diff --git a/CHANGELOG.md b/CHANGELOG.md index c05682a7879..c985a2f6a4b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -4,6 +4,8 @@ Docs: https://docs.openclaw.ai ## Unreleased +## 2026.4.25 (Unreleased) + ### Changes - Browser/config: allow local managed Chrome launch discovery and post-launch @@ -48,13 +50,12 @@ Docs: https://docs.openclaw.ai - Plugins/Bonjour: stop the gateway from crash-looping on `CIAO PROBING CANCELLED` when the mDNS watchdog cancels a stuck probe. Restores the rejection-handler wiring dropped during the bonjour plugin migration and shares unhandled-rejection state across module instances so plugin-staged copies of `openclaw/plugin-sdk/runtime` register into the same handler set the host consults. Especially affects Docker on macOS, where mDNS probing reliably hits the watchdog. Thanks @troyhitch. - Plugins/startup: remove ownerless bundled runtime-dependency install locks after a short grace window and include lock owner details when startup times - out waiting for a plugin runtime-deps lock. Thanks @steipete. + out waiting for a plugin runtime-deps lock. - Live tests/voice: accept common STT variants for OpenClaw and ElevenLabs brand names so provider smoke tests fail on real regressions rather than equivalent transcripts. - Agents/replies: forward sanitized underlying agent failure details on external channels instead of replacing unknown failures with a generic retry message. - Thanks @steipete. - Browser/CDP: honor configured remote and `attachOnly` CDP HTTP/WebSocket timeouts when opening tabs through raw CDP or `/json/new` fallback. (#54238) Thanks @FuncWei. @@ -96,7 +97,7 @@ Docs: https://docs.openclaw.ai - Gateway/dashboard: render Control UI and WebSocket links with `https://`/`wss://` when `gateway.tls.enabled=true`, including `openclaw gateway status`. Fixes #71494. (#71499) Thanks @deepkilo. - Agents/OpenAI-compatible: default proxy/local completions tool requests to `tool_choice: "auto"` when tools are present, so providers enter native tool-calling mode instead of replying with plain-text tool directives. (#71472) Thanks @Speed-maker. - OpenAI image generation: use `gpt-5.5` for the Codex OAuth responses transport instead of the retired `gpt-5.4` model, fixing 500s from ChatGPT Codex image generation. Fixes #71513. Thanks @baolongl. -- OpenAI image generation: route transparent-background default-model requests to `gpt-image-1.5`, document the expected `image_generate` call shape, and keep Azure/custom OpenAI-compatible deployment names untouched. Thanks @steipete. +- OpenAI image generation: route transparent-background default-model requests to `gpt-image-1.5`, document the expected `image_generate` call shape, and keep Azure/custom OpenAI-compatible deployment names untouched. - Google video generation: download direct MLDev Veo `video.uri` results instead of passing them through the Files API path, fixing 404s after successful generation/polling. Fixes #71200. Thanks @panhaishan. - Google video generation: fall back to the REST `predictLongRunning` Veo endpoint for text-only SDK 404s while keeping reference image/video generation on the SDK path. Fixes #62309 and #63008. (#62343) Thanks @leoleedev. - MiniMax music generation: switch the bundled default model from the unsupported `music-2.5+` id to the current `music-2.6` API model. Fixes #64870 and addresses the music default from #62315. Thanks @noahclanman and @edwardzheng1. @@ -158,7 +159,15 @@ Docs: https://docs.openclaw.ai - Agents/Claude CLI: pass the OpenClaw system prompt through Claude's prompt-file flag so Windows runs avoid argv length failures without changing system prompt semantics. Fixes #69158. (#69211) Thanks @skylee-01, @cassioanorte, @Syu0, and @Stache73. - Agents/CLI sessions: bind `google-gemini-cli` session auth-epoch to the Google account identity in `~/.gemini/oauth_creds.json`, so Gemini-backed agents resume their conversation after gateway restart instead of minting a fresh session, and stale bindings are invalidated when the authenticated Google account changes. Fixes #70973. (#71076) Thanks @openperf. -## 2026.4.25 (Unreleased) +## 2026.4.24 + +### Highlights + +- Google Meet joins OpenClaw as a bundled participant plugin, with personal Google auth, Chrome/Twilio realtime sessions, paired-node Chrome support, artifact/attendance exports, and recovery tooling for already-open Meet tabs. +- DeepSeek V4 Flash and V4 Pro are in the bundled catalog, V4 Flash is the onboarding default, and DeepSeek thinking/replay behavior is fixed for follow-up tool-call turns. +- Talk, Voice Call, and Google Meet can use realtime voice loops that consult the full OpenClaw agent for deeper tool-backed answers. +- Browser automation gets coordinate clicks, longer default action budgets, per-profile headless overrides, and steadier tab reuse/recovery. +- Plugin and model infrastructure is lighter at startup: static model catalogs, manifest-backed model rows, lazy provider dependencies, and external runtime-dependency repair for packaged installs. ### Breaking @@ -207,9 +216,9 @@ Docs: https://docs.openclaw.ai - Diagnostics/OTEL: make exporter startup restart-safe so config reloads do not retain stale SDKs, log transports, or diagnostic event listeners. Thanks @vincentkoc. - Diagnostics: emit structured tool execution diagnostic events with trace context, timing, and redacted error metadata. Thanks @vincentkoc. - Diagnostics: emit structured run and model-call diagnostic events with trace context, duration, and non-message error metadata. Thanks @vincentkoc. -- Control UI/chat: add a Steer action on queued messages so a browser follow-up can be injected into the active run without retyping it. Thanks @steipete. +- Control UI/chat: add a Steer action on queued messages so a browser follow-up can be injected into the active run without retyping it. - Control UI/avatars: render authenticated assistant avatar routes through local blob URLs and allow those managed blobs in the dashboard CSP, restoring configured chat avatars. Fixes #71422. Thanks @blaspat. -- Control UI/Talk: add browser WebRTC realtime voice sessions backed by OpenAI Realtime, with Gateway-minted ephemeral client secrets and `openclaw_agent_consult` handoff to the full OpenClaw agent. Thanks @steipete. +- Control UI/Talk: add browser WebRTC realtime voice sessions backed by OpenAI Realtime, with Gateway-minted ephemeral client secrets and `openclaw_agent_consult` handoff to the full OpenClaw agent. - Plugin SDK/Codex harness: add provider-owned transport/auth/follow-up seams and harness result classification so Codex-style runtimes can participate in fallback policy without core special-casing. (#70772) Thanks @100yenadmin. - Codex harness: bridge Codex-native tool hooks into OpenClaw plugin hooks and approvals, with bounded relay payloads and approval spam protection. (#71008) Thanks @pashpashpash. - Dependencies/Pi: update bundled Pi packages to `0.70.2`, use Pi's upstream `gpt-5.5` and DeepSeek V4 catalog metadata, and keep only local `gpt-5.5-pro` forward-compat handling. Thanks @lsdsjy. @@ -219,25 +228,25 @@ Docs: https://docs.openclaw.ai - Models/commands: deprecate `/models add` so chat attempts now return a deprecation message instead of writing model configuration, and remove the add action from `/models` provider menus. (#71175) Thanks @Takhoffman. - Codex harness/context-engine: run context-engine bootstrap, assembly, post-turn maintenance, and engine-owned compaction in Codex app-server sessions while keeping native Codex thread state and compaction auditable. (#70809) Thanks @jalehman. - Codex runtime plan: consolidate contract-first Pi/Codex parity coverage and accept legacy Codex auth-provider aliases in app-server profile login and refresh paths. (#71096) Thanks @100yenadmin. -- Plugins/Google Meet: add a bundled participant plugin with personal Google auth, explicit meeting URL joins, Chrome and Twilio transports, and realtime voice support. (#70765) Thanks @steipete. -- Plugins/Google Meet: default Chrome realtime sessions to OpenAI plus SoX `rec`/`play` audio bridge commands, so the usual setup only needs the plugin enabled and `OPENAI_API_KEY`. Thanks @steipete. -- Plugins/Google Meet: add a `chrome-node` transport so a paired macOS node, such as a Parallels VM, can own Chrome, BlackHole, and SoX while the Gateway machine keeps the agent and model key. Thanks @steipete. -- Plugins/Google Meet: add `googlemeet artifacts` and `googlemeet attendance` commands plus matching tool/gateway actions for conference records, recordings, transcripts and transcript entries, smart notes, and participant sessions. Thanks @steipete. -- Plugins/Google Meet: add markdown and file output for `googlemeet artifacts` and `googlemeet attendance` reports. Thanks @steipete. -- Plugins/Google Meet: add `googlemeet latest` plus matching tool/gateway actions to find the newest conference record for a meeting. Thanks @steipete. -- Plugins/Google Meet: make meeting-based artifact and attendance lookups use the latest conference record by default, with `--all-conference-records` for full history. Thanks @steipete. -- Plugins/Google Meet: add Calendar-aware Meet lookup, CSV attendance with timing flags, and `googlemeet export` bundles for artifacts, attendance, transcripts, and raw JSON. Thanks @steipete. -- Plugins/Google Meet: add `googlemeet calendar-events`, Drive-backed document body export, ZIP bundles, transcript speaker names, reauth hints, and a guarded live smoke. Thanks @steipete. -- Plugins/Google Meet: add `manifest.json` export metadata, warning summaries for partial artifact/body failures, and matching `google_meet` tool/gateway export support. Thanks @steipete. -- Plugins/Google Meet: add dry-run export manifests so CLI, tool, and gateway callers can validate selected records, counts, and warnings without writing bundle files. Thanks @steipete. -- Plugins/Google Meet: add `googlemeet doctor --oauth` so operators can verify OAuth token refresh, Meet space reads, and side-effecting space creation without printing secrets. Thanks @steipete. -- Plugins/Voice Call: expose the shared `openclaw_agent_consult` realtime tool so live phone calls can ask the full OpenClaw agent for deeper/tool-backed answers. Thanks @steipete. -- Plugins/Voice Call: add `voicecall setup` and a dry-run-by-default `voicecall smoke` command so Twilio/provider readiness can be checked before placing a live test call. Thanks @steipete. -- Plugins/Google Meet: add `googlemeet doctor` and a `recover_current_tab`/`recover-tab` flow so agents can inspect an already-open Meet tab and report the blocker without opening another window. Thanks @steipete. +- Plugins/Google Meet: add a bundled participant plugin with personal Google auth, explicit meeting URL joins, Chrome and Twilio transports, and realtime voice support. (#70765). +- Plugins/Google Meet: default Chrome realtime sessions to OpenAI plus SoX `rec`/`play` audio bridge commands, so the usual setup only needs the plugin enabled and `OPENAI_API_KEY`. +- Plugins/Google Meet: add a `chrome-node` transport so a paired macOS node, such as a Parallels VM, can own Chrome, BlackHole, and SoX while the Gateway machine keeps the agent and model key. +- Plugins/Google Meet: add `googlemeet artifacts` and `googlemeet attendance` commands plus matching tool/gateway actions for conference records, recordings, transcripts and transcript entries, smart notes, and participant sessions. +- Plugins/Google Meet: add markdown and file output for `googlemeet artifacts` and `googlemeet attendance` reports. +- Plugins/Google Meet: add `googlemeet latest` plus matching tool/gateway actions to find the newest conference record for a meeting. +- Plugins/Google Meet: make meeting-based artifact and attendance lookups use the latest conference record by default, with `--all-conference-records` for full history. +- Plugins/Google Meet: add Calendar-aware Meet lookup, CSV attendance with timing flags, and `googlemeet export` bundles for artifacts, attendance, transcripts, and raw JSON. +- Plugins/Google Meet: add `googlemeet calendar-events`, Drive-backed document body export, ZIP bundles, transcript speaker names, reauth hints, and a guarded live smoke. +- Plugins/Google Meet: add `manifest.json` export metadata, warning summaries for partial artifact/body failures, and matching `google_meet` tool/gateway export support. +- Plugins/Google Meet: add dry-run export manifests so CLI, tool, and gateway callers can validate selected records, counts, and warnings without writing bundle files. +- Plugins/Google Meet: add `googlemeet doctor --oauth` so operators can verify OAuth token refresh, Meet space reads, and side-effecting space creation without printing secrets. +- Plugins/Voice Call: expose the shared `openclaw_agent_consult` realtime tool so live phone calls can ask the full OpenClaw agent for deeper/tool-backed answers. +- Plugins/Voice Call: add `voicecall setup` and a dry-run-by-default `voicecall smoke` command so Twilio/provider readiness can be checked before placing a live test call. +- Plugins/Google Meet: add `googlemeet doctor` and a `recover_current_tab`/`recover-tab` flow so agents can inspect an already-open Meet tab and report the blocker without opening another window. - Plugins/Bonjour: move LAN Gateway discovery advertising into a default-enabled bundled plugin with its own `@homebridge/ciao` dependency, so users can disable Bonjour without cutting wide-area discovery. Thanks @vincentkoc. -- Providers/Google: add a Gemini Live realtime voice provider for backend Voice Call and Google Meet audio bridges, with bidirectional audio and function-call support. Thanks @steipete. +- Providers/Google: add a Gemini Live realtime voice provider for backend Voice Call and Google Meet audio bridges, with bidirectional audio and function-call support. - Providers/Google: let Gemini TTS prepend configured `audioProfile` and `speakerName` prompt text for reusable speech style control. Thanks @tdack. -- Plugins/Google Meet: let realtime Meet sessions consult the full OpenClaw agent for deeper answers while staying in the live voice loop. Thanks @steipete. +- Plugins/Google Meet: let realtime Meet sessions consult the full OpenClaw agent for deeper answers while staying in the live voice loop. - Gateway/VoiceClaw: add a realtime brain WebSocket endpoint backed by Gemini Live, with owner-auth gating and async OpenClaw tool handoff. (#70938) Thanks @yagudaev. - Providers/DeepSeek: add DeepSeek V4 Flash and V4 Pro to the bundled catalog and make V4 Flash the onboarding default. Thanks @lsdsjy. - CLI/Gateway: make `gateway status` start faster by skipping plugin loading on the read-only status path. (#71364) Thanks @andyylin. @@ -322,7 +331,7 @@ Docs: https://docs.openclaw.ai - Providers/OpenAI-compatible: strip OpenAI-only Completions `store` from proxy payloads and allow `extra_body`/`extraBody` passthrough params for provider-specific request fields. Fixes #61826 and #69717. - Discord/subagents: preserve thread-bound completion delivery by keeping the requester-agent announce path primary and falling back to direct thread sends only when the announce produces no visible output. (#71064) Thanks @DolencLuka. - Discord/proxy: serialize proxied multipart attachment uploads with undici `FormData`, so Discord media sends work through configured REST proxies. (#71383) Thanks @TC500. -- Browser/tool: give Chrome MCP existing-session manage calls a longer default timeout, pass explicit tool timeouts through tab management, and recover stale selected-page MCP sessions instead of forcing a manual reset. Thanks @steipete. +- Browser/tool: give Chrome MCP existing-session manage calls a longer default timeout, pass explicit tool timeouts through tab management, and recover stale selected-page MCP sessions instead of forcing a manual reset. - Browser/sandbox: clean up idle tracked tabs opened by primary-agent browser sessions, while preserving active tab reuse and lifecycle cleanup for subagents, cron, and ACP sessions. Fixes #71165. Thanks @dwbutler. - Plugins/Voice Call: reuse the webhook runtime across in-process plugin contexts, avoiding `EADDRINUSE` when agent tools or CLI commands run while the Gateway already owns the voice webhook port. Fixes #58115. Thanks @sfbrian. - Plugins/Voice Call: answer accepted Telnyx inbound Call Control legs on `call.initiated`, so webhooks that reach OpenClaw no longer leave the caller ringing until hangup. Fixes #58231 and #40131. Thanks @KonsultDigital. @@ -332,49 +341,49 @@ Docs: https://docs.openclaw.ai - Plugins/Voice Call: scope embedded voice response sandbox resolution to the selected voice agent, so implicit `main` voice sessions respect `agents.defaults.sandbox.mode: "off"` even when other agents define sandboxed Docker binds. Fixes #56367. Thanks @crpol. - Media tools: honor the configured web-fetch SSRF policy for media understanding, image/music/video generation references, and PDF inputs, so explicit RFC2544 opt-ins cover WebChat OSS uploads without weakening defaults. Fixes #71300. (#71321) Thanks @neeravmakwana. - Agents/TTS: suppress successful spoken transcripts from verbose chat tool output when structured voice media is already queued, while preserving text output for non-builtin tool-name collisions. Fixes #71282. Thanks @neeravmakwana. -- Plugins/Google Meet: reuse existing Meet tabs and active sessions across harmless URL query differences, avoiding duplicate Chrome windows when agents retry a join. Thanks @steipete. -- Plugins/Google Meet: tell agents to recover already-open Meet tabs after browser timeouts, and make the dev CLI release its build lock if compiler spawning fails. Thanks @steipete. -- Plugins/Google Meet: return structured manual-action details when browser-based meeting creation needs login or permissions, so agents can guide the operator without opening duplicate Meet tabs. Thanks @steipete. -- Plugins/CLI: provide Gateway-backed node inspection to plugin commands, so `googlemeet recover-tab` can inspect paired browser nodes from the terminal. Thanks @steipete. +- Plugins/Google Meet: reuse existing Meet tabs and active sessions across harmless URL query differences, avoiding duplicate Chrome windows when agents retry a join. +- Plugins/Google Meet: tell agents to recover already-open Meet tabs after browser timeouts, and make the dev CLI release its build lock if compiler spawning fails. +- Plugins/Google Meet: return structured manual-action details when browser-based meeting creation needs login or permissions, so agents can guide the operator