastTouched\* paths in config set/unset (#80856).
·Test state: seed isolated auth-profile secret keys for generated homes, preventing helper-backed proof runs from falling back to host Keychain secrets. (#81393)
·Plugins/update: clear stale allow/deny entries and selected plugin slots when disabling a plugin after update failure, keeping failed external plugin updates from leaving half-disabled config. (#81512)
·Memory/LanceDB: make auto-capture recognize short CJK memory phrases and configurable literal triggers, so Chinese, Japanese, and Korean users can capture memories without regex or LLM intent detection. Fixes #75680.
·Plugins doctor: report stale plugin config warnings and avoid claiming full plugin health when config warnings remain. (#81515)
·Sessions: display `model: "<agentId>-acp"` / `modelProvider: "acpx"` (ACP-runtime sentinel) for ACP control-plane sessions in `openclaw sessions` output, instead of the agent's configured model which was misleading. Catalog finding 20. (#79543)
·Slack: normalize message read `before` and `after` timestamp bounds before calling Slack history or thread reply APIs. Fixes #80835. (#81338)
·Gateway: throttle assistant/thinking agent event fanout during streaming bursts without dropping buffered deltas. (#80335)
·Models: restore authenticated CLI runtime providers in the `/models` picker while keeping legacy runtime aliases hidden from setup/default model choices. Closes #81212. (#81239)
·Changelog gates: reject bot/app handles as `Thanks` attribution and require explicit human credit for bot/app-authored changelog entries. (#81357)
·Agents/heartbeat: fix seven layered issues that broke multi-agent heartbeat cadence — (1) fan out the scheduler broadcast wake across agents in parallel via `Promise.all` instead of awaiting each `runOnce` sequentially, so one agent doing real work no longer starves every later agent in iteration order; (2) scope `skipWhenBusy` to lanes attributable to the firing agent via session-key parsing of `session:agent:<id>:…` / `nested:agent:<id>:…` lane names, instead of consulting the global `subagent` lane, so a single stuck subagent on one agent no longer silently disables every other agent's heartbeat; (3) always append workspace `HEARTBEAT.md` directives (everything outside an optional `tasks:` block) to the dispatch prompt, so prose-runbook `HEARTBEAT.md` files reach the model directly instead of being silently dropped unless periodic tasks are declared; (4) race the initial stream-establishment promise inside `streamWithIdleTimeout` against the same watchdog timer that previously only guarded inter-token gaps, so SDK requests stuck at TCP/TLS handshake or before the first response byte no longer hang indefinitely (the stalled-session diagnostic's `recovery=none` case); (5) emit an `openclaw doctor` warning when `heartbeat.session` pins a session key that has no entry in the agent's session store, so silently-dropped heartbeat deliveries surface at config-validation time; (6) also route the commitment-only task dispatch path (tasks configured, none due) through `appendHeartbeatFileDirectives` so prose directives outside the `tasks:` block reach the model on this path as well; (7) wrap the synchronous `baseFn(...)` invocation inside `streamWithIdleTimeout` in a try/catch that clears the connect watchdog timer before rethrowing, so a provider stream function that throws during setup no longer leaves a live timer that can fire `onIdleTimeout` later with a stale error and keep the process open past the real failure.
·Matrix: stop running `npm install`/`pnpm install` at runtime from a parent-derived plugin path; missing Matrix runtime dependencies now fail with repair guidance instead of mutating the wrong `node_modules` tree. Fixes #80758. (#80876)
·Agents/memory-flush: surface non-abort memory-flush failures (provider timeout, transport error, generic agent failure) as visible reply payloads so the outer reply loop short-circuits and isolated cron runs propagate the error into `meta.error` instead of completing silently with `status: "ok"` and an empty payload. Previously only the specific "Memory flush writes are restricted to ..." message was surfaced. Fixes #80755.
·Channels/loop-guard: enforce shared per-pair bot loop protection in the core channel-turn kernel, with Discord, Slack, Matrix, and Google Chat supplying bot-pair facts where they can reliably identify accepted bot-authored messages. The generic guard keys on `(scope, conversation, participant pair)`, suppresses every additional bot-to-bot event in either direction once a pair crosses the configured budget, and lifts suppression after `cooldownSeconds`. Defaults are `maxEventsPerWindow: 20`, `windowSeconds: 60`, and `cooldownSeconds: 60` whenever a channel lets bot-authored messages reach dispatch; they can be set globally via `channels.defaults.botLoopProtection` and overridden per channel/account or supported per-conversation config. Fixes #58789.
·Agents/memory-flush: surface non-abort memory-flush failures (provider timeout, transport error, generic agent failure) as visible reply payloads so the outer reply loop short-circuits and isolated cron runs propagate the error into `meta.error` instead of completing silently with `status: "ok"` and an empty payload. Previously only the specific "Memory flush writes are restricted to ..." message was surfaced. Refs #80755.
·Codex harness: use the active Codex runtime context window for OpenAI-selected budgeting, manual `/compact`, and `/status`, so stale OpenAI session metadata no longer overstates context limits. (#81906)

v2026.5.14-beta.1pre-release2026-05-14

openclaw 2026.5.14-beta.1

GitHub ↗

Changes

·Dependencies: route root ambient Node proxy agents through `@openclaw/proxyline` and drop root `proxy-agent`, `https-proxy-agent`, and `minimatch` dependencies.
·Control UI/i18n: add a `pnpm ui:i18n:report` baseline report for hardcoded-copy focus areas and locale fallback metadata. (#81320)
·Maintainer tooling: add a repo-local `codex-review` skill for Codex closeout reviews, including local dirty-work and PR-branch review helpers that rerun until no accepted/actionable findings remain and avoid unsupported inline prompts with `--base`.
·Maintainer tooling: fail CI when pull requests add package patch files or pnpm patched dependencies, preserving the upstream-and-bump dependency workflow.
·Codex app-server: stream commentary preambles into editable channel progress drafts without promoting them to final answers.
·Codex migration: remove the bundled `codex-cli` backend and repair legacy `codex-cli/*` model refs to the Codex app-server route on `openai/*`.
·Gateway/startup: add owner-level startup trace attribution for auth, plugin loading, lookup counts, and plugin sidecar services. (#81738)
·Channels/status reactions: wire `StatusReactionController` into WhatsApp message turns (queued → thinking → tool → done/error lifecycle, on par with Telegram and Discord), add `deploy`/`build`/`concierge` emoji categories with tool-token routing, and replace the status reaction defaults with self-explanatory emoji (🧠 thinking, 🛠️ tool, 💻 coding, 🌐 web, ⏳ stallSoft, ⚠️ stallHard, ✅ done, ❌ error, 🗜️ compacting) so stall and lifecycle reactions read as status indicators instead of emotional commentary. Fixes #59077. (#80612)
·Control UI: add a browser-local Text size setting in Appearance and Quick Settings, scaling chat and dense UI text while keeping inputs above the mobile Safari focus-zoom threshold. Fixes #8547.
·Docs: add a dedicated ds4 provider page with local DeepSeek V4 Flash config, on-demand startup, context sizing, and live verification steps.
·Release validation: add a package-installed Docker user-journey lane that verifies onboarding, mocked model setup, external plugin install/uninstall, ClickClack outbound/inbound messaging, Gateway restart survival, and doctor.
·Release validation: add package-installed Docker lanes for real TTY onboarding, media and memory persistence, published-package upgrade journeys, and local marketplace plugin install/update/uninstall coverage.
·Maintainers: add a Clawdtributor skill for Discrawl-backed contributor PR triage, live status checks, and compact review formatting.
·Telegram: support Mini App `web_app` buttons in generic message presentation payloads, allowing `openclaw message send --presentation` to render Telegram Web App inline buttons for private chats. (#81356)
·Scripts: add `OPENCLAW_HEAVY_CHECK_LOCK_SCOPE=worktree` so high-capacity local worktrees can use independent heavy-check locks while shared locks remain the default. Fixes #80729. (#80734)
·Agents/subagents: deliver native `sessions_spawn` tasks in the child session's first visible `[Subagent Task]` message instead of hiding the task in the sub-agent system prompt, keeping delegation auditable without duplicating tokens. Fixes #78592.
·Messages/queue: make mid-turn prompts steer active runs by default via `/queue steer`, preserve `/queue followup` and `/queue collect` for users who want messages to queue by default, and make `/steer` continue as a normal prompt when steering is unavailable. (#77023)
·Voice Call/Telnyx: add realtime media-streaming call support for conversational voice calls. (#81024)
·Dependencies: add release dependency evidence reports, npm advisory gating, and PR dependency-change awareness so maintainers can review dependency risk before and during releases.
·Gateway: expose optional `isHeartbeat` metadata on agent event payloads so clients can distinguish scheduled heartbeat runs from ordinary chat runs. (#80610)
·Agents: add `agents.defaults.runRetries` and `agents.list[].runRetries` config for embedded Pi runner retry loop limits. (#80661)
·Codex: add node-backed Codex CLI session listing and binding so an OpenClaw conversation can continue an existing Codex CLI session running on a paired node.

Fixes

·Cron/Codex: default exact-command scheduled agent turns to lightweight bootstrap context so automation runs the command before loading workspace identity or memory context.
·Codex plugin/Gateway: strip unpaired UTF-16 surrogates from Codex app-server JSON-RPC payloads and let stale reply-work recovery abort stalled reply runs, preventing malformed media turns from wedging gateway lanes.
·Codex app server: force OAuth refresh requests to perform a real token refresh instead of reusing unchanged inherited auth-profile tokens after refresh failures. (#80738)
·Control UI/WebChat: render `/tts audio` replies as playable audio attachments through the assistant-media ticket path, with structured-audio compatibility for older live payloads. (#81722)
·Bind gateway approval access to requester metadata [AI]. (#81380)
·Telegram: let isolated polling drain independent topics, DMs, and status/control commands concurrently while preserving same-lane order. (#81849)
·Build: keep externalized Slack, OpenShell sandbox, and Anthropic Vertex runtime dependency declarations out of the root dist artifact build.
·ClawHub: include Amazon Bedrock and Bedrock Mantle provider packages in the published registry metadata so the externalized providers are discoverable from ClawHub as well as npm.
·Auto-reply/Claude CLI: bridge CLI-runtime assistant text-delta agent events into the chat reasoning preview through `onReasoningStream`, mirroring the existing assistant-text (#76914) and tool-event (#80046) bridges and adding gating so non-CLI runtimes are unaffected.
·Mantis: keep QA evidence in Actions artifacts only and stop publishing evidence files to Git-backed artifact branches.
·CLI/migrate: handle delayed Codex plugin marketplace responses so warnings, next-steps, and conflict states render with ⚠️ glyphs and post-install migration retries the marketplace fetch instead of silently skipping plugin items. (#81625)
·Channels/Weixin: bump the bundled `@tencent-weixin/openclaw-weixin` external entry to `2.4.3` (from `2.4.1`) so onboarding and `openclaw channels add` install the current Tencent Weixin (personal WeChat) plugin release. (#81730)
·CLI: lazy-load model, plugin, and device runtime helpers and keep channel option help on generated startup metadata or generic fallback text so parent/help output renders without importing those runtime paths.
·CLI: route `plugins list --json` through the parsed command fast path and cover it in response budgets so plugin JSON inventory avoids full CLI registration work.
·Gateway/network: keep OpenClaw-installed undici dispatchers on HTTP/1.1 and treat destroyed HTTP/2 session errors as recoverable network teardown, preventing `ERR_HTTP2_INVALID_SESSION` from crashing active gateway turns. Fixes #81627. (#81838)
·Memory/daily-files: widen the daily-memory file matcher used by Dreaming, rem-backfill, rem-harness, the doctor sweep, and short-term promotion so `memory/YYYY-MM-DD-<slug>.md` files written by the bundled session-memory hook (and any future slugged variants) are discovered alongside the date-only `memory/YYYY-MM-DD.md` shape. Date extraction still uses the leading `YYYY-MM-DD` capture group, so per-day ingestion/promotion semantics are unchanged for existing date-only files; slugged files now flow through the same paths instead of being silently skipped. Fixes #69536.
·macOS/Gateway: fail managed LaunchAgent stop and restart when the configured gateway port remains busy after cleanup instead of reporting success while a listener survives. Fixes #73132.
·Telegram: reuse the sticky IPv4 Bot API transport for periodic getMe health checks, so IPv4-working hosts with broken IPv6 egress stop logging repeated probe timeouts. Fixes #76852. (#76856)
·Telegram: ship the isolated polling worker at the root dist path used by the bundled worker loader, avoiding startup failures looking for `dist/telegram-ingress-worker.runtime.js`.
·Control UI/Gateway: stop stale token-mismatch reconnect loops when no trusted device-token retry is available, and cap rendered chat history by raw tool-output size so dashboard auth/history work cannot keep degrading channel sockets. Fixes #72139.
·Memory/daily-files: prioritize the canonical `memory/YYYY-MM-DD.md` daily note before same-day slugged session captures during capped live ingestion and historical seeding, preserving existing daily-note behavior when slugged files exist.
·Gateway/OpenAI-compatible HTTP: parse shared JSON endpoint paths without trusting malformed Host headers, avoiding 500s before `/v1/chat/completions`, `/v1/responses`, and `/v1/embeddings` request handling.
·Telegram: resolve plugin native commands with the active runtime config so commands like `/codex ...` stay on the native command path.
·Voice-call webhooks: parse webhook and realtime upgrade paths without trusting malformed Host headers, avoiding 500s before provider signature checks or path rejection.
·Media store: reject malformed redirect `Location` headers as media-download failures instead of letting URL parsing escape the async response callback.
·ClickClack: skip malformed realtime websocket frames instead of stopping the channel monitor on a single bad JSON event.
·Browser tool: treat malformed node proxy `payloadJSON` responses as browser proxy failures instead of leaking raw JSON parser errors.
·Gateway HTTP: match models, session kill, and session history route paths without trusting malformed Host headers, avoiding pre-auth 500s on those endpoints.
·Google Meet/Codex: report malformed node proxy `payloadJSON` responses with plugin-owned errors instead of leaking raw JSON parser failures.
·Debug proxy: reject malformed relative-form proxy targets with a controlled 400 response instead of letting URL parsing escape the request handler.
·File transfer: reject malformed inline `file_write` base64 before computing hashes or invoking paired nodes, avoiding Node's lenient base64 decoder.
·QA channel: skip malformed inline inbound attachment base64 instead of staging silently corrupted media for agent turns.
·Microsoft Teams: reject malformed inline HTML image base64 padding instead of decoding corrupted `data:` image attachments.
·Voice-call realtime: ignore malformed provider media-frame base64 before forwarding audio into bridge and transcription paths.
·QQBot: reject malformed stored cron payload base64 before JSON decoding structured reminder data.
·Telnyx voice-call: use the raw `client_state` fallback when webhook state is malformed base64 instead of using silently corrupted decoded text.
·Google Meet: report malformed node-host params JSON with plugin-owned errors instead of leaking raw JSON parser failures.
·CLI/export-trajectory: report malformed encoded request JSON with a stable CLI error instead of leaking raw parser output.
·Twilio voice-call: report malformed successful API JSON responses with provider-owned errors instead of leaking raw parser failures.
·Voice-call provider APIs: report malformed successful guarded JSON responses with provider-prefixed errors instead of leaking raw parser failures.
·Realtime transcription: report malformed provider websocket JSON frames with owned parser errors instead of leaking raw `SyntaxError` objects.
·Microsoft Foundry: report malformed Azure CLI token JSON with owned auth errors instead of leaking raw parser failures.
·Gateway/model pricing: report malformed external pricing catalog JSON with source-owned errors instead of leaking raw parser failures.
·QA Lab: report malformed model-catalog subprocess JSON with an owned error and ignore invalid catalog rows.
·Google Meet: report malformed browser-control status JSON with plugin-owned errors instead of leaking raw parser failures.
·Google provider: report malformed SSE stream JSON with provider-owned errors instead of leaking raw parser failures.
·Node host: report malformed built-in invoke `paramsJSON` with stable invalid-request errors instead of leaking raw parser failures.
·Amazon Bedrock embeddings: report malformed provider response JSON with provider-owned errors instead of leaking raw parser failures.
·QQBot: report malformed access-token JSON with provider-owned errors instead of leaking raw parser failures.
·OpenAI embeddings: report malformed batch output JSONL with provider-owned errors instead of leaking raw parser failures.
·Synology Chat: report malformed JSON webhook payloads with stable channel-owned parser errors.
·Mattermost: report malformed interaction callback JSON with stable channel-owned parser errors.
·Matrix: ignore malformed percent-encoding in optional location URI parameters instead of letting a bad `geo:` event abort inbound message handling.
·Web search: auto-detect Brave through its legacy `tools.web.search.apiKey` compatibility fallback while keeping doctor migration to `plugins.entries.brave.config.webSearch.apiKey` as the canonical repair, so allowlisted isolated cron runs do not report `web_search` unavailable before migration. Fixes #81538.
·Plugins: memoize repeated in-process plugin metadata snapshots and keep vanished managed-install residue from forcing full derived discovery, reducing gateway/status startup scans under large plugin sets. Fixes #81143 and #79806. (#81570)
·CLI/plugins: route lazy plugin command-registration chatter to stderr only during JSON-output command registration, keeping plugin-backed `--json` stdout parseable without changing parse-only or pass-through `--json` behavior. Fixes #81535. (#81536)
·Plugins: treat git plugin install refs as refs instead of checkout flags, so option-like selectors fail checkout instead of silently installing the default branch. Fixes #79898. (#79901)
·Web: honor explicitly configured global `web_search` providers during provider ownership resolution while keeping sandboxed `web_fetch` limited to bundled providers.
·Plugins/doctor: repair configured legacy npm declaration stubs by reinstalling their npm packages into the managed plugin root instead of loading workspace `node_modules`, and warn when discovery sees those stubs. Fixes #79632.
·Channels: keep configured third-party channel plugins visible in `openclaw channels list` when their manifest declares `channels` but has not added `channelConfigs` metadata yet. Fixes #81334. (#81340)
·Agents: skip bootstrap file and hook preload work on completed `continuation-skip` turns when no workspace bootstrap is pending, reducing isolated-agent prep latency without changing first-turn bootstrap behavior. Fixes #81548.
·Config: validate JSON dry-runs against plugin-owned channel schemas, so external channel fields are not rejected by stale bundled schemas. Fixes #77887. (#81504)
·iOS: restore first-use Contacts, Calendar, and Reminders permission prompts and add Privacy & Access status/actions in Settings.
·Canvas: return not found for malformed percent-encoded Canvas/A2UI/document asset paths and keep decoded parent traversal blocked before path normalization.
·Telegram: allow trusted local Bot API media files whose filenames start with dots instead of falling back to remote download.
·Agents/Codex app-server: remap injected context files under dot-dot-prefixed workspace directories when a run switches to an effective sandbox workspace.
·Control UI/i18n: use the installed workspace pi runtime for locale refreshes, update the fallback package pin, and skip scheduled refreshes with invalid provider credentials instead of failing main.
·CI/performance: authenticate the clawgrit report repository remote during both checkout and publish so performance report pushes do not fail after benchmarks complete.
·Hooks: load workspace-relative legacy hook modules from dot-dot-prefixed directories without treating the filename prefix as parent traversal.
·Plugins: preserve installed package metadata and persisted registry freshness checks for plugin package paths under dot-dot-prefixed directories.
·Agents: allow dot-dot-prefixed filenames such as `..note.txt` through sandbox FS bridge, remote sandbox reads, and apply_patch summaries without mistaking the name for parent traversal.
·CLI/migrate: hide per-item source/plugin hints on non-conflicting Codex skill and plugin selection prompts, keeping the hint text reserved for rows that actually need attention.
·Codex harness: treat high-confidence app-server OAuth refresh invalidation as a terminal auth-profile failure, stopping repeated raw token-refresh errors without turning entitlement or usage-limit payloads into re-auth prompts.
·CLI/migrate: humanize Codex conflict-status messaging across the migrate UI so selection prompts and plan/result rows say "Codex skill already installed in workspace" instead of surfacing internal `MIGRATION_REASON_*` codes.
·CLI/migrate: render migrate result rows with distinct glyphs for manual-review (🔍) and archive (📖) items instead of the misleading "skipped" and "migrated" checkmarks, so users can see which entries still need attention versus which were filed away.
·CLI/migrate: split Codex migrate output into separate preview and result phases so the Before plan and After result render through clack with independently tunable copy.
·Codex app-server: project bundle and user MCP servers into Codex threads, rotate threads when an MCP server is disabled, scope bundle MCP injection to bundled servers, and resend user MCP config on resume so MCP changes take effect mid-session without restarting the agent. (#81551)
·Codex migration: invoke the managed Codex binary instead of a stale system `codex` for source-config migration plans, so users running the bundled Codex runtime get plan output that matches the binary the gateway will actually use. (#81582)
·Subagents/maintenance: preserve pending subagent registry sessions during session-store cleanup, pruning, and disk-budget enforcement so in-flight subagent runs are not deleted by background maintenance before they complete. (#81498)
·Control UI/chat: reconcile terminal and reconnect run cleanup with cached session activity, stale compaction/fallback indicators, and a compact composer run-status chip so completed or interrupted turns do not leave Stop active. Fixes #76874 and #64220; refs #71630.
·Maintainer tooling: clarify which pnpm test/check commands are safe locally versus inside Codex worktrees, routing linked-worktree gates through node wrappers and Crabbox/Testbox.
·Auto-reply: preserve same-key ordering when debounced inbound work falls back to immediate flushes, so follow-up turns cannot overtake an active buffered flush.
·Telegram/WhatsApp: keep Telegram same-chat replies ordered behind active no-delay turns without blocking WhatsApp follow-up message dispatch.
·Codex migration: avoid duplicate cached plugin bundle warnings when app-server plugin inventory is available.
·Agents: suppress aborted embedded assistant partials, reasoning text, reply directives, and stale prior replies before user-facing delivery while preserving clean timeout/error payloads. Fixes #48241.
·Agents: allow dot-dot-prefixed filenames such as `..file.txt` inside workspace and sandbox path policy while still rejecting real parent traversal.
·Native image input: detect Windows drive image paths in plain prompts so `C:\...\screenshot.png` references are not missed.
·Media: normalize Windows-style filename hints before staging attachments, remote media, audio transcodes, and saved-media display names, so POSIX hosts do not preserve drive or directory text in generated filenames.
·Media references: resolve first-level inbound media files whose IDs start with dots instead of treating names like `..photo.png` as parent traversal.
·iOS/chat: resize PhotosPicker image attachments to capped JPEGs before staging and sending, stripping source metadata and keeping oversized camera photos under the chat upload budget. Fixes #68524.
·Control UI: keep shared form, config, and usage text-entry controls at 16px on touch-primary devices while preserving chat composer input sizing, so iOS Safari no longer auto-zooms focused fields. Fixes #64651; carries forward #64673.
·Agents/trajectory: make the trajectory flush cleanup timeout configurable with `OPENCLAW_TRAJECTORY_FLUSH_TIMEOUT_MS`, preserving the 10s default while slower stores drain. Refs #75839.
·Codex auth: accept OAuth profiles backed by `oauthRef` during runtime auth selection, so official Codex OAuth logins are used by app-server agent runs. (#81633)
·Telegram: release stopped polling leases after the gateway stop grace so in-process restarts can reuse the same bot token without weakening active duplicate-poller protection. Fixes #81507. (#81890)
·ACP: preserve redacted numeric JSON-RPC `RequestError` details in runtime failure text, so backend diagnostics are visible instead of only `Internal error`. Fixes #81126. (#81188)
·Agents: cache unchanged PI model discovery stores and model lookups, reducing repeated model-resolution startup latency under large model configs. Fixes #78851.
·Onboarding: carry returned Codex plugin migration config through the OpenAI model wizard so accepted plugin migrations are saved with the final config write.
·Security/Windows ACL audit: classify Anonymous Logon, Guests, Interactive, Local, and Network SIDs as world-equivalent principals so broadly writable paths stay critical instead of being downgraded to group-writable. Fixes #74350. (#74383)
·Media-understanding: retry transient remote attachment fetch failures before audio or vision processing, so Discord voice notes are not lost after one network/CDN blip. Fixes #74316.
·Control UI: order timestamped live stream and tool items before untimestamped history fallbacks, keeping chat history in visible time order. Fixes #80759. (#81016)
·ClawHub: cancel stalled archive body reads for skill, package, and ClawPack downloads instead of leaving installs hanging after headers arrive. Fixes #52073. Refs #80006.
·Control UI/config: discard stale redacted placeholders from form-mode config saves while preserving restorable saved secrets, so unrelated settings changes no longer submit `__OPENCLAW_REDACTED__` as real data. Fixes #60917.
·OpenAI plugin: clarify remote Codex OAuth login copy so tunneled users know sign-in may finish automatically before they paste the redirect URL. (#81301)
·SGLang: preserve replayed reasoning history for OpenAI-compatible chat completions, keeping thinking-capable local models from losing prior reasoning turns. (#81091)
·Plugins/install: derive managed peer dependency pins from npm's lockfile planner instead of recursively scanning `node_modules`, while keeping OpenClaw host peers out of managed root ownership and preserving active root-managed runtimes.
·Control UI/WebChat: keep short assistant replies clear of in-bubble copy/open action buttons by applying the existing reserved action spacing in the grouped chat renderer. Fixes #79509. (#81244)
·Codex harness: make the live test wrapper portable to Windows and defer locked temp cleanup so native Windows and WSL2 live runs complete.
·Link understanding: fetch page content through the SSRF guard before running configured CLI summarizers, preventing curl/wget-style link fetchers from reaching private redirect or DNS-rebound targets.
·fix: harden safe-bin argument validation [AI]. (#80999)
·Codex/status: align `/codex status` rate-limit wording with `/status` by showing remaining quota and compact reset durations instead of used quota and raw ISO timestamps.
·Mattermost: log a structured `mattermost no-visible-reply` diagnostic when a substantive (non-reasoning) final reply payload reaches `deliverMattermostReplyPayload` but the underlying `deliverTextOrMediaReply` returns `"empty"` — previously the run completed with a misleading `delivered reply to <channel>` log even though no Mattermost API send happened, masking silent completions in channel/thread contexts. No behavior change; the diagnostic surfaces the failure so operators can detect it instead of seeing the agent appear to go silent. Fixes #80501.
·Telegram: limit concurrent startup `getMe` probes across multi-account bots so large Telegram configs do not fan out all account probes at once during gateway startup. Refs #80695. (#80986)
·fix(config): reject auto-managed meta.lastTouched\* paths in config set/unset (#80856).
·Test state: seed isolated auth-profile secret keys for generated homes, preventing helper-backed proof runs from falling back to host Keychain secrets. (#81393)
·Plugins/update: clear stale allow/deny entries and selected plugin slots when disabling a plugin after update failure, keeping failed external plugin updates from leaving half-disabled config. (#81512)
·Memory/LanceDB: make auto-capture recognize short CJK memory phrases and configurable literal triggers, so Chinese, Japanese, and Korean users can capture memories without regex or LLM intent detection. Fixes #75680.
·Plugins doctor: report stale plugin config warnings and avoid claiming full plugin health when config warnings remain. (#81515)
·Sessions: display `model: "<agentId>-acp"` / `modelProvider: "acpx"` (ACP-runtime sentinel) for ACP control-plane sessions in `openclaw sessions` output, instead of the agent's configured model which was misleading. Catalog finding 20. (#79543)
·Slack: normalize message read `before` and `after` timestamp bounds before calling Slack history or thread reply APIs. Fixes #80835. (#81338)
·Gateway: throttle assistant/thinking agent event fanout during streaming bursts without dropping buffered deltas. (#80335)
·Models: restore authenticated CLI runtime providers in the `/models` picker while keeping legacy runtime aliases hidden from setup/default model choices. Closes #81212. (#81239)
·Changelog gates: reject bot/app handles as `Thanks` attribution and require explicit human credit for bot/app-authored changelog entries. (#81357)
·Agents/heartbeat: fix seven layered issues that broke multi-agent heartbeat cadence — (1) fan out the scheduler broadcast wake across agents in parallel via `Promise.all` instead of awaiting each `runOnce` sequentially, so one agent doing real work no longer starves every later agent in iteration order; (2) scope `skipWhenBusy` to lanes attributable to the firing agent via session-key parsing of `session:agent:<id>:…` / `nested:agent:<id>:…` lane names, instead of consulting the global `subagent` lane, so a single stuck subagent on one agent no longer silently disables every other agent's heartbeat; (3) always append workspace `HEARTBEAT.md` directives (everything outside an optional `tasks:` block) to the dispatch prompt, so prose-runbook `HEARTBEAT.md` files reach the model directly instead of being silently dropped unless periodic tasks are declared; (4) race the initial stream-establishment promise inside `streamWithIdleTimeout` against the same watchdog timer that previously only guarded inter-token gaps, so SDK requests stuck at TCP/TLS handshake or before the first response byte no longer hang indefinitely (the stalled-session diagnostic's `recovery=none` case); (5) emit an `openclaw doctor` warning when `heartbeat.session` pins a session key that has no entry in the agent's session store, so silently-dropped heartbeat deliveries surface at config-validation time; (6) also route the commitment-only task dispatch path (tasks configured, none due) through `appendHeartbeatFileDirectives` so prose directives outside the `tasks:` block reach the model on this path as well; (7) wrap the synchronous `baseFn(...)` invocation inside `streamWithIdleTimeout` in a try/catch that clears the connect watchdog timer before rethrowing, so a provider stream function that throws during setup no longer leaves a live timer that can fire `onIdleTimeout` later with a stale error and keep the process open past the real failure.
·Matrix: stop running `npm install`/`pnpm install` at runtime from a parent-derived plugin path; missing Matrix runtime dependencies now fail with repair guidance instead of mutating the wrong `node_modules` tree. Fixes #80758. (#80876)
·Agents/memory-flush: surface non-abort memory-flush failures (provider timeout, transport error, generic agent failure) as visible reply payloads so the outer reply loop short-circuits and isolated cron runs propagate the error into `meta.error` instead of completing silently with `status: "ok"` and an empty payload. Previously only the specific "Memory flush writes are restricted to ..." message was surfaced. Fixes #80755.
·Channels/loop-guard: enforce shared per-pair bot loop protection in the core channel-turn kernel, with Discord, Slack, Matrix, and Google Chat supplying bot-pair facts where they can reliably identify accepted bot-authored messages. The generic guard keys on `(scope, conversation, participant pair)`, suppresses every additional bot-to-bot event in either direction once a pair crosses the configured budget, and lifts suppression after `cooldownSeconds`. Defaults are `maxEventsPerWindow: 20`, `windowSeconds: 60`, and `cooldownSeconds: 60` whenever a channel lets bot-authored messages reach dispatch; they can be set globally via `channels.defaults.botLoopProtection` and overridden per channel/account or supported per-conversation config. Fixes #58789.
·Agents/memory-flush: surface non-abort memory-flush failures (provider timeout, transport error, generic agent failure) as visible reply payloads so the outer reply loop short-circuits and isolated cron runs propagate the error into `meta.error` instead of completing silently with `status: "ok"` and an empty payload. Previously only the specific "Memory flush writes are restricted to ..." message was surfaced. Refs #80755.