without opening duplicate Meet tabs. +- Plugins/CLI: provide Gateway-backed node inspection to plugin commands, so `googlemeet recover-tab` can inspect paired browser nodes from the terminal. - Cron/isolated sessions: clear stale runtime, lifecycle, auth, model, exec, heartbeat, usage, privilege, routing, and delivery artifacts when creating a fresh isolated run, and persist per-run session rows as snapshots so old base-session state no longer leaks into new cron executions. Thanks @vincentkoc. - Gateway/sessions: recover main-agent turns interrupted by a gateway restart from stale transcript-lock evidence, avoiding stuck `status: "running"` sessions without broad post-boot transcript scans. Fixes #70555. Thanks @bitloi. - Codex approvals: sanitize MCP elicitation approval titles, descriptions, and display parameters before forwarding them to OpenClaw approval prompts. (#71343) Thanks @Lucenx9. - Codex approvals: keep command approval responses within Codex app-server `availableDecisions`, including deny/cancel fallbacks for prompts that do not offer `decline`. (#71338) Thanks @Lucenx9. - Codex harness: reject same-thread app-server notifications without `turnId` or `turn.id` after a bound turn starts, preventing unscoped events from mutating or completing the active reply. (#71317) Thanks @Lucenx9. -- Plugins/Google Meet: include live Chrome-node readiness in `googlemeet setup` and document the Parallels recovery checks, so stale node tokens or disconnected VM browsers are visible before an agent opens a meeting. Thanks @steipete. -- Context engine: keep safeguard compaction checks active after context-engine windowing and for `ownsCompaction` engines, so large transcripts can compact before prompt submission instead of waiting for provider overflow. Fixes #71325. Thanks @steipete. -- Approvals: compact structured home-directory paths to `~` across Codex permission prompts and exec approval metadata without repeating them as a separate high-risk warning, while preserving filesystem root and wildcard host warnings. Thanks @steipete. -- Plugins/runtime deps: isolate the internal npm cache used for bundled plugin runtime-dependency repair and let package updates refresh/verify already-current installs, so failed update or sudo doctor runs can be repaired by rerunning `openclaw update`. Thanks @steipete. +- Plugins/Google Meet: include live Chrome-node readiness in `googlemeet setup` and document the Parallels recovery checks, so stale node tokens or disconnected VM browsers are visible before an agent opens a meeting. +- Context engine: keep safeguard compaction checks active after context-engine windowing and for `ownsCompaction` engines, so large transcripts can compact before prompt submission instead of waiting for provider overflow. Fixes #71325. +- Approvals: compact structured home-directory paths to `~` across Codex permission prompts and exec approval metadata without repeating them as a separate high-risk warning, while preserving filesystem root and wildcard host warnings. +- Plugins/runtime deps: isolate the internal npm cache used for bundled plugin runtime-dependency repair and let package updates refresh/verify already-current installs, so failed update or sudo doctor runs can be repaired by rerunning `openclaw update`. - Agents/delete: keep `--json` output machine-readable and retain workspaces that overlap another agent's workspace instead of moving shared state to Trash. Fixes #70889 and #70890. (#70897) Thanks @kaseonedge. - Browser/screenshot: honor `timeoutMs` through host and node screenshot requests, bound raw CDP screenshot commands, and avoid beyond-viewport CDP capture for ordinary viewport screenshots, so Windows Chrome captures no longer hang past the requested deadline. Fixes #68330. Thanks @Woodylai24. - Telegram/model picker: show configured model display names when browsing models through provider buttons, matching typed `/models ` output. Fixes #70560. (#71016) Thanks @iskim77. -- Plugins/runtime deps: stage bundled plugin runtime dependencies for packaged/global installs in an external runtime root and retain already staged deps across repairs, avoiding package-tree update races and npm pruning after upgrades. Thanks @steipete. -- Plugins/runtime deps: log bundled plugin runtime-dependency staging before synchronous npm installs start and include elapsed timing afterward, so first boot after upgrades no longer looks hung while dependencies are being repaired. Thanks @steipete. +- Plugins/runtime deps: stage bundled plugin runtime dependencies for packaged/global installs in an external runtime root and retain already staged deps across repairs, avoiding package-tree update races and npm pruning after upgrades. +- Plugins/runtime deps: log bundled plugin runtime-dependency staging before synchronous npm installs start and include elapsed timing afterward, so first boot after upgrades no longer looks hung while dependencies are being repaired. - Memory/Bedrock: skip Bedrock during automatic memory embedding selection when AWS credentials are unavailable, so `memory_search` can fall back to lexical search instead of failing on the first embed call. Fixes #71143 via #71245. Thanks @bitloi. -- Agents/failover: forward embedded run abort signals into provider-owned model streams, cap implicit LLM idle watchdogs below long run timeouts, and mark 429 responses without usable retry timing as non-retryable so GitHub Copilot rate limits fail over or surface promptly instead of hanging until run timeout. Fixes #71120. Thanks @steipete. -- Plugins/Google Meet: make meeting creation join by default, with an explicit URL-only opt-out, so agents that create a Meet also enter it. Thanks @steipete. -- Telegram/polling: persist accepted update offsets before long-running handlers complete so poller restarts do not replay already-ingested updates, while keeping same-process retries for handler failures. Thanks @steipete. -- Telegram/config: include generated Telegram channel config schema metadata in packaged plugin manifests so forum-topic/group config is accepted before runtime loads. Thanks @steipete. +- Agents/failover: forward embedded run abort signals into provider-owned model streams, cap implicit LLM idle watchdogs below long run timeouts, and mark 429 responses without usable retry timing as non-retryable so GitHub Copilot rate limits fail over or surface promptly instead of hanging until run timeout. Fixes #71120. +- Plugins/Google Meet: make meeting creation join by default, with an explicit URL-only opt-out, so agents that create a Meet also enter it. +- Telegram/polling: persist accepted update offsets before long-running handlers complete so poller restarts do not replay already-ingested updates, while keeping same-process retries for handler failures. +- Telegram/config: include generated Telegram channel config schema metadata in packaged plugin manifests so forum-topic/group config is accepted before runtime loads. - CLI/Claude: include user-configured `mcp.servers` in the strict Claude CLI MCP bundle config, matching Pi runs while preserving the OpenClaw loopback override. Fixes #70909. Thanks @keishingu. - Browser/tool: keep explicit AI snapshots from inheriting the efficient role-snapshot default and preserve numeric Playwright AI refs, so `--format ai` remains a real AI snapshot path. Fixes #62550. Thanks @ly85206559. - Gateway/config: keep in-process config patch reload comparisons on the resolved source snapshot when `${VAR}` env refs are restored on disk, avoiding false full gateway restarts for unchanged gateway/plugin secrets. Fixes #71208. Thanks @robbiethompson18. - Slack/messages: serialize write-client requests and whole outbound sends per target so rapid multi-message Slack replies preserve send order. Fixes #69101. (#69105) Thanks @nightq and @ztexydt-cqh. -- Slack/messages: keep Slack bot tokens out of internal message-ordering and DM cache keys. Thanks @steipete. +- Slack/messages: keep Slack bot tokens out of internal message-ordering and DM cache keys. - Slack/exec approvals: resolve native approval button clicks over the Gateway instead of delivering `/approve ...` as plain agent text, preserving retry buttons if Gateway resolution fails. Fixes #71023. (#71025) Thanks @marusan03. - Browser/tool: expose browser doctor diagnostics to agents and extend `openclaw doctor` browser readiness notes for managed Chromium launch prerequisites. (#62948, #62936) Thanks @seanc-dev. - Slack/files: return non-image `download-file` results as local file paths instead of image payloads, and include Slack file IDs in inbound file placeholders so agents can call `download-file`. Fixes #71212. Thanks @teamrazo. - Browser control: scope standalone loopback auth to the resolved active gateway credential and fail closed when password mode lacks a resolved password, so inactive tokens or passwords no longer authorize browser routes. Fixes #65626. (#65639) Thanks @coygeek. - Control UI/Codex harness: emit native Codex app-server assistant and lifecycle completion events so live webchat runs stop spinning without needing a transcript reload fallback. (#70815) Thanks @lesaai. - Agents/sessions: persist the runtime-resolved context budget from embedded agent runs, so Codex GPT-5.5 sessions keep the catalog/runtime context cap instead of falling back to the generic 200k status value. Fixes #71294. Thanks @tud0r. -- Agents/tools: fail runs before model submission when explicit tool allowlists resolve to no callable tools, preventing text-only hallucinated tool results for missing tools such as plugin commands that were not registered. Fixes #71292. Thanks @steipete. -- Agents/embedded: skip provider submission when an embedded run has no prompt, replay history, or prompt-local images, preventing empty OpenAI Responses requests from surfacing provider errors into user channels. Fixes #71130. Thanks @steipete. -- Providers/Google: map `/think adaptive` to Gemini dynamic thinking instead of a fixed medium/high budget, using Gemini 3's provider default and Gemini 2.5's `thinkingBudget: -1`. Fixes #71316. Thanks @steipete. +- Agents/tools: fail runs before model submission when explicit tool allowlists resolve to no callable tools, preventing text-only hallucinated tool results for missing tools such as plugin commands that were not registered. Fixes #71292. +- Agents/embedded: skip provider submission when an embedded run has no prompt, replay history, or prompt-local images, preventing empty OpenAI Responses requests from surfacing provider errors into user channels. Fixes #71130. +- Providers/Google: map `/think adaptive` to Gemini dynamic thinking instead of a fixed medium/high budget, using Gemini 3's provider default and Gemini 2.5's `thinkingBudget: -1`. Fixes #71316. - Providers/MiniMax: keep M2.7 chat model metadata text-only so image tool requests route through `MiniMax-VL-01` instead of the Anthropic-compatible chat endpoint. Fixes #71296. Thanks @ilker-cevikkaya. - Discord/replies: run `message_sending` plugin hooks for Discord reply delivery, including DM targets, so plugins can transform or cancel outbound Discord replies consistently with other channels. Fixes #59350. (#71094) Thanks @wei840222. -- Discord/replies: preserve single-use native reply semantics across shared payload fallback, component, voice, and queued delivery paths, so explicit reply tags no longer consume implicit reply slots and chunked fallback sends reply only once. Thanks @steipete. +- Discord/replies: preserve single-use native reply semantics across shared payload fallback, component, voice, and queued delivery paths, so explicit reply tags no longer consume implicit reply slots and chunked fallback sends reply only once. - Control UI/commands: carry provider-owned thinking option ids/labels in session rows and defaults so fresh sessions show and accept dynamic modes such as `adaptive`, `xhigh`, and `max`. Fixes #71269. Thanks @Young-Khalil. -- Image generation: make explicit `model=` overrides exact-only so failed `openai/gpt-image-2` requests no longer fall through to Gemini or other configured providers, and update `image_generate list` to mention OpenAI Codex OAuth as valid auth for `openai/gpt-image-2`. Fixes #71290 and #71231. Thanks @Young-Khalil and @steipete. -- Providers/GitHub Copilot: keep the plugin stream wrapper from claiming transport selection before OpenClaw picks a boundary-aware stream path, avoiding Pi's stale fallback Copilot headers on normal model turns. Thanks @steipete. +- Image generation: make explicit `model=` overrides exact-only so failed `openai/gpt-image-2` requests no longer fall through to Gemini or other configured providers, and update `image_generate list` to mention OpenAI Codex OAuth as valid auth for `openai/gpt-image-2`. Fixes #71290 and #71231. Thanks @Young-Khalil. +- Providers/GitHub Copilot: keep the plugin stream wrapper from claiming transport selection before OpenClaw picks a boundary-aware stream path, avoiding Pi's stale fallback Copilot headers on normal model turns. - Discord/subagents: pass runtime config into thread-bound native subagent binding and require it at the helper boundary so Discord channel resolution keeps account-aware config. Fixes #71054. (#70945) Thanks @jai. - Slack/Assistant: accept Slack Assistant DM `message_changed` events when their metadata identifies the human sender, while continuing to drop self-authored bot edits. Fixes #55445. Thanks @AlfredPros. - Slack/native streaming: suppress reasoning-only payloads before `chat.startStream`/`appendStream`, so Claude extended-thinking blocks no longer appear as visible Slack messages. Fixes #59687. Thanks @vision-ifc. @@ -384,11 +393,11 @@ Docs: https://docs.openclaw.ai - Agents/failover: stop body-less HTTP 400/422 proxy failures from defaulting to `"format"` classification, so embedded retries surface the opaque provider failure instead of falling into a compaction loop. Fixes #66462. (#67024) Thanks @altaywtf and @HongzhuLiu. - Plugins/loader: use cached discovery-mode snapshot loads for read-only plugin capability lookups, keep snapshot caches isolated from active Gateway registries, and make same-plugin channel/HTTP route re-registration idempotent so repeated snapshot or hot-reload paths no longer rerun full plugin side effects or accumulate duplicate surfaces. Fixes #51781, #52031, #54181, and #57514. Thanks @livingghost, @okuyam2y, @ShionEria, and @bbshih. - Plugins/loader: reuse the compatible active Gateway registry for broad runtime plugin ensure calls after a gateway-bindable boot load, so non-bundled plugins no longer re-run `register()` during the same boot path. Fixes #69250. Thanks @markthebest12. -- Plugins/hooks: keep the gateway-bindable hook runner installed when later default-mode plugin loads activate a different registry, preserving Gateway subagent lifecycle hooks across runtime cache misses. Fixes #63166. Thanks @steipete. -- Plugins/hooks: refresh live Gateway runtime hooks before inbound channel dispatch, so externally installed plugins keep `message_received`, `before_dispatch`, and reply hooks active after scoped startup plugin loads. Fixes #71167. Thanks @steipete. -- Media/input: resolve canonical inbound media refs through the shared media loader so native prompt image replay and explicit image/PDF tools can read `media://inbound/` and managed inbound replay paths under workspace-only file policy. Thanks @steipete. -- Media/tools: centralize media reference scheme classification for image, PDF, image-generation, video-generation, and music-generation inputs so managed inbound refs are accepted consistently. Thanks @steipete. -- Control UI/media: resolve canonical inbound media refs before serving assistant media previews, so `media://inbound/` sources no longer pass access checks but fail file open. Thanks @steipete. +- Plugins/hooks: keep the gateway-bindable hook runner installed when later default-mode plugin loads activate a different registry, preserving Gateway subagent lifecycle hooks across runtime cache misses. Fixes #63166. +- Plugins/hooks: refresh live Gateway runtime hooks before inbound channel dispatch, so externally installed plugins keep `message_received`, `before_dispatch`, and reply hooks active after scoped startup plugin loads. Fixes #71167. +- Media/input: resolve canonical inbound media refs through the shared media loader so native prompt image replay and explicit image/PDF tools can read `media://inbound/` and managed inbound replay paths under workspace-only file policy. +- Media/tools: centralize media reference scheme classification for image, PDF, image-generation, video-generation, and music-generation inputs so managed inbound refs are accepted consistently. +- Control UI/media: resolve canonical inbound media refs before serving assistant media previews, so `media://inbound/` sources no longer pass access checks but fail file open. - Auth/Codex: bootstrap `openai-codex:default` from Codex CLI credentials on fresh installs without replacing a locally refreshed OpenClaw OAuth token later. Fixes #71305. Thanks @Gforce10-design. - Plugin SDK/tool-result transforms: bound middleware `details`, validate in-place result mutations, and mark fail-closed middleware fallbacks with canonical `error` status. Thanks @vincentkoc. - Discord/gateway: prevent startup from getting stuck at `awaiting gateway readiness` when Carbon gateway registration races with a lifecycle reconnect. Fixes #52372. (#68159) Thanks @IVY-AI-gif. @@ -400,7 +409,7 @@ Docs: https://docs.openclaw.ai - Plugin SDK/tool-result transforms: restrict harness tool-result middleware to bundled plugins, fail closed on middleware errors, validate rewritten result shapes, preserve Pi per-call ids, and keep Codex media trust checks anchored to raw tool provenance. Thanks @vincentkoc. - Gateway/MCP loopback: apply owner-only tool policy and run before-tool-call hooks on `127.0.0.1/mcp` `tools/list` and `tools/call`, so non-owner bearer callers can no longer see or invoke owner-only tools such as `cron`, `gateway`, and `nodes`, matching the existing HTTP `/tools/invoke` and embedded-agent paths. (#71159) Thanks @mmaps. - Codex harness/security: wait for final app-server approval decisions and sanitize approval preview text, so native Codex permission prompts cannot be resolved by an early placeholder decision or render unsafe terminal/control content. (#70751, #70569) Thanks @Lucenx9. -- Providers/voice security: route ElevenLabs TTS and OpenAI Realtime browser-session secret creation through guarded fetch paths, preserving provider calls while keeping SSRF protections on voice surfaces. Thanks @steipete. +- Providers/voice security: route ElevenLabs TTS and OpenAI Realtime browser-session secret creation through guarded fetch paths, preserving provider calls while keeping SSRF protections on voice surfaces. - Agents/OpenAI WS: match Codex's Responses WebSocket continuation strategy, sending only strict incremental follow-up input with `previous_response_id` and falling back to full context when the replay chain or request shape differs. Fixes #44948. Thanks @hss-oss. - Plugins/Google Chat: log webhook auth rejection reasons only after all candidates fail, and warn when add-on `appPrincipal` values do not match configuration. Fixes #71078. (#71145) Thanks @luyao618. - Models/configure: preserve the existing default model when provider auth is re-run from configure while keeping explicit default-setting commands authoritative. Fixes #70696. (#70793) Thanks @Sathvik-1007. @@ -409,28 +418,28 @@ Docs: https://docs.openclaw.ai - Plugins/runtime deps: respect explicit plugin and channel disablement when repairing bundled runtime dependencies, so doctor and health checks no longer install deps for disabled configured channels. Thanks @vincentkoc. - Diagnostics/OTEL: export logs through bounded diagnostic log events instead of a direct logger transport hook. Thanks @vincentkoc. - WhatsApp/plugins: support an explicit opt-in for inbound `message_received` hooks with canonical channel, conversation, session, and sender fields. Thanks @vincentkoc. -- Channels/setup: keep bundled setup entries dependency-light and stage WhatsApp runtime dependencies only when login actually needs them, so first-run setup and read-only channel discovery avoid unused SDK imports. Thanks @steipete. +- Channels/setup: keep bundled setup entries dependency-light and stage WhatsApp runtime dependencies only when login actually needs them, so first-run setup and read-only channel discovery avoid unused SDK imports. - Slack/HTTP: keep webhook handlers in a process-global registry so HTTP mode survives plugin-loader/native-import splits and `/slack/events/` no longer returns 404 after logging as active. Fixes #67955, #46245, and #46246. Thanks @chrisabad and @cesararevalo. - Diagnostics: harden tool and model diagnostic events against hostile errors, blocking listeners, and unsafe stability reason fields. Thanks @vincentkoc. - Plugins/onboarding: record local plugin install source metadata without duplicating raw absolute local paths in persisted `plugins.installs`, while preserving linked load-path cleanup. (#70970) Thanks @vincentkoc. - Group chats/silent replies: tighten `NO_REPLY` prompt guidance so groups stay quiet without narrating silence or emitting fallback chatter when silence is the intended outcome. (#70954, #71209) Thanks @Takhoffman. - WhatsApp/groups+direct: setting `systemPrompt: ""` on a specific `groups.` or `direct.` entry now suppresses the wildcard system prompt instead of falling through to it, so users can silence the global prompt for a specific group or peer. (#70381) Thanks @Bluetegu. -- Browser/tool: tell agents not to pass per-call `timeoutMs` on existing-session type, evaluate, and other Chrome MCP actions that reject timeout overrides. Thanks @steipete. -- Browser/tool: use Playwright's current AI aria snapshot API for `refs="aria"` and fall back to role refs when a node browser cannot provide aria refs, so agents can still inspect and click controls such as Google Meet admission buttons. Thanks @steipete. -- Browser/tool: expose stable `tabId` handles such as `t1` plus optional tab labels, and accept those handles anywhere a browser tab target is needed. Thanks @steipete. -- Browser/tool: return `suggestedTargetId` first in tab payloads so agents naturally reuse labels or stable tab handles instead of raw DevTools ids. Thanks @steipete. -- Browser/tool: bundle a `browser-automation` skill with the multi-step snapshot, stable-tab, stale-ref, and manual-blocker loop for agent-controlled pages. Thanks @steipete. -- Browser/tool: add `openclaw browser doctor`, URL-expanded snapshots, direct labeled screenshots, and clearer tab-target errors for agents that accidentally pass positional indexes. Thanks @steipete. -- Plugins/Google Meet: use browser automation to classify and clear Meet's microphone-choice interstitial during browser meeting creation, and reuse in-progress create tabs on retry instead of opening duplicates. Thanks @steipete. +- Browser/tool: tell agents not to pass per-call `timeoutMs` on existing-session type, evaluate, and other Chrome MCP actions that reject timeout overrides. +- Browser/tool: use Playwright's current AI aria snapshot API for `refs="aria"` and fall back to role refs when a node browser cannot provide aria refs, so agents can still inspect and click controls such as Google Meet admission buttons. +- Browser/tool: expose stable `tabId` handles such as `t1` plus optional tab labels, and accept those handles anywhere a browser tab target is needed. +- Browser/tool: return `suggestedTargetId` first in tab payloads so agents naturally reuse labels or stable tab handles instead of raw DevTools ids. +- Browser/tool: bundle a `browser-automation` skill with the multi-step snapshot, stable-tab, stale-ref, and manual-blocker loop for agent-controlled pages. +- Browser/tool: add `openclaw browser doctor`, URL-expanded snapshots, direct labeled screenshots, and clearer tab-target errors for agents that accidentally pass positional indexes. +- Plugins/Google Meet: use browser automation to classify and clear Meet's microphone-choice interstitial during browser meeting creation, and reuse in-progress create tabs on retry instead of opening duplicates. - Codex/GPT-5.4: harden fallback, auth-profile, tool-schema, and replay edge cases across native and embedded runtime paths. (#70743) Thanks @100yenadmin. -- Models/fallback: resolve bare fallback model provider ids before model switching, so configured fallback chains keep working when a fallback is named without an explicit provider prefix. Thanks @steipete. -- Voice-call/Telnyx: preserve inbound/outbound callback metadata and read transcription text from Telnyx's current `transcription_data` payload. Thanks @steipete. +- Models/fallback: resolve bare fallback model provider ids before model switching, so configured fallback chains keep working when a fallback is named without an explicit provider prefix. +- Voice-call/Telnyx: preserve inbound/outbound callback metadata and read transcription text from Telnyx's current `transcription_data` payload. - Providers/DeepSeek: wire V4 thinking controls and OpenAI-compatible replay policy so follow-up turns preserve DeepSeek `reasoning_content`, while the None/off thinking path strips replayed reasoning fields. Fixes #70931. Thanks @lsdsjy. -- Providers/GitHub Copilot: align Copilot request headers across Anthropic, Responses, and built-in compaction summarization paths, including tool-result and image follow-up turns, without enabling unverified Responses continuation. Thanks @steipete. +- Providers/GitHub Copilot: align Copilot request headers across Anthropic, Responses, and built-in compaction summarization paths, including tool-result and image follow-up turns, without enabling unverified Responses continuation. - Codex harness: send verbose tool progress to chat channels for native app-server runs, matching the Pi harness `/verbose on` and `/verbose full` behavior. (#70966) Thanks @jalehman. -- Codex models: fetch paginated Codex app-server model catalogs, mark truncated `/codex models` output, and keep ChatGPT OAuth defaults on the `openai-codex/gpt-5.5` route instead of the OpenAI API-key route. Thanks @steipete. +- Codex models: fetch paginated Codex app-server model catalogs, mark truncated `/codex models` output, and keep ChatGPT OAuth defaults on the `openai-codex/gpt-5.5` route instead of the OpenAI API-key route. - Codex status: report Codex CLI OAuth as `oauth (codex-cli)` for native `codex/*` sessions instead of showing unknown auth. Fixes #70688. Thanks @jb510. -- Channels/CLI: accept explicit shared-secret, base-URL, and auth-directory setup flags, and map legacy Nextcloud Talk `--url`/`--token` add commands to the bundled plugin setup input. Fixes #61759 and #61923. Thanks @steipete. +- Channels/CLI: accept explicit shared-secret, base-URL, and auth-directory setup flags, and map legacy Nextcloud Talk `--url`/`--token` add commands to the bundled plugin setup input. Fixes #61759 and #61923. - Models/CLI: keep `openclaw models list` read-only while still showing eligible configured-provider rows, so listing models no longer rewrites per-agent `models.json`. (#70847) Thanks @shakkernerd. - Agents/transport: propagate configured attempt timeouts into guarded per-request dispatchers, so slow local LLM calls such as Ollama no longer fail at Undici's default 60-second body timeout. Fixes #70829. (#70831) Thanks @DranboFieldston. - Plugins/providers: mirror runtime auth choices in bundled provider manifests and detect `KIMI_API_KEY` for Moonshot/Kimi web search before plugin runtime loads. Thanks @vincentkoc. @@ -438,8 +447,8 @@ Docs: https://docs.openclaw.ai - Plugins/QQ Bot: enable the bundled qqbot plugin by default so its runtime dependency `@tencent-connect/qqbot-connector` is installed on first launch, unblocking the QR-code binding flow that dynamically imports the connector before any account is configured. (#71051) Thanks @cxyhhhhh. - Gateway/agent RPC: register active `agent` runs into the chat abort controller map so `chat.abort` and `sessions.abort` can interrupt them, matching `chat.send` behavior and unblocking external runtimes that drive the Gateway through the public `agent` RPC. Fixes #71128. (#71214) Thanks @bitloi. - Matrix/CLI: pass resolved runtime config into verify commands, so `openclaw matrix verify status` and sibling verify subcommands no longer crash before acquiring the Matrix client. Fixes #70992. (#71102) Thanks @luyao618. -- Gateway/startup: await startup sidecars before channel monitors report ready, reducing Discord and plugin startup races while still keeping gateway boot observability intact. Thanks @steipete. -- Plugins/Google Meet: report required manual actions for Chrome joins, use browser automation for Meet entry, and persist the private-WS node opt-in so paired-node realtime sessions keep their intended network policy. Thanks @steipete. +- Gateway/startup: await startup sidecars before channel monitors report ready, reducing Discord and plugin startup races while still keeping gateway boot observability intact. +- Plugins/Google Meet: report required manual actions for Chrome joins, use browser automation for Meet entry, and persist the private-WS node opt-in so paired-node realtime sessions keep their intended network policy. - Slack: route native stream fallback replies through the normal chunked sender so long buffered Slack Connect responses are not dropped or duplicated. (#71124) Thanks @martingarramon. - WhatsApp: transcribe accepted voice notes before agent dispatch while keeping spoken transcripts out of command authorization. (#64120) Thanks @rogerdigital. - Plugins/CLI: expose channel plugin CLI descriptors during discovery-mode plugin loads so snapshot registries keep channel commands visible without activating full runtimes. (#71309) Thanks @gumadeiras. @@ -456,55 +465,55 @@ Docs: https://docs.openclaw.ai ### Changes -- Providers/OpenAI: add image generation and reference-image editing through Codex OAuth, so `openai/gpt-image-2` works without an `OPENAI_API_KEY`. Fixes #70703. Thanks @steipete. +- Providers/OpenAI: add image generation and reference-image editing through Codex OAuth, so `openai/gpt-image-2` works without an `OPENAI_API_KEY`. Fixes #70703. - Providers/OpenRouter: add image generation and reference-image editing through `image_generate`, so OpenRouter image models work with `OPENROUTER_API_KEY`. Fixes #55066 via #67668. Thanks @notamicrodose. - Image generation: let agents request provider-supported quality and output format hints, and pass OpenAI-specific background, moderation, compression, and user hints through the `image_generate` tool. (#70503) Thanks @ottodeng. -- Agents/subagents: add optional forked context for native `sessions_spawn` runs so agents can let a child inherit the requester transcript when needed, while keeping clean isolated sessions as the default; includes prompt guidance, context-engine hook metadata, docs, and QA coverage. Thanks @steipete. -- Agents/tools: add optional per-call `timeoutMs` support for image, video, music, and TTS generation tools so agents can extend provider request timeouts only when a specific generation needs it. Thanks @steipete. +- Agents/subagents: add optional forked context for native `sessions_spawn` runs so agents can let a child inherit the requester transcript when needed, while keeping clean isolated sessions as the default; includes prompt guidance, context-engine hook metadata, docs, and QA coverage. +- Agents/tools: add optional per-call `timeoutMs` support for image, video, music, and TTS generation tools so agents can extend provider request timeouts only when a specific generation needs it. - Memory/local embeddings: add configurable `memorySearch.local.contextSize` with a 4096 default so local embedding contexts can be tuned for constrained hosts without patching the memory host. (#70544) Thanks @aalekh-sarvam. -- Dependencies/Pi: update bundled Pi packages to `0.70.0`, use Pi's upstream `gpt-5.5` catalog metadata for OpenAI and OpenAI Codex, and keep only local `gpt-5.5-pro` forward-compat handling. Thanks @steipete. +- Dependencies/Pi: update bundled Pi packages to `0.70.0`, use Pi's upstream `gpt-5.5` catalog metadata for OpenAI and OpenAI Codex, and keep only local `gpt-5.5-pro` forward-compat handling. - Codex harness: add structured debug logging for embedded harness selection decisions so `/status` stays simple while gateway logs explain auto-selection and Pi fallback reasons. (#70760) Thanks @100yenadmin. ### Fixes - Agents/bootstrap: repair completed workspaces that still have a stale `BOOTSTRAP.md` by detecting customized identity/profile files, deleting the stale bootstrap file, and recording setup completion (#71230). Thanks @Patrick-Erichsen. -- Codex harness: route native `request_user_input` prompts back to the originating chat, preserve queued follow-up answers, and honor newer app-server command approval amendment decisions. Thanks @steipete. +- Codex harness: route native `request_user_input` prompts back to the originating chat, preserve queued follow-up answers, and honor newer app-server command approval amendment decisions. - Codex harness/context-engine: redact context-engine assembly failures before logging, so fallback warnings do not serialize raw error objects. (#70809) Thanks @jalehman. -- WhatsApp/onboarding: keep first-run setup entry loading off the Baileys runtime dependency path, so packaged QuickStart installs can show WhatsApp setup before runtime deps are staged. Fixes #70932. Thanks @steipete. -- Block streaming: suppress final assembled text after partial block-delivery aborts when the already-sent text chunks exactly cover the final reply, preventing duplicate replies without dropping unrelated short messages. Fixes #70921. Thanks @steipete. -- Codex harness/Windows: resolve npm-installed `codex.cmd` shims through PATHEXT before starting the native app-server, so `codex/*` models work without a manual `.exe` shim. Fixes #70913. Thanks @steipete. -- Slack/groups: classify MPIM group DMs as group chat context and suppress verbose tool/plan progress on Slack non-DM surfaces, so internal "Working…" traces no longer leak into rooms. Fixes #70912. Thanks @steipete. +- WhatsApp/onboarding: keep first-run setup entry loading off the Baileys runtime dependency path, so packaged QuickStart installs can show WhatsApp setup before runtime deps are staged. Fixes #70932. +- Block streaming: suppress final assembled text after partial block-delivery aborts when the already-sent text chunks exactly cover the final reply, preventing duplicate replies without dropping unrelated short messages. Fixes #70921. +- Codex harness/Windows: resolve npm-installed `codex.cmd` shims through PATHEXT before starting the native app-server, so `codex/*` models work without a manual `.exe` shim. Fixes #70913. +- Slack/groups: classify MPIM group DMs as group chat context and suppress verbose tool/plan progress on Slack non-DM surfaces, so internal "Working…" traces no longer leak into rooms. Fixes #70912. - Agents/replay: stop OpenAI/Codex transcript replay from synthesizing missing tool results while still preserving synthetic repair on Anthropic, Gemini, and Bedrock transport-owned sessions. (#61556) Thanks @VictorJeon and @vincentkoc. - Telegram/media replies: parse remote markdown image syntax into outbound media payloads on the final reply path, so Telegram group chats stop falling back to plain-text image URLs when the model or a tool emits `![...](...)