v2026.5.122026-05-14

openclaw 2026.5.12

GitHub ↗

Highlights

·Leaner installs: WhatsApp, Slack, Amazon Bedrock, Anthropic Vertex, and related provider/plugin dependency cones moved out of the core runtime so installs only pull what you use.
·Telegram got much more resilient: isolated polling, durable local spooling, safer group-media handling, and preserved HTML/Markdown formatting in streamed and scheduled replies.
·Codex/OpenAI paths are smoother: auth-profile-backed media tools, MCP server projection, context-engine thread rotation, and better app-server/runtime fallback behavior.
·Plugin installs and updates are harder to wedge, with pnpm 11 support, peer-dependency preservation, safer runtime scans, and source/git install fixes.
·Gateway, browser, Slack, node pairing, sandbox, and transcript paths picked up a broad security/provenance hardening pass.
·UI and reply delivery improved across Control UI, WebChat, TUI, rich-only replies, session history, and streaming auto-scroll.

Changes

·Amazon Bedrock: externalize the Bedrock and Bedrock Mantle provider packages so core installs no longer pull AWS SDK dependencies unless those providers are installed.
·Plugins: externalize Slack, OpenShell sandbox, and Anthropic Vertex so their runtime dependency cones install only when those plugins are installed.
·Control UI/WebChat: add a persisted auto-scroll mode selector so users can keep the current near-bottom behavior, always follow streaming output, or turn automatic streaming scroll off and use the New messages button manually. Fixes #7648 and #81287.
·ACP: add `acp.fallbacks` so ACP turns can try configured backup runtime backends when the primary backend is unavailable before any output is emitted. (#69542)

Fixes

·Doctor/Codex: stop warning that the message tool is unavailable for source-reply paths where OpenClaw grants `message` at runtime, keeping update and doctor output aligned with the OpenAI happy path.
·Channels/Weixin: bump the external Weixin catalog entry to `@tencent-weixin/openclaw-weixin@2.4.3` with the matching package integrity. (#81730)
·Agents/subagents: apply `agents.defaults.subagents.model` before target agent primary models during `sessions_spawn`, so model-scoped runtimes such as `claude-cli` stay attached to default child runs. Fixes #81395. (#81783)
·Telegram: keep Bot API polling alive during main event-loop stalls by moving ingress to an isolated worker with a durable local spool. Fixes #81132. (#81746)
·Telegram: preserve rendered HTML formatting through lazy cron announce delivery so Markdown links stay clickable instead of falling back to literal anchor tags. Fixes #81742. (#81758)
·Telegram: skip unmentioned group media before download when `requireMention` is active, avoiding failed media-download replies for messages that should be ignored. Fixes #81181. (#81785)
·CLI/plugins: keep bare plugin and parent-command help on the lightweight path, avoiding plugin registry discovery before rendering help.
·Gateway/session history: carry monotonic transcript message sequence through live updates and refresh SSE history when stale sequence input would otherwise append bad incremental state. (#81474)
·Security/sandbox: include Windows `USERPROFILE` in the sandbox blocked home roots so credential-bearing binds (such as `.codex`, `.openclaw`, or `.ssh` under the Windows user profile) are denied even when `HOME` points at a different shell home. (#63074)
·Models config/auth: stop inferring provider env-var markers from broad `^[A-Z_][A-Z0-9_]*$` strings, and resolve config-backed provider `apiKey` values only through structured env SecretRefs (`secrets.providers[id]` / `secrets.defaults`), so unrelated env vars cannot accidentally become provider credentials.
·Media fetch: skip allocating and buffering the response body for bodyless media responses (HEAD probes and 204-style empty bodies), avoiding wasted heap on streams that carry no payload.
·CLI/onboarding: forward provider-specific auth flags (e.g. `--openai-api-key`) through the onboarding wizard so they reach provider auth methods via `ctx.opts`, letting `--openai-api-key "$OPENAI_API_KEY"` skip the redundant "use existing env var?" prompt in non-interactive harnesses. (#81669)
·CLI/migrate: drop trailing periods from Codex migrate item messages and `REASON_CODE_MESSAGES` strings so plan/result rows read as labels instead of sentence fragments. (#81705)
·Slack: treat malformed private-file redirect `Location` headers as unfollowable redirects instead of failing Slack media downloads.
·Plugins: discover provider plugins from `setup.providers[].envVars` credentials during provider discovery while keeping the deprecated `providerAuthEnvVars` fallback. (#81542)
·Docs/Codex harness: clarify that per-agent `CODEX_HOME` isolates `~/.codex` while inherited `HOME` intentionally keeps `.agents` discovery and subprocess user-home state available.
·Auth: reclaim dead-owner stale file locks before retrying locked writes, so crashed OAuth refreshes no longer wedge `auth-profiles.json` until manual cleanup.
·CLI tables: preserve muted/color styling on wrapped continuation lines after multiline cells, keeping `openclaw plugins list` descriptions readable.
·Process execution: collapse case-insensitive duplicate child environment keys on Windows so caller-provided overrides such as `PATH` cannot be shadowed by host `Path`.
·Gateway/diagnostics: suppress cold-start liveness warnings during the startup grace window while still sampling liveness metrics. Fixes #79915. (#81699)
·Codex harness: keep `oauthRef`-backed Codex OAuth profiles usable and stop high-confidence app-server OAuth refresh invalidation from retry-spamming raw token-refresh errors without turning entitlement or usage-limit payloads into re-auth prompts.
·Browser CLI: request the existing `operator.admin` gateway scope explicitly for browser control commands, avoiding unnecessary scope-upgrade approval loops. Fixes #81555. (#81716)
·Gateway/diagnostics: suppress cold-start liveness warnings during the startup grace window while still sampling liveness metrics. Fixes #79915. (#81699)
·Plugin SDK: restore the deprecated `openclaw/plugin-sdk/memory-core` package subpath as an alias of `memory-host-core`, so published memory companion plugins that still import it resolve on current hosts.
·Control UI/i18n: use the installed workspace pi runtime for locale refreshes, update the fallback package pin, prefer the Anthropic CI provider when available, and skip invalid provider credentials instead of failing main.
·Codex harness: classify native app-server token-refresh logout and relogin failures as authentication refresh errors, so users get re-authentication guidance instead of a raw runtime failure.
·Codex startup: treat selectable configured OpenAI agent models as Codex runtime requirements during plugin auto-enable, startup planning, and doctor install repair, so Anthropic-primary configs can still switch to OpenAI/Codex cleanly.
·Agents: preserve source-reply delivery metadata when merging tool-returned media into the final reply, keeping message-tool-only replies deliverable and mirrored.
·Replies: treat rich presentation, interactive controls, and channel-native payload data as outbound content across follow-up, heartbeat, cron, ACP, and block-streaming delivery paths, preventing card/button-only replies from being dropped as empty.
·WebChat/TUI: route Codex `tools.message` source replies to the active internal UI turn and mirror them to session history, so message-tool-only harness replies, including rich presentation and button-only replies, no longer disappear while WebChat and TUI remain non-targetable outbound channels. (#81586)
·Replies: deliver rich-only block replies even when block-streaming coalescing is enabled, keeping card and button payloads from being dropped by the text coalescer.
·macOS/companion: require system TLS trust before pinning a first-use direct `wss://` gateway certificate and honor `gateway.remote.tlsFingerprint` as the explicit pin for remote node-mode sessions, so fresh endpoints fail closed when macOS cannot trust the certificate unless configured out of band. Fixes #50642.
·Update: snapshot config before update-time repair and restart writes, preserve plugin install records through doctor cleanup, and keep update-time config size drops from blocking the update while pointing users to the pre-update backup. Fixes #80077. (#80257)
·Sessions/status: classify ACP spawn-child sessions as `kind: "spawn-child"` instead of `"direct"` in `openclaw sessions` and status output; extract the duplicated session-kind classifier into a shared helper (`src/sessions/classify-session-kind.ts`) so both surfaces stay in sync. Fixes catalog #19. (#79544)
·Sessions/Gateway: report `agentRuntime.id: "acpx"` (or stored backend id) with `source: "session-key"` for ACP control-plane session rows in `openclaw sessions --json`, `openclaw status`, and Gateway session RPC responses instead of the incorrect `"auto"` / `"pi"` implicit fallback. Fixes catalog #18. (#79550)
·Telegram: delete tool-progress-only draft bubbles before rotating to the real answer, preventing orphaned progress messages in streamed replies.
·Codex app-server: keep per-agent `CODEX_HOME` isolation without rewriting `HOME` by default, so Codex-run subprocesses can still find normal user-home config, tokens, and CLI state unless the launch explicitly overrides `HOME`.
·iMessage: stop sending visible `<media:image>` placeholder text for media-only native image sends while preserving the internal echo key that prevents self-echo duplicate replies. (#81209)
·Agents/sessions: create configured agent main sessions before first `sessions_send` or gateway send, so agent-to-agent messages no longer fail when the target agent has not started yet.
·gateway: pass Talk session scope to resolver [AI]. (#81379)
·Gateway protocol: require v4 clients and stream explicit chat `deltaText`/`replace` frames so SDK clients can consume assistant updates without local diffing. (#80725)
·GitHub Copilot: exchange OAuth tokens for Copilot API tokens on image understanding requests and route Gemini image payloads through Chat Completions, fixing Copilot Gemini image descriptions. (#80393, #80442)
·Gateway: hide pending Node pairing commands, capabilities, and permissions until approval, and refresh the live approved surface when pairings change. (#80741)
·Plugins/Feishu/WhatsApp/Line: enforce inbound media size caps while reading download streams, avoiding full buffering of oversized attachments. (#81044, #81050)
·Plugins/install: limit install-time code safety scans to plugin-owned runtime entrypoints while keeping dependency manifest denylist checks, so trusted packages with large dependency trees no longer get blocked or warned on third-party runtime internals.
·Config: serialize and retry semantic config mutations centrally, so concurrent commands can rebase safe changes instead of clobbering or hand-rolling command-local retry loops. (#76601)
·Installer: honor `--no-git-update` for existing git checkouts before resolving release refs, preventing pinned source installs from moving during reinstall.
·Plugins/install: refresh OpenClaw-managed peer dependency pins when installed plugin peer ranges change, while preserving user-owned dependency pins.
·Require approval for setup-code device pairing [AI]. (#81292)
·Plugins/install: preserve third-party peer dependencies in the managed npm root when later plugin installs or updates recalculate the shared dependency tree.
·Plugins/memory: prefer the npm-installed memory-lancedb plugin over the bundled fallback during duplicate resolution, keeping Active Memory's `memory_recall` tool visible after managed installs. Fixes #81193.
·Plugins/uninstall: prune managed third-party peer dependencies after their owning npm plugin is removed, without blocking plugin cleanup on peer-prune failures.
·Docker: pin setup-time container paths so stale host `.env` OpenClaw paths cannot leak into Linux containers. Fixes #80381. (#81105)
·Channels/WeCom: refresh the official onboarding install to `@wecom/wecom-openclaw-plugin@2026.5.7` and update existing managed npm installs instead of failing on the package directory. Fixes #79884. (#80390)
·Anthropic: reseed Claude CLI fresh-session retries from bounded OpenClaw transcript history after session rotation, preventing conversation amnesia. Fixes #80905. (#80934)
·Require explicit browser device pairing [AI]. (#81289)
·Require Control UI pairing before proxy-scoped access [AI]. (#81288)
·Installer: honor `--version` for git installs and install from the checked-in lockfile, preventing recent dependency pins from tripping pnpm's minimum-release-age gate during tag installs.
·Agents: deliver same-process subagent completion handoffs through the in-process agent dispatcher instead of opening a Gateway RPC loopback.
·Harden trusted-proxy source validation [AI]. (#81290)
·Agents: add permissive item schemas to array tool parameters before provider submission, preventing OpenAI-compatible schema validation from rejecting plugin tools that omit `items`. Fixes #81175. (#81217)
·Agents: escalate LLM idle watchdog timeouts through profile rotation and configured model fallback instead of leaving agent turns stuck after a silent model stream. Fixes #76877. (#80449)
·Discord voice: treat OpenAI Realtime startup auth failures as fatal, suppress duplicate realtime error logs, and stop autoJoin from retrying the same broken voice channel until credentials are fixed.
·ACPX: stop forwarding unsupported timeout config options to Claude ACP while preserving OpenClaw's own turn timeout. (#80812)
·Session transcripts: redact sensitive message content in the centralized JSONL append path so CLI turns, gateway transcript injection, transcript mirrors, and guarded tool results use the same configured redaction behavior. Fixes #73565. Refs #73563. (#79645)
·Channels/iMessage: ignore Apple link-preview plugin payload attachments when users paste URLs, keeping the URL text while avoiding phantom media context. (#79374)
·Telegram: detect polling stalls from `getUpdates` liveness only, so outbound API calls no longer mask dead inbound polling; log polling-cycle starts after transport rebuilds. Fixes #78473.
·fix: scan plugin runtime entries during install [AI]. (#80998)
·fix(plugins): scan installed dependency runtime code [AI]. (#81066)
·Inherit tool restrictions for delegated sessions [AI]. (#80979)
·Telegram: discard legacy long-poll update offsets that cannot be tied to the current bot token, so token rotation no longer leaves bots silently skipping new messages. (#80671)
·browser: enforce navigation checks for act interactions [AI]. (#81070)
·Validate node exec event provenance [AI]. (#81071)
·Gateway: keep active reply runs visible to stuck-session diagnostics and clear no-active-work recovery state, preventing stale queued lanes after compaction or tool failures. Fixes #80677. (#81302)
·Codex app-server: rotate incompatible context-engine-managed native threads so Lossless-managed sessions do not resume stale hidden Codex history. (#81223)
·Codex cron: execute scheduled command-style automation payloads before workspace bootstrap or memory review, preserving existing isolated cron jobs after Codex harness migration. (#81510)
·Plugin LLM completions: honor Codex agent-runtime policy for canonical OpenAI model refs, so context-engine summarizers can use Codex OAuth instead of requiring direct `OPENAI_API_KEY` auth. (#81511)
·Gateway/OpenAI HTTP: return OpenAI-compatible 400 errors for invalid sampling params and provider validation failures instead of collapsing them to 500s. (#81275)
·Telegram: publish plugin and skill command description localizations to native command menus while filtering unsupported locale codes and preserving Telegram command limits. (#81351)
·Limit hook CLI tool authority [AI]. (#81065)
·Require admin scope for node device token management [AI]. (#81067)
·Restrict chat sender allowlist matching [AI]. (#80898)
·Update: suppress the false newer-config warning during restart health probing after an update handoff, while keeping future-version mutation guards intact. (#78652)
·Sessions: redact persisted tool result detail metadata before writing transcripts so diagnostic secrets do not survive tool output redaction. (#80444)
·Codex runtime: allow the official installed `@openclaw/codex` package to use its private task-runtime and MCP projection SDK helpers, fixing `MODULE_NOT_FOUND` during migrated OpenAI/Codex beta runs.
·Codex migration: make Enter activate the highlighted checkbox row before continuing, so `Skip for now` and bulk-selection rows work even when planned items start preselected.
·Codex harness: keep auth-profile-backed media tools such as `image_generate` available when OpenAI auth lives in the agent's auth-profile store instead of environment variables.
·WhatsApp/install: allow Baileys' pinned libsignal git subdependency under pnpm 11 so source installs and local checks can complete.
·Require auth for sandbox browser CDP relay [AI]. (#81002)
·fix: detect carried exec command forms [AI]. (#81000)
·Reject truncated exec approval commands [AI]. (#81001)
·Enforce inline shell wrapper payload matching [AI]. (#80978)
·fix(node-pairing): replace changed pending requests [AI]. (#80894)
·Rate limit Google Chat webhook requests [AI]. (#80974)
·Docker: mount the auth-profile secret key directory so OAuth-backed auth profiles survive container rebuilds. (#80991)
·Onboarding: accept Codex auth profiles for canonical OpenAI model checks, avoiding false missing-auth warnings. (#80913)
·fix(feishu): normalize webhook rate-limit client keys [AI]. (#80975)
·fix(auth): prevent bootstrap pairing scope changes [AI]. (#80976)
·Validate Control UI loopback retry endpoints [AI]. (#80900)
·Harden exported markdown link rendering [AI]. (#80902)
·fix(gateway): honor minimal discovery mode for wide-area DNS-SD [AI]. (#80903)
·slack: enforce reaction notification policy [AI]. (#80907)
·Enforce gateway command scopes by caller context [AI]. (#80891)
·Telegram/groups: in single-account setups, treat an explicit empty `accounts.<id>.groups: {}` map the same as undefined so the root `channels.telegram.groups` allowlist still applies, instead of silently dropping every group update under the default `groupPolicy: "allowlist"`. Multi-account semantics are unchanged so per-account explicit-empty groups still scope-disable a single account without affecting siblings; the explicit way to block all groups for any account remains `groupPolicy: "disabled"`. Fixes #79427. (#81030)
·Codex (app-server): project user-configured `mcp.servers` into new Codex thread configs, matching the codex-cli runtime's existing `-c mcp_servers=...` behavior so app-server-runtime agents see the same user MCP servers the CLI runtime already exposes. Plugin-curated apps remain attached via the separate `apps` config patch. Fixes #80814.
·Enforce Slack plugin approval button authorization [AI]. (#80899)
·Recognize PowerShell -ec inline commands [AI]. (#80893)
·fix(qqbot): authorize approval button callbacks [AI]. (#80892)
·Telegram: render supported HTML tags in streamed and durable replies instead of showing literal markup. (#80977)
·Scrub streamable MCP redirect headers [AI]. (#80906)
·fix(memory-wiki): require admin scope for ingest [AI]. (#80897)
·memory-wiki: require write scope for Obsidian search [AI]. (#80904)
·WhatsApp/install: allow Baileys' pinned libsignal git subdependency under pnpm 11 so source installs and local checks can complete.
·WhatsApp: externalize the channel as a ClawHub/npm plugin outside the core npm runtime bundle, and bump Baileys to `7.0.0-rc11` so libsignal resolves from the registry instead of a GitHub tarball.
·WhatsApp: keep optional audio decoding dependencies local to the external plugin so the core npm install no longer pulls WhatsApp-only media helpers.
·Build: skip copied metadata for bundled plugins that are excluded from build entries, preventing update/status rebuilds from advertising missing QQ Bot runtime files. (#80925)
·Control UI/sessions: nest subagent sessions under their parent session in the session picker dropdown using a visual `└─ ` prefix, making the parent-child relationship clear. Fixes #77628. (#78623)
·Auto-reply: surface a visible error when the configured model backend fails and fallback produces no visible reply, while preserving intentional silent turns and side-effect-only deliveries. (#80917)
·Agents/exec: skip redundant heartbeat wake-ups for subagent session exec completions, preventing spurious LLM invocations on parent sessions. Fixes #66748. (#66749)
·Provider streams: keep OpenAI-compatible SSE and JSON fallback streams draining across split chunks and fail Azure Responses streams with a bounded first-event diagnostic instead of stalling. Refs #80926. (#80927)
·Agents: rewrite generic provider internal errors with support request IDs into user-friendly transient error copy. (#49401)
·WhatsApp: finish handling pending debounced inbound messages before closing the socket. (#81246)
·CLI/commitments: write `--json` output to stdout instead of diagnostic logs so automation can parse commitment list and dismiss results. (#81215)
·Update: allow pnpm GitHub-source OpenClaw updates to approve the OpenClaw package build, so source installs complete their prepare/prepack lifecycle. (#81294)
·Telegram: preserve supported HTML tags in visible replies and durable mirrors so formatted messages render correctly instead of degrading to escaped text. (#80977)
·Plugins/runtime: attribute deprecated runtime config load/write warnings to the plugin id and source that triggered them so logs and plugin doctor runs are actionable. Refs #81394. (#81425)
·Agents/cron: honor a cron payload's explicit `timeoutSeconds` for the LLM idle watchdog even when it numerically equals `agents.defaults.timeoutSeconds`, preserving explicit per-run timeout intent and preventing stalled streaming replies from being cut to the implicit 120s cap. (#79426)
·Codex app-server: keep the short post-tool completion watchdog armed across dynamic tool completion bookkeeping so embedded Codex runs fail fast and release their session lane when Codex goes quiet after a tool result. (#81697)