` instead of a `MEDIA:` token. (#66191) Thanks @apezam and @vincentkoc. - Agents/WebChat: surface non-retryable provider failures such as billing, auth, and rate-limit errors from the embedded runner instead of logging `surface_error` and leaving webchat with no rendered error. Fixes #70124. (#70848) Thanks @truffle-dev. - WhatsApp: unify outbound media normalization across direct sends and auto-replies. Thanks @mcaxtr. - Memory/CLI: declare the built-in `local` embedding provider in the memory-core manifest, so standalone `openclaw memory status`, `index`, and `search` can resolve local embeddings just like the gateway runtime. Fixes #70836. (#70873) Thanks @mattznojassist. -- Gateway/WebChat: preserve image attachments for text-only primary models by offloading them as media refs instead of dropping them, so configured image tools can still inspect the original file. Fixes #68513, #44276, #51656, #70212. Thanks @steipete. -- Plugins/Google Meet: hang up delegated Twilio calls on leave, clean up Chrome realtime audio bridges when launch fails, and use a flat provider-safe tool schema. Thanks @steipete. -- Media understanding: honor explicit image-model configuration before native-vision skips, including `agents.defaults.imageModel`, `tools.media.image.models`, and provider image defaults such as MiniMax VL when the active chat model is text-only. Fixes #47614, #63722, #69171. Thanks @steipete. -- Codex/media understanding: support `codex/*` image models through bounded Codex app-server image turns, while keeping `openai-codex/*` on the OpenAI Codex OAuth route and validating app-server responses against generated protocol contracts. Fixes #70201. Thanks @steipete. -- Providers/OpenAI Codex: synthesize the `openai-codex/gpt-5.5` OAuth model row when Codex catalog discovery omits it, so cron and subagent runs do not fail with `Unknown model` while the account is authenticated. Thanks @steipete. +- Gateway/WebChat: preserve image attachments for text-only primary models by offloading them as media refs instead of dropping them, so configured image tools can still inspect the original file. Fixes #68513, #44276, #51656, #70212. +- Plugins/Google Meet: hang up delegated Twilio calls on leave, clean up Chrome realtime audio bridges when launch fails, and use a flat provider-safe tool schema. +- Media understanding: honor explicit image-model configuration before native-vision skips, including `agents.defaults.imageModel`, `tools.media.image.models`, and provider image defaults such as MiniMax VL when the active chat model is text-only. Fixes #47614, #63722, #69171. +- Codex/media understanding: support `codex/*` image models through bounded Codex app-server image turns, while keeping `openai-codex/*` on the OpenAI Codex OAuth route and validating app-server responses against generated protocol contracts. Fixes #70201. +- Providers/OpenAI Codex: synthesize the `openai-codex/gpt-5.5` OAuth model row when Codex catalog discovery omits it, so cron and subagent runs do not fail with `Unknown model` while the account is authenticated. - Models/Codex: preserve Codex provider metadata when adding models from chat or CLI commands, so manually added Codex models keep the right auth and routing behavior. (#70820) Thanks @Takhoffman. -- Providers/OpenAI: route `openai/gpt-image-2` through configured Codex OAuth directly when an `openai-codex` profile is active, instead of probing `OPENAI_API_KEY` first. Thanks @steipete. +- Providers/OpenAI: route `openai/gpt-image-2` through configured Codex OAuth directly when an `openai-codex` profile is active, instead of probing `OPENAI_API_KEY` first. - Providers/OpenAI: harden image generation auth routing and Codex OAuth response parsing so fallback only applies to public OpenAI API routes and bounded SSE results. Thanks @Takhoffman. - OpenAI/image generation: send reference-image edits as guarded multipart uploads instead of JSON data URLs, restoring complex multi-reference `gpt-image-2` edits. Fixes #70642. Thanks @dashhuang. -- Providers/OpenRouter: send image-understanding prompts as user text before image parts, restoring non-empty vision responses for OpenRouter multimodal models. Fixes #70410. Thanks @steipete. -- Providers/Google: honor the private-network SSRF opt-in for Gemini image generation requests, so trusted proxy setups that resolve Google API hosts to private addresses can use `image_generate`. Fixes #67216. Thanks @steipete. +- Providers/OpenRouter: send image-understanding prompts as user text before image parts, restoring non-empty vision responses for OpenRouter multimodal models. Fixes #70410. +- Providers/Google: honor the private-network SSRF opt-in for Gemini image generation requests, so trusted proxy setups that resolve Google API hosts to private addresses can use `image_generate`. Fixes #67216. - Agents/transport: stop embedded runs from lowering the process-wide undici stream timeouts, so slow Gemini image generation and other long-running provider requests no longer inherit short run-attempt headers timeouts. Fixes #70423. Thanks @giangthb. - Providers/OpenAI: honor the private-network SSRF opt-in for OpenAI-compatible image generation endpoints, so trusted LocalAI/LAN `image_generate` routes work without disabling SSRF checks globally. Fixes #62879. Thanks @seitzbg. -- Providers/OpenAI: stop advertising the removed `gpt-5.3-codex-spark` Codex model through fallback catalogs, and suppress stale rows with a GPT-5.5 recovery hint. Thanks @steipete. +- Providers/OpenAI: stop advertising the removed `gpt-5.3-codex-spark` Codex model through fallback catalogs, and suppress stale rows with a GPT-5.5 recovery hint. - Control UI/chat: persist assistant-generated images as authenticated managed media and accept paired-device tokens for assistant media fetches, so webchat history reloads keep showing generated images. (#70719, #70741) Thanks @Patrick-Erichsen. - Control UI/chat: queue Stop-button aborts across Gateway reconnects so a disconnected active run is canceled on reconnect instead of only clearing local UI state. (#70673) Thanks @chinar-amrutkar. -- Memory/QMD: recreate stale managed QMD collections when startup repair finds the collection name already exists, so root memory narrows back to `MEMORY.md` instead of staying on broad workspace markdown indexing. Thanks @steipete. +- Memory/QMD: recreate stale managed QMD collections when startup repair finds the collection name already exists, so root memory narrows back to `MEMORY.md` instead of staying on broad workspace markdown indexing. - Agents/OpenAI: surface selected-model capacity failures from PI, Codex, and auto-reply harness paths with a model-switch hint instead of the generic empty-response error. Thanks @vincentkoc. - Plugins/QR: replace legacy `qrcode-terminal` QR rendering with bounded `qrcode-tui` helpers for plugin login/setup flows. (#65969) Thanks @vincentkoc. - Voice-call/realtime: wait for OpenAI session configuration before greeting or forwarding buffered audio, and reject non-allowlisted Twilio callers before stream setup. (#43501) Thanks @forrestblount. -- ACPX/Codex: stop materializing `auth.json` bridge files for Codex ACP, Codex app-server, and Codex CLI runs; Codex-owned runtimes now use their normal `CODEX_HOME`/`~/.codex` auth path directly. Thanks @steipete. +- ACPX/Codex: stop materializing `auth.json` bridge files for Codex ACP, Codex app-server, and Codex CLI runs; Codex-owned runtimes now use their normal `CODEX_HOME`/`~/.codex` auth path directly. - Auto-reply/system events: route async exec-event completion replies through the persisted session delivery context, so long-running command results return to the originating channel instead of being dropped when live origin metadata is missing. (#70258) Thanks @wzfukui. - Gateway/sessions: extend the webchat session-mutation guard to `sessions.compact` and `sessions.compaction.restore`, so `WEBCHAT_UI` clients are rejected from compaction-side session mutations consistently with the existing patch/delete guards. (#70716) Thanks @drobison00. - QA channel/security: reject non-HTTP(S) inbound attachment URLs before media fetch, and log rejected schemes so suspicious or misconfigured payloads are visible during debugging. (#70708) Thanks @vincentkoc. - Plugins/install: link the host OpenClaw package into external plugins that declare `openclaw` as a peer dependency, so peer-only plugin SDK imports resolve after install without bundling a duplicate host package. (#70462) Thanks @anishesg. -- Plugins/Windows: refresh the packaged plugin SDK alias in place during bundled runtime dependency repair, so gateway and CLI plugin startup no longer race on `ENOTEMPTY`/`EPERM` after same-guest npm updates. Thanks @steipete. +- Plugins/Windows: refresh the packaged plugin SDK alias in place during bundled runtime dependency repair, so gateway and CLI plugin startup no longer race on `ENOTEMPTY`/`EPERM` after same-guest npm updates. - Teams/security: require shared Bot Framework audience tokens to name the configured Teams app via verified `appid` or `azp`, blocking cross-bot token replay on the global audience. (#70724) Thanks @vincentkoc. - Plugins/startup: resolve bundled plugin Jiti loads relative to the target plugin module instead of the central loader, so Bun global installs no longer hang while discovering bundled image providers. (#70073) Thanks @yidianyiko. - Anthropic/CLI security: derive Claude CLI `bypassPermissions` from OpenClaw's existing YOLO exec policy, preserve explicit raw Claude `--permission-mode` overrides, and strip malformed permission-mode args instead of silently falling back to a bypass. (#70723) Thanks @vincentkoc. @@ -519,17 +528,17 @@ Docs: https://docs.openclaw.ai - QQBot/security: require framework auth for `/bot-approve` so unauthorized QQ senders cannot change exec approval settings through the unauthenticated pre-dispatch slash-command path. (#70706) Thanks @vincentkoc. - MCP/tools: stop the ACPX OpenClaw tools bridge from listing or invoking owner-only tools such as `cron`, closing a privilege-escalation path for non-owner MCP callers. (#70698) Thanks @vincentkoc. - Feishu/onboarding: load Feishu setup surfaces through a setup-only barrel so first-run setup no longer imports Feishu's Lark SDK before bundled runtime deps are staged. (#70339) Thanks @andrejtr. -- Approvals/startup: let native approval handlers report ready after gateway authentication while replaying pending approvals in the background, so slow or failing replay delivery no longer blocks handler startup or amplifies reconnect storms. Thanks @steipete. -- WhatsApp/security: keep contact/vCard/location structured-object free text out of the inline message body and render it through fenced untrusted metadata JSON, limiting hidden prompt-injection payloads in names, phone fields, and location labels/comments. Thanks @steipete. -- Group-chat/security: keep channel-sourced group names and participant labels out of inline group system prompts and render them through fenced untrusted metadata JSON. Thanks @steipete. +- Approvals/startup: let native approval handlers report ready after gateway authentication while replaying pending approvals in the background, so slow or failing replay delivery no longer blocks handler startup or amplifies reconnect storms. +- WhatsApp/security: keep contact/vCard/location structured-object free text out of the inline message body and render it through fenced untrusted metadata JSON, limiting hidden prompt-injection payloads in names, phone fields, and location labels/comments. +- Group-chat/security: keep channel-sourced group names and participant labels out of inline group system prompts and render them through fenced untrusted metadata JSON. - Agents/replay: preserve Kimi-style `functions.:` tool-call IDs during strict replay sanitization so custom OpenAI-compatible Kimi routes keep multi-turn tool use intact. (#70693) Thanks @geri4. -- Discord/replies: preserve final reply permission context through outbound delivery so Discord replies keep the same channel/member routing rules at send time. Thanks @steipete. +- Discord/replies: preserve final reply permission context through outbound delivery so Discord replies keep the same channel/member routing rules at send time. - Plugins/startup: restore bundled plugin `openclaw/plugin-sdk/*` resolution from packaged installs and external runtime-deps stage roots, so Telegram/Discord no longer crash-loop with `Cannot find package 'openclaw'` after missing dependency repair. (#70852) Thanks @simonemacario. - CLI/Claude: run the same prompt-build hooks and trigger/channel context on `claude-cli` turns as on direct embedded runs, keeping Claude Code sessions aligned with OpenClaw workspace identity, routing, and hook-driven prompt mutations. (#70625) Thanks @mbelinky. -- Discord/plugin startup: keep subagent hooks lazy behind Discord's channel entry so packaged entry imports stay narrow and report import failures with the channel id and entry path. Thanks @steipete. +- Discord/plugin startup: keep subagent hooks lazy behind Discord's channel entry so packaged entry imports stay narrow and report import failures with the channel id and entry path. - Memory/doctor: keep root durable memory canonicalized on `MEMORY.md`, stop treating lowercase `memory.md` as a runtime fallback, and let `openclaw doctor --fix` merge true split-brain root files into `MEMORY.md` with a backup. (#70621) Thanks @mbelinky. - Providers/Anthropic Vertex: restore ADC-backed model discovery after the lightweight provider-discovery path by resolving emitted discovery entries, exposing synthetic auth on bootstrap discovery, and honoring copied env snapshots when probing the default GCP ADC path. Fixes #65715. (#65716) Thanks @feiskyer. -- Codex harness/status: pin embedded harness selection per session, show active non-PI harness ids such as `codex` in `/status`, and keep legacy transcripts on PI until `/new` or `/reset` so config changes cannot hot-switch existing sessions. Thanks @steipete. +- Codex harness/status: pin embedded harness selection per session, show active non-PI harness ids such as `codex` in `/status`, and keep legacy transcripts on PI until `/new` or `/reset` so config changes cannot hot-switch existing sessions. - Gateway/security: fail closed on agent-driven `gateway config.apply`/`config.patch` runtime edits by allowlisting a narrow set of agent-tunable prompt, model, and mention-gating paths (including Telegram topic-level `requireMention`) instead of relying on a hand-maintained denylist of protected subtrees that could miss new sensitive config keys. (#70726) Thanks @drobison00. - Webhooks/security: re-resolve `SecretRef`-backed webhook route secrets on each request so `openclaw secrets reload` revokes the previous secret immediately instead of waiting for a gateway restart. (#70727) Thanks @drobison00. - Memory/dreaming: decouple the managed dreaming cron from heartbeat by running it as an isolated lightweight agent turn, so dreaming runs even when heartbeat is disabled for the default agent and is no longer skipped by `heartbeat.activeHours`. `openclaw doctor --fix` migrates stale main-session dreaming jobs in persisted cron configs to the new shape. Fixes #69811, #67397, #68972. (#70737) Thanks @jalehman. @@ -543,10 +552,10 @@ Docs: https://docs.openclaw.ai ### Changes - Providers/xAI: add image generation, text-to-speech, and speech-to-text support, including `grok-imagine-image` / `grok-imagine-image-pro`, reference-image edits, six live xAI voices, MP3/WAV/PCM/G.711 TTS formats, `grok-stt` audio transcription, and xAI realtime transcription for Voice Call streaming. (#68694) Thanks @KateWilkins. -- Providers/STT: add Voice Call streaming transcription for Deepgram, ElevenLabs, and Mistral, alongside the existing OpenAI and xAI realtime STT paths; ElevenLabs also gains Scribe v2 batch audio transcription for inbound media. Thanks @steipete. +- Providers/STT: add Voice Call streaming transcription for Deepgram, ElevenLabs, and Mistral, alongside the existing OpenAI and xAI realtime STT paths; ElevenLabs also gains Scribe v2 batch audio transcription for inbound media. - TUI: add local embedded mode for running terminal chats without a Gateway while keeping plugin approval gates enforced. (#66767) Thanks @fuller-stack-dev. - Onboarding: auto-install missing provider and channel plugins during setup so first-run configuration can complete without manual plugin recovery. Thanks @vincentkoc. -- OpenAI/Responses: use OpenAI's native `web_search` tool automatically for direct OpenAI Responses models when web search is enabled and no managed search provider is pinned; explicit providers such as Brave keep the managed `web_search` tool. Thanks @steipete. +- OpenAI/Responses: use OpenAI's native `web_search` tool automatically for direct OpenAI Responses models when web search is enabled and no managed search provider is pinned; explicit providers such as Brave keep the managed `web_search` tool. - Models/commands: add `/models add ` so you can register a model from chat and use it without restarting the gateway; keep `/models` as a simple provider browser while adding clearer add guidance and copy-friendly command examples. (#70211) Thanks @Takhoffman. - WhatsApp: add configurable native reply quoting with replyToMode for WhatsApp conversations. Thanks @mcaxtr. - WhatsApp/groups+direct: forward per-group and per-direct `systemPrompt` config into inbound context `GroupSystemPrompt` so configured per-chat behavioral instructions are injected on every turn. Supports `"*"` wildcard fallback and account-scoped overrides under `channels.whatsapp.accounts..{groups,direct}`; account maps fully replace root maps (no deep merge), matching the existing `requireMention` pattern. Closes #7011. (#59553) Thanks @Bluetegu. @@ -557,19 +566,19 @@ Docs: https://docs.openclaw.ai - Providers/Tencent: add the bundled Tencent Cloud provider plugin with TokenHub onboarding, docs, `hy3-preview` model catalog entries, and tiered Hy3 pricing metadata. (#68460) Thanks @JuniperSling. - WeCom: surface the official WeCom channel plugin during setup and refresh its display name and description so onboarding points at the supported bundled channel. Thanks @vincentkoc. - Providers/Amazon Bedrock Mantle: add Claude Opus 4.7 through Mantle's Anthropic Messages route with provider-owned bearer-auth streaming, so the model is actually callable without treating AWS bearer tokens like Anthropic API keys. Thanks @wirjo. -- Providers/GPT-5: move the GPT-5 prompt overlay into the shared provider runtime so compatible GPT-5 models receive the same behavior and heartbeat guidance through OpenAI, OpenRouter, OpenCode, Codex, and other GPT providers; add `agents.defaults.promptOverlays.gpt5.personality` as the global friendly-style toggle while keeping the OpenAI plugin setting as a fallback. Thanks @steipete. +- Providers/GPT-5: move the GPT-5 prompt overlay into the shared provider runtime so compatible GPT-5 models receive the same behavior and heartbeat guidance through OpenAI, OpenRouter, OpenCode, Codex, and other GPT providers; add `agents.defaults.promptOverlays.gpt5.personality` as the global friendly-style toggle while keeping the OpenAI plugin setting as a fallback. - Providers/OpenAI Codex: remove the Codex CLI auth import path from onboarding and provider discovery so OpenClaw no longer copies `~/.codex` OAuth material into agent auth stores; use browser login or device pairing instead. (#70390) Thanks @pashpashpash. - CLI/Claude: default `claude-cli` runs to warm stdio sessions, including custom configs that omit transport fields, and resume from the stored Claude session after Gateway restarts or idle exits. (#69679) Thanks @obviyus. -- Pi/models: update the bundled pi packages to `0.68.1` and let the OpenCode Go catalog come from pi instead of plugin-maintained model aliases, adding the refreshed `opencode-go/kimi-k2.6`, Qwen, GLM, MiMo, and MiniMax entries. Thanks @steipete. +- Pi/models: update the bundled pi packages to `0.68.1` and let the OpenCode Go catalog come from pi instead of plugin-maintained model aliases, adding the refreshed `opencode-go/kimi-k2.6`, Qwen, GLM, MiMo, and MiniMax entries. - Tokenjuice: add bundled native OpenClaw support for tokenjuice as an opt-in plugin that compacts noisy `exec` and `bash` tool results in Pi embedded runs. (#69946) Thanks @vincentkoc. -- ACPX: add an explicit `openClawToolsMcpBridge` option that injects a core OpenClaw MCP server for selected built-in tools, starting with `cron`. Thanks @steipete. +- ACPX: add an explicit `openClawToolsMcpBridge` option that injects a core OpenClaw MCP server for selected built-in tools, starting with `cron`. - CLI/doctor plugins: lazy-load doctor plugin paths and prefer installed plugin `dist/*` runtime entries over source-adjacent JavaScript fallbacks, reducing the measured `doctor --non-interactive` runtime by about 74% while keeping cold doctor startup on built plugin artifacts. (#69840) Thanks @gumadeiras. - CLI/debugging: add an opt-in temporary debug timing helper for local CLI performance investigations, with readable stderr output, JSONL capture, and docs for removing probes before landing fixes. (#70469) Thanks @shakkernerd. -- Docs/i18n: add Thai translation support for the docs site. Thanks @steipete. +- Docs/i18n: add Thai translation support for the docs site. - Providers/OpenAI-compatible: mark known local backends such as vLLM, SGLang, llama.cpp, LM Studio, LocalAI, Jan, TabbyAPI, and text-generation-webui as streaming-usage compatible, so their token accounting no longer degrades to unknown/stale totals. (#68711) Thanks @gaineyllc. - Providers/OpenAI-compatible: recover streamed token usage from llama.cpp-style `timings.prompt_n` / `timings.predicted_n` metadata and sanitize usage counts before accumulation, fixing unknown or stale totals when compatible servers do not emit an OpenAI-shaped `usage` object. (#41056) Thanks @xaeon2026. - Plugins/startup: prefer native Jiti loading for built bundled plugin dist modules on supported runtimes, cutting measured bundled plugin load time by 82-90% while keeping source TypeScript on the transform path. (#69925) Thanks @aauren. -- Plugin SDK/STT: share realtime transcription WebSocket transport and multipart batch transcription form helpers across bundled STT providers, reducing provider plugin boilerplate while preserving proxy capture, reconnects, audio queueing, close flushing, upload filename normalization, and ready handshakes. Thanks @steipete. +- Plugin SDK/STT: share realtime transcription WebSocket transport and multipart batch transcription form helpers across bundled STT providers, reducing provider plugin boilerplate while preserving proxy capture, reconnects, audio queueing, close flushing, upload filename normalization, and ready handshakes. - Plugin SDK/Pi embedded runs: add a bundled-plugin embedded extension factory seam so native plugins can extend Pi embedded runs with async runtime hooks such as `tool_result` handling instead of falling back to the older synchronous persistence path. (#69946) Thanks @vincentkoc. - Codex harness/hooks: route native Codex app-server turns through `before_prompt_build` and emit `before_compaction` / `after_compaction` for native compaction items so prompt and compaction hooks stop drifting from Pi. Thanks @vincentkoc. - Codex harness/plugins: add a bundled-plugin Codex app-server extension seam for async `tool_result` middleware, fire `after_tool_call` for Codex tool runs, and route mirrored Codex transcript writes through `before_message_write` so tool integrations stop diverging from Pi. Thanks @vincentkoc. @@ -581,77 +590,77 @@ Docs: https://docs.openclaw.ai - CLI/Gateway: wait for one-shot gateway RPC clients to finish WebSocket teardown before the CLI process exits, reducing hangs where commands like `openclaw status` or `openclaw version` could finish their work but stay alive until an external timeout killed them (#70691). Thanks @Takhoffman. - Thinking defaults/status: raise the implicit default thinking level for reasoning-capable models from legacy `off`/`low` fallback behavior to a safe provider-supported `medium` equivalent when no explicit config default is set, preserve configured-model reasoning metadata when runtime catalog loading is empty, and make `/status` report the same resolved default as runtime (#70601). Thanks @Takhoffman. -- Gateway/model pricing: fetch OpenRouter and LiteLLM pricing asynchronously at startup and extend catalog fetch timeouts to 30 seconds, reducing noisy timeout warnings during slow upstream responses. Thanks @steipete. +- Gateway/model pricing: fetch OpenRouter and LiteLLM pricing asynchronously at startup and extend catalog fetch timeouts to 30 seconds, reducing noisy timeout warnings during slow upstream responses. - Agents/failover: classify bare undici transport failures (`terminated`, `UND_ERR_SOCKET`, `UND_ERR_CONNECT_TIMEOUT`, body/header timeouts, aborted streams) and pi-ai's openai-codex `Request failed` sentinel as `timeout`, so Cloudflare 502s with empty bodies and mid-response socket resets actually enter the configured fallback chain instead of surfacing as unclassified errors. Fixes #69368. (#69677) Thanks @sk7n4k3d. - Providers/Anthropic Vertex: restore ADC-backed model discovery after the lightweight provider-discovery path by resolving emitted discovery entries, exposing synthetic auth on bootstrap discovery, and honoring copied env snapshots when probing the default GCP ADC path. Fixes #65715. (#65716) Thanks @feiskyer. -- Plugins/install: add newly installed plugin ids to an existing `plugins.allow` list before enabling them, so allowlisted configs load installed plugins after restart. Thanks @steipete. -- Status: show `Fast` in `/status` when fast mode is enabled, including config/default-derived fast mode, and omit it when disabled. Thanks @steipete. +- Plugins/install: add newly installed plugin ids to an existing `plugins.allow` list before enabling them, so allowlisted configs load installed plugins after restart. +- Status: show `Fast` in `/status` when fast mode is enabled, including config/default-derived fast mode, and omit it when disabled. - OpenAI/image generation: detect Azure OpenAI-style image endpoints, use Azure `api-key` auth plus deployment-scoped image URLs, and honor `AZURE_OPENAI_API_VERSION` so image generation and edits work against Azure-hosted OpenAI resources. (#70570) Thanks @zhanggpcsu. - Control UI/chat: include cache-read and cache-write tokens when computing the message footer context percentage, so cached Claude/OpenAI sessions no longer show `0% ctx` while `/status` reports substantial context use. Fixes #70491. (#70532) Thanks @chen-zhang-cs-code. - Models/auth: merge provider-owned default-model additions from `openclaw models auth login` instead of replacing `agents.defaults.models`, so re-authenticating an OAuth provider such as OpenAI Codex no longer wipes other providers' aliases and per-model params. Migrations that must rename keys (Anthropic -> Claude CLI) opt in with `replaceDefaultModels`. Fixes #69414. (#70435) Thanks @neeravmakwana. -- Media understanding/audio: prefer configured or key-backed STT providers before auto-detected local Whisper CLIs, so installed local transcription tools no longer shadow API providers such as Groq/OpenAI in `tools.media.audio` auto mode. Fixes #68727. Thanks @steipete. +- Media understanding/audio: prefer configured or key-backed STT providers before auto-detected local Whisper CLIs, so installed local transcription tools no longer shadow API providers such as Groq/OpenAI in `tools.media.audio` auto mode. Fixes #68727. - Providers/OpenAI: lock the auth picker wording for OpenAI API key, Codex browser login, and Codex device pairing so the setup choices no longer imply a mixed Codex/API-key auth path. (#67848) Thanks @tmlxrd. - Agents/BTW: route `/btw` side questions through provider stream registration with the session workspace, so Ollama provider URL construction and workspace-scoped hooks apply correctly. Fixes #68336. (#70413) Thanks @suboss87. -- Agents/sessions: make session transcript write locks non-reentrant by default, so same-process transcript writers contend unless a helper explicitly opts into nested lock ownership. Thanks @steipete. +- Agents/sessions: make session transcript write locks non-reentrant by default, so same-process transcript writers contend unless a helper explicitly opts into nested lock ownership. - ACPX/probe: expose an optional `probeAgent` plugin config field so the embedded ACP runtime health probe can target a configured agent (for example `opencode` or `claude`) instead of hardcoding `codex`, and stop marking the entire ACP runtime backend unavailable when the default probe agent is simply not installed or not authenticated. (#68409) Thanks @lyfuci. - Memory search: use sqlite-vec KNN for vector recall while preserving full post-filter result limits in multi-model indexes. Fixes #69666. (#69680) Thanks @aalekh-sarvam. - Providers/OpenAI Codex: stop stale per-agent `openai-codex:default` OAuth profiles from shadowing a newer main-agent identity-scoped profile, and let `openclaw doctor` offer the matching cleanup. (#70393) Thanks @pashpashpash. - ACPX: route OpenClaw ACP bridge commands through the MCP-free runtime path even when the command is wrapped with `env`, has bridge flags, or is resumed from persisted session state, so documented `acpx openclaw` setups no longer fail on per-session MCP injection. (#68741) Thanks @alexlomt. - Codex harness: route Codex-tagged MCP tool approval elicitations through OpenClaw plugin approvals, including current empty-schema app-server requests, while leaving generic user-input prompts fail-closed. (#68807) Thanks @kesslerio. - WhatsApp/outbound: hold an in-memory active-delivery claim while a live outbound send is in flight, so a concurrent reconnect drain no longer re-drives the same pending queue entry and duplicates cron sends 7-12x after the 30-minute inbound-silence watchdog fires mid-delivery. Crash-replay of fresh queue entries left behind by a dead process is preserved because the claim is intentionally process-local. Fixes #70386. (#70428) Thanks @neeravmakwana. -- Matrix/commands: keep Matrix DM allowlist state out of room control-command authorization, so trusted DM senders do not accidentally gain room-command access. Thanks @steipete. +- Matrix/commands: keep Matrix DM allowlist state out of room control-command authorization, so trusted DM senders do not accidentally gain room-command access. - Providers/SDK retry: cap long `Retry-After` sleeps in Stainless-based Anthropic/OpenAI model SDKs so 60s+ retry windows surface immediately for OpenClaw failover instead of blocking the run. (#68474) Thanks @jetd1. - Agents/TTS: preserve spoken text in TTS tool results while defusing reply directives in transcript content, so future turns remember voice replies without treating spoken `MEDIA:` or voice tags as delivery metadata. (#68869) Thanks @zqchris. -- Providers/OpenAI: harden Voice Call realtime transcription against OpenAI Realtime session-update drift, forward language and prompt hints, and add live coverage for realtime STT. Thanks @steipete. +- Providers/OpenAI: harden Voice Call realtime transcription against OpenAI Realtime session-update drift, forward language and prompt hints, and add live coverage for realtime STT. - Agents/Pi embedded runs: suppress the "⚠️ Agent couldn't generate a response" warning when the assistant already delivered user-visible content through a messaging tool and the turn ended cleanly (`stopReason=stop`). Real failure modes (tool errors, provider `stopReason=error`, interrupted tool use) still surface the existing "verify before retrying" warning. Fixes #70396. (#70425) Thanks @neeravmakwana. - Gateway/Linux: wrap gateway-managed supervisor, PTY, MCP stdio, and browser child processes in a tiny `/bin/sh` shim that raises the child's own `oom_score_adj` on Linux, so under cgroup memory pressure the kernel prefers transient workers over the long-lived gateway. Opt out with `OPENCLAW_CHILD_OOM_SCORE_ADJ=0`. Fixes #70404. (#70419) Thanks @neeravmakwana. - Providers/Moonshot: stop strict-sanitizing Kimi's native tool_call IDs (shaped like `functions.:`) on the OpenAI-compatible transport, so multi-turn agentic flows through Kimi K2.6 no longer break after 2-3 tool-calling rounds when the serving layer fails to match mangled IDs against the original tool definitions. Adds a `sanitizeToolCallIds` opt-out to the shared `openai-compatible` replay family helper and wires Moonshot to it. Fixes #62319. (#70030) Thanks @LeoDu0314. -- Dependencies/security: override transitive `uuid` to `14.0.0`, clearing the runtime advisory across dependencies. Thanks @steipete. +- Dependencies/security: override transitive `uuid` to `14.0.0`, clearing the runtime advisory across dependencies. - Codex harness: ignore dynamic tool descriptions when deciding whether to reuse a native app-server thread while still fingerprinting tool schemas, so channel-specific copy changes no longer reset otherwise compatible Codex conversations. (#69976) Thanks @chen-zhang-cs-code. -- Codex harness: expose the Codex app-server model catalog in `models list/status`, avoid startup hangs from app-server discovery timeouts, and accept current Codex turn-completion notifications so Docker live gateway turns finish reliably. Thanks @steipete. -- Codex harness: drop invalid legacy app-server `serviceTier` values such as `"priority"` before native thread and turn requests, while keeping supported Codex tiers limited to `"fast"` and `"flex"`. Fixes #64815. Thanks @steipete. +- Codex harness: expose the Codex app-server model catalog in `models list/status`, avoid startup hangs from app-server discovery timeouts, and accept current Codex turn-completion notifications so Docker live gateway turns finish reliably. +- Codex harness: drop invalid legacy app-server `serviceTier` values such as `"priority"` before native thread and turn requests, while keeping supported Codex tiers limited to `"fast"` and `"flex"`. Fixes #64815. - Codex harness: show bounded, sanitized permission target samples in app-server approval prompts, so native permission requests keep their specific hosts, roots, and paths visible without leaking home usernames or URL credentials. (#70340) Thanks @Lucenx9. - Docs/Codex harness: narrow native compaction docs to the current start/completion signals, without promising a readable summary or kept-entry audit list yet. (#69612) Thanks @91wan. - Providers/Amazon Bedrock: use known context-window metadata for discovered models while keeping the unknown-model fallback conservative, so compaction and overflow handling improve for newer Bedrock models without overstating unlisted model limits. Thanks @wirjo. - Providers/Amazon Bedrock Mantle: refresh IAM-backed bearer tokens at runtime instead of baking discovery-time tokens into provider config, so long-lived Mantle sessions keep working after the initial token ages out. Thanks @wirjo. -- Config/includes: write through single-file top-level includes for isolated OpenClaw-owned mutations, so `plugins install` and `plugins update` update an included `plugins.json5` file instead of flattening modular `$include` configs. Fixes #41050 and #66048. Thanks @steipete. -- Config/reload: plan gateway reloads from source-authored config instead of runtime-materialized snapshots, so plugin update writes no longer trigger false restarts from derived provider/plugin config paths. Fixes #68732. Thanks @steipete. -- Plugins/update: skip npm plugin reinstall/config rewrites when the installed version and recorded artifact identity already match the registry target, let bare npm package names resolve back to tracked install records, and point already-installed `plugins install` attempts at `plugins update` / `--force` instead of a hook-pack fallback. Fixes #46955, #67957, and #68073. Thanks @steipete. -- Agents/MCP: keep `mcp.servers` and bundle MCP tools available in Pi embedded runs. Thanks @steipete. +- Config/includes: write through single-file top-level includes for isolated OpenClaw-owned mutations, so `plugins install` and `plugins update` update an included `plugins.json5` file instead of flattening modular `$include` configs. Fixes #41050 and #66048. +- Config/reload: plan gateway reloads from source-authored config instead of runtime-materialized snapshots, so plugin update writes no longer trigger false restarts from derived provider/plugin config paths. Fixes #68732. +- Plugins/update: skip npm plugin reinstall/config rewrites when the installed version and recorded artifact identity already match the registry target, let bare npm package names resolve back to tracked install records, and point already-installed `plugins install` attempts at `plugins update` / `--force` instead of a hook-pack fallback. Fixes #46955, #67957, and #68073. +- Agents/MCP: keep `mcp.servers` and bundle MCP tools available in Pi embedded runs. `coding` and `messaging` sessions while preserving `minimal` profile and `tools.deny: ["bundle-mcp"]` opt-out behavior. Fixes #68875 and #68818. -- Plugins/startup: tolerate transient bundled-channel catalog/metadata drift while auto-enabling configured plugins, so CLI and gateway startup no longer crash when a channel id is known but its display metadata is unavailable. Thanks @steipete. -- CLI/Claude: report CLI-backed reply runs as streaming while Claude/Codex CLI turns are still in flight, so WebChat keeps visible response state until the backend finishes. Fixes #70125. Thanks @steipete. +- Plugins/startup: tolerate transient bundled-channel catalog/metadata drift while auto-enabling configured plugins, so CLI and gateway startup no longer crash when a channel id is known but its display metadata is unavailable. +- CLI/Claude: report CLI-backed reply runs as streaming while Claude/Codex CLI turns are still in flight, so WebChat keeps visible response state until the backend finishes. Fixes #70125. - Slack/streaming: fall back to normal Slack replies for Slack Connect streams rejected before the SDK flushes its local buffer, so short replies no longer disappear or report success before Slack acknowledges delivery. Fixes #70295. (#70370) Thanks @mvanhorn. - Codex harness: rotate the shared app-server websocket client when the configured bearer token changes, so auth-token refreshes reconnect with the new `Authorization` header instead of reusing a stale socket. (#70328) Thanks @Lucenx9. -- Channels/sandbox: derive runtime policy keys for external