Changes

·Gateway/OpenAI HTTP: honor `max_completion_tokens` and `max_tokens` on inbound `/v1/chat/completions` requests so client-provided token caps reach the upstream provider via `streamParams.maxTokens`, with `max_completion_tokens` taking precedence when both are sent.
·Models/OpenAI CLI auth: make `openclaw models auth login --provider openai` start the ChatGPT/Codex account login by default, while `--method api-key` remains the explicit OpenAI API-key setup path.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids inside explicit SDK OAuth auth-result config patches, so provider helpers emit `google/gemini-3.1-pro-preview` for Gemini 3.1 testing.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids inside SDK OAuth auth-result default config patches, so helper-built provider auth flows emit `google/gemini-3.1-pro-preview` for Gemini 3.1 testing.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids returned by direct `openclaw models auth login --set-default` provider auth flows before writing config, so Gemini testing targets `google/gemini-3.1-pro-preview`.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids in per-agent config defaults and auth patches, so agent-specific emitted config keeps targeting `google/gemini-3.1-pro-preview`.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids in provider catalog rows when API-key onboarding only reapplies the agent default, so emitted config keeps testing `google/gemini-3.1-pro-preview`.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids in `config set` mutation output for agent overrides and provider catalog rows, so current config emits `google/gemini-3.1-pro-preview`.
·Google/Gemini: canonicalize provider-qualified retired Gemini 3 Pro Preview refs during Google forward-compatible model resolution, so emitted config uses `google/gemini-3.1-pro-preview` for Gemini 3.1 testing.
·Google/Gemini: normalize proxy-prefixed retired Gemini 3 Pro Preview catalog rows, so emitted configs use `google/gemini-3.1-pro-preview` for Gemini 3.1 testing.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids inside per-agent model overrides before writing config, so agent-specific config emits `google/gemini-3.1-pro-preview` for Gemini 3.1 testing.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids in subagent, heartbeat, compaction, and subagent-tool model config during writes, so current config keeps emitting `google/gemini-3.1-pro-preview`.
·Docs/subagents: document `agents.defaults.subagents.announceTimeoutMs` in the sub-agent and configuration references. (#75509)
·Cron: add direct `cron.get`, `openclaw cron get <id>`, and agent-tool `get` support for inspecting one stored cron job by id. (#75117)
·Agents/tools: add per-sender tool policies with canonical channel-scoped sender keys, so operators can restrict dangerous tools by requester identity across global, agent, group, core, bundled, and plugin tool surfaces. (#66933)
·ACP: expose Gateway session lineage metadata through ACP session listings and session info snapshots so clients can render subagent graphs without private Gateway side channels. (#73458)
·Channels/iMessage: add `openclaw channels status --channel <name>` filtering and document the BlueBubbles-to-imsg cutover path so operators can probe iMessage without starting both channel monitors. (#80706)
·CI: add a non-blocking `plugin-inspector-advisory` artifact to Plugin Prerelease so release runs capture bundled plugin compatibility triage without changing the blocking gate.
·Runtime/Fly: detect Fly Machines as container environments from their runtime env vars, so gateway bind and Bonjour defaults match remote container launches. (#80209)
·Providers/fal: route GPT Image 2 and Nano Banana 2 reference-image edit requests to `/edit` with `image_urls` array, enforce NB2 edit geometry using `aspect_ratio` and `resolution` params, lift Fal edit mode input-image caps to 10 for GPT Image 2 and 14 for Nano Banana 2, and allow aspect-ratio hints in edit mode. (#77295)
·Control UI: show a plain HTML recovery panel when the app module never registers, giving blank dashboard pages a retry path and browser-extension troubleshooting link. Fixes #44107.
·Docs: rename the broad tools nav to Capabilities, keep automation and agent coordination as sections, and keep the tools overview focused on tools, skills, and plugins. https://docs.openclaw.ai/tools
·Build: enable additional low-churn oxlint rules for promise, TypeScript, and runtime footgun checks.
·Build: enable stricter Vitest lint rules for focused, disabled, conditional, hook, matcher, and expectation hazards.
·Build: pin explicit oxfmt defaults in the shared formatter config to keep formatting behavior stable across upgrades.
·TypeScript: enable stricter compiler checks for implicit returns, side-effect imports, overrides, and unused production code.
·Logging: add targeted model transport, payload, SSE, and code-mode diagnostics with redacted URL handling.
·Agents: allow `session.agentToAgent.maxPingPongTurns` up to 20 while keeping the default at 5 for longer agent-to-agent reply chains. Fixes #52382. (#52400)
·Agents: add per-agent `tools.message.crossContext` overrides so sandboxed/public agents can restrict message sends to the current conversation without changing the global bot policy.
·Agents: add per-agent `tools.message.actions.allow` overrides so sandboxed/public agents can expose and enforce send-only message tools.
·Agents: omit the sandbox workspace marker from compact command progress previews while keeping internal sandbox diagnostics unchanged.
·Agents: widen progress draft command preview lines by 50% so Discord inline tool updates preserve more useful command context.
·Codex app-server: retire timed-out app-server clients after bounded turn interrupts so Discord agents do not reuse a CPU-spinning Codex process after an attempt timeout.
·Codex app-server: default migrated native plugin destructive-action policy to enabled while preserving explicit global and per-plugin false overrides.
·Build: upgrade workspace package management to pnpm 11 and keep Docker, install, update, and release workflows on the pnpm 11 config surface. (#79414)
·Build: align Telegram QA workflows and git source installs with the pnpm 11 workspace build allowlist surface. (#80588)
·Models: add provider-level `localService` startup for on-demand local model servers before OpenAI-compatible requests, including one-shot model probes.
·Agents: trim default system prompt guidance and send-only message tool schemas to reduce prompt tokens while preserving GPT-5 personality guidance.
·Context: add `/context map` to send a treemap image of the current session context contributors. (#79867)
·Slack: add `unfurlLinks` and `unfurlMedia` config for bot `chat.postMessage` replies, including per-account overrides, so Slack link and media previews can be suppressed without workspace-wide settings. Fixes #48435. (#80145)
·Slack: add explicit `replyBroadcast` support for text and Block Kit thread replies so agents can opt into Slack's parent-channel `reply_broadcast` behavior. (#64365)
·Slack: preserve mention target/source metadata in inbound prompt context so agents can distinguish direct bot mentions from implicit thread wakes that mention someone else. Fixes #79025. (#75356)
·Slack: canonicalize outbound delivery-mirror routes for native DM channel IDs to the peer user session so `message.send` calls to `D...` targets do not split the same Slack DM thread into a channel session. Fixes #80091. (#80111)
·Plugin SDK: deprecate public subpaths that existed for at least one month and have no bundled extension production imports, keep legacy barrel/test/zod subpath package exports for backwards compatibility, and track both sets in the SDK surface report.
·Plugin SDK: deprecate public subpaths currently used by only one or two bundled plugin owners, keeping them importable while steering new plugin code to focused shared SDK seams or plugin-owned APIs.
·Plugin SDK: remove the owner-specific `provider-auth-login` public subpath after moving Chutes, GitHub Copilot, and OpenAI Codex auth flows back to provider-owned modules.
·Plugin SDK: remove provider-specific model, stream, and xAI compatibility helpers from public exports after moving bundled callers to provider-owned modules.
·Plugin SDK: expose runtime-supplied active model metadata to native plugin tool factories for diagnostics and plugin-owned policy decisions. Fixes #77857.
·QA/Mantis: add Telegram live PR evidence automation with Convex-leased credentials, Crabbox transcript capture, motion GIF previews, and inline PR comments.
·QA/Mantis: add a Telegram desktop scenario builder that leases Crabbox, installs native Telegram Desktop, configures an OpenClaw Telegram gateway with leased bot credentials, and records VNC screenshot/video artifacts.
·Discord/voice: add realtime voice diagnostics for speaker turns, playback resets, barge-in detection, and audio cutoff analysis.
·Talk: add `talk.realtime.instructions` so operators can append realtime voice style instructions while preserving OpenClaw's built-in agent-consult guidance. (#79081)
·Discord/voice: default test and source installs to the pure-JS `opusscript` decoder by ignoring optional native `@discordjs/opus` builds, avoiding slow native addon compiles outside dedicated voice-performance lanes.
·Discord/voice: add an opt-in native `@discordjs/opus` install script and decoder preference for live voice-performance lanes without charging unrelated Docker/tests for native addon builds.
·Discord/voice: add `voice.allowedChannels` to restrict voice joins and bot voice-state moves to configured channels while preserving open voice behavior when unset.
·Gateway/skills: add an opt-in private skill archive upload install path gated by `skills.install.allowUploadedArchives`, so trusted Gateway clients can stage and install zip-backed skills only when operators explicitly enable the code-install surface. (#74430)
·Codex app-server: enable Codex native code-mode-only for harness threads so deferred OpenClaw dynamic tools run through Codex's own searchable code execution surface instead of a PI-style wrapper.
·Dependencies: refresh workspace pins and patch targets, including ACPX `@agentclientprotocol/claude-agent-acp` `0.33.1`, Codex ACP `0.14.0`, Baileys `7.0.0-rc10`, Google GenAI `2.0.1`, OpenAI `6.37.0`, AWS SDK `3.1045.0`, Kysely `0.29.0`, Tlon skill `0.3.6`, Aimock `1.19.5`, and tsdown `0.22.0`.
·Dependencies: refresh workspace pins for Anthropic SDK, Smithy shared ini loading, Playwright, YAML, Aimock, TypeScript native preview, Vitest, Oxlint/Oxfmt, Vite, and pnpm 11.1.0.
·Dependencies: hard-pin non-peer direct dependency specs across bundled packages and add a changed-check guard so runtime installs resolve the exact versions tested by maintainers.
·Dependencies: move embedded Pi packages to the `@earendil-works` namespace, refresh Twitch Twurple packages, and move `@openclaw/fs-safe` from the GitHub release pin to the published npm package.
·Build: route Testbox changed-check delegation through Crabbox and remove the OpenClaw-specific Blacksmith Testbox helper scripts.
·Agents/compaction: preserve scoped background exec/process session references across embedded compaction and after-turn runtime contexts without exposing sessions from unrelated scopes. Fixes #79284. (#79307)
·Agents/process: tell agents to inspect background sessions with `process log` before sending interactive input and to use `waitingForInput`/`stdinWritable` hints from `log`/`poll`.
·CLI/onboarding: improve setup, onboarding, configure, and channel command wayfinding so terminal flows explain the next useful command instead of relying on terse setup labels.
·Agents/Codex: remove the configurable Codex dynamic-tools profile so Codex app-server always owns workspace, edit, patch, exec, process, and plan tools while OpenClaw integration tools remain available.
·macOS app: update the Peekaboo bridge dependency to Peekaboo 3.0.0.
·Dependencies: refresh workspace pins and move the WhatsApp plugin from `@whiskeysockets/baileys` to `baileys` while keeping the `7.0.0-rc10` runtime.
·Plugin SDK: add bundled-plugin session actions, `sendSessionAttachment`, and Cron-backed `scheduleSessionTurn`/tag cleanup under the grouped session namespace. Replaces #75578/#75581/#75588 and part of #73384/#74483.
·Plugin SDK/media-understanding: add `extractStructuredWithModel(...)` plus the optional provider-side `extractStructured(...)` seam so trusted plugins can run bounded image-first structured extraction with optional supplemental text context through provider-owned runtimes such as Codex.
·Exec approvals: add `tools.exec.commandHighlighting` so parser-derived command highlighting in approval prompts can be enabled globally or per agent. (#79348)
·Codex app-server: mirror native Codex subagent spawn lifecycle events into Task Registry so app-server child agents appear in task/status surfaces without relying on transcript text. (#79512)

Fixes

·CLI/media: render terminal QR codes with full-block characters by default so the bundled `qrcode` terminal renderer does not emit a pathologically dense ANSI final row in compact half-block mode that breaks scanning in some terminals. Fixes #77820.
·Agents/compaction: read post-compaction AGENTS.md refresh context from the queued run workspace instead of the runner process cwd, so CLI-backed follow-up turns re-inject the correct workspace startup rules after compaction. Fixes #70541. (#75532)
·Agents/read tool: treat positive offsets beyond EOF as empty ranges instead of surfacing the upstream read error, so stale pagination cursors no longer crash tool calls while unrelated read failures still fail loud. Fixes #62466. (#75536)
·Google/Gemini: normalize retired Gemini 3 Pro Preview refs left in Google API-key onboarding model allowlists and fallbacks, so setup-emitted config keeps testing `google/gemini-3.1-pro-preview` instead of `google/gemini-3-pro-preview`.
·Telegram/context: bound selected topic context to the active session so messages from before `/new` or `/reset` are not replayed into later turns. (#80848)
·Google/Gemini: normalize retired nested Gemini 3 Pro Preview ids when resolving exact configured proxy-provider refs, so `kilocode/google/gemini-3-pro-preview` resolves to `kilocode/google/gemini-3.1-pro-preview` for Gemini 3.1 testing.
·CLI: strip generic OSC terminal escape payloads from sanitized output fields, preventing clipboard/title escape bodies from leaking into commitment tables and other terminal-safe text.
·Codex app-server: match connector-backed plugin approval elicitations by stable connector id so enabled destructive actions no longer fall through to display-name-only rejection.
·Build: replace selected build utility `tsx` preloads with Node native type stripping so Node 26 build paths no longer emit `DEP0205` module loader deprecation warnings. (#78584)
·Media generation: honor configured music and video generation timeouts when tool calls omit `timeoutMs`, matching image generation behavior. (#80687)
·CLI/update/status: label beta-channel plugin fallback and model-pricing refresh failures as warnings, keeping mixed beta/latest plugin cohorts visible without making core update or Gateway reachability look failed. Fixes #80689.
·Doctor/plugins: relink managed npm plugin `openclaw` peer dependencies during `doctor --fix`, while refusing to follow package-local `node_modules` symlinks outside the plugin package. (#77412)
·iMessage: route inbound tapbacks as reaction system events instead of normal messages, defaulting to bot-authored-message notifications while allowing `reactionNotifications: "off" | "own" | "all"` overrides. Fixes #60274; refs #39031 and #39322.
·Control UI/performance: scope Nodes polling to the active Nodes tab, debounce stale session-list reconciliation, and bound chat-side session refreshes so long-running dashboards avoid background reload churn.
·Plugins/channels: explain bundled channel entry files that reach the legacy plugin loader as setup-runtime loader mismatches instead of generic missing-register failures.
·Plugins/session-end: fire a typed `session_end` plugin hook with reason `shutdown` (or `restart` when a restart is expected) for every session that was still active when the gateway process stops. Previously SIGTERM/SIGINT/restart paths closed the gateway without enumerating active sessions, leaving downstream `session_end` plugins (e.g. claude-mem) with ghost rows accumulating across restarts. The new shutdown finalizer drains an in-memory tracker that is populated by `session_start` and forgotten by replace / reset / delete / compaction emitters, so previously-finalized sessions are never double-fired. The drain is bounded to a 2 s total budget so a slow plugin cannot block process exit. Adds `"shutdown"` and `"restart"` to `PluginHookSessionEndReason`. Fixes #57790.
·Codex app-server: clamp Codex code-mode sandboxing to workspace-write when an OpenClaw sandbox is active, preventing Docker gateway socket access from becoming a danger-full-access Codex turn.
·TUI: exit immediately on Ctrl+C/SIGINT after gateway disconnect and bound shutdown drain so terminal teardown cannot strand sessions. Fixes #75379. (#75381)
·Matrix: default outbound markdown tables to bullet lists instead of fenced code blocks. Fixes #78990. (#80890)
·Bonjour/Gateway: treat active ciao probing and fresh name-conflict renames as in-progress so the mDNS watchdog waits for probe settlement before retrying, preventing rapid re-advertise loops on Windows, WSL, and other multicast-hostile hosts. (#74778) Refs #74242.
·Providers/MiniMax: send a minimal Anthropic-compatible user fallback when message conversion filters a turn to an empty payload, so MiniMax M2.7 no longer returns `chat content is empty` after tool-heavy sessions. Fixes #74589.
·Tools/media: preserve implicit allow-all semantics from `tools.alsoAllow`-only policies when preconstructing built-in media generation and PDF tools, so configured media tools become live without forcing `tools.allow: ["*", ...]`. Fixes #77841.
·Codex/Telegram: separate code-mode tool progress from final replies, render bridged tool calls with native tool labels, and repair persisted missing tool results for safer follow-up turns. (#80663)
·Memory/search: load the platform-specific `sqlite-vec-<platform>-<arch>` variant directly when the meta `sqlite-vec` package is missing from a global install, so vector recall keeps working on `npm install -g openclaw@latest` upgrades where optionalDependencies left only the platform variant on disk. Fixes #77838.
·Cron: keep long manual cron runs active in the task registry until completion, preventing transient `lost` markers before durable recovery reconciles. Fixes #78233. (#78243)
·Doctor/GitHub CLI: surface a `GH_CONFIG_DIR` hint when the GitHub skill is usable but `gh` auth lives under a different operator HOME than the agent process, without warning for disabled or filtered skills. Fixes #78063. (#78095)
·Gateway: dedupe concurrent `send`, `poll`, and `message.action` requests while delivery is still in flight, preventing duplicate outbound work for the same idempotency key. (#68341)
·Cron: keep main-session `systemEvent` heartbeat wakes on their bound session route for both direct and queued wake paths by dropping inherited explicit heartbeat destinations when forcing `target: "last"`. Fixes #73900.
·Telegram: honor forced document delivery for video media so `--force-document` sends MP4s as documents instead of typed videos. Fixes #80389. (#80405)
·Gateway: clear speculative node wake state when APNs registration is missing, preventing unregistered or mistyped node IDs from retaining wake throttle entries. Fixes #68847. (#68848)
·Auto-reply: keep late follow-up queue drain finalizers from deleting a replacement queue registered after `/stop`, preventing immediate follow-up messages from being orphaned. Fixes #68838. (#68839)
·Feishu: make manual App ID/App Secret setup the default channel-binding path while keeping QR scan-to-create as an optional best-effort flow, and document the manual fallback for domestic Feishu mobile clients that do not react to the QR code. Fixes #80591.
·Memory: cap dreaming promotion writes to `MEMORY.md` by compacting oldest auto-promoted sections while preserving user-authored notes, keeping active memory below the bootstrap budget. Fixes #73691. (#74088)
·Telegram: show resolved thinking defaults in native `/status` and `/think` menus while preserving explicit session overrides. (#80341)
·Channels: cache selected channel registry lookups against the active fallback snapshot so pinned-empty registries refresh native command and alias routing after active registry swaps. (#80333)
·Codex app-server: reuse native Codex CLI OAuth for isolated app-server harness login, refresh, and app inventory cache keys so ChatGPT-authenticated Codex runs no longer fall back to unauthenticated OpenAI API calls. (#79877)
·Gateway: scope `sessions.resolve` sessionId and label store loads to the requested agent so large unrelated agent stores are not parsed for scoped lookups. Fixes #51264. (#79474)
·Gateway: share serialized streaming event envelopes across eligible WebSocket and node subscribers while preserving per-client sequence numbers. (#80299)
·Gateway: consolidate duplicate `openclaw doctor` service config panels while preserving the declined-repair `--force` hint. Fixes #80287. (#78688)
·Browser: report Chrome MCP existing-session page readiness in browser status without letting status probes exceed the client timeout. Fixes #80268. (#80280)
·WhatsApp: route opening-phase Baileys 428 connectionClosed through the WhatsApp reconnect policy and keep post-open 428 closes retryable, so transient setup socket closes retry with WhatsApp diagnostics instead of escaping as a bare `channel exited` error. Fixes #75736; mitigates #77443.
·Agents: disable Pi's default filesystem resource discovery for embedded runs while keeping OpenClaw inline extension factories active, avoiding Windows event-loop stalls during first WhatsApp-triggered agent startup. Fixes #77443.
·Providers/self-hosted: read model-scoped llama.cpp runtime context from `/props.default_generation_settings.n_ctx` while keeping top-level `n_ctx` as a fallback, so session budgeting reflects the loaded context window. Fixes #73664. (#74057)
·Memory: reject symlinked directory components in configured extra memory paths before reading Markdown files. (#80331)
·Sessions/transcripts: replace whole-file `readFile` scans with shared streaming helpers (`streamSessionTranscriptLines` and `streamSessionTranscriptLinesReverse`) for idempotency lookup, latest/tail assistant text reads, delivery-mirror dedupe, and compaction fork loading, so long-running sessions no longer materialize the full transcript in memory. Forward scans use `readline` over a bounded `createReadStream`; reverse scans read bounded chunks from the file end and decode complete JSONL lines newest-first without a fixed tail cap. Synthetic 200 MiB transcript: peak RSS delta drops from +252 MiB to +27 MiB while preserving malformed-line tolerance and idempotency-key return semantics. Fixes #54296.
·Browser/CDP: filter browser-internal targets from raw CDP and persistent Playwright tab selection so navigation opens real page tabs. Fixes #55734.
·WhatsApp: apply hot-reloaded `dmPolicy` and `allowFrom` settings to the active Web listener before processing new inbound DMs. Fixes #80538.
·Plugins: let `openclaw doctor --fix` repair managed plugin installs whose package entrypoints fail package-directory boundary validation after local state moves. Fixes #80592.
·Voice-call: resume voice-originated exec approval follow-ups as internal non-delivery turns instead of rejecting them as `unknown channel: voice`. Fixes #80540.
·Control UI: preserve the composer draft when Stop is tapped during an active chat run, preventing accidental prompt loss on mobile. Fixes #80586.
·Infra/retry: keep jittered retry delays at or above server-supplied Retry-After lower bounds when the hint can be honored. Fixes #68541. (#68543)
·Docs: clarify that `/model provider/model` is an exact session route, while duplicate bare model ids only use configured fallback order on non-session override paths. Refs #80562.
·Redact persisted secret-shaped payloads [AI]. (#79006)
·Agents: label `.openclaw/sandboxes` exec workdirs as sandbox runs in compact tool summaries instead of showing the full path.
·OpenAI Codex: surface browser OAuth and device-code login failures instead of treating failed logins as empty successful auth results. Refs #80363.
·CLI agents: carry runtime-only current-turn sender/reply context into CLI model prompts while keeping prompt-build hook input and transcript text clean.
·Control UI: keep workspace file presence checks from treating `fs-safe` stat helper failures as missing files, restoring Agents file status for existing Windows workspace files. Fixes #79953.
·Microsoft Foundry: report an explicit error when the Azure subscription prompt returns an id that is not present in the enabled subscription list, instead of continuing from an unsafe subscription assertion. (#62742)
·fix(matrix): gate name-based allowlist resolution [AI]. (#79007)
·Slack: include the bot's own root/parent message in new thread sessions so in-thread replies reach the agent with the parent text the user is responding to, instead of only `reply_to_id` metadata. Fixes #79338.
·Docker: keep image builds on the source pnpm workspace policy so pnpm 11 can prune production dependencies without a Docker-only workspace rewrite.
·Agents/compaction: restore info-level gateway logs for embedded compaction start, completion, and incomplete outcomes. (#71961)
·Telegram: build reply-aware inbound turns through the shared channel context path so agents see the current reply target inline with the current message.
·Telegram: recover legacy message cache files that mixed JSON-array and line-delimited entries so restarted gateways preserve reply-window context. (#80567)
·Telegram: update the reply-context cache when messages are edited, so streamed bot replies appear in later agent context with their final text instead of the first draft.
·Skills/Windows: normalize compacted skill prompt locations to forward slashes after home-prefix compaction so Windows skill paths remain readable by model file tools. (#52200)
·Control UI/Windows: update `@openclaw/fs-safe` so agent workspace file presence checks fall back correctly on Windows, preventing existing AGENTS.md, SOUL.md, TOOLS.md, IDENTITY.md, USER.md, HEARTBEAT.md, and MEMORY.md files from showing as missing. Fixes #79953.
·Memory: skip managed dreaming cron reconciliation warnings for ordinary cron and heartbeat hook contexts that cannot manage Gateway cron. (#77027)
·Cron: treat Codex app-server turn acceptance, CLI process spawn, and tool starts as execution milestones, preventing isolated runs from tripping the early startup watchdog after work has begun.
·Codex app-server: treat current-turn `<turn_aborted>` raw markers as terminal so interrupted native-tool turns release Discord agent sessions instead of waiting for the outer timeout.
·Yuanbao: bump `openclaw-plugin-yuanbao` to 2.13.1 to support `sourceReplyDeliveryMode: "automatic"` for group chat. (#79814)
·Memory: keep `memory_search` result `corpus` labels aligned with the hit source, so session transcript hits surface as `sessions` and memory-file hits stay `memory`. Fixes #72885. (#71898, #72886)
·Codex app-server: default native plugin app tool approvals to automatic so non-destructive read tools run when destructive actions are disabled.
·Plugins: allow untracked local source plugins in the global extensions directory to load TypeScript package entries while keeping managed installs strict about compiled runtime output. Fixes #80503.
·Google/Gemini: normalize retired nested Gemini 3 Pro Preview ids while converting manifest catalog rows into emitted provider config, so `google/gemini-3.1-pro-preview` is used for testing instead of `google/gemini-3-pro-preview`.
·Google/Gemini: normalize retired nested Gemini 3 Pro Preview ids inside saved model allowlists and fallback chains, so proxy routes like `openrouter/google/gemini-3-pro-preview` are persisted as Gemini 3.1 Pro Preview.
·Google/Gemini: normalize retired nested Gemini 3 Pro Preview ids in configured proxy/provider-auth model catalogs, so regenerated config keeps testing `google/gemini-3.1-pro-preview` instead of `google/gemini-3-pro-preview`.
·Google/Gemini: normalize retired nested Gemini 3 Pro Preview ids while onboarding provider catalog presets, so setup-emitted proxy configs test `google/gemini-3.1-pro-preview` instead of `google/gemini-3-pro-preview`.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids in provider catalog rows during generic config writes, so unrelated config changes keep testing `google/gemini-3.1-pro-preview`.
·Models: keep configured fallback chains ahead of configured primary models for override selections with duplicate model ids, preventing fallback jumps to the wrong provider. Fixes #80562.
·Native apps: advertise the Gateway protocol compatibility range so chat and node sessions can connect to v3 gateways after additive v4 client updates.
·Gateway/agents: keep stale `sessions_send` ACP manager and `web_fetch` runtime chunks importable after package updates, preventing live gateways from breaking before restart. Fixes #78804.
·Gateway/install: preserve service environment value-source metadata in `openclaw gateway install`, so systemd reinstall paths keep env-file-backed secrets out of inline unit metadata. Refs #77406, #77427.
·Auto-reply/reset: include inbound sender context in bare `/new` and `/reset` model prompts while keeping startup instructions out of transcript prompts, so agents see sender identity on the first reset turn. Fixes #77360.
·Gateway: avoid synchronous restart-sentinel state probes during post-attach startup, preventing slow Windows or redirected state directories from blocking channel turns. Fixes #79264.
·Agents/auth: update successful model auth profile status with one locked store write, reducing post-model reply latency from duplicate `auth-profiles.json` saves.
·Agents/image: honor explicit `image` tool model overrides even when `agents.defaults.imageModel` is unset, restoring one-off vision calls for configured multimodal providers. Fixes #79341.
·Doctor/update: leave live systemd gateway units unchanged during noninteractive update-mode service repair, so update-time doctor does not silently overwrite operator-owned unit directives. Refs #80462.
·Update: accept optional leading `v` prefixes when verifying exact npm package install targets, so `openclaw update --tag v2026...` does not roll back after installing the matching bare package version. Refs #74069; #80480.
·Doctor: treat missing plugin ids in `plugins.deny` as stale config warnings instead of fatal validation errors, and remove them during stale plugin cleanup so update repair does not restore last-known-good config for deny-only stale plugin refs. Refs #77802.
·Codex app-server: preserve prompt-local current-turn context through context-engine prompt projection, so replied-to Telegram messages stay visible to the Codex model input.
·Telegram: pass agent-scoped media roots through gateway message actions so workspace-local media from the active agent is not rejected as cross-agent access.
·CLI/gateway: keep `gateway status --deep` plugin-aware so configured plugin manifest warnings, including missing channel config metadata, stay visible during install and update smoke checks.
·Doctor/status: clarify gateway token source conflict warnings and suppress them inside the managed Gateway service credential context.
·Feishu: accept Schema 2 card callbacks whose operator identity is nested under `operator.user_id`, so card buttons dispatch instead of being dropped as malformed. Fixes #71670. (#71787)
·Feishu: fall back to a top-level group send when normal group quoted replies target a withdrawn or missing message, preventing replies from disappearing silently while preserving native topic safety. Fixes #79349.
·Doctor: stop flagging the live compatibility agent directory as orphaned when the configured default agent is not `main`. Fixes #74313. (#74438)
·Auth/Claude CLI: persist fresher managed external CLI OAuth credentials back to `auth-profiles.json`, preventing stale `anthropic:claude-cli` profiles from repeatedly bootstrapping and flooding debug logs. Fixes #80129.
·Context: render `/context map` only from actual run context and persist Codex app-server run reports without counting deferred tool-search schemas as prompt-loaded tool schemas.
·Codex app-server: report Codex-native tool execution to diagnostics so long-running native `bash`, web, file, and MCP tools no longer look like stale embedded runs to the watchdog. (#80217)
·Codex app-server: refresh Codex account rate limits after subscription usage-limit failures so Discord and other channel replies can show the next reset time instead of saying Codex returned none.
·Agents/auth: let Codex-backed OpenAI agent turns use `auth.order.openai` entries for Codex-compatible OAuth and API-key profiles while keeping existing `openai-codex` profile ordering valid.
·Codex app-server: emit async `after_tool_call` observations for native tool completions not covered by the native hook relay so observability plugins can record Codex-native tools. (#80372)
·Tasks: route group and channel task completions through the requester session so the parent agent can send the visible summary instead of stopping at a generic task-status line. Fixes #77251. (#77365)
·Telegram: preserve blank lines between manually indented bullet blocks and following numbered sections in rendered replies. Fixes #76998.
·Agents/sandbox: allow read-only sandbox sessions to read the `/agent` workspace mount while keeping write/edit/apply_patch workspace-only guarded, restoring `read /agent/...` for `workspaceAccess: "ro"`. Fixes #39497.
·Slack: pass configured agent identity through draft preview sends so partial streaming replies keep custom username/avatar on the initial Slack message. Fixes #38235. (#38237)
·Slack: support `allowBots: "mentions"` for bot-authored messages that mention the receiving bot, matching the documented Discord-style mode without accepting every bot message. Fixes #43587. (#43588)
·Slack: refresh private file URLs with `files.info` when inbound DM file events omit or stale attachment URLs, preventing file attachments from being dropped before media hydration. Fixes #50129. (#50200)
·Slack: add scoped message-tool formatting hints so agents use Markdown for plain sends and direct mrkdwn for Block Kit fields. Fixes #34609. (#50979)
·Slack: describe `download-file` file ids separately from message timestamps and return a targeted recovery error when agents pass `messageId` instead of `fileId`. (#74155)
·Slack: retain processed room messages for `requireMention=false` channels so always-on Slack rooms keep recent conversation context between turns. (#38658)
·Slack: compile interactive reply directives for direct outbound sends without bypassing the `interactiveReplies` capability gate, preserving Block Kit for Slack CLI and cron deliveries. (#78220)
·Slack: keep DM last-route updates scoped to the active non-main DM session, including threaded DM turns, so isolated Slack DM sessions do not overwrite the shared main route. (#73085)
·Slack/ACP: route Slack channel and DM messages through configured ACP bindings when no runtime binding exists, keeping bound thread replies pinned to the persistent ACP session and dropping unavailable configured targets instead of falling back to `main`. (#73101)
·Slack: mark unresolved thread replies as ambiguous and skip them instead of treating them as root channel messages, keeping thread continuation on the SDK-backed participation store. (#75630)
·Slack: let same-channel message tool sends opt out of inherited thread context with `topLevel: true` or `threadId: null`, allowing agents to post a new parent-channel message from inside a Slack thread. Fixes #79807.
·Slack: prefer full rich-text block content over truncated socket-mode message previews so long inbound Slack messages reach agents intact. Fixes #79027.
·Slack: include structured Slack API error details in setup, probe, streaming, and reply logs while preserving token redaction. (#53966)
·Gateway/agents: keep structured reasons when active-run queueing fails and deprecate the legacy boolean queue helper, so steering and subagent wake diagnostics distinguish completed, non-streaming, and compacting runs. Fixes #80156.
·System events: dedupe keyed events across the queue while preserving unkeyed, delivery-route, and trust-boundary event identity. (#73040)
·Agents/UI: compact exec and tool progress rows by hiding redundant shell tool names, replacing known workspace paths with short context markers, and preserving Discord trace scrubbing for compact command lines.
·ACPX: run and await the embedded ACP backend startup probe by default so the gateway `ready` signal no longer fires before the acpx runtime has either become usable or reported a probe failure; set `OPENCLAW_ACPX_RUNTIME_STARTUP_PROBE=0` to restore lazy startup. Fixes #79596.
·Gateway/status: surface model-pricing bootstrap and refresh failures as degraded health/status warnings while keeping Gateway liveness healthy. Fixes #79599.
·OpenAI-compatible models: strip prior assistant reasoning fields from replayed Chat Completions history by default, preventing oMLX/vLLM Qwen follow-up turns from rejecting or stalling on stale `reasoning` payloads. Fixes #46637.
·CLI/onboarding: give non-Azure custom providers a safe generated context window and heal legacy 4k wizard entries without overwriting explicit valid small model limits, preventing first-turn compaction loops. Fixes #79428. (#79911)
·OpenAI-compatible models: add `compat.strictMessageKeys` to strip Chat Completions replay messages to `role` and `content` for strict providers that reject OpenAI-style tool and metadata keys. Fixes #50374.
·Bedrock Mantle: add `plugins.entries.amazon-bedrock-mantle.config.discovery.enabled=false` to suppress automatic Mantle discovery and IAM bearer-token generation while keeping the plugin enabled. Fixes #67288.
·Ollama: stop native `/api/chat` requests from copying catalog `contextWindow` or `maxTokens` into `options.num_ctx` unless `params.num_ctx` is explicitly configured, avoiding pathological prompt-ingestion latency on local large-context models. Fixes #62267.
·Ollama: keep the model idle watchdog enabled for `*:cloud` models routed through a local Ollama host, so cloud-backed tool-loop stalls fail over visibly instead of inheriting local-model no-idle behavior. Fixes #79350.
·Voice/Ollama: honor routed voice agent `tools.allow` for classic embedded voice responses, including empty allowlists, so no-tool Ollama agents do not receive tool schemas. Fixes #79506.
·Agents/doctor: warn when channel-routed agents cannot call the `message` tool, so operators can fix tool policy mismatches before explicit channel actions such as attachments or thread replies fail. Refs #80128.
·Gateway: reread config from disk after the first in-process restart loop startup, preventing SIGUSR1 restarts from reusing a stale startup snapshot and dropping config written after boot. Fixes #79947.
·Codex app-server: deliver native image-generation outputs from Codex `savedPath` events as reply media, so blank-text image generation turns still attach the generated file.
·Network/SSRF: keep pinned automatic DNS lookups on IPv4 when dual-stack hosts also publish AAAA records, and treat `EADDRNOTAVAIL` as a transient gateway network failure instead of a fatal crash. Fixes #80078.
·Control UI: show compact one-line live/idle/terminal run status badges in the Sessions table and rename the active-minute filter to its updated-within meaning. Fixes #78307.
·Control UI: scope chat session-list refreshes by agent and skip disk-only agent store discovery for configured-only lists, preventing post-first-message session switching stalls on large Windows stores. Fixes #79675.
·Control UI: allow Appearance tweakcn theme imports through the served CSP so browser-local custom theme links no longer fail with a `connect-src` violation. Fixes #78504.
·Control UI/config: remove plugin allowlist entries that the form auto-added when a plugin enable toggle is reverted before saving, so reverting the visible toggle clears dirty state without persisting unintended allowlist changes. (#78329)
·Gateway/mobile: reuse bootstrap-issued device-token scopes on handoff reconnects and surface device-token scope mismatches separately from token mismatches while preserving full shared-token dashboard/native sessions. Fixes #79292.
·Media/host-read: allow buffer-verified gzip, tar, and 7z archives in the shared host-local media validator alongside ZIP and document attachments.
·Plugins/install: retry managed npm plugin installs without npm alias overrides after npm's `Invalid comparator: npm:` failure, so older npm versions can install official plugins instead of aborting. (#80539)
·Plugins/doctor: invalidate persisted plugin registry snapshots when plugin diagnostics point at deleted source paths, so `openclaw doctor` stops repeating stale warnings after a local extension is replaced by a managed npm plugin. Fixes #80087. (#80134)
·Doctor/OpenAI Codex: preserve Codex auth intent when auto-repairing legacy `openai-codex/*` model refs to canonical `openai/*` by adding provider/model-scoped Codex runtime policy, preventing repaired configs from falling through to direct OpenAI API-key auth. Fixes #78533 and #78570.
·CLI/agents: surface durable message delivery status from `sendDurableMessageBatch` in `deliverAgentCommandResult` and `openclaw agent --json --deliver`, preserving suppressed hook outcomes as terminal no-retry results while exposing partial and failed sends for automation. Supersedes #53961 and #57755.
·Agents: apply the LLM idle watchdog while provider stream setup is still pending, preventing silent pre-stream model hangs from waiting for the full agent timeout.
·Cron: let isolated self-cleanup runs inspect their own job run history while keeping other cron jobs and mutation actions blocked. Fixes #80019.
·Cron: report isolated agent-turn setup and pre-model stalls with phase-specific timeout errors instead of waiting for the full job budget when no model call starts. Fixes #74803.
·CLI/plugins: treat arbitrary unknown subcommands outside plugin CLI metadata as normal unknown commands instead of suggesting `plugins.allow`, while preserving allowlist guidance for real plugin command roots. Fixes #80109. (#80123)
·CLI/config: persist explicit `config set` and `config patch` values that equal runtime defaults instead of reporting success while dropping them. Fixes #79856. (#80106)
·OpenAI/realtime voice: accept Codex-compatible legacy audio and transcript event aliases so provider protocol drift does not drop assistant audio or captions.
·Discord/voice: keep default agent-proxy realtime sessions from auto-speaking filler before the forced OpenClaw consult answer, finish Discord playback on realtime response completion, and queue later exact-speech answers until playback idles to avoid mid-sentence replacement.
·Gateway: return deterministic `400 invalid_request_error` responses for malformed encoded session-kill HTTP paths instead of letting route-shaped requests fall through to later Gateway handlers. (#72439)
·Control UI: serve root PWA and favicon assets from `/__openclaw__/` SPA routes so tab icons, install metadata, and the service worker do not 404 after internal navigation. Fixes #80072.
·Exec/safe bins: compare trusted safe-bin dirs with path-specific case folding on case-insensitive filesystems so Windows and default macOS paths match without weakening case-sensitive mounts. (#42131)
·OpenAI/realtime voice: honor disabled input-audio interruption locally so server VAD speech-start events do not clear Discord playback after operators set `interruptResponseOnInputAudio: false`.
·Telegram: keep no-response DM turns quiet instead of rewriting them into visible silent-reply chatter. Fixes #78188. (#78228)
·Telegram: handle managed select button callbacks before the raw callback fallback while preserving delimiter-containing option values such as `env|prod`. (#79816)
·OpenAI-compatible models: handle JSON chat-completion bodies returned to streaming requests, preserving reasoning fields and visible text instead of completing an empty agent turn. Fixes #77870.
·Discord/models: defer model picker component interactions before loading route, model, and preference data, preventing "This interaction failed" timeouts under gateway load. Fixes #77283.
·xAI: expose `/think low|medium|high` for reasoning-capable Grok models and keep `reasoning.effort` on native Responses payloads while preserving off-only behavior for non-reasoning routes. Fixes #79210.
·CLI/media: let explicit image description model refs use bundled static provider catalogs and generic model-backed image hooks, so `openclaw infer image describe --model zai/glm-4.6v` works like direct model runs and Anthropic auth probes avoid stale Claude 3 Haiku catalog entries.
·Models/Anthropic: add `anthropic/claude-haiku-4-5` to Anthropic API-key agent allowlist defaults when an Anthropic default model is configured, so cron model overrides can select the current Haiku alias. Fixes #78000.
·Agents/compaction: initialize built-in context engines before CLI transcript compaction resolves the default engine, preventing clean-process `legacy` engine registration failures during CLI session persistence. Fixes #79446.
·Agents/Anthropic-compatible: strip replayed thinking blocks for custom Anthropic-compatible models that explicitly declare `supportsReasoningEffort: false`, preventing Kimi-compatible providers from resending unsupported `thinking` content. Fixes #47452.
·Kimi: keep Anthropic-compatible thinking streams valid by supplying required thinking budgets and enough output room for hidden reasoning plus final text. (#80481)
·Browser: wait longer for existing-session Chrome MCP status and non-deep doctor probes so slow first attaches do not falsely report offline while keeping raw CDP status probes short. (#77473)
·Gateway/logging: install console capture before foreground Gateway fast-path parsing and suppress known libsignal session dumps even in verbose mode, preventing raw terminal logs from printing WhatsApp session key material. (#76306)
·Exec approvals: keep `exec.approval.list` on the lightweight policy-summary path so listing pending approvals no longer loads the rich tree-sitter command explainer. (#76943)
·Agents: surface concise default-visible warnings when `exec`/`bash` tool calls fail after the assistant claims success, while keeping raw stderr hidden unless verbose details are enabled. Fixes #60497. (#80003)
·Channels/iMessage: keep redacted failed probe details in non-sensitive health snapshots so Full Disk Access failures no longer appear as configured/OK in status output. Fixes #79795.
·Agents: stop blank model-emitted tool calls before dispatch while preserving id-based tool-name recovery, preventing Kimi/NVIDIA blank-name retry loops without creating a callable `_blank` sentinel. Fixes #34129. (#56391)
·Agents/Telegram: deliver the canonical final assistant answer instead of replaying accumulated pre-tool text blocks, preventing duplicate Telegram replies and raw-looking tool-output fragments from leaking into chat delivery. Fixes #79621 and #79986.
·Auto-reply/TUI: keep fallback timeout recovery deliverable after a primary model lifecycle error by emitting fallback progress and deferring terminal TUI errors until recovery has a chance to finish. Fixes #80000. (#80009)
·Heartbeat: clear stale auto fallback model overrides when the configured default model changes, so heartbeat runs follow updated `agents.defaults.model.primary` without requiring a manual reset. Fixes #74284.
·CLI/agent: let `openclaw agent --model` use the backend/admin Gateway scope without cached device-token scopes silently downscoping the request. (#78837)
·CLI/help: keep help and version invocations configless while improving shared port, channel, plugin, task, session, message, pairing, and auth recovery text.
·CLI/config: explain strict JSON parse failures with a valid example and the plain-string escape hatch.
·CLI/secrets: turn offline Gateway reload failures into actionable recovery text.
·CLI/channels: explain missing or ambiguous channel selections with next commands.
·CLI/channels: defer guided channel status collection until a channel is selected, keeping `openclaw channels add` first screen quieter.
·CLI/channels: exit guided channel setup cleanly on cancellation instead of printing the internal wizard error.
·Plugins/CLI: route disabled Matrix and LanceDB memory command roots to plugin-enable guidance instead of generic unknown-command errors.
·Browser/Docker: detect Playwright-managed Chromium from `PLAYWRIGHT_BROWSERS_PATH` and the default Playwright cache on Linux, so Docker installs that persist `/home/node/.cache/ms-playwright` no longer need `browser.executablePath`.
·Ollama: keep DeepSeek V4 cloud models thinking-capable even when Ollama Cloud `/api/show` omits the `thinking` capability, so `/think high` no longer rejects `ollama/deepseek-v4-*:cloud`.
·ACPX/Claude ACP: keep foreground prompts waiting for their own result when autonomous task-notification results arrive during the same session, and retarget the patch for Claude Agent ACP `0.33.1`.
·WhatsApp: keep Baileys media uploads from passing non-Dispatcher agents to undici in `7.0.0-rc10`, and patch the bundled Baileys declaration so the latest tsdown build stays warning-clean.
·Build: keep tsdown `0.22.0` warning-clean by externalizing known third-party declaration edges and replacing relative channel config module augmentations with explicit built-in channel fields.
·ACP sessions: map canonical runtime options to backend-advertised ACP config keys like Claude's `effort` while keeping persisted OpenClaw state canonical. (#79926)
·Models/Discord: support `provider/*` entries in `agents.defaults.models` so `/model`, `/models`, and model pickers can show dynamically discovered models for selected providers without exact model allowlists. Fixes #79485.
·Gateway/watch: rebuild or restage missing bundled-plugin dist and runtime-postbuild outputs before launching the Gateway from a source checkout, preventing incomplete watch-mode runtime trees. (#70805)
·CLI/update: allow restart health probes from the previous gateway protocol during self-update, and make plugin dry-runs report exact npm target versions instead of `unknown` while preserving unchanged status.
·OpenAI/Codex: forward persisted `openai-codex` OAuth profile metadata into Codex plugin harness attempts after canonical `openai/*` migration, so OAuth-only installs keep using native Codex auth instead of falling through to direct OpenAI API-key auth. Fixes #79978.
·OpenAI/Codex: point gateway missing-key recovery and wizard docs at the canonical `openai/gpt-5.5` plus Codex OAuth route, and fix trajectory export errors so they suggest the valid `openclaw sessions` command.
·Google/Gemini: normalize retired `google/gemini-3-pro-preview` primary, fallback, and model-map refs during config load and unrelated config writes so saved config keeps targeting Gemini 3.1 Pro Preview.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids inside emitted Google provider model config, so regenerated models.json rows test `google/gemini-3.1-pro-preview`.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids for explicit OpenAI-compatible Google and Gemini CLI provider configs, so emitted config targets `google/gemini-3.1-pro-preview`.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids preserved from existing merged models.json providers so config emission keeps targeting `google/gemini-3.1-pro-preview`.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids inside provider auth config patches so setup-emitted provider catalogs test `google/gemini-3.1-pro-preview`.
·GitHub Copilot: mint short-lived Copilot API tokens with the same `vscode-chat` integration identity used by runtime requests, and refresh legacy cached tokens missing that identity so image-capable Copilot models no longer inherit the `copilot-language-server` scope. Fixes #79946, #80074.
·Plugins/doctor: drop stale managed npm install records when `openclaw doctor --fix` removes npm packages that shadow bundled plugins, so the rebuilt registry no longer resurrects the removed package metadata.
·Doctor: warn when a per-agent model config omits the `fallbacks` key and `agents.defaults.model.fallbacks` is non-empty. Covers both string-form (`"model": "..."`) and partial-object form (`"model": { "primary": "..." }`) — both silently clobber the defaults chain at runtime. Use `"fallbacks": []` to explicitly opt out of fallbacks, or add `"fallbacks": [...]` to inherit or override. Fixes #79369.
·Discord/voice: reuse or suppress late realtime consult tool calls without stealing newer speaker context or speaking forced fallback answers twice.
·Discord/voice: skip likely incomplete realtime forced-consult transcript fragments and non-actionable closings so stale partial speech does not queue delayed answers over the next turn.
·Discord/voice: keep realtime forced consults from clearing active exact-speech playback, so back-to-back voice answers queue instead of cutting each other off.
·Discord/voice: synthesize realtime playback timestamps from emitted Discord PCM so OpenAI realtime barge-in truncation no longer sees `audioEndMs=0` and skips legitimate interruptions.
·Plugin SDK: keep activated linked plugin runtime facades loadable when bundled plugin fallback is disabled.
·Feishu: auto-thread `message(action="send")` replies inside the topic when the active session is group_topic or group_topic_sender, and propagate `replyInThread` through text, card, and media outbound adapters so topic-scoped sessions no longer post at the group root. Fixes #74903. (#77151)
·WhatsApp: pass routing context into voice-note transcript echo preflight so echoed transcripts can deliver to the originating chat. Fixes #79778. (#79788)
·Cron/failover: classify structured OpenAI-compatible `server_error` payloads as `server_error`, expose that reason in cron state, and let one-shot cron retry policy honor `retryOn: ["server_error"]` without requiring raw `5xx` text. (#45594)
·Slack: wake the resolved thread session after interactive reply button/select clicks and carry Slack delivery context through the queued interaction event, so clicks continue the visible conversation. Fixes #79676 and #61502. (#79836)
·WhatsApp/streaming: send only the new suffix when text-end block replies repeat prior preambles across tool-call cycles, preventing cumulative WhatsApp preamble messages. Fixes #78946. (#79120)
·Tests/security audit: sandbox `audit-exec-surface.test.ts` under a per-case OpenClaw home tempdir, redirecting `OPENCLAW_HOME` (which wins over `HOME`/`USERPROFILE` in `resolveRawHomeDir`) alongside `HOME` and `USERPROFILE`, so its `saveExecApprovals(...)` calls never touch the live `~/.openclaw/exec-approvals.json` on the host running the suite. Sibling exec-approvals tests already used the tempdir pattern; this file did not, so running `pnpm test` against a contributor's local checkout was silently truncating their real approvals to `{ "version": 1, "agents": {} }`. (#79885)
·ACP/gateway: preserve `AcpRuntimeError` cause chain (code/method/JSON-RPC detail) through the lifecycle boundary so gateway logs, telegram replies, and tool-result text show the actual upstream failure instead of opaque `Internal error`/`[object Object]`, with redaction applied before the chain reaches log or reply surfaces.
·Channels/iMessage: wire `action: "reply"` attachments through `imsg send-rich --file` when the installed imsg build advertises that capability (probed once via `imsg send-rich --help` and cached on the private-API status). Reply now hydrates `media`/`mediaUrl`/`fileUrl`/`mediaUrls[0]`/`filePath`/`path`/base64 `buffer`+`filename` through the shared outbound resolver, stages buffers via the existing `withTempFile` helper, rejects `http(s)://` URL attachments with a targeted error pointing callers at `send`'s full attachment-resolver pipeline, and falls back to the explicit `imsg#114 not landed yet` error on older imsg builds. Depends on the upstream `openclaw/imsg#114` capability landing in an installable release; until then the new path stays gated and users see the same explicit fallback `#79822` introduced. (#79864)
·Telegram: preserve the first-preview debounce while appending true partial-stream deltas, so edited draft previews no longer duplicate earlier text when providers emit incremental output. (#80045)
·Agents/Anthropic: report 1M session context for Claude Opus/Sonnet 4 models even when local model config still advertises 200k, matching model discovery and preventing premature status/UI overflow. Fixes #66766.
·Models/OpenRouter: hide missing-auth direct provider rows in `/model status` when they are only duplicated by a nested OpenRouter model id such as `openrouter/google/...`, while preserving explicitly configured direct providers. Fixes #62317.
·Models: preserve an explicitly selected provider/model such as `opencode-go/deepseek-v4-pro` when another provider owns the same bare model alias. Fixes #79325.
·Models/config: explain missing `models.providers.<provider>.models[]` registration when a model exists only in `agents.defaults.models`, instead of returning a bare unknown-model error. Fixes #80089.
·MCP/tools: prefix bundle MCP server/tool fragments that would start with digits, keeping generated tool names valid for Moonshot/Kimi and other strict providers. Fixes #79179.
·Models/OpenRouter: treat `403 API key budget limit exceeded` as billing so model fallback advances instead of retrying the exhausted primary. Fixes #60191.
·Models/OpenRouter: repair stale session overrides that lost the outer `openrouter/` provider wrapper, so sessions return to the configured OpenRouter model instead of failing as an unknown direct-provider model. Fixes #78161.
·Google/Gemini: default API-key onboarding back to `google/gemini-3.1-pro-preview` so fresh Gemini test configs exercise Gemini 3.1 Pro Preview.
·Telegram: show full provider/model labels for nested OpenRouter model ids in the model picker, so `openrouter/openai/gpt-5.4-mini` no longer displays as `openai/gpt-5.4-mini`. Fixes #67792. (#72752)
·Models/OpenRouter: preserve live `supported_parameters` tool support metadata so non-tool Perplexity Sonar models no longer receive agent tool payloads and fall back unnecessarily. Fixes #64175.
·Models/OpenRouter: add MoonshotAI Kimi K2.5 to the bundled OpenRouter catalog so onboarding/model pickers can offer it without waiting for live discovery. Fixes #14601.
·Models/OpenRouter: keep keyRef/tokenRef-backed auth profiles visible to read-only PI model discovery, so OpenRouter models stay available in model pickers without storing plaintext keys. Fixes #58106.
·Models/list: include explicit configured provider rows and read-only auth-backed catalog rows in the default configured view without loading PI's full registry, keeping Control UI pickers aligned with usable model auth. Refs #79381.
·Security/audit: honor `tools.byProvider["provider/model"].deny` when reporting small-model web/browser exposure, so per-model OpenRouter mitigations clear the `models.small_params` exposure signal. Fixes #80118.
·Models/Moonshot: accept direct `moonshotai/...` and `moonshot-ai/...` refs as aliases for canonical `moonshot/...`, so copied OpenRouter Kimi ids no longer fail as unknown direct models. Fixes #73876. (#74946)
·Kimi Code: use Kimi's stable `kimi-for-coding` API model id in bundled catalog, onboarding, and docs while normalizing legacy `kimi-code` and `k2p5` refs. Fixes #79965.
·Telegram: render cached reply targets and nearby group chatter as one selected conversation context window, so stale replies no longer split JSON reply chains from local chat context.
·Volcengine/Kimi: strip provider-unsupported tool schema length and item constraint keywords for direct and coding-plan models so hosted Kimi runs do not reject message tools with `minLength`. Fixes #38817.
·DeepSeek: backfill V4 `reasoning_content` replay fields for unowned OpenAI-compatible proxy providers, preventing follow-up request failures outside the bundled DeepSeek and OpenRouter routes. Fixes #79608.
·iMessage: emit a WARN log when an action is blocked because the imsg private API bridge is not attached, so operators see the silent-drop in `~/.openclaw/logs/openclaw.log` instead of having to read per-session trajectory JSONL `tool.result` payloads. Common after a gateway restart un-injects the dylib from Messages.app. (#80035)
·Codex: cross-fill missing `thread.id` and `thread.sessionId` before schema validation so live Codex app-server responses that omit `sessionId` no longer fail `thread/start` or `thread/resume`. Fixes #80124. (#80137)
·Agents/Pi: wait for embedded abort cleanup to settle before releasing the session write lock, preventing follow-up turns from racing previous prompt teardown. (#80239)
·WhatsApp: downgrade OpenClaw watchdog-triggered Web reconnects from runtime errors to recovery warnings and clear the recovered reconnect status after the next healthy connection. (#77026)
·ACPX/Windows: hide the MCP proxy target child process window on Windows so ACP-backed agents do not flash or fail because of terminal window handling. Fixes #60672. (#60678)
·Agents: abort generic repeated no-progress tool loops at the critical threshold when identical calls keep returning identical outcomes. (#80668)
·Exec approvals: omit generated command highlights for non-POSIX Windows and shell-wrapper approval commands until those command languages have native highlighting support. (#80566)
·Telegram: keep verbose tool progress and result drafts separate from the final assistant answer so tool output no longer blends into the final Telegram message. (#80294)
·Plugin SDK/Windows: enable the native require fast path for root `openclaw/plugin-sdk` dist aliases instead of forcing Jiti transforms. (#80878)