direct messages that share the main conversation, so sandbox/tool policy no longer treats channel-originated DMs as local main-session runs. Thanks @steipete. -- Config/models: merge provider-scoped model allowlist updates and protect model/provider map writes from accidental full replacement, adding `config set --merge` for additive updates and `--replace` for intentional clobbers. Fixes #65920, #68392, and #68653. Thanks @steipete. +- Channels/sandbox: derive runtime policy keys for external direct messages that share the main conversation, so sandbox/tool policy no longer treats channel-originated DMs as local main-session runs. +- Config/models: merge provider-scoped model allowlist updates and protect model/provider map writes from accidental full replacement, adding `config set --merge` for additive updates and `--replace` for intentional clobbers. Fixes #65920, #68392, and #68653. - Agents/Pi auth: preserve AWS SDK-authenticated Bedrock runs for IMDS and task-role setups, clear stale refresh timers on sentinel fallback, and log unexpected runtime-auth prep failures instead of silently leaving the provider unauthenticated. Thanks @wirjo. -- Config/gateway: restore last-known-good config on critical clobber signatures such as missing metadata, missing `gateway.mode`, or sharp size drops, preventing gateway crash loops when a valid backup exists. Fixes #70336. Thanks @steipete. -- Config/gateway: recover configs accidentally prefixed with non-JSON output during gateway startup or `openclaw doctor --fix`, preserving the clobbered file as a backup while leaving normal config reads read-only. Thanks @steipete. +- Config/gateway: restore last-known-good config on critical clobber signatures such as missing metadata, missing `gateway.mode`, or sharp size drops, preventing gateway crash loops when a valid backup exists. Fixes #70336. +- Config/gateway: recover configs accidentally prefixed with non-JSON output during gateway startup or `openclaw doctor --fix`, preserving the clobbered file as a backup while leaving normal config reads read-only. - Agents/GitHub Copilot: normalize connection-bound Responses item IDs in the Copilot provider wrapper so replayed histories no longer fail after the upstream connection changes. (#69362) Thanks @Menci. - Pi embedded runs: pass real built-in tools into Pi session creation and then narrow active tool names after custom tool registration, so the runner and compaction paths compile cleanly and keep OpenClaw-managed custom tool allowlists without feeding string arrays into `createAgentSession`. Thanks @vincentkoc. - Agents/OpenAI websocket: route native OpenAI websocket metadata and session-header decisions through the shared endpoint classifier so local mocks and custom `models.providers.openai.baseUrl` endpoints stay out of the native OpenAI path consistently across embedded-runner and websocket transport code. Thanks @vincentkoc. -- Cron/MCP: retire bundled MCP runtimes through one shared cleanup path for isolated cron run ends, persistent cron session rollover, and direct cron `deleteAfterRun` fallback cleanup. Fixes #69145, #68623, and #68827. Thanks @steipete. +- Cron/MCP: retire bundled MCP runtimes through one shared cleanup path for isolated cron run ends, persistent cron session rollover, and direct cron `deleteAfterRun` fallback cleanup. Fixes #69145, #68623, and #68827. - Cron: default legacy persisted jobs that are missing `sessionTarget` during store load and report a clear validation error if a malformed job still reaches execution, preventing undefined `startsWith` crashes on scheduled ticks. Fixes #70360 and #63383. (#70367) Thanks @mvanhorn. -- MCP/gateway: tear down stdio MCP process trees on transport close and dispose bundled MCP runtimes during session delete/reset, preventing orphaned wrapper/server processes from accumulating. Fixes #68809 and #69465. Thanks @steipete. -- Agents/MCP: retire bundled MCP runtimes after completed one-shot subagent cleanup and nested `sessions_send` steps, while keeping persistent subagent sessions warm. Thanks @steipete. -- Config: render validation warnings with real line breaks instead of a literal `\n` sequence in CLI/audit output. Fixes #70140. Thanks @steipete. -- Cron/doctor: repair malformed persisted cron job IDs through `openclaw doctor`, including legacy `jobId`, non-string `id`, and missing `id` rows, so `cron list` no longer needs display-layer coercion for corrupt store data. Fixes #70128. Thanks @steipete. +- MCP/gateway: tear down stdio MCP process trees on transport close and dispose bundled MCP runtimes during session delete/reset, preventing orphaned wrapper/server processes from accumulating. Fixes #68809 and #69465. +- Agents/MCP: retire bundled MCP runtimes after completed one-shot subagent cleanup and nested `sessions_send` steps, while keeping persistent subagent sessions warm. +- Config: render validation warnings with real line breaks instead of a literal `\n` sequence in CLI/audit output. Fixes #70140. +- Cron/doctor: repair malformed persisted cron job IDs through `openclaw doctor`, including legacy `jobId`, non-string `id`, and missing `id` rows, so `cron list` no longer needs display-layer coercion for corrupt store data. Fixes #70128. - Discord: normalize prefixed channel targets only at the thread-binding API boundary, so `sessions_spawn({ runtime: "acp", thread: true })` can create child threads from Discord channels without breaking current-channel ACP bindings. (#68034) Thanks @Zetarcos. - Discord: harden inbound thread metadata handling against partial Carbon channel getters, so non-command thread messages and queued jobs no longer crash when `name`, `parentId`, `parent`, or `ownerId` requires fetched raw data. Thanks @neeravmakwana. -- Discord: let `message` tool reactions resolve `user:` DM targets and preserve `channels.discord.guilds..channels..requireMention: false` during reply-stage activation fallback. Fixes #70165 and #69441. Thanks @steipete. -- Plugins/startup: pre-normalize and cache Jiti alias maps before creating plugin loaders, so module-scoped loader filenames do not reintroduce per-plugin alias-normalization startup cost. Fixes #70186. Thanks @steipete. +- Discord: let `message` tool reactions resolve `user:` DM targets and preserve `channels.discord.guilds..channels..requireMention: false` during reply-stage activation fallback. Fixes #70165 and #69441. +- Plugins/startup: pre-normalize and cache Jiti alias maps before creating plugin loaders, so module-scoped loader filenames do not reintroduce per-plugin alias-normalization startup cost. Fixes #70186. - ACP/Codex: run the bundled Codex ACP harness with an isolated `CODEX_HOME` and avoid writing incomplete ChatGPT auth bridge files, so Codex ACP sessions no longer clobber the user's real Codex CLI auth. Fixes #70234. Thanks @Lonobers88. -- Gateway/client: keep long-running RPCs such as ACP `agent.wait` calls in charge of their own timeout instead of closing the websocket on a missed app-level tick while work is still pending. Thanks @steipete. +- Gateway/client: keep long-running RPCs such as ACP `agent.wait` calls in charge of their own timeout instead of closing the websocket on a missed app-level tick while work is still pending. - Telegram/webhooks: lower the grammY webhook callback timeout to 5s so Telegram gets an early 200 response instead of retrying long-running updates as read timeouts. (#70146) Thanks @friday-james. - Telegram/polling: rebuild the polling HTTP transport after `getUpdates` 409 conflicts, so retries use a fresh TCP connection instead of looping on a Telegram-terminated keep-alive socket. (#69873) Thanks @hclsys. -- Media delivery: strip persisted base64 audio payloads from webchat history, resolve stored `media://inbound/*` attachments before local-root checks, suppress duplicate Telegram voice/audio sends when TTS emits the same media twice, and support custom image-model IDs that already include their provider prefix. Thanks @steipete. +- Media delivery: strip persisted base64 audio payloads from webchat history, resolve stored `media://inbound/*` attachments before local-root checks, suppress duplicate Telegram voice/audio sends when TTS emits the same media twice, and support custom image-model IDs that already include their provider prefix. - Slack/files: resolve `downloadFile` bot tokens from the runtime config when callers provide `cfg` without an explicit token or prebuilt client, preserving cfg-only file downloads outside the action runtime path. (#70160) Thanks @martingarramon. - Slack/HTTP: dispatch registered Request URL webhooks through the same handler registry used by Slack monitor setup, so HTTP-mode Slack events no longer 404 after successful route registration. (#70275) Thanks @FroeMic. - Slack/runtime bindings: route focused Slack thread replies through their bound ACP session instead of preparing replies against the default agent shell. Fixes #67739. Thanks @Frankla20. - CLI/Claude: keep stored Claude CLI sessions through OAuth refresh-token rotation by keying auth epochs on stable account identity instead of mutable OAuth token material. (#70452) Thanks @obviyus. -- CLI/Claude: verify stored Claude CLI session ids have a readable project transcript before resuming, clearing phantom bindings with `reason=transcript-missing` instead of silently starting fresh under `--resume`. Fixes #70177. Thanks @steipete. +- CLI/Claude: verify stored Claude CLI session ids have a readable project transcript before resuming, clearing phantom bindings with `reason=transcript-missing` instead of silently starting fresh under `--resume`. Fixes #70177. - CLI sessions: persist CLI session clearing through the atomic session-store merge path, so expired Claude/Codex CLI bindings are actually removed before retrying without the stale session id. (#70298) Thanks @HFConsultant. - ACP/sessions_spawn: honor explicit `model` overrides for ACP child sessions instead of silently falling back to the target agent default model. (#70210) Thanks @felix-miao. - Diffs/viewer: re-read remote viewer access policy from live runtime config on each request, so toggling `plugins.entries.diffs.config.security.allowRemoteViewer` closes proxied viewer access immediately instead of waiting for a restart. Thanks @vincentkoc. @@ -666,19 +675,19 @@ Docs: https://docs.openclaw.ai - Amazon Bedrock: re-read live discovery and guardrail plugin config, so toggling `plugins.entries.amazon-bedrock.config.discovery` or `plugins.entries.amazon-bedrock.config.guardrail` takes effect without a restart. Thanks @vincentkoc. - Codex: re-read the plugin discovery config from the live runtime snapshot, so toggling `plugins.entries.codex.config.discovery` takes effect without a restart. Thanks @vincentkoc. - Agents/subagents: drop bare `NO_REPLY` from the parent turn when the session still has pending spawned children, so direct-conversation surfaces such as Telegram DMs no longer rewrite the sentinel into visible fallback chatter while waiting for the child completion event. (#69942) Thanks @neeravmakwana. -- Plugins/install: keep bundled plugin dependencies off npm install while repairing them when plugins activate from a packaged install, including Feishu/Lark, Browser, and direct bundled channel setup-entry loads. Thanks @steipete. -- CLI/channels: skip and cache bundled channel plugin, setup, and secrets load failures during read-only discovery, so one broken unused bundled channel cannot crash `openclaw status` or bootstrap secret scans. Thanks @steipete. -- Memory/LanceDB: retry initialization after a failed LanceDB load and report unsupported Intel macOS native runtime clearly instead of caching the failure or repeatedly attempting an install that cannot work. Thanks @steipete. +- Plugins/install: keep bundled plugin dependencies off npm install while repairing them when plugins activate from a packaged install, including Feishu/Lark, Browser, and direct bundled channel setup-entry loads. +- CLI/channels: skip and cache bundled channel plugin, setup, and secrets load failures during read-only discovery, so one broken unused bundled channel cannot crash `openclaw status` or bootstrap secret scans. +- Memory/LanceDB: retry initialization after a failed LanceDB load and report unsupported Intel macOS native runtime clearly instead of caching the failure or repeatedly attempting an install that cannot work. - CLI/Claude: hash only static extra system prompt parts when deciding whether to reuse a CLI session, so per-message inbound metadata no longer resets Claude CLI conversations on every turn. (#70122) Thanks @zijunl. - Hooks/Slack: standardize shared message hook routing fields (`threadId` / `replyToId`) and stop Slack outbound delivery from re-running `message_sending` inside the channel adapter, so plugins like thread-ownership make one outbound routing decision per reply. Thanks @vincentkoc. - Auto-reply/media: share one run-scoped reply media context between streamed block delivery and final payload filtering, so a local `MEDIA:` attachment is staged once and duplicate media sends are suppressed reliably. (#68111) Thanks @ayeshakhalid192007-dev. - Plugins/gateway hooks: expose startup config, workspace dir, and a live cron getter on the typed `gateway_start` hook, and move memory-core managed dreaming off the internal `gateway:startup` bridge so cron reconciliation stays on the public plugin hook path. Thanks @vincentkoc. -- Plugins/config: read plugin trust decisions from the source config snapshot when a resolved runtime snapshot is active, so `plugins.allow` remains enforced and `doctor`/gateway startup no longer warn that the allowlist is empty when it is configured. Fixes #70161. Also fixes #70141. Thanks @steipete. +- Plugins/config: read plugin trust decisions from the source config snapshot when a resolved runtime snapshot is active, so `plugins.allow` remains enforced and `doctor`/gateway startup no longer warn that the allowlist is empty when it is configured. Fixes #70161. Also fixes #70141. - Agents/openai-completions: enable malformed streamed tool-call argument repair for self-hosted OpenAI-compatible backends such as Kimi/SGLang, so fragmented tool-call arguments no longer reach tools as empty or unusable objects. Fixes #69672. (#70294) Thanks @MonkeyLeeT. - Gateway/restart: preserve group and channel chat context when resuming an agent turn after a Gateway restart, so continuation replies keep the same prompt, routing, and tool-status behavior as the original conversation. Thanks @obviyus. - Gateway/pairing: shared-secret loopback CLI clients now silently auto-approve `metadata-upgrade` pairing (platform / device family refresh) instead of being disconnected with `1008 pairing required`. This matches the scope-upgrade and role-upgrade behavior added in #69431 and unblocks non-interactive CLI automation when a paired-device record has a stale platform string (e.g. device key replicated across hosts, install migrated between OSes, or platform-string format changed between OpenClaw versions). Browser / Control-UI clients keep the existing approval-required flow for metadata changes (#70224). Thanks @perlowja. -- Gateway/pairing: treat any forwarded-header evidence (`Forwarded`, `X-Forwarded-*`, or `X-Real-IP`) as proxied WebSocket traffic before pairing locality checks, so reverse-proxy topologies cannot use the loopback shared-secret helper auto-pairing path. Thanks @steipete. -- Agents/OpenAI: treat exact `NO_REPLY` assistant output as a deliberate silent reply in embedded runs, so GPT-5.4 turns with signed reasoning plus a silent final no longer surface a false incomplete-turn error. Thanks @steipete. +- Gateway/pairing: treat any forwarded-header evidence (`Forwarded`, `X-Forwarded-*`, or `X-Real-IP`) as proxied WebSocket traffic before pairing locality checks, so reverse-proxy topologies cannot use the loopback shared-secret helper auto-pairing path. +- Agents/OpenAI: treat exact `NO_REPLY` assistant output as a deliberate silent reply in embedded runs, so GPT-5.4 turns with signed reasoning plus a silent final no longer surface a false incomplete-turn error. - Auto-reply/streaming: preserve streamed reply directives through chunk boundaries and phase-aware `final_answer` delivery, so split `MEDIA:` lines, voice tags, and reply targets reach channel delivery instead of leaking as text or being dropped. (#70243) Thanks @zqchris. - Anthropic/Claude Opus 4.7: normalize Opus 4.7 and `claude-cli` Opus 4.7 variants to a 1M context window in resolved runtime metadata and active-agent status/context reporting, so they no longer inherit the stale 200k fallback. Thanks @BunsDev. - Gateway/pairing webchat: render `/pair qr` replies as structured media instead of raw markdown text, preserve inline reply threading and silent-control handling on media replies, avoid persisting sensitive QR images into transcript history, and keep local webchat media embedding behind internal-only trust markers. (#70047) Thanks @BunsDev. @@ -688,11 +697,11 @@ Docs: https://docs.openclaw.ai - WhatsApp/login QR: propagate refreshed QR images through `web.login.wait` consumers and compare against each caller's current QR instead of shared waiter state, so rotated QR codes stay synchronized across Control UI, macOS, and concurrent waiters. (#70009) Thanks @BunsDev. - Codex harness: add an explicit Guardian mode for Codex app-server approvals, plus a Docker live probe for approved and ask-back Guardian decisions, while keeping default app-server runs unchained for unattended local heartbeats. The legacy `OPENCLAW_CODEX_APP_SERVER_GUARDIAN` shortcut is removed; use plugin config `appServer.mode: "guardian"` or `OPENCLAW_CODEX_APP_SERVER_MODE=guardian`. Thanks @pashpashpash. - OpenAI/Responses: keep embedded OpenAI Responses runs on HTTP when `models.providers.openai.baseUrl` points at a local mock or other non-public endpoint, so mocked/custom endpoints no longer drift onto the hardcoded public websocket transport. (#69815) Thanks @vincentkoc. -- Channels/config: require resolved runtime config on channel send/action/client helpers and block runtime helper `loadConfig()` calls, so SecretRefs are resolved at startup/boundaries instead of being re-read during sends. Thanks @steipete. +- Channels/config: require resolved runtime config on channel send/action/client helpers and block runtime helper `loadConfig()` calls, so SecretRefs are resolved at startup/boundaries instead of being re-read during sends. - Discord: pass resolved runtime config through guild and moderation action helpers, so thread-originated