Release verification

·npm version: https://www.npmjs.com/package/openclaw/v/2026.5.12
·npm tarball: https://registry.npmjs.org/openclaw/-/openclaw-2026.5.12.tgz
·npm integrity: sha512-hHg88OFSF0rhDNUbmjMEJO0UdnGn4mNq0F23Hk/NmTKY3OaPCUXiHutd8Ea6S5TGouponytMMWCYgPRrwsW2Xg==
·npm publish proof: https://github.com/openclaw/openclaw/actions/runs/25877630156
·release publish proof: https://github.com/openclaw/openclaw/actions/runs/25877174574
·plugin npm proof: https://github.com/openclaw/openclaw/actions/runs/25877249367
·plugin ClawHub proof: https://github.com/openclaw/openclaw/actions/runs/25877252545
·macOS release validation: https://github.com/openclaw/openclaw/actions/runs/25877979171

v2026.5.12-beta.8pre-release2026-05-14

openclaw 2026.5.12-beta.8

GitHub ↗

Changes

·Amazon Bedrock: externalize the Bedrock and Bedrock Mantle provider packages so core installs no longer pull AWS SDK dependencies unless those providers are installed.
·Plugins: externalize Slack, OpenShell sandbox, and Anthropic Vertex so their runtime dependency cones install only when those plugins are installed.
·Control UI/WebChat: add a persisted auto-scroll mode selector so users can keep the current near-bottom behavior, always follow streaming output, or turn automatic streaming scroll off and use the New messages button manually. Fixes #7648 and #81287.
·ACP: add `acp.fallbacks` so ACP turns can try configured backup runtime backends when the primary backend is unavailable before any output is emitted. (#69542)