Discord commands can run channel, member, role, and guild actions without falling back to runtime config reads. (#70215) Thanks @szponeczek. -- CLI/channels: preserve bundled setup promotion metadata when a loaded partial channel plugin omits it, so adding a non-default account still moves legacy single-account fields such as Telegram `streaming` into `accounts.default`. Thanks @steipete. -- Telegram: keep the sent-message ownership cache isolated per configured session store, so own-message reaction filtering remains correct with custom `session.store` paths. Thanks @steipete. -- Security/update: fail closed when exact pinned npm plugin or hook-pack updates detect integrity drift, and expose aborted plugin drift details in `openclaw update --json`. Thanks @steipete. +- CLI/channels: preserve bundled setup promotion metadata when a loaded partial channel plugin omits it, so adding a non-default account still moves legacy single-account fields such as Telegram `streaming` into `accounts.default`. +- Telegram: keep the sent-message ownership cache isolated per configured session store, so own-message reaction filtering remains correct with custom `session.store` paths. +- Security/update: fail closed when exact pinned npm plugin or hook-pack updates detect integrity drift, and expose aborted plugin drift details in `openclaw update --json`. - Ollama: forward OpenClaw thinking control to native `/api/chat` requests as top-level `think`, so `/think off` and `openclaw agent --thinking off` suppress thinking on models such as qwen3 instead of idling until the watchdog fires. Fixes #69902. (#69967) Thanks @WZH8898. - Memory-core/dreaming: suppress the startup-only managed dreaming cron unavailable warning when the cron service is still attaching, while preserving the runtime warning if cron genuinely remains unavailable. Fixes #69939. (#69941) Thanks @Sanjays2402. - Mattermost: suppress reasoning-only payloads even when they arrive as blockquoted `> Reasoning:` text, preventing `/reasoning on` from leaking thinking into channel posts. (#69927) Thanks @lawrence3699. @@ -703,9 +712,9 @@ Docs: https://docs.openclaw.ai - Browser/Chrome MCP: propagate click timeouts and abort signals to existing-session actions so a stuck click fails fast and reconnects instead of poisoning the browser tool until gateway restart. (#63524) Thanks @dongseok0. - Amazon Bedrock/prompt caching: resolve opaque application inference profile targets before injecting Bedrock cache points, require every routed target to support explicit cache points, and retry transient profile lookups instead of caching a false negative for the rest of the process. (#69953) Thanks @anirudhmarc and @vincentkoc. - Gateway/channel health: base stale-socket recovery on provider-proven transport activity instead of inbound app-event freshness, preventing quiet Slack, Discord, Telegram, Matrix, and local-style channels from being restarted solely because no user traffic arrived. (#69833) Thanks @bek91. -- OpenCode Go: canonicalize stale bundled `opencode-go` base URLs from `/go` or `/go/v1` to `/zen/go` or `/zen/go/v1`, so older generated model metadata stops hitting the 404 HTML endpoint. (#69898) Thanks @steipete. -- CLI/channels: honor `channels..enabled=false` as a hard read-only presence opt-out, so env vars, manifest env vars, or stale persisted auth state no longer make disabled channel plugins appear in status, doctor, or setup-only discovery. Thanks @steipete. -- Channels/preview streaming: centralize draft-preview finalization so Slack, Discord, Mattermost, and Matrix no longer flush temporary preview messages for media/error finals, and preserve first-reply threading for normal fallback delivery. Thanks @steipete. +- OpenCode Go: canonicalize stale bundled `opencode-go` base URLs from `/go` or `/go/v1` to `/zen/go` or `/zen/go/v1`, so older generated model metadata stops hitting the 404 HTML endpoint. (#69898). +- CLI/channels: honor `channels..enabled=false` as a hard read-only presence opt-out, so env vars, manifest env vars, or stale persisted auth state no longer make disabled channel plugins appear in status, doctor, or setup-only discovery. +- Channels/preview streaming: centralize draft-preview finalization so Slack, Discord, Mattermost, and Matrix no longer flush temporary preview messages for media/error finals, and preserve first-reply threading for normal fallback delivery. - Discord: keep slash command follow-up chunks ephemeral when the command is configured for ephemeral replies, so long `/status` output no longer leaks fallback model or runtime details into the public channel. (#69869) thanks @gumadeiras. - Gateway/session history: re-check current auth and `chat.history` scope before later SSE keepalives and transcript updates, so active session-history streams close before delivering post-revocation events (#70237). Thanks @drobison00. - Plugins/discovery: reject package plugin source entries that escape the package directory before explicit runtime entries or inferred built JavaScript peers can be used. (#69868) thanks @gumadeiras. @@ -740,10 +749,10 @@ Docs: https://docs.openclaw.ai ### Changes -- OpenAI/images: default the bundled image-generation provider and live media smoke tests to `gpt-image-2`, and advertise the newer 2K/4K OpenAI size hints in image-generation docs and tool metadata. Thanks @steipete. -- Plugins/skills: add the Skill Workshop plugin, which captures reusable workflow corrections as pending or auto-applied workspace skills, runs threshold-based reviewer passes for stronger completion bias on reusable procedures, quarantines unsafe proposals, and refreshes skill availability after safe writes. Thanks @steipete. -- Plugin SDK/channels: add presentation and skills runtime contracts, decouple channel presentation rendering, and document message presentation cards so plugins can own richer interactive surfaces without channel-specific glue. Thanks @steipete. -- Fireworks/models: add Kimi K2.6 (`fireworks/accounts/fireworks/models/kimi-k2p6`) to the bundled catalog and live-model priority list, while keeping Kimi thinking disabled for Fireworks K2.6 requests. Thanks @steipete. +- OpenAI/images: default the bundled image-generation provider and live media smoke tests to `gpt-image-2`, and advertise the newer 2K/4K OpenAI size hints in image-generation docs and tool metadata. +- Plugins/skills: add the Skill Workshop plugin, which captures reusable workflow corrections as pending or auto-applied workspace skills, runs threshold-based reviewer passes for stronger completion bias on reusable procedures, quarantines unsafe proposals, and refreshes skill availability after safe writes. +- Plugin SDK/channels: add presentation and skills runtime contracts, decouple channel presentation rendering, and document message presentation cards so plugins can own richer interactive surfaces without channel-specific glue. +- Fireworks/models: add Kimi K2.6 (`fireworks/accounts/fireworks/models/kimi-k2p6`) to the bundled catalog and live-model priority list, while keeping Kimi thinking disabled for Fireworks K2.6 requests. - Onboard/wizard: simplify the security disclaimer copy, and switch remaining onboarding pickers with long dynamic option lists to searchable autocompletes for search providers, plugin configuration, and model provider filtering (#69760). Thanks @Patrick-Erichsen. - Channels/preview streaming: stream tool-progress updates into live preview edits for Discord, Slack, and Telegram so in-flight replies show incremental tool state in the same preview message before finalization. (#69611) Thanks @thewilloftheshadow. - Ollama/onboard: populate the cloud-only model list from `ollama.com/api/tags`, cap the discovered list at 500, and fall back to static suggestions when ollama.com is unavailable. (#68463) Thanks @BruceMacD. @@ -755,15 +764,15 @@ Docs: https://docs.openclaw.ai ### Fixes - Agents/ACP: skip the `sessions_send` A2A ping-pong flow when a parent sends to its own background oneshot ACP child, preventing parent/child echo loops while preserving normal A2A delivery for non-parent senders. (#69817) Thanks @scotthuang. -- Image generation: log failed provider/model candidates at warn level before automatic provider fallback, so OpenAI image failures are visible in the gateway log even when a later provider succeeds. Thanks @steipete. -- Agents/subagents: stop terminal failed subagent runs from freezing or announcing captured reply text, so failover-exhausted runs report a clean failure instead of replaying stale assistant/tool output. Thanks @steipete. -- Security/external content: strip common self-hosted LLM chat-template special-token literals, including Qwen/ChatML, Llama, Gemma, Mistral, Phi, and GPT-OSS markers, from wrapped external content and metadata, preventing tokenizer-layer role-boundary spoofing against OpenAI-compatible backends that preserve special tokens in user text. Thanks @steipete. +- Image generation: log failed provider/model candidates at warn level before automatic provider fallback, so OpenAI image failures are visible in the gateway log even when a later provider succeeds. +- Agents/subagents: stop terminal failed subagent runs from freezing or announcing captured reply text, so failover-exhausted runs report a clean failure instead of replaying stale assistant/tool output. +- Security/external content: strip common self-hosted LLM chat-template special-token literals, including Qwen/ChatML, Llama, Gemma, Mistral, Phi, and GPT-OSS markers, from wrapped external content and metadata, preventing tokenizer-layer role-boundary spoofing against OpenAI-compatible backends that preserve special tokens in user text. - npm/install: mirror the `node-domexception` alias into root `package.json` `overrides`, so npm installs stop surfacing the deprecated `google-auth-library -> gaxios -> node-fetch -> fetch-blob -> node-domexception` chain pulled through Pi/Google runtime deps. Thanks @vincentkoc. - Auth/commands: require owner identity (an owner-candidate match or internal `operator.admin`) for owner-enforced commands instead of treating wildcard channel `allowFrom` or empty owner-candidate lists as sufficient, so non-owner senders can no longer reach owner-only commands through a permissive fallback when `enforceOwnerForCommands=true` and `commands.ownerAllowFrom` is unset. (#69774) Thanks @drobison00. - Control UI/CSP: tighten `img-src` to `'self' data:` only, and make Control UI avatar helpers drop remote `http(s)` and protocol-relative URLs so the UI falls back to the built-in logo/badge instead of issuing arbitrary remote image fetches. Same-origin avatar routes (relative paths) and `data:image/...` avatars still render. (#69773) Thanks @drobison00. - CLI/channels: keep `status`, `health`, `channels list`, and `channels status` on read-only channel metadata when Telegram, Slack, Discord, or third-party channel plugins are configured, avoiding full bundled plugin runtime imports on those cold paths. Fixes #69042. (#69479) Thanks @gumadeiras. - Synology Chat: validate outbound webhook `file_url` values against the shared SSRF policy before forwarding to the NAS, rejecting malformed URLs, non-`http(s)` schemes, and private/blocked network targets so the NAS cannot be used as a confused deputy to fetch internal addresses. (#69784) Thanks @eleqtrizit. -- LINE: validate outbound media URLs against the shared public-network guard before handing them to LINE, preserving arbitrary public HTTPS media while rejecting loopback, link-local, and private-network targets. Thanks @steipete. +- LINE: validate outbound media URLs against the shared public-network guard before handing them to LINE, preserving arbitrary public HTTPS media while rejecting loopback, link-local, and private-network targets. - Gateway/Control UI: require gateway auth on the Control UI avatar route (`GET /avatar/` and `?meta=1` metadata) when auth is configured, matching the sibling assistant-media route, and propagate the existing gateway token through the UI avatar fetch (bearer header + authenticated blob URL) so authenticated dashboards still load local avatars. (#69775) Thanks @drobison00. - Google Chat/auth: replace the Google auth `gaxios` shim with a scoped SSRF-guarded transport, validate service-account auth endpoints against trusted Google URLs, and let the plugin own its staged `gaxios` auth runtime instead of patching process-wide globals or the root CLI startup path. Thanks @vincentkoc. - Exec/allowlist: reject POSIX parameter expansion forms such as `$VAR`, `$?`, `$$`, `$1`, and `$@` inside unquoted heredocs during shell approval analysis, so these heredocs no longer pass allowlist review as plain text. (#69795) Thanks @drobison00. @@ -771,10 +780,10 @@ Docs: https://docs.openclaw.ai - GitHub Copilot: update the default Opus model from `claude-opus-4.6` to `claude-opus-4.7` after GitHub removed Copilot support for 4.6. (#69818) Thanks @shakkernerd. - OpenShell: pin host-side sandbox writes under the mounted root so symlink-parent rebinds cannot redirect `writeFile` outside the workspace during local mirror updates. (#69797) Thanks @drobison00. - Ollama/media understanding: register Ollama as an image-capable media-understanding provider so `agents.defaults.imageModel.primary` values like `ollama/qwen2.5vl:7b` route through the Ollama plugin instead of failing as unknown models. (#69816) Thanks @soloclz. -- CLI/media understanding: make `openclaw infer image describe --model ` execute the explicit image model instead of skipping description when that model supports native vision (#69816). Thanks @steipete. -- Usage/providers: keep plugin-owned usage auth enabled when manifest-declared provider auth env vars such as `MINIMAX_CODE_PLAN_KEY` are present, so `/usage` can resolve MiniMax billing credentials through the provider plugin. Thanks @steipete. +- CLI/media understanding: make `openclaw infer image describe --model ` execute the explicit image model instead of skipping description when that model supports native vision (#69816). +- Usage/providers: keep plugin-owned usage auth enabled when manifest-declared provider auth env vars such as `MINIMAX_CODE_PLAN_KEY` are present, so `/usage` can resolve MiniMax billing credentials through the provider plugin. - Tlon/uploads: route both hosted Memex upload targets and custom-S3 presigned upload URLs through the shared SSRF guard so blocked private or loopback destinations fail before upload, while public upload URLs continue through the existing hosted upload flow. (#69794) Thanks @drobison00. -- Channels/thread routing: keep outbound replies in existing Slack, Mattermost, Matrix, Telegram, Discord, and QA-channel thread sessions by sharing the Plugin SDK thread-aware route builder across bundled plugins. Thanks @steipete. +- Channels/thread routing: keep outbound replies in existing Slack, Mattermost, Matrix, Telegram, Discord, and QA-channel thread sessions by sharing the Plugin SDK thread-aware route builder across bundled plugins. - Agents/replay: normalize restored assistant text content before provider replay and prompt submission, so legacy or repaired sessions no longer crash on `assistantMsg.content.flatMap`. (#69850) Thanks @fuller-stack-dev. ## 2026.4.20 @@ -782,7 +791,7 @@ Docs: https://docs.openclaw.ai ### Changes - Onboard/wizard: restyle the setup security disclaimer with a single yellow warning banner, section headings and bulleted checklists, and un-dim the note body so key guidance is easy to scan; add a loading spinner during the initial model catalog load so the wizard no longer goes blank while it runs; add an "API key" placeholder to provider API key prompts. (#69553) Thanks @Patrick-Erichsen. -- Agents/prompts: strengthen the default system prompt and OpenAI GPT-5 overlay with clearer completion bias, live-state checks, weak-result recovery, and verification-before-final guidance. Thanks @steipete. +- Agents/prompts: strengthen the default system prompt and OpenAI GPT-5 overlay with clearer completion bias, live-state checks, weak-result recovery, and verification-before-final guidance. - Models/costs: support tiered model pricing from cached catalogs and configured models, and include bundled Moonshot Kimi K2.6/K2.5 cost estimates for token-usage reports. (#67605) Thanks @sliverp. - Sessions/Maintenance: enforce the built-in entry cap and age prune by default, and prune oversized stores at load time so accumulated cron/executor session backlogs cannot OOM the gateway before the write path runs. (#69404) Thanks @bobrenze-bot. - Plugins/tests: reuse plugin loader alias and Jiti config resolution across repeated same-context loads, reducing import-heavy test overhead. (#69316) Thanks @amknight. @@ -798,20 +807,20 @@ Docs: https://docs.openclaw.ai ### Fixes -- Exec/YOLO: stop rejecting gateway-host exec in `security=full` plus `ask=off` mode via the Python/Node script preflight hardening path, so promptless YOLO exec once again runs direct interpreter stdin and heredoc forms such as `node <<'NODE' ... NODE`. Thanks @steipete. +- Exec/YOLO: stop rejecting gateway-host exec in `security=full` plus `ask=off` mode via the Python/Node script preflight hardening path, so promptless YOLO exec once again runs direct interpreter stdin and heredoc forms such as `node <<'NODE' .. NODE`. - OpenAI Codex: normalize legacy `openai-completions` transport overrides on default OpenAI/Codex and GitHub Copilot-compatible hosts back to the native Codex Responses transport while leaving custom proxies untouched. (#45304, #42194) Thanks @dyss1992 and @DeadlySilent. -- Anthropic/plugins: scope Anthropic `api: "anthropic-messages"` defaulting to Anthropic-owned providers, so `openai-codex` and other providers without an explicit `api` no longer get rewritten to the wrong transport. Fixes #64534. Thanks @steipete. +- Anthropic/plugins: scope Anthropic `api: "anthropic-messages"` defaulting to Anthropic-owned providers, so `openai-codex` and other providers without an explicit `api` no longer get rewritten to the wrong transport. Fixes #64534. - fix(qqbot): add SSRF guard to direct-upload URL paths in uploadC2CMedia and uploadGroupMedia [AI-assisted]. (#69595) Thanks @pgondhi987. - fix(gateway): enforce allowRequestSessionKey gate on template-rendered mapping sessionKeys. (#69381) Thanks @pgondhi987. -- Browser/Chrome MCP: surface `DevToolsActivePort` attach failures as browser-connectivity errors instead of a generic "waiting for tabs" timeout, and point signed-out fallbacks toward the managed `openclaw` profile. Thanks @steipete. +- Browser/Chrome MCP: surface `DevToolsActivePort` attach failures as browser-connectivity errors instead of a generic "waiting for tabs" timeout, and point signed-out fallbacks toward the managed `openclaw` profile. - Webchat/images: treat inline image attachments as media for empty-turn gating while still ignoring metadata-only blank turns. (#69474) Thanks @Jaswir. -- Discord/think: only show `adaptive` in `/think` autocomplete for provider/model pairs that actually support provider-managed adaptive thinking, so GPT/OpenAI models no longer advertise an Anthropic-only option. Thanks @steipete. -- Thinking: only expose `max` for models that explicitly support provider max reasoning, and remap stored `max` settings to the largest supported thinking mode when users switch to another model. Thanks @steipete. +- Discord/think: only show `adaptive` in `/think` autocomplete for provider/model pairs that actually support provider-managed adaptive thinking, so GPT/OpenAI models no longer advertise an Anthropic-only option. +- Thinking: only expose `max` for models that explicitly support provider max reasoning, and remap stored `max` settings to the largest supported thinking mode when users switch to another model. - Gateway/usage: bound the cost usage cache with FIFO eviction so date/range lookups cannot grow unbounded. (#68842) Thanks @Feelw00. -- OpenAI/Responses: resolve `/think` levels against each GPT model's supported reasoning efforts so `/think off` no longer becomes high reasoning or sends unsupported `reasoning.effort: "none"` payloads. Thanks @steipete. +- OpenAI/Responses: resolve `/think` levels against each GPT model's supported reasoning efforts so `/think off` no longer becomes high reasoning or sends unsupported `reasoning.effort: "none"` payloads. - Lobster/TaskFlow: allow managed approval resumes to use `approvalId` without a resume token, and persist that id in approval wait state. (#69559) Thanks @kirkluokun. -- Plugins/startup: install bundled runtime dependencies into each plugin's own runtime directory, reuse source-checkout repair caches after rebuilds, and log only packages that were actually installed so repeated Gateway starts stay quiet once deps are present. Thanks @steipete. -- Plugins/startup: ignore pnpm's `npm_execpath` when repairing bundled plugin runtime dependencies and skip workspace-only package specs so npm-only install flags or local workspace links do not break packaged plugin startup. Thanks @steipete. +- Plugins/startup: install bundled runtime dependencies into each plugin's own runtime directory, reuse source-checkout repair caches after rebuilds, and log only packages that were actually installed so repeated Gateway starts stay quiet once deps are present. +- Plugins/startup: ignore pnpm's `npm_execpath` when repairing bundled plugin runtime dependencies and skip workspace-only package specs so npm-only install flags or local workspace links do not break packaged plugin startup. - MCP: block interpreter-startup env keys such as `NODE_OPTIONS` for stdio servers while preserving ordinary credential and proxy env vars. (#69540) Thanks @drobison00. - Agents/shell: ignore non-interactive placeholder shells like `/usr/bin/false` and `/sbin/nologin`, falling back to `sh` so service-user exec runs no longer exit immediately. (#69308) Thanks @sk7n4k3d. - Setup/TUI: relaunch the setup hatch TUI in a fresh process while preserving the configured gateway target and auth source, so onboarding recovers terminal state cleanly without exposing gateway secrets on command-line args. (#69524) Thanks @shakkernerd. @@ -834,7 +843,7 @@ Docs: https://docs.openclaw.ai - Plugins: keep only the highest-precedence manifest when distinct discovered plugins share an id, so lower-precedence global or workspace duplicates no longer load beside bundled or config-selected plugins. (#41626) Thanks @Tortes. - fix(security): block MINIMAX_API_HOST workspace env injection and remove env-driven URL routing [AI-assisted]. (#67300) Thanks @pgondhi987. - Cron/delivery: treat explicit `delivery.mode: "none"` runs as not requested even if the runner reports `delivered: false`, so no-delivery cron jobs no longer persist false delivery failures or errors. (#69285) Thanks @matsuri1987. -- Plugins/install: repair active and default-enabled bundled plugin runtime dependencies before import in packaged installs, so bundled Discord, WhatsApp, Slack, Telegram, and provider plugins work without putting their dependency trees in core. Thanks @steipete. +- Plugins/install: repair active and default-enabled bundled plugin runtime dependencies before import in packaged installs, so bundled Discord, WhatsApp, Slack, Telegram, and provider plugins work without putting their dependency trees in core. - BlueBubbles: raise the outbound `/api/v1/message/text` send timeout default from 10s to 30s, and add a configurable `channels.bluebubbles.sendTimeoutMs` (also per-account) so macOS 26 setups where Private API iMessage sends stall for 60+ seconds no longer silently lose messages at the 10s abort. Probes, chat lookups, and health checks keep the shorter 10s default. Fixes #67486. (#69193) Thanks @omarshahine. - Agents/bootstrap: budget truncation markers against per-file caps, preserve source content instead of silently wasting bootstrap bytes, and avoid marker-only output in tiny-budget truncation cases. (#69114) Thanks @BKF-Gitty. - Context engine/plugins: stop rejecting third-party context engines whose `info.id` differs from the registered plugin slot id. The strict-match contract added in 2026.4.14 broke `lossless-claw` and other plugins whose internal engine id does not equal the slot id they are registered under, producing repeated `info.id must match registered id` lane failures on every turn. Fixes #66601. (#66678) Thanks @GodsBoy. @@ -886,7 +895,7 @@ Docs: https://docs.openclaw.ai - Agents/openai-completions: always send `stream_options.include_usage` on streaming requests, so local and custom OpenAI-compatible backends report real context usage instead of showing 0%. (#68746) Thanks @kagura-agent. - Agents/nested lanes: scope nested agent work per target session so a long-running nested run on one session no longer head-of-line blocks unrelated sessions across the gateway. (#67785) Thanks @stainlu. - Agents/status: preserve carried-forward session token totals for providers that omit usage metadata, so `/status` and `openclaw sessions` keep showing the last known context usage instead of dropping back to unknown/0%. (#67695) Thanks @stainlu. -- Install/update: keep legacy update verification compatible with the QA Lab runtime shim, so updating older global installs to beta no longer fails after npm installs the package successfully. Thanks @steipete. +- Install/update: keep legacy update verification compatible with the QA Lab runtime shim, so updating older global installs to beta no longer fails after npm installs the package successfully. ## 2026.4.19-beta.1 @@ -896,14 +905,14 @@ Docs: https://docs.openclaw.ai - Telegram/callbacks: treat permanent callback edit errors as completed updates so stale command pagination buttons no longer wedge the update watermark and block newer Telegram updates. (#68588) Thanks @Lucenx9. - Browser/CDP: allow the selected remote CDP profile host for CDP health and control checks without widening browser navigation SSRF policy, so WSL-to-Windows Chrome endpoints no longer appear offline under strict defaults. Fixes #68108. (#68207) Thanks @Mlightsnow. - Codex: stop cumulative app-server token totals from being treated as fresh context usage, so session status no longer reports inflated context percentages after long Codex threads. (#64669) Thanks @cyrusaf. -- Browser/CDP: add phase-specific CDP readiness diagnostics and normalize loopback WebSocket host aliases, so Windows browser startup failures surface whether HTTP discovery, WebSocket discovery, SSRF validation, or the `Browser.getVersion` health check failed. Thanks @steipete. +- Browser/CDP: add phase-specific CDP readiness diagnostics and normalize loopback WebSocket host aliases, so Windows browser startup failures surface whether HTTP discovery, WebSocket discovery, SSRF validation, or the `Browser.getVersion` health check failed. - Browser/CDP: discover Chrome’s real DevTools websocket from bare `ws://host:port` attach-only roots before declaring the profile down, while still falling back to direct websocket providers that do not expose `/json/version`. Fixes #68027. (#68715) Thanks @visionik. ## 2026.4.18 ### Changes -- Anthropic/models: add Claude Opus 4.7 `xhigh` reasoning effort support and keep it separate from adaptive thinking. Thanks @steipete. +- Anthropic/models: add Claude Opus 4.7 `xhigh` reasoning effort support and keep it separate from adaptive thinking. - Control UI/settings: overhaul the settings and slash-command experience with faster presets, quick-create flows, and refreshed command discovery. (#67819) Thanks @BunsDev. - macOS/gateway: add `screen.snapshot` support for macOS app nodes, including runtime plumbing, default macOS allowlisting, and docs for monitor preview flows. (#67954) Thanks @BunsDev. @@ -919,20 +928,20 @@ Docs: https://docs.openclaw.ai - OpenAI Codex/Responses: unify native Responses API capability detection so Codex OAuth requests emit the required `store: false` field on the native Responses path. (#67918) Thanks @obviyus. - WhatsApp/setup: guard personal-phone and allowlist prompt values so setup fails with clear validation errors instead of crashing on undefined prompt text. (#67895) Thanks @lawrence3699. - Models/config: preserve an existing `models.json` provider `baseUrl` during merge-mode regeneration so custom endpoints do not get reset on restart. (#67893) Thanks @lawrence3699. -- Plugin SDK: preserve `secret-input-runtime` function exports in published builds so provider plugins can read SecretRef-backed setup inputs. Thanks @steipete. +- Plugin SDK: preserve `secret-input-runtime` function exports in published builds so provider plugins can read SecretRef-backed setup inputs. - Plugins/discovery: reuse bundled and global plugin discovery results across workspace cache misses so Windows multi-workspace startup stops redoing the shared synchronous scan. (#67940) Thanks @obviyus. -- Bundled plugins/install: keep staged bundled plugin runtime imports resolving through the packaged Plugin SDK while omitting checkout-only aliases from the dist inventory, so published installs do not fail on repo-local paths. Thanks @steipete. +- Bundled plugins/install: keep staged bundled plugin runtime imports resolving through the packaged Plugin SDK while omitting checkout-only aliases from the dist inventory, so published installs do not fail on repo-local paths. - Plugins/webhooks: enforce synchronous plugin registration with full rollback of failed plugin side effects, and cache SecretRef-backed webhook auth per route so plugin startup and inbound webhook auth stay deterministic. (#67941) Thanks @obviyus. -- Telegram/polling transport: give the Telegram undici dispatcher pool bounded keep-alive defaults and an explicit lifecycle. Previously every recoverable network error and stall watchdog trip silently replaced the transport, abandoning the old dispatcher pool and its sockets; long-running gateway processes accumulated hundreds of ESTABLISHED connections to `api.telegram.org`, saturating per-IP upstream proxy quotas and causing the actively-used outbound proxy node to time out while every other node still tested healthy. Transports now expose `close()`, `TelegramPollingTransportState` destroys the stale transport on dirty-rebuild, and `TelegramPollingSession` disposes the transport when polling exits — backed by a strict per-origin pool cap on every constructed `Agent`, `ProxyAgent`, and `EnvHttpProxyAgent` as defence in depth (#69476). Thanks @steipete. -- Telegram/polling: publish successful `getUpdates` calls as account health liveness, avoid false stall restarts after recoverable `getUpdates` errors, and force Telegram API dispatchers to HTTP/1.1 so stalled polling recovers instead of sitting connected-but-dead (#69476). Thanks @steipete. +- Telegram/polling transport: give the Telegram undici dispatcher pool bounded keep-alive defaults and an explicit lifecycle. Previously every recoverable network error and stall watchdog trip silently replaced the transport, abandoning the old dispatcher pool and its sockets; long-running gateway processes accumulated hundreds of ESTABLISHED connections to `api.telegram.org`, saturating per-IP upstream proxy quotas and causing the actively-used outbound proxy node to time out while every other node still tested healthy. Transports now expose `close()`, `TelegramPollingTransportState` destroys the stale transport on dirty-rebuild, and `TelegramPollingSession` disposes the transport when polling exits — backed by a strict per-origin pool cap on every constructed `Agent`, `ProxyAgent`, and `EnvHttpProxyAgent` as defence in depth (#69476). +- Telegram/polling: publish successful `getUpdates` calls as account health liveness, avoid false stall restarts after recoverable `getUpdates` errors, and force Telegram API dispatchers to HTTP/1.1 so stalled polling recovers instead of sitting connected-but-dead (#69476). - Telegram/ACP bindings: drop persisted DM bindings that still point at missing or failed ACP sessions on restart, while preserving plugin-owned bindings and uncertain store reads. (#67822) Thanks @chinar-amrutkar. - Telegram/streaming: keep a transient preview on the same Telegram message when auto-compaction retries an in-flight answer, so streamed replies no longer appear duplicated after compaction. (#66939) Thanks @rubencu. - Memory/sqlite-vec: emit the degraded sqlite-vec warning once per degraded episode instead of repeating it for every file write, while preserving the latch across safe-reindex rollback and resetting it when vector state is genuinely rebuilt. (#67898) Thanks @rubencu. -- Memory-core: preserve stored vector dimensions during read-only recovery so memory indexes do not lose vector metadata while repairing read-only state. Thanks @steipete. +- Memory-core: preserve stored vector dimensions during read-only recovery so memory indexes do not lose vector metadata while repairing read-only state. - Reply/block streaming: preserve post-stream incomplete-turn error payloads after block streaming already emitted content, so users get the warning instead of silence. (#67991) Thanks @obviyus. - Telegram/streaming: clear the compaction replay guard after visible non-final boundaries so a post-tool assistant reply rotates to a fresh preview instead of editing the pre-compaction message. (#67993) Thanks @obviyus. - Matrix: fix `sessions_spawn --thread` subagent session spawning — thread binding creation, cleanup on session end, and completion-message delivery target resolution now work end-to-end. (#67643) Thanks @eejohnso-ops and @gumadeiras. -- Slack/streaming: resolve native streaming recipient teams from the inbound user when available, with a monitor-team fallback, so DM and shared-workspace streams target the right recipient more reliably. Thanks @steipete. +- Slack/streaming: resolve native streaming recipient teams from the inbound user when available, with a monitor-team fallback, so DM and shared-workspace streams target the right recipient more reliably. - macOS/webchat: enable Undo and Redo in the composer text input by turning on the native `NSTextView` undo manager. (#34962) Thanks @tylerbittner. - macOS/remote SSH: require an already-trusted host key on the macOS remote command, gateway probe, port tunnel, and pairing probe paths by switching `StrictHostKeyChecking=accept-new` to `StrictHostKeyChecking=yes` and centralizing the shared SSH option fragments in `CommandResolver`, so first-time macOS remote connections no longer silently accept an unknown host key and must be trusted ahead of time via `~/.ssh/known_hosts`. (#68199) Thanks @drobison00. - CLI/configure: show the channel picker before probing statuses and let remove mode delete configured channel blocks directly from config. (#68007) Thanks @gumadeiras. @@ -952,7 +961,7 @@ Docs: https://docs.openclaw.ai - Failover/google: only treat `INTERNAL` status payloads as retryable timeouts when they also carry a `500` code, so malformed non-500 payloads do not enter the retry path. (#68238) Thanks @altaywtf and @Openbling. - Agents/tools: filter bundled MCP/LSP tools through the final owner-only and tool-policy pipeline after merging them into the effective tool list, so existing allowlists, deny rules, sandbox policy, subagent policy, and owner-only restrictions apply to bundled tools the same way they apply to core tools. (#68195) Thanks @drobison00. - Gateway/assistant media: require `operator.read` scope for assistant-media file and metadata requests on identity-bearing HTTP auth paths so callers without a read scope can no longer access assistant media. (#68175) Thanks @eleqtrizit. -- Gateway/web: allow same-origin microphone access in the Permissions-Policy header so browser voice capture can work from the Control UI and webchat origin. (#68368) Thanks @steipete. +- Gateway/web: allow same-origin microphone access in the Permissions-Policy header so browser voice capture can work from the Control UI and webchat origin. (#68368). - Exec approvals/display: escape raw control characters (including newline and carriage return) in the shared and macOS approval-prompt command sanitizers, so trailing command payloads no longer render on hidden extra lines in the approval UI. (#68198) Thanks @drobison00. - Telegram/streaming: fence same-session stale preview and finalization work after aborts so Telegram no longer replays an older reply or flushes a hidden short preview after the abort confirmation lands. (#68100) Thanks @rubencu. - OpenAI Codex/OAuth + Pi: keep imported Codex CLI OAuth bootstrap, Pi auth export, and runtime overlay handling aligned so Codex sessions survive refresh and health checks without leaking transient CLI state into saved auth files. Thanks @vincentkoc. @@ -971,7 +980,7 @@ Docs: https://docs.openclaw.ai - Gateway/auth: reject gateway auth credentials that match published example placeholders at startup and secret reload, and keep cloud install snippets from publishing copy-paste gateway/keyring secrets. (#68404) Thanks @coygeek. - CLI/update: preserve macOS restart helper launchctl failures in the update restart log without letting log setup block the restart path. (#68492) Thanks @hclsys. - Slack/threads: keep file