Fixes

·Agents/subagents: apply `agents.defaults.subagents.model` before target agent primary models during `sessions_spawn`, so model-scoped runtimes such as `claude-cli` stay attached to default child runs. Fixes #81395. (#81783)
·Telegram: keep Bot API polling alive during main event-loop stalls by moving ingress to an isolated worker with a durable local spool. Fixes #81132. (#81746)
·Telegram: preserve rendered HTML formatting through lazy cron announce delivery so Markdown links stay clickable instead of falling back to literal anchor tags. Fixes #81742. (#81758)
·Telegram: skip unmentioned group media before download when `requireMention` is active, avoiding failed media-download replies for messages that should be ignored. Fixes #81181. (#81785)
·CLI/plugins: keep bare plugin and parent-command help on the lightweight path, avoiding plugin registry discovery before rendering help.
·Gateway/session history: carry monotonic transcript message sequence through live updates and refresh SSE history when stale sequence input would otherwise append bad incremental state. (#81474)
·Security/sandbox: include Windows `USERPROFILE` in the sandbox blocked home roots so credential-bearing binds (such as `.codex`, `.openclaw`, or `.ssh` under the Windows user profile) are denied even when `HOME` points at a different shell home. (#63074)
·Models config/auth: stop inferring provider env-var markers from broad `^[A-Z_][A-Z0-9_]*$` strings, and resolve config-backed provider `apiKey` values only through structured env SecretRefs (`secrets.providers[id]` / `secrets.defaults`), so unrelated env vars cannot accidentally become provider credentials.
·Media fetch: skip allocating and buffering the response body for bodyless media responses (HEAD probes and 204-style empty bodies), avoiding wasted heap on streams that carry no payload.
·CLI/onboarding: forward provider-specific auth flags (e.g. `--openai-api-key`) through the onboarding wizard so they reach provider auth methods via `ctx.opts`, letting `--openai-api-key "$OPENAI_API_KEY"` skip the redundant "use existing env var?" prompt in non-interactive harnesses. (#81669)
·CLI/migrate: drop trailing periods from Codex migrate item messages and `REASON_CODE_MESSAGES` strings so plan/result rows read as labels instead of sentence fragments. (#81705)
·Slack: treat malformed private-file redirect `Location` headers as unfollowable redirects instead of failing Slack media downloads.
·Plugins: discover provider plugins from `setup.providers[].envVars` credentials during provider discovery while keeping the deprecated `providerAuthEnvVars` fallback. (#81542)
·Docs/Codex harness: clarify that per-agent `CODEX_HOME` isolates `~/.codex` while inherited `HOME` intentionally keeps `.agents` discovery and subprocess user-home state available.
·Auth: reclaim dead-owner stale file locks before retrying locked writes, so crashed OAuth refreshes no longer wedge `auth-profiles.json` until manual cleanup.
·CLI tables: preserve muted/color styling on wrapped continuation lines after multiline cells, keeping `openclaw plugins list` descriptions readable.
·Process execution: collapse case-insensitive duplicate child environment keys on Windows so caller-provided overrides such as `PATH` cannot be shadowed by host `Path`.
·Gateway/diagnostics: suppress cold-start liveness warnings during the startup grace window while still sampling liveness metrics. Fixes #79915. (#81699)
·Codex harness: keep `oauthRef`-backed Codex OAuth profiles usable and stop high-confidence app-server OAuth refresh invalidation from retry-spamming raw token-refresh errors without turning entitlement or usage-limit payloads into re-auth prompts.
·Browser CLI: request the existing `operator.admin` gateway scope explicitly for browser control commands, avoiding unnecessary scope-upgrade approval loops. Fixes #81555. (#81716)
·Gateway/diagnostics: suppress cold-start liveness warnings during the startup grace window while still sampling liveness metrics. Fixes #79915. (#81699)
·Plugin SDK: restore the deprecated `openclaw/plugin-sdk/memory-core` package subpath as an alias of `memory-host-core`, so published memory companion plugins that still import it resolve on current hosts.
·Control UI/i18n: use the installed workspace pi runtime for locale refreshes, update the fallback package pin, prefer the Anthropic CI provider when available, and skip invalid provider credentials instead of failing main.
·Codex harness: classify native app-server token-refresh logout and relogin failures as authentication refresh errors, so users get re-authentication guidance instead of a raw runtime failure.
·Codex startup: treat selectable configured OpenAI agent models as Codex runtime requirements during plugin auto-enable, startup planning, and doctor install repair, so Anthropic-primary configs can still switch to OpenAI/Codex cleanly.
·Agents: preserve source-reply delivery metadata when merging tool-returned media into the final reply, keeping message-tool-only replies deliverable and mirrored.
·Replies: treat rich presentation, interactive controls, and channel-native payload data as outbound content across follow-up, heartbeat, cron, ACP, and block-streaming delivery paths, preventing card/button-only replies from being dropped as empty.
·WebChat/TUI: route Codex `tools.message` source replies to the active internal UI turn and mirror them to session history, so message-tool-only harness replies, including rich presentation and button-only replies, no longer disappear while WebChat and TUI remain non-targetable outbound channels. (#81586)
·Replies: deliver rich-only block replies even when block-streaming coalescing is enabled, keeping card and button payloads from being dropped by the text coalescer.
·macOS/companion: require system TLS trust before pinning a first-use direct `wss://` gateway certificate and honor `gateway.remote.tlsFingerprint` as the explicit pin for remote node-mode sessions, so fresh endpoints fail closed when macOS cannot trust the certificate unless configured out of band. Fixes #50642.
·Update: snapshot config before update-time repair and restart writes, preserve plugin install records through doctor cleanup, and keep update-time config size drops from blocking the update while pointing users to the pre-update backup. Fixes #80077. (#80257)
·Sessions/status: classify ACP spawn-child sessions as `kind: "spawn-child"` instead of `"direct"` in `openclaw sessions` and status output; extract the duplicated session-kind classifier into a shared helper (`src/sessions/classify-session-kind.ts`) so both surfaces stay in sync. Fixes catalog #19. (#79544)
·Sessions/Gateway: report `agentRuntime.id: "acpx"` (or stored backend id) with `source: "session-key"` for ACP control-plane session rows in `openclaw sessions --json`, `openclaw status`, and Gateway session RPC responses instead of the incorrect `"auto"` / `"pi"` implicit fallback. Fixes catalog #18. (#79550)
·Telegram: delete tool-progress-only draft bubbles before rotating to the real answer, preventing orphaned progress messages in streamed replies.
·Codex app-server: keep per-agent `CODEX_HOME` isolation without rewriting `HOME` by default, so Codex-run subprocesses can still find normal user-home config, tokens, and CLI state unless the launch explicitly overrides `HOME`.
·iMessage: stop sending visible `<media:image>` placeholder text for media-only native image sends while preserving the internal echo key that prevents self-echo duplicate replies. (#81209)
·Agents/sessions: create configured agent main sessions before first `sessions_send` or gateway send, so agent-to-agent messages no longer fail when the target agent has not started yet.
·gateway: pass Talk session scope to resolver [AI]. (#81379)
·Gateway protocol: require v4 clients and stream explicit chat `deltaText`/`replace` frames so SDK clients can consume assistant updates without local diffing. (#80725)
·GitHub Copilot: exchange OAuth tokens for Copilot API tokens on image understanding requests and route Gemini image payloads through Chat Completions, fixing Copilot Gemini image descriptions. (#80393, #80442)
·Gateway: hide pending Node pairing commands, capabilities, and permissions until approval, and refresh the live approved surface when pairings change. (#80741)
·Plugins/Feishu/WhatsApp/Line: enforce inbound media size caps while reading download streams, avoiding full buffering of oversized attachments. (#81044, #81050)
·Plugins/install: limit install-time code safety scans to plugin-owned runtime entrypoints while keeping dependency manifest denylist checks, so trusted packages with large dependency trees no longer get blocked or warned on third-party runtime internals.
·Config: serialize and retry semantic config mutations centrally, so concurrent commands can rebase safe changes instead of clobbering or hand-rolling command-local retry loops. (#76601)
·Installer: honor `--no-git-update` for existing git checkouts before resolving release refs, preventing pinned source installs from moving during reinstall.
·Plugins/install: refresh OpenClaw-managed peer dependency pins when installed plugin peer ranges change, while preserving user-owned dependency pins.
·Require approval for setup-code device pairing [AI]. (#81292)
·Plugins/install: preserve third-party peer dependencies in the managed npm root when later plugin installs or updates recalculate the shared dependency tree.
·Plugins/memory: prefer the npm-installed memory-lancedb plugin over the bundled fallback during duplicate resolution, keeping Active Memory's `memory_recall` tool visible after managed installs. Fixes #81193.
·Plugins/uninstall: prune managed third-party peer dependencies after their owning npm plugin is removed, without blocking plugin cleanup on peer-prune failures.
·Docker: pin setup-time container paths so stale host `.env` OpenClaw paths cannot leak into Linux containers. Fixes #80381. (#81105)
·Channels/WeCom: refresh the official onboarding install to `@wecom/wecom-openclaw-plugin@2026.5.7` and update existing managed npm installs instead of failing on the package directory. Fixes #79884. (#80390)
·Anthropic: reseed Claude CLI fresh-session retries from bounded OpenClaw transcript history after session rotation, preventing conversation amnesia. Fixes #80905. (#80934)
·Require explicit browser device pairing [AI]. (#81289)
·Require Control UI pairing before proxy-scoped access [AI]. (#81288)
·Installer: honor `--version` for git installs and install from the checked-in lockfile, preventing recent dependency pins from tripping pnpm's minimum-release-age gate during tag installs.
·Agents: deliver same-process subagent completion handoffs through the in-process agent dispatcher instead of opening a Gateway RPC loopback.
·Harden trusted-proxy source validation [AI]. (#81290)
·Agents: add permissive item schemas to array tool parameters before provider submission, preventing OpenAI-compatible schema validation from rejecting plugin tools that omit `items`. Fixes #81175. (#81217)
·Agents: escalate LLM idle watchdog timeouts through profile rotation and configured model fallback instead of leaving agent turns stuck after a silent model stream. Fixes #76877. (#80449)
·Discord voice: treat OpenAI Realtime startup auth failures as fatal, suppress duplicate realtime error logs, and stop autoJoin from retrying the same broken voice channel until credentials are fixed.
·ACPX: stop forwarding unsupported timeout config options to Claude ACP while preserving OpenClaw's own turn timeout. (#80812)
·Session transcripts: redact sensitive message content in the centralized JSONL append path so CLI turns, gateway transcript injection, transcript mirrors, and guarded tool results use the same configured redaction behavior. Fixes #73565. Refs #73563. (#79645)
·Channels/iMessage: ignore Apple link-preview plugin payload attachments when users paste URLs, keeping the URL text while avoiding phantom media context. (#79374)
·Telegram: detect polling stalls from `getUpdates` liveness only, so outbound API calls no longer mask dead inbound polling; log polling-cycle starts after transport rebuilds. Fixes #78473.
·fix: scan plugin runtime entries during install [AI]. (#80998)
·fix(plugins): scan installed dependency runtime code [AI]. (#81066)
·Inherit tool restrictions for delegated sessions [AI]. (#80979)
·Telegram: discard legacy long-poll update offsets that cannot be tied to the current bot token, so token rotation no longer leaves bots silently skipping new messages. (#80671)
·browser: enforce navigation checks for act interactions [AI]. (#81070)
·Validate node exec event provenance [AI]. (#81071)
·Gateway: keep active reply runs visible to stuck-session diagnostics and clear no-active-work recovery state, preventing stale queued lanes after compaction or tool failures. Fixes #80677. (#81302)
·Codex app-server: rotate incompatible context-engine-managed native threads so Lossless-managed sessions do not resume stale hidden Codex history. (#81223)
·Codex cron: execute scheduled command-style automation payloads before workspace bootstrap or memory review, preserving existing isolated cron jobs after Codex harness migration. (#81510)
·Plugin LLM completions: honor Codex agent-runtime policy for canonical OpenAI model refs, so context-engine summarizers can use Codex OAuth instead of requiring direct `OPENAI_API_KEY` auth. (#81511)
·Gateway/OpenAI HTTP: return OpenAI-compatible 400 errors for invalid sampling params and provider validation failures instead of collapsing them to 500s. (#81275)
·Telegram: publish plugin and skill command description localizations to native command menus while filtering unsupported locale codes and preserving Telegram command limits. (#81351)
·Limit hook CLI tool authority [AI]. (#81065)
·Require admin scope for node device token management [AI]. (#81067)
·Restrict chat sender allowlist matching [AI]. (#80898)
·Update: suppress the false newer-config warning during restart health probing after an update handoff, while keeping future-version mutation guards intact. (#78652)
·Sessions: redact persisted tool result detail metadata before writing transcripts so diagnostic secrets do not survive tool output redaction. (#80444)
·Codex runtime: allow the official installed `@openclaw/codex` package to use its private task-runtime and MCP projection SDK helpers, fixing `MODULE_NOT_FOUND` during migrated OpenAI/Codex beta runs.
·Codex migration: make Enter activate the highlighted checkbox row before continuing, so `Skip for now` and bulk-selection rows work even when planned items start preselected.
·Codex harness: keep auth-profile-backed media tools such as `image_generate` available when OpenAI auth lives in the agent's auth-profile store instead of environment variables.
·WhatsApp/install: allow Baileys' pinned libsignal git subdependency under pnpm 11 so source installs and local checks can complete.
·Require auth for sandbox browser CDP relay [AI]. (#81002)
·fix: detect carried exec command forms [AI]. (#81000)
·Reject truncated exec approval commands [AI]. (#81001)
·Enforce inline shell wrapper payload matching [AI]. (#80978)
·fix(node-pairing): replace changed pending requests [AI]. (#80894)
·Rate limit Google Chat webhook requests [AI]. (#80974)
·Docker: mount the auth-profile secret key directory so OAuth-backed auth profiles survive container rebuilds. (#80991)
·Onboarding: accept Codex auth profiles for canonical OpenAI model checks, avoiding false missing-auth warnings. (#80913)
·fix(feishu): normalize webhook rate-limit client keys [AI]. (#80975)
·fix(auth): prevent bootstrap pairing scope changes [AI]. (#80976)
·Validate Control UI loopback retry endpoints [AI]. (#80900)
·Harden exported markdown link rendering [AI]. (#80902)
·fix(gateway): honor minimal discovery mode for wide-area DNS-SD [AI]. (#80903)
·slack: enforce reaction notification policy [AI]. (#80907)
·Enforce gateway command scopes by caller context [AI]. (#80891)
·Telegram/groups: in single-account setups, treat an explicit empty `accounts.<id>.groups: {}` map the same as undefined so the root `channels.telegram.groups` allowlist still applies, instead of silently dropping every group update under the default `groupPolicy: "allowlist"`. Multi-account semantics are unchanged so per-account explicit-empty groups still scope-disable a single account without affecting siblings; the explicit way to block all groups for any account remains `groupPolicy: "disabled"`. Fixes #79427. (#81030)
·Codex (app-server): project user-configured `mcp.servers` into new Codex thread configs, matching the codex-cli runtime's existing `-c mcp_servers=...` behavior so app-server-runtime agents see the same user MCP servers the CLI runtime already exposes. Plugin-curated apps remain attached via the separate `apps` config patch. Fixes #80814.
·Enforce Slack plugin approval button authorization [AI]. (#80899)
·Recognize PowerShell -ec inline commands [AI]. (#80893)
·fix(qqbot): authorize approval button callbacks [AI]. (#80892)
·Telegram: render supported HTML tags in streamed and durable replies instead of showing literal markup. (#80977)
·Scrub streamable MCP redirect headers [AI]. (#80906)
·fix(memory-wiki): require admin scope for ingest [AI]. (#80897)
·memory-wiki: require write scope for Obsidian search [AI]. (#80904)
·WhatsApp/install: allow Baileys' pinned libsignal git subdependency under pnpm 11 so source installs and local checks can complete.
·WhatsApp: externalize the channel as a ClawHub/npm plugin outside the core npm runtime bundle, and bump Baileys to `7.0.0-rc11` so libsignal resolves from the registry instead of a GitHub tarball.
·WhatsApp: keep optional audio decoding dependencies local to the external plugin so the core npm install no longer pulls WhatsApp-only media helpers.
·Build: skip copied metadata for bundled plugins that are excluded from build entries, preventing update/status rebuilds from advertising missing QQ Bot runtime files. (#80925)
·Control UI/sessions: nest subagent sessions under their parent session in the session picker dropdown using a visual `└─ ` prefix, making the parent-child relationship clear. Fixes #77628. (#78623)
·Auto-reply: surface a visible error when the configured model backend fails and fallback produces no visible reply, while preserving intentional silent turns and side-effect-only deliveries. (#80917)
·Agents/exec: skip redundant heartbeat wake-ups for subagent session exec completions, preventing spurious LLM invocations on parent sessions. Fixes #66748. (#66749)
·Provider streams: keep OpenAI-compatible SSE and JSON fallback streams draining across split chunks and fail Azure Responses streams with a bounded first-event diagnostic instead of stalling. Refs #80926. (#80927)
·Agents: rewrite generic provider internal errors with support request IDs into user-friendly transient error copy. (#49401)
·WhatsApp: finish handling pending debounced inbound messages before closing the socket. (#81246)
·CLI/commitments: write `--json` output to stdout instead of diagnostic logs so automation can parse commitment list and dismiss results. (#81215)
·Update: allow pnpm GitHub-source OpenClaw updates to approve the OpenClaw package build, so source installs complete their prepare/prepack lifecycle. (#81294)
·Telegram: preserve supported HTML tags in visible replies and durable mirrors so formatted messages render correctly instead of degrading to escaped text. (#80977)
·Plugins/runtime: attribute deprecated runtime config load/write warnings to the plugin id and source that triggered them so logs and plugin doctor runs are actionable. Refs #81394. (#81425)
·Agents/cron: honor a cron payload's explicit `timeoutSeconds` for the LLM idle watchdog even when it numerically equals `agents.defaults.timeoutSeconds`, preserving explicit per-run timeout intent and preventing stalled streaming replies from being cut to the implicit 120s cap. (#79426)
·Codex app-server: keep the short post-tool completion watchdog armed across dynamic tool completion bookkeeping so embedded Codex runs fail fast and release their session lane when Codex goes quiet after a tool result. (#81697)

Changes

·Gateway/OpenAI HTTP: honor `max_completion_tokens` and `max_tokens` on inbound `/v1/chat/completions` requests so client-provided token caps reach the upstream provider via `streamParams.maxTokens`, with `max_completion_tokens` taking precedence when both are sent.
·Models/OpenAI CLI auth: make `openclaw models auth login --provider openai` start the ChatGPT/Codex account login by default, while `--method api-key` remains the explicit OpenAI API-key setup path.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids inside explicit SDK OAuth auth-result config patches, so provider helpers emit `google/gemini-3.1-pro-preview` for Gemini 3.1 testing.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids inside SDK OAuth auth-result default config patches, so helper-built provider auth flows emit `google/gemini-3.1-pro-preview` for Gemini 3.1 testing.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids returned by direct `openclaw models auth login --set-default` provider auth flows before writing config, so Gemini testing targets `google/gemini-3.1-pro-preview`.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids in per-agent config defaults and auth patches, so agent-specific emitted config keeps targeting `google/gemini-3.1-pro-preview`.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids in provider catalog rows when API-key onboarding only reapplies the agent default, so emitted config keeps testing `google/gemini-3.1-pro-preview`.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids in `config set` mutation output for agent overrides and provider catalog rows, so current config emits `google/gemini-3.1-pro-preview`.
·Google/Gemini: canonicalize provider-qualified retired Gemini 3 Pro Preview refs during Google forward-compatible model resolution, so emitted config uses `google/gemini-3.1-pro-preview` for Gemini 3.1 testing.
·Google/Gemini: normalize proxy-prefixed retired Gemini 3 Pro Preview catalog rows, so emitted configs use `google/gemini-3.1-pro-preview` for Gemini 3.1 testing.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids inside per-agent model overrides before writing config, so agent-specific config emits `google/gemini-3.1-pro-preview` for Gemini 3.1 testing.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids in subagent, heartbeat, compaction, and subagent-tool model config during writes, so current config keeps emitting `google/gemini-3.1-pro-preview`.
·Docs/subagents: document `agents.defaults.subagents.announceTimeoutMs` in the sub-agent and configuration references. (#75509)
·Cron: add direct `cron.get`, `openclaw cron get <id>`, and agent-tool `get` support for inspecting one stored cron job by id. (#75117)
·Agents/tools: add per-sender tool policies with canonical channel-scoped sender keys, so operators can restrict dangerous tools by requester identity across global, agent, group, core, bundled, and plugin tool surfaces. (#66933)
·ACP: expose Gateway session lineage metadata through ACP session listings and session info snapshots so clients can render subagent graphs without private Gateway side channels. (#73458)
·Channels/iMessage: add `openclaw channels status --channel <name>` filtering and document the BlueBubbles-to-imsg cutover path so operators can probe iMessage without starting both channel monitors. (#80706)
·CI: add a non-blocking `plugin-inspector-advisory` artifact to Plugin Prerelease so release runs capture bundled plugin compatibility triage without changing the blocking gate.
·Runtime/Fly: detect Fly Machines as container environments from their runtime env vars, so gateway bind and Bonjour defaults match remote container launches. (#80209)
·Providers/fal: route GPT Image 2 and Nano Banana 2 reference-image edit requests to `/edit` with `image_urls` array, enforce NB2 edit geometry using `aspect_ratio` and `resolution` params, lift Fal edit mode input-image caps to 10 for GPT Image 2 and 14 for Nano Banana 2, and allow aspect-ratio hints in edit mode. (#77295)
·Control UI: show a plain HTML recovery panel when the app module never registers, giving blank dashboard pages a retry path and browser-extension troubleshooting link. Fixes #44107.
·Docs: rename the broad tools nav to Capabilities, keep automation and agent coordination as sections, and keep the tools overview focused on tools, skills, and plugins. https://docs.openclaw.ai/tools
·Build: enable additional low-churn oxlint rules for promise, TypeScript, and runtime footgun checks.
·Build: enable stricter Vitest lint rules for focused, disabled, conditional, hook, matcher, and expectation hazards.
·Build: pin explicit oxfmt defaults in the shared formatter config to keep formatting behavior stable across upgrades.
·TypeScript: enable stricter compiler checks for implicit returns, side-effect imports, overrides, and unused production code.
·Logging: add targeted model transport, payload, SSE, and code-mode diagnostics with redacted URL handling.
·Agents: allow `session.agentToAgent.maxPingPongTurns` up to 20 while keeping the default at 5 for longer agent-to-agent reply chains. Fixes #52382. (#52400)
·Agents: add per-agent `tools.message.crossContext` overrides so sandboxed/public agents can restrict message sends to the current conversation without changing the global bot policy.
·Agents: add per-agent `tools.message.actions.allow` overrides so sandboxed/public agents can expose and enforce send-only message tools.
·Agents: omit the sandbox workspace marker from compact command progress previews while keeping internal sandbox diagnostics unchanged.
·Agents: widen progress draft command preview lines by 50% so Discord inline tool updates preserve more useful command context.
·Codex app-server: retire timed-out app-server clients after bounded turn interrupts so Discord agents do not reuse a CPU-spinning Codex process after an attempt timeout.
·Codex app-server: default migrated native plugin destructive-action policy to enabled while preserving explicit global and per-plugin false overrides.
·Build: upgrade workspace package management to pnpm 11 and keep Docker, install, update, and release workflows on the pnpm 11 config surface. (#79414)
·Build: align Telegram QA workflows and git source installs with the pnpm 11 workspace build allowlist surface. (#80588)
·Models: add provider-level `localService` startup for on-demand local model servers before OpenAI-compatible requests, including one-shot model probes.
·Agents: trim default system prompt guidance and send-only message tool schemas to reduce prompt tokens while preserving GPT-5 personality guidance.
·Context: add `/context map` to send a treemap image of the current session context contributors. (#79867)
·Slack: add `unfurlLinks` and `unfurlMedia` config for bot `chat.postMessage` replies, including per-account overrides, so Slack link and media previews can be suppressed without workspace-wide settings. Fixes #48435. (#80145)
·Slack: add explicit `replyBroadcast` support for text and Block Kit thread replies so agents can opt into Slack's parent-channel `reply_broadcast` behavior. (#64365)
·Slack: preserve mention target/source metadata in inbound prompt context so agents can distinguish direct bot mentions from implicit thread wakes that mention someone else. Fixes #79025. (#75356)
·Slack: canonicalize outbound delivery-mirror routes for native DM channel IDs to the peer user session so `message.send` calls to `D...` targets do not split the same Slack DM thread into a channel session. Fixes #80091. (#80111)
·Plugin SDK: deprecate public subpaths that existed for at least one month and have no bundled extension production imports, keep legacy barrel/test/zod subpath package exports for backwards compatibility, and track both sets in the SDK surface report.
·Plugin SDK: deprecate public subpaths currently used by only one or two bundled plugin owners, keeping them importable while steering new plugin code to focused shared SDK seams or plugin-owned APIs.
·Plugin SDK: remove the owner-specific `provider-auth-login` public subpath after moving Chutes, GitHub Copilot, and OpenAI Codex auth flows back to provider-owned modules.
·Plugin SDK: remove provider-specific model, stream, and xAI compatibility helpers from public exports after moving bundled callers to provider-owned modules.
·Plugin SDK: expose runtime-supplied active model metadata to native plugin tool factories for diagnostics and plugin-owned policy decisions. Fixes #77857.
·QA/Mantis: add Telegram live PR evidence automation with Convex-leased credentials, Crabbox transcript capture, motion GIF previews, and inline PR comments.
·QA/Mantis: add a Telegram desktop scenario builder that leases Crabbox, installs native Telegram Desktop, configures an OpenClaw Telegram gateway with leased bot credentials, and records VNC screenshot/video artifacts.
·Discord/voice: add realtime voice diagnostics for speaker turns, playback resets, barge-in detection, and audio cutoff analysis.
·Talk: add `talk.realtime.instructions` so operators can append realtime voice style instructions while preserving OpenClaw's built-in agent-consult guidance. (#79081)
·Discord/voice: default test and source installs to the pure-JS `opusscript` decoder by ignoring optional native `@discordjs/opus` builds, avoiding slow native addon compiles outside dedicated voice-performance lanes.
·Discord/voice: add an opt-in native `@discordjs/opus` install script and decoder preference for live voice-performance lanes without charging unrelated Docker/tests for native addon builds.
·Discord/voice: add `voice.allowedChannels` to restrict voice joins and bot voice-state moves to configured channels while preserving open voice behavior when unset.
·Gateway/skills: add an opt-in private skill archive upload install path gated by `skills.install.allowUploadedArchives`, so trusted Gateway clients can stage and install zip-backed skills only when operators explicitly enable the code-install surface. (#74430)
·Codex app-server: enable Codex native code-mode-only for harness threads so deferred OpenClaw dynamic tools run through Codex's own searchable code execution surface instead of a PI-style wrapper.
·Dependencies: refresh workspace pins and patch targets, including ACPX `@agentclientprotocol/claude-agent-acp` `0.33.1`, Codex ACP `0.14.0`, Baileys `7.0.0-rc10`, Google GenAI `2.0.1`, OpenAI `6.37.0`, AWS SDK `3.1045.0`, Kysely `0.29.0`, Tlon skill `0.3.6`, Aimock `1.19.5`, and tsdown `0.22.0`.
·Dependencies: refresh workspace pins for Anthropic SDK, Smithy shared ini loading, Playwright, YAML, Aimock, TypeScript native preview, Vitest, Oxlint/Oxfmt, Vite, and pnpm 11.1.0.
·Dependencies: hard-pin non-peer direct dependency specs across bundled packages and add a changed-check guard so runtime installs resolve the exact versions tested by maintainers.
·Dependencies: move embedded Pi packages to the `@earendil-works` namespace, refresh Twitch Twurple packages, and move `@openclaw/fs-safe` from the GitHub release pin to the published npm package.
·Build: route Testbox changed-check delegation through Crabbox and remove the OpenClaw-specific Blacksmith Testbox helper scripts.
·Agents/compaction: preserve scoped background exec/process session references across embedded compaction and after-turn runtime contexts without exposing sessions from unrelated scopes. Fixes #79284. (#79307)
·Agents/process: tell agents to inspect background sessions with `process log` before sending interactive input and to use `waitingForInput`/`stdinWritable` hints from `log`/`poll`.
·CLI/onboarding: improve setup, onboarding, configure, and channel command wayfinding so terminal flows explain the next useful command instead of relying on terse setup labels.
·Agents/Codex: remove the configurable Codex dynamic-tools profile so Codex app-server always owns workspace, edit, patch, exec, process, and plan tools while OpenClaw integration tools remain available.
·macOS app: update the Peekaboo bridge dependency to Peekaboo 3.0.0.
·Dependencies: refresh workspace pins and move the WhatsApp plugin from `@whiskeysockets/baileys` to `baileys` while keeping the `7.0.0-rc10` runtime.
·Plugin SDK: add bundled-plugin session actions, `sendSessionAttachment`, and Cron-backed `scheduleSessionTurn`/tag cleanup under the grouped session namespace. Replaces #75578/#75581/#75588 and part of #73384/#74483.
·Plugin SDK/media-understanding: add `extractStructuredWithModel(...)` plus the optional provider-side `extractStructured(...)` seam so trusted plugins can run bounded image-first structured extraction with optional supplemental text context through provider-owned runtimes such as Codex.
·Exec approvals: add `tools.exec.commandHighlighting` so parser-derived command highlighting in approval prompts can be enabled globally or per agent. (#79348)
·Codex app-server: mirror native Codex subagent spawn lifecycle events into Task Registry so app-server child agents appear in task/status surfaces without relying on transcript text. (#79512)

Fixes

·CLI/media: render terminal QR codes with full-block characters by default so the bundled `qrcode` terminal renderer does not emit a pathologically dense ANSI final row in compact half-block mode that breaks scanning in some terminals. Fixes #77820.
·Agents/compaction: read post-compaction AGENTS.md refresh context from the queued run workspace instead of the runner process cwd, so CLI-backed follow-up turns re-inject the correct workspace startup rules after compaction. Fixes #70541. (#75532)
·Agents/read tool: treat positive offsets beyond EOF as empty ranges instead of surfacing the upstream read error, so stale pagination cursors no longer crash tool calls while unrelated read failures still fail loud. Fixes #62466. (#75536)
·Google/Gemini: normalize retired Gemini 3 Pro Preview refs left in Google API-key onboarding model allowlists and fallbacks, so setup-emitted config keeps testing `google/gemini-3.1-pro-preview` instead of `google/gemini-3-pro-preview`.
·Telegram/context: bound selected topic context to the active session so messages from before `/new` or `/reset` are not replayed into later turns. (#80848)
·Google/Gemini: normalize retired nested Gemini 3 Pro Preview ids when resolving exact configured proxy-provider refs, so `kilocode/google/gemini-3-pro-preview` resolves to `kilocode/google/gemini-3.1-pro-preview` for Gemini 3.1 testing.
·CLI: strip generic OSC terminal escape payloads from sanitized output fields, preventing clipboard/title escape bodies from leaking into commitment tables and other terminal-safe text.
·Codex app-server: match connector-backed plugin approval elicitations by stable connector id so enabled destructive actions no longer fall through to display-name-only rejection.
·Build: replace selected build utility `tsx` preloads with Node native type stripping so Node 26 build paths no longer emit `DEP0205` module loader deprecation warnings. (#78584)
·Media generation: honor configured music and video generation timeouts when tool calls omit `timeoutMs`, matching image generation behavior. (#80687)
·CLI/update/status: label beta-channel plugin fallback and model-pricing refresh failures as warnings, keeping mixed beta/latest plugin cohorts visible without making core update or Gateway reachability look failed. Fixes #80689.
·Doctor/plugins: relink managed npm plugin `openclaw` peer dependencies during `doctor --fix`, while refusing to follow package-local `node_modules` symlinks outside the plugin package. (#77412)
·iMessage: route inbound tapbacks as reaction system events instead of normal messages, defaulting to bot-authored-message notifications while allowing `reactionNotifications: "off" | "own" | "all"` overrides. Fixes #60274; refs #39031 and #39322.
·Control UI/performance: scope Nodes polling to the active Nodes tab, debounce stale session-list reconciliation, and bound chat-side session refreshes so long-running dashboards avoid background reload churn.
·Plugins/channels: explain bundled channel entry files that reach the legacy plugin loader as setup-runtime loader mismatches instead of generic missing-register failures.
·Plugins/session-end: fire a typed `session_end` plugin hook with reason `shutdown` (or `restart` when a restart is expected) for every session that was still active when the gateway process stops. Previously SIGTERM/SIGINT/restart paths closed the gateway without enumerating active sessions, leaving downstream `session_end` plugins (e.g. claude-mem) with ghost rows accumulating across restarts. The new shutdown finalizer drains an in-memory tracker that is populated by `session_start` and forgotten by replace / reset / delete / compaction emitters, so previously-finalized sessions are never double-fired. The drain is bounded to a 2 s total budget so a slow plugin cannot block process exit. Adds `"shutdown"` and `"restart"` to `PluginHookSessionEndReason`. Fixes #57790.
·Codex app-server: clamp Codex code-mode sandboxing to workspace-write when an OpenClaw sandbox is active, preventing Docker gateway socket access from becoming a danger-full-access Codex turn.
·TUI: exit immediately on Ctrl+C/SIGINT after gateway disconnect and bound shutdown drain so terminal teardown cannot strand sessions. Fixes #75379. (#75381)
·Matrix: default outbound markdown tables to bullet lists instead of fenced code blocks. Fixes #78990. (#80890)
·Bonjour/Gateway: treat active ciao probing and fresh name-conflict renames as in-progress so the mDNS watchdog waits for probe settlement before retrying, preventing rapid re-advertise loops on Windows, WSL, and other multicast-hostile hosts. (#74778) Refs #74242.
·Providers/MiniMax: send a minimal Anthropic-compatible user fallback when message conversion filters a turn to an empty payload, so MiniMax M2.7 no longer returns `chat content is empty` after tool-heavy sessions. Fixes #74589.
·Tools/media: preserve implicit allow-all semantics from `tools.alsoAllow`-only policies when preconstructing built-in media generation and PDF tools, so configured media tools become live without forcing `tools.allow: ["*", ...]`. Fixes #77841.
·Codex/Telegram: separate code-mode tool progress from final replies, render bridged tool calls with native tool labels, and repair persisted missing tool results for safer follow-up turns. (#80663)
·Memory/search: load the platform-specific `sqlite-vec-<platform>-<arch>` variant directly when the meta `sqlite-vec` package is missing from a global install, so vector recall keeps working on `npm install -g openclaw@latest` upgrades where optionalDependencies left only the platform variant on disk. Fixes #77838.
·Cron: keep long manual cron runs active in the task registry until completion, preventing transient `lost` markers before durable recovery reconciles. Fixes #78233. (#78243)
·Doctor/GitHub CLI: surface a `GH_CONFIG_DIR` hint when the GitHub skill is usable but `gh` auth lives under a different operator HOME than the agent process, without warning for disabled or filtered skills. Fixes #78063. (#78095)
·Gateway: dedupe concurrent `send`, `poll`, and `message.action` requests while delivery is still in flight, preventing duplicate outbound work for the same idempotency key. (#68341)
·Cron: keep main-session `systemEvent` heartbeat wakes on their bound session route for both direct and queued wake paths by dropping inherited explicit heartbeat destinations when forcing `target: "last"`. Fixes #73900.
·Telegram: honor forced document delivery for video media so `--force-document` sends MP4s as documents instead of typed videos. Fixes #80389. (#80405)
·Gateway: clear speculative node wake state when APNs registration is missing, preventing unregistered or mistyped node IDs from retaining wake throttle entries. Fixes #68847. (#68848)
·Auto-reply: keep late follow-up queue drain finalizers from deleting a replacement queue registered after `/stop`, preventing immediate follow-up messages from being orphaned. Fixes #68838. (#68839)
·Feishu: make manual App ID/App Secret setup the default channel-binding path while keeping QR scan-to-create as an optional best-effort flow, and document the manual fallback for domestic Feishu mobile clients that do not react to the QR code. Fixes #80591.
·Memory: cap dreaming promotion writes to `MEMORY.md` by compacting oldest auto-promoted sections while preserving user-authored notes, keeping active memory below the bootstrap budget. Fixes #73691. (#74088)
·Telegram: show resolved thinking defaults in native `/status` and `/think` menus while preserving explicit session overrides. (#80341)
·Channels: cache selected channel registry lookups against the active fallback snapshot so pinned-empty registries refresh native command and alias routing after active registry swaps. (#80333)
·Codex app-server: reuse native Codex CLI OAuth for isolated app-server harness login, refresh, and app inventory cache keys so ChatGPT-authenticated Codex runs no longer fall back to unauthenticated OpenAI API calls. (#79877)
·Gateway: scope `sessions.resolve` sessionId and label store loads to the requested agent so large unrelated agent stores are not parsed for scoped lookups. Fixes #51264. (#79474)
·Gateway: share serialized streaming event envelopes across eligible WebSocket and node subscribers while preserving per-client sequence numbers. (#80299)
·Gateway: consolidate duplicate `openclaw doctor` service config panels while preserving the declined-repair `--force` hint. Fixes #80287. (#78688)
·Browser: report Chrome MCP existing-session page readiness in browser status without letting status probes exceed the client timeout. Fixes #80268. (#80280)
·WhatsApp: route opening-phase Baileys 428 connectionClosed through the WhatsApp reconnect policy and keep post-open 428 closes retryable, so transient setup socket closes retry with WhatsApp diagnostics instead of escaping as a bare `channel exited` error. Fixes #75736; mitigates #77443.
·Agents: disable Pi's default filesystem resource discovery for embedded runs while keeping OpenClaw inline extension factories active, avoiding Windows event-loop stalls during first WhatsApp-triggered agent startup. Fixes #77443.
·Providers/self-hosted: read model-scoped llama.cpp runtime context from `/props.default_generation_settings.n_ctx` while keeping top-level `n_ctx` as a fallback, so session budgeting reflects the loaded context window. Fixes #73664. (#74057)
·Memory: reject symlinked directory components in configured extra memory paths before reading Markdown files. (#80331)
·Sessions/transcripts: replace whole-file `readFile` scans with shared streaming helpers (`streamSessionTranscriptLines` and `streamSessionTranscriptLinesReverse`) for idempotency lookup, latest/tail assistant text reads, delivery-mirror dedupe, and compaction fork loading, so long-running sessions no longer materialize the full transcript in memory. Forward scans use `readline` over a bounded `createReadStream`; reverse scans read bounded chunks from the file end and decode complete JSONL lines newest-first without a fixed tail cap. Synthetic 200 MiB transcript: peak RSS delta drops from +252 MiB to +27 MiB while preserving malformed-line tolerance and idempotency-key return semantics. Fixes #54296.
·Browser/CDP: filter browser-internal targets from raw CDP and persistent Playwright tab selection so navigation opens real page tabs. Fixes #55734.
·WhatsApp: apply hot-reloaded `dmPolicy` and `allowFrom` settings to the active Web listener before processing new inbound DMs. Fixes #80538.
·Plugins: let `openclaw doctor --fix` repair managed plugin installs whose package entrypoints fail package-directory boundary validation after local state moves. Fixes #80592.
·Voice-call: resume voice-originated exec approval follow-ups as internal non-delivery turns instead of rejecting them as `unknown channel: voice`. Fixes #80540.
·Control UI: preserve the composer draft when Stop is tapped during an active chat run, preventing accidental prompt loss on mobile. Fixes #80586.
·Infra/retry: keep jittered retry delays at or above server-supplied Retry-After lower bounds when the hint can be honored. Fixes #68541. (#68543)
·Docs: clarify that `/model provider/model` is an exact session route, while duplicate bare model ids only use configured fallback order on non-session override paths. Refs #80562.
·Redact persisted secret-shaped payloads [AI]. (#79006)
·Agents: label `.openclaw/sandboxes` exec workdirs as sandbox runs in compact tool summaries instead of showing the full path.
·OpenAI Codex: surface browser OAuth and device-code login failures instead of treating failed logins as empty successful auth results. Refs #80363.
·CLI agents: carry runtime-only current-turn sender/reply context into CLI model prompts while keeping prompt-build hook input and transcript text clean.
·Control UI: keep workspace file presence checks from treating `fs-safe` stat helper failures as missing files, restoring Agents file status for existing Windows workspace files. Fixes #79953.
·Microsoft Foundry: report an explicit error when the Azure subscription prompt returns an id that is not present in the enabled subscription list, instead of continuing from an unsafe subscription assertion. (#62742)
·fix(matrix): gate name-based allowlist resolution [AI]. (#79007)
·Slack: include the bot's own root/parent message in new thread sessions so in-thread replies reach the agent with the parent text the user is responding to, instead of only `reply_to_id` metadata. Fixes #79338.
·Docker: keep image builds on the source pnpm workspace policy so pnpm 11 can prune production dependencies without a Docker-only workspace rewrite.
·Agents/compaction: restore info-level gateway logs for embedded compaction start, completion, and incomplete outcomes. (#71961)
·Telegram: build reply-aware inbound turns through the shared channel context path so agents see the current reply target inline with the current message.
·Telegram: recover legacy message cache files that mixed JSON-array and line-delimited entries so restarted gateways preserve reply-window context. (#80567)
·Telegram: update the reply-context cache when messages are edited, so streamed bot replies appear in later agent context with their final text instead of the first draft.
·Skills/Windows: normalize compacted skill prompt locations to forward slashes after home-prefix compaction so Windows skill paths remain readable by model file tools. (#52200)
·Control UI/Windows: update `@openclaw/fs-safe` so agent workspace file presence checks fall back correctly on Windows, preventing existing AGENTS.md, SOUL.md, TOOLS.md, IDENTITY.md, USER.md, HEARTBEAT.md, and MEMORY.md files from showing as missing. Fixes #79953.
·Memory: skip managed dreaming cron reconciliation warnings for ordinary cron and heartbeat hook contexts that cannot manage Gateway cron. (#77027)
·Cron: treat Codex app-server turn acceptance, CLI process spawn, and tool starts as execution milestones, preventing isolated runs from tripping the early startup watchdog after work has begun.
·Codex app-server: treat current-turn `<turn_aborted>` raw markers as terminal so interrupted native-tool turns release Discord agent sessions instead of waiting for the outer timeout.
·Yuanbao: bump `openclaw-plugin-yuanbao` to 2.13.1 to support `sourceReplyDeliveryMode: "automatic"` for group chat. (#79814)
·Memory: keep `memory_search` result `corpus` labels aligned with the hit source, so session transcript hits surface as `sessions` and memory-file hits stay `memory`. Fixes #72885. (#71898, #72886)
·Codex app-server: default native plugin app tool approvals to automatic so non-destructive read tools run when destructive actions are disabled.
·Plugins: allow untracked local source plugins in the global extensions directory to load TypeScript package entries while keeping managed installs strict about compiled runtime output. Fixes #80503.
·Google/Gemini: normalize retired nested Gemini 3 Pro Preview ids while converting manifest catalog rows into emitted provider config, so `google/gemini-3.1-pro-preview` is used for testing instead of `google/gemini-3-pro-preview`.
·Google/Gemini: normalize retired nested Gemini 3 Pro Preview ids inside saved model allowlists and fallback chains, so proxy routes like `openrouter/google/gemini-3-pro-preview` are persisted as Gemini 3.1 Pro Preview.
·Google/Gemini: normalize retired nested Gemini 3 Pro Preview ids in configured proxy/provider-auth model catalogs, so regenerated config keeps testing `google/gemini-3.1-pro-preview` instead of `google/gemini-3-pro-preview`.
·Google/Gemini: normalize retired nested Gemini 3 Pro Preview ids while onboarding provider catalog presets, so setup-emitted proxy configs test `google/gemini-3.1-pro-preview` instead of `google/gemini-3-pro-preview`.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids in provider catalog rows during generic config writes, so unrelated config changes keep testing `google/gemini-3.1-pro-preview`.
·Models: keep configured fallback chains ahead of configured primary models for override selections with duplicate model ids, preventing fallback jumps to the wrong provider. Fixes #80562.
·Native apps: advertise the Gateway protocol compatibility range so chat and node sessions can connect to v3 gateways after additive v4 client updates.
·Gateway/agents: keep stale `sessions_send` ACP manager and `web_fetch` runtime chunks importable after package updates, preventing live gateways from breaking before restart. Fixes #78804.
·Gateway/install: preserve service environment value-source metadata in `openclaw gateway install`, so systemd reinstall paths keep env-file-backed secrets out of inline unit metadata. Refs #77406, #77427.
·Auto-reply/reset: include inbound sender context in bare `/new` and `/reset` model prompts while keeping startup instructions out of transcript prompts, so agents see sender identity on the first reset turn. Fixes #77360.
·Gateway: avoid synchronous restart-sentinel state probes during post-attach startup, preventing slow Windows or redirected state directories from blocking channel turns. Fixes #79264.
·Agents/auth: update successful model auth profile status with one locked store write, reducing post-model reply latency from duplicate `auth-profiles.json` saves.
·Agents/image: honor explicit `image` tool model overrides even when `agents.defaults.imageModel` is unset, restoring one-off vision calls for configured multimodal providers. Fixes #79341.
·Doctor/update: leave live systemd gateway units unchanged during noninteractive update-mode service repair, so update-time doctor does not silently overwrite operator-owned unit directives. Refs #80462.
·Update: accept optional leading `v` prefixes when verifying exact npm package install targets, so `openclaw update --tag v2026...` does not roll back after installing the matching bare package version. Refs #74069; #80480.
·Doctor: treat missing plugin ids in `plugins.deny` as stale config warnings instead of fatal validation errors, and remove them during stale plugin cleanup so update repair does not restore last-known-good config for deny-only stale plugin refs. Refs #77802.
·Codex app-server: preserve prompt-local current-turn context through context-engine prompt projection, so replied-to Telegram messages stay visible to the Codex model input.
·Telegram: pass agent-scoped media roots through gateway message actions so workspace-local media from the active agent is not rejected as cross-agent access.
·CLI/gateway: keep `gateway status --deep` plugin-aware so configured plugin manifest warnings, including missing channel config metadata, stay visible during install and update smoke checks.
·Doctor/status: clarify gateway token source conflict warnings and suppress them inside the managed Gateway service credential context.
·Feishu: accept Schema 2 card callbacks whose operator identity is nested under `operator.user_id`, so card buttons dispatch instead of being dropped as malformed. Fixes #71670. (#71787)
·Feishu: fall back to a top-level group send when normal group quoted replies target a withdrawn or missing message, preventing replies from disappearing silently while preserving native topic safety. Fixes #79349.
·Doctor: stop flagging the live compatibility agent directory as orphaned when the configured default agent is not `main`. Fixes #74313. (#74438)
·Auth/Claude CLI: persist fresher managed external CLI OAuth credentials back to `auth-profiles.json`, preventing stale `anthropic:claude-cli` profiles from repeatedly bootstrapping and flooding debug logs. Fixes #80129.
·Context: render `/context map` only from actual run context and persist Codex app-server run reports without counting deferred tool-search schemas as prompt-loaded tool schemas.
·Codex app-server: report Codex-native tool execution to diagnostics so long-running native `bash`, web, file, and MCP tools no longer look like stale embedded runs to the watchdog. (#80217)
·Codex app-server: refresh Codex account rate limits after subscription usage-limit failures so Discord and other channel replies can show the next reset time instead of saying Codex returned none.
·Agents/auth: let Codex-backed OpenAI agent turns use `auth.order.openai` entries for Codex-compatible OAuth and API-key profiles while keeping existing `openai-codex` profile ordering valid.
·Codex app-server: emit async `after_tool_call` observations for native tool completions not covered by the native hook relay so observability plugins can record Codex-native tools. (#80372)
·Tasks: route group and channel task completions through the requester session so the parent agent can send the visible summary instead of stopping at a generic task-status line. Fixes #77251. (#77365)
·Telegram: preserve blank lines between manually indented bullet blocks and following numbered sections in rendered replies. Fixes #76998.
·Agents/sandbox: allow read-only sandbox sessions to read the `/agent` workspace mount while keeping write/edit/apply_patch workspace-only guarded, restoring `read /agent/...` for `workspaceAccess: "ro"`. Fixes #39497.
·Slack: pass configured agent identity through draft preview sends so partial streaming replies keep custom username/avatar on the initial Slack message. Fixes #38235. (#38237)
·Slack: support `allowBots: "mentions"` for bot-authored messages that mention the receiving bot, matching the documented Discord-style mode without accepting every bot message. Fixes #43587. (#43588)
·Slack: refresh private file URLs with `files.info` when inbound DM file events omit or stale attachment URLs, preventing file attachments from being dropped before media hydration. Fixes #50129. (#50200)
·Slack: add scoped message-tool formatting hints so agents use Markdown for plain sends and direct mrkdwn for Block Kit fields. Fixes #34609. (#50979)
·Slack: describe `download-file` file ids separately from message timestamps and return a targeted recovery error when agents pass `messageId` instead of `fileId`. (#74155)
·Slack: retain processed room messages for `requireMention=false` channels so always-on Slack rooms keep recent conversation context between turns. (#38658)
·Slack: compile interactive reply directives for direct outbound sends without bypassing the `interactiveReplies` capability gate, preserving Block Kit for Slack CLI and cron deliveries. (#78220)
·Slack: keep DM last-route updates scoped to the active non-main DM session, including threaded DM turns, so isolated Slack DM sessions do not overwrite the shared main route. (#73085)
·Slack/ACP: route Slack channel and DM messages through configured ACP bindings when no runtime binding exists, keeping bound thread replies pinned to the persistent ACP session and dropping unavailable configured targets instead of falling back to `main`. (#73101)
·Slack: mark unresolved thread replies as ambiguous and skip them instead of treating them as root channel messages, keeping thread continuation on the SDK-backed participation store. (#75630)
·Slack: let same-channel message tool sends opt out of inherited thread context with `topLevel: true` or `threadId: null`, allowing agents to post a new parent-channel message from inside a Slack thread. Fixes #79807.
·Slack: prefer full rich-text block content over truncated socket-mode message previews so long inbound Slack messages reach agents intact. Fixes #79027.
·Slack: include structured Slack API error details in setup, probe, streaming, and reply logs while preserving token redaction. (#53966)
·Gateway/agents: keep structured reasons when active-run queueing fails and deprecate the legacy boolean queue helper, so steering and subagent wake diagnostics distinguish completed, non-streaming, and compacting runs. Fixes #80156.
·System events: dedupe keyed events across the queue while preserving unkeyed, delivery-route, and trust-boundary event identity. (#73040)
·Agents/UI: compact exec and tool progress rows by hiding redundant shell tool names, replacing known workspace paths with short context markers, and preserving Discord trace scrubbing for compact command lines.
·ACPX: run and await the embedded ACP backend startup probe by default so the gateway `ready` signal no longer fires before the acpx runtime has either become usable or reported a probe failure; set `OPENCLAW_ACPX_RUNTIME_STARTUP_PROBE=0` to restore lazy startup. Fixes #79596.
·Gateway/status: surface model-pricing bootstrap and refresh failures as degraded health/status warnings while keeping Gateway liveness healthy. Fixes #79599.
·OpenAI-compatible models: strip prior assistant reasoning fields from replayed Chat Completions history by default, preventing oMLX/vLLM Qwen follow-up turns from rejecting or stalling on stale `reasoning` payloads. Fixes #46637.
·CLI/onboarding: give non-Azure custom providers a safe generated context window and heal legacy 4k wizard entries without overwriting explicit valid small model limits, preventing first-turn compaction loops. Fixes #79428. (#79911)
·OpenAI-compatible models: add `compat.strictMessageKeys` to strip Chat Completions replay messages to `role` and `content` for strict providers that reject OpenAI-style tool and metadata keys. Fixes #50374.
·Bedrock Mantle: add `plugins.entries.amazon-bedrock-mantle.config.discovery.enabled=false` to suppress automatic Mantle discovery and IAM bearer-token generation while keeping the plugin enabled. Fixes #67288.
·Ollama: stop native `/api/chat` requests from copying catalog `contextWindow` or `maxTokens` into `options.num_ctx` unless `params.num_ctx` is explicitly configured, avoiding pathological prompt-ingestion latency on local large-context models. Fixes #62267.
·Ollama: keep the model idle watchdog enabled for `*:cloud` models routed through a local Ollama host, so cloud-backed tool-loop stalls fail over visibly instead of inheriting local-model no-idle behavior. Fixes #79350.
·Voice/Ollama: honor routed voice agent `tools.allow` for classic embedded voice responses, including empty allowlists, so no-tool Ollama agents do not receive tool schemas. Fixes #79506.
·Agents/doctor: warn when channel-routed agents cannot call the `message` tool, so operators can fix tool policy mismatches before explicit channel actions such as attachments or thread replies fail. Refs #80128.
·Gateway: reread config from disk after the first in-process restart loop startup, preventing SIGUSR1 restarts from reusing a stale startup snapshot and dropping config written after boot. Fixes #79947.
·Codex app-server: deliver native image-generation outputs from Codex `savedPath` events as reply media, so blank-text image generation turns still attach the generated file.
·Network/SSRF: keep pinned automatic DNS lookups on IPv4 when dual-stack hosts also publish AAAA records, and treat `EADDRNOTAVAIL` as a transient gateway network failure instead of a fatal crash. Fixes #80078.
·Control UI: show compact one-line live/idle/terminal run status badges in the Sessions table and rename the active-minute filter to its updated-within meaning. Fixes #78307.
·Control UI: scope chat session-list refreshes by agent and skip disk-only agent store discovery for configured-only lists, preventing post-first-message session switching stalls on large Windows stores. Fixes #79675.
·Control UI: allow Appearance tweakcn theme imports through the served CSP so browser-local custom theme links no longer fail with a `connect-src` violation. Fixes #78504.
·Control UI/config: remove plugin allowlist entries that the form auto-added when a plugin enable toggle is reverted before saving, so reverting the visible toggle clears dirty state without persisting unintended allowlist changes. (#78329)
·Gateway/mobile: reuse bootstrap-issued device-token scopes on handoff reconnects and surface device-token scope mismatches separately from token mismatches while preserving full shared-token dashboard/native sessions. Fixes #79292.
·Media/host-read: allow buffer-verified gzip, tar, and 7z archives in the shared host-local media validator alongside ZIP and document attachments.
·Plugins/install: retry managed npm plugin installs without npm alias overrides after npm's `Invalid comparator: npm:` failure, so older npm versions can install official plugins instead of aborting. (#80539)
·Plugins/doctor: invalidate persisted plugin registry snapshots when plugin diagnostics point at deleted source paths, so `openclaw doctor` stops repeating stale warnings after a local extension is replaced by a managed npm plugin. Fixes #80087. (#80134)
·Doctor/OpenAI Codex: preserve Codex auth intent when auto-repairing legacy `openai-codex/*` model refs to canonical `openai/*` by adding provider/model-scoped Codex runtime policy, preventing repaired configs from falling through to direct OpenAI API-key auth. Fixes #78533 and #78570.
·CLI/agents: surface durable message delivery status from `sendDurableMessageBatch` in `deliverAgentCommandResult` and `openclaw agent --json --deliver`, preserving suppressed hook outcomes as terminal no-retry results while exposing partial and failed sends for automation. Supersedes #53961 and #57755.
·Agents: apply the LLM idle watchdog while provider stream setup is still pending, preventing silent pre-stream model hangs from waiting for the full agent timeout.
·Cron: let isolated self-cleanup runs inspect their own job run history while keeping other cron jobs and mutation actions blocked. Fixes #80019.
·Cron: report isolated agent-turn setup and pre-model stalls with phase-specific timeout errors instead of waiting for the full job budget when no model call starts. Fixes #74803.
·CLI/plugins: treat arbitrary unknown subcommands outside plugin CLI metadata as normal unknown commands instead of suggesting `plugins.allow`, while preserving allowlist guidance for real plugin command roots. Fixes #80109. (#80123)
·CLI/config: persist explicit `config set` and `config patch` values that equal runtime defaults instead of reporting success while dropping them. Fixes #79856. (#80106)
·OpenAI/realtime voice: accept Codex-compatible legacy audio and transcript event aliases so provider protocol drift does not drop assistant audio or captions.
·Discord/voice: keep default agent-proxy realtime sessions from auto-speaking filler before the forced OpenClaw consult answer, finish Discord playback on realtime response completion, and queue later exact-speech answers until playback idles to avoid mid-sentence replacement.
·Gateway: return deterministic `400 invalid_request_error` responses for malformed encoded session-kill HTTP paths instead of letting route-shaped requests fall through to later Gateway handlers. (#72439)
·Control UI: serve root PWA and favicon assets from `/__openclaw__/` SPA routes so tab icons, install metadata, and the service worker do not 404 after internal navigation. Fixes #80072.
·Exec/safe bins: compare trusted safe-bin dirs with path-specific case folding on case-insensitive filesystems so Windows and default macOS paths match without weakening case-sensitive mounts. (#42131)
·OpenAI/realtime voice: honor disabled input-audio interruption locally so server VAD speech-start events do not clear Discord playback after operators set `interruptResponseOnInputAudio: false`.
·Telegram: keep no-response DM turns quiet instead of rewriting them into visible silent-reply chatter. Fixes #78188. (#78228)
·Telegram: handle managed select button callbacks before the raw callback fallback while preserving delimiter-containing option values such as `env|prod`. (#79816)
·OpenAI-compatible models: handle JSON chat-completion bodies returned to streaming requests, preserving reasoning fields and visible text instead of completing an empty agent turn. Fixes #77870.
·Discord/models: defer model picker component interactions before loading route, model, and preference data, preventing "This interaction failed" timeouts under gateway load. Fixes #77283.
·xAI: expose `/think low|medium|high` for reasoning-capable Grok models and keep `reasoning.effort` on native Responses payloads while preserving off-only behavior for non-reasoning routes. Fixes #79210.
·CLI/media: let explicit image description model refs use bundled static provider catalogs and generic model-backed image hooks, so `openclaw infer image describe --model zai/glm-4.6v` works like direct model runs and Anthropic auth probes avoid stale Claude 3 Haiku catalog entries.
·Models/Anthropic: add `anthropic/claude-haiku-4-5` to Anthropic API-key agent allowlist defaults when an Anthropic default model is configured, so cron model overrides can select the current Haiku alias. Fixes #78000.
·Agents/compaction: initialize built-in context engines before CLI transcript compaction resolves the default engine, preventing clean-process `legacy` engine registration failures during CLI session persistence. Fixes #79446.
·Agents/Anthropic-compatible: strip replayed thinking blocks for custom Anthropic-compatible models that explicitly declare `supportsReasoningEffort: false`, preventing Kimi-compatible providers from resending unsupported `thinking` content. Fixes #47452.
·Kimi: keep Anthropic-compatible thinking streams valid by supplying required thinking budgets and enough output room for hidden reasoning plus final text. (#80481)
·Browser: wait longer for existing-session Chrome MCP status and non-deep doctor probes so slow first attaches do not falsely report offline while keeping raw CDP status probes short. (#77473)
·Gateway/logging: install console capture before foreground Gateway fast-path parsing and suppress known libsignal session dumps even in verbose mode, preventing raw terminal logs from printing WhatsApp session key material. (#76306)
·Exec approvals: keep `exec.approval.list` on the lightweight policy-summary path so listing pending approvals no longer loads the rich tree-sitter command explainer. (#76943)
·Agents: surface concise default-visible warnings when `exec`/`bash` tool calls fail after the assistant claims success, while keeping raw stderr hidden unless verbose details are enabled. Fixes #60497. (#80003)
·Channels/iMessage: keep redacted failed probe details in non-sensitive health snapshots so Full Disk Access failures no longer appear as configured/OK in status output. Fixes #79795.
·Agents: stop blank model-emitted tool calls before dispatch while preserving id-based tool-name recovery, preventing Kimi/NVIDIA blank-name retry loops without creating a callable `_blank` sentinel. Fixes #34129. (#56391)
·Agents/Telegram: deliver the canonical final assistant answer instead of replaying accumulated pre-tool text blocks, preventing duplicate Telegram replies and raw-looking tool-output fragments from leaking into chat delivery. Fixes #79621 and #79986.
·Auto-reply/TUI: keep fallback timeout recovery deliverable after a primary model lifecycle error by emitting fallback progress and deferring terminal TUI errors until recovery has a chance to finish. Fixes #80000. (#80009)
·Heartbeat: clear stale auto fallback model overrides when the configured default model changes, so heartbeat runs follow updated `agents.defaults.model.primary` without requiring a manual reset. Fixes #74284.
·CLI/agent: let `openclaw agent --model` use the backend/admin Gateway scope without cached device-token scopes silently downscoping the request. (#78837)
·CLI/help: keep help and version invocations configless while improving shared port, channel, plugin, task, session, message, pairing, and auth recovery text.
·CLI/config: explain strict JSON parse failures with a valid example and the plain-string escape hatch.
·CLI/secrets: turn offline Gateway reload failures into actionable recovery text.
·CLI/channels: explain missing or ambiguous channel selections with next commands.
·CLI/channels: defer guided channel status collection until a channel is selected, keeping `openclaw channels add` first screen quieter.
·CLI/channels: exit guided channel setup cleanly on cancellation instead of printing the internal wizard error.
·Plugins/CLI: route disabled Matrix and LanceDB memory command roots to plugin-enable guidance instead of generic unknown-command errors.
·Browser/Docker: detect Playwright-managed Chromium from `PLAYWRIGHT_BROWSERS_PATH` and the default Playwright cache on Linux, so Docker installs that persist `/home/node/.cache/ms-playwright` no longer need `browser.executablePath`.
·Ollama: keep DeepSeek V4 cloud models thinking-capable even when Ollama Cloud `/api/show` omits the `thinking` capability, so `/think high` no longer rejects `ollama/deepseek-v4-*:cloud`.
·ACPX/Claude ACP: keep foreground prompts waiting for their own result when autonomous task-notification results arrive during the same session, and retarget the patch for Claude Agent ACP `0.33.1`.
·WhatsApp: keep Baileys media uploads from passing non-Dispatcher agents to undici in `7.0.0-rc10`, and patch the bundled Baileys declaration so the latest tsdown build stays warning-clean.
·Build: keep tsdown `0.22.0` warning-clean by externalizing known third-party declaration edges and replacing relative channel config module augmentations with explicit built-in channel fields.
·ACP sessions: map canonical runtime options to backend-advertised ACP config keys like Claude's `effort` while keeping persisted OpenClaw state canonical. (#79926)
·Models/Discord: support `provider/*` entries in `agents.defaults.models` so `/model`, `/models`, and model pickers can show dynamically discovered models for selected providers without exact model allowlists. Fixes #79485.
·Gateway/watch: rebuild or restage missing bundled-plugin dist and runtime-postbuild outputs before launching the Gateway from a source checkout, preventing incomplete watch-mode runtime trees. (#70805)
·CLI/update: allow restart health probes from the previous gateway protocol during self-update, and make plugin dry-runs report exact npm target versions instead of `unknown` while preserving unchanged status.
·OpenAI/Codex: forward persisted `openai-codex` OAuth profile metadata into Codex plugin harness attempts after canonical `openai/*` migration, so OAuth-only installs keep using native Codex auth instead of falling through to direct OpenAI API-key auth. Fixes #79978.
·OpenAI/Codex: point gateway missing-key recovery and wizard docs at the canonical `openai/gpt-5.5` plus Codex OAuth route, and fix trajectory export errors so they suggest the valid `openclaw sessions` command.
·Google/Gemini: normalize retired `google/gemini-3-pro-preview` primary, fallback, and model-map refs during config load and unrelated config writes so saved config keeps targeting Gemini 3.1 Pro Preview.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids inside emitted Google provider model config, so regenerated models.json rows test `google/gemini-3.1-pro-preview`.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids for explicit OpenAI-compatible Google and Gemini CLI provider configs, so emitted config targets `google/gemini-3.1-pro-preview`.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids preserved from existing merged models.json providers so config emission keeps targeting `google/gemini-3.1-pro-preview`.
·Google/Gemini: normalize retired Gemini 3 Pro Preview ids inside provider auth config patches so setup-emitted provider catalogs test `google/gemini-3.1-pro-preview`.
·GitHub Copilot: mint short-lived Copilot API tokens with the same `vscode-chat` integration identity used by runtime requests, and refresh legacy cached tokens missing that identity so image-capable Copilot models no longer inherit the `copilot-language-server` scope. Fixes #79946, #80074.
·Plugins/doctor: drop stale managed npm install records when `openclaw doctor --fix` removes npm packages that shadow bundled plugins, so the rebuilt registry no longer resurrects the removed package metadata.
·Doctor: warn when a per-agent model config omits the `fallbacks` key and `agents.defaults.model.fallbacks` is non-empty. Covers both string-form (`"model": "..."`) and partial-object form (`"model": { "primary": "..." }`) — both silently clobber the defaults chain at runtime. Use `"fallbacks": []` to explicitly opt out of fallbacks, or add `"fallbacks": [...]` to inherit or override. Fixes #79369.
·Discord/voice: reuse or suppress late realtime consult tool calls without stealing newer speaker context or speaking forced fallback answers twice.
·Discord/voice: skip likely incomplete realtime forced-consult transcript fragments and non-actionable closings so stale partial speech does not queue delayed answers over the next turn.
·Discord/voice: keep realtime forced consults from clearing active exact-speech playback, so back-to-back voice answers queue instead of cutting each other off.
·Discord/voice: synthesize realtime playback timestamps from emitted Discord PCM so OpenAI realtime barge-in truncation no longer sees `audioEndMs=0` and skips legitimate interruptions.
·Plugin SDK: keep activated linked plugin runtime facades loadable when bundled plugin fallback is disabled.
·Feishu: auto-thread `message(action="send")` replies inside the topic when the active session is group_topic or group_topic_sender, and propagate `replyInThread` through text, card, and media outbound adapters so topic-scoped sessions no longer post at the group root. Fixes #74903. (#77151)
·WhatsApp: pass routing context into voice-note transcript echo preflight so echoed transcripts can deliver to the originating chat. Fixes #79778. (#79788)
·Cron/failover: classify structured OpenAI-compatible `server_error` payloads as `server_error`, expose that reason in cron state, and let one-shot cron retry policy honor `retryOn: ["server_error"]` without requiring raw `5xx` text. (#45594)
·Slack: wake the resolved thread session after interactive reply button/select clicks and carry Slack delivery context through the queued interaction event, so clicks continue the visible conversation. Fixes #79676 and #61502. (#79836)
·WhatsApp/streaming: send only the new suffix when text-end block replies repeat prior preambles across tool-call cycles, preventing cumulative WhatsApp preamble messages. Fixes #78946. (#79120)
·Tests/security audit: sandbox `audit-exec-surface.test.ts` under a per-case OpenClaw home tempdir, redirecting `OPENCLAW_HOME` (which wins over `HOME`/`USERPROFILE` in `resolveRawHomeDir`) alongside `HOME` and `USERPROFILE`, so its `saveExecApprovals(...)` calls never touch the live `~/.openclaw/exec-approvals.json` on the host running the suite. Sibling exec-approvals tests already used the tempdir pattern; this file did not, so running `pnpm test` against a contributor's local checkout was silently truncating their real approvals to `{ "version": 1, "agents": {} }`. (#79885)
·ACP/gateway: preserve `AcpRuntimeError` cause chain (code/method/JSON-RPC detail) through the lifecycle boundary so gateway logs, telegram replies, and tool-result text show the actual upstream failure instead of opaque `Internal error`/`[object Object]`, with redaction applied before the chain reaches log or reply surfaces.
·Channels/iMessage: wire `action: "reply"` attachments through `imsg send-rich --file` when the installed imsg build advertises that capability (probed once via `imsg send-rich --help` and cached on the private-API status). Reply now hydrates `media`/`mediaUrl`/`fileUrl`/`mediaUrls[0]`/`filePath`/`path`/base64 `buffer`+`filename` through the shared outbound resolver, stages buffers via the existing `withTempFile` helper, rejects `http(s)://` URL attachments with a targeted error pointing callers at `send`'s full attachment-resolver pipeline, and falls back to the explicit `imsg#114 not landed yet` error on older imsg builds. Depends on the upstream `openclaw/imsg#114` capability landing in an installable release; until then the new path stays gated and users see the same explicit fallback `#79822` introduced. (#79864)
·Telegram: preserve the first-preview debounce while appending true partial-stream deltas, so edited draft previews no longer duplicate earlier text when providers emit incremental output. (#80045)
·Agents/Anthropic: report 1M session context for Claude Opus/Sonnet 4 models even when local model config still advertises 200k, matching model discovery and preventing premature status/UI overflow. Fixes #66766.
·Models/OpenRouter: hide missing-auth direct provider rows in `/model status` when they are only duplicated by a nested OpenRouter model id such as `openrouter/google/...`, while preserving explicitly configured direct providers. Fixes #62317.
·Models: preserve an explicitly selected provider/model such as `opencode-go/deepseek-v4-pro` when another provider owns the same bare model alias. Fixes #79325.
·Models/config: explain missing `models.providers.<provider>.models[]` registration when a model exists only in `agents.defaults.models`, instead of returning a bare unknown-model error. Fixes #80089.
·MCP/tools: prefix bundle MCP server/tool fragments that would start with digits, keeping generated tool names valid for Moonshot/Kimi and other strict providers. Fixes #79179.
·Models/OpenRouter: treat `403 API key budget limit exceeded` as billing so model fallback advances instead of retrying the exhausted primary. Fixes #60191.
·Models/OpenRouter: repair stale session overrides that lost the outer `openrouter/` provider wrapper, so sessions return to the configured OpenRouter model instead of failing as an unknown direct-provider model. Fixes #78161.
·Google/Gemini: default API-key onboarding back to `google/gemini-3.1-pro-preview` so fresh Gemini test configs exercise Gemini 3.1 Pro Preview.
·Telegram: show full provider/model labels for nested OpenRouter model ids in the model picker, so `openrouter/openai/gpt-5.4-mini` no longer displays as `openai/gpt-5.4-mini`. Fixes #67792. (#72752)
·Models/OpenRouter: preserve live `supported_parameters` tool support metadata so non-tool Perplexity Sonar models no longer receive agent tool payloads and fall back unnecessarily. Fixes #64175.
·Models/OpenRouter: add MoonshotAI Kimi K2.5 to the bundled OpenRouter catalog so onboarding/model pickers can offer it without waiting for live discovery. Fixes #14601.
·Models/OpenRouter: keep keyRef/tokenRef-backed auth profiles visible to read-only PI model discovery, so OpenRouter models stay available in model pickers without storing plaintext keys. Fixes #58106.
·Models/list: include explicit configured provider rows and read-only auth-backed catalog rows in the default configured view without loading PI's full registry, keeping Control UI pickers aligned with usable model auth. Refs #79381.
·Security/audit: honor `tools.byProvider["provider/model"].deny` when reporting small-model web/browser exposure, so per-model OpenRouter mitigations clear the `models.small_params` exposure signal. Fixes #80118.
·Models/Moonshot: accept direct `moonshotai/...` and `moonshot-ai/...` refs as aliases for canonical `moonshot/...`, so copied OpenRouter Kimi ids no longer fail as unknown direct models. Fixes #73876. (#74946)
·Kimi Code: use Kimi's stable `kimi-for-coding` API model id in bundled catalog, onboarding, and docs while normalizing legacy `kimi-code` and `k2p5` refs. Fixes #79965.
·Telegram: render cached reply targets and nearby group chatter as one selected conversation context window, so stale replies no longer split JSON reply chains from local chat context.
·Volcengine/Kimi: strip provider-unsupported tool schema length and item constraint keywords for direct and coding-plan models so hosted Kimi runs do not reject message tools with `minLength`. Fixes #38817.
·DeepSeek: backfill V4 `reasoning_content` replay fields for unowned OpenAI-compatible proxy providers, preventing follow-up request failures outside the bundled DeepSeek and OpenRouter routes. Fixes #79608.
·iMessage: emit a WARN log when an action is blocked because the imsg private API bridge is not attached, so operators see the silent-drop in `~/.openclaw/logs/openclaw.log` instead of having to read per-session trajectory JSONL `tool.result` payloads. Common after a gateway restart un-injects the dylib from Messages.app. (#80035)
·Codex: cross-fill missing `thread.id` and `thread.sessionId` before schema validation so live Codex app-server responses that omit `sessionId` no longer fail `thread/start` or `thread/resume`. Fixes #80124. (#80137)
·Agents/Pi: wait for embedded abort cleanup to settle before releasing the session write lock, preventing follow-up turns from racing previous prompt teardown. (#80239)
·WhatsApp: downgrade OpenClaw watchdog-triggered Web reconnects from runtime errors to recovery warnings and clear the recovered reconnect status after the next healthy connection. (#77026)
·ACPX/Windows: hide the MCP proxy target child process window on Windows so ACP-backed agents do not flash or fail because of terminal window handling. Fixes #60672. (#60678)
·Agents: abort generic repeated no-progress tool loops at the critical threshold when identical calls keep returning identical outcomes. (#80668)
·Exec approvals: omit generated command highlights for non-POSIX Windows and shell-wrapper approval commands until those command languages have native highlighting support. (#80566)
·Telegram: keep verbose tool progress and result drafts separate from the final assistant answer so tool output no longer blends into the final Telegram message. (#80294)
·Plugin SDK/Windows: enable the native require fast path for root `openclaw/plugin-sdk` dist aliases instead of forcing Jiti transforms. (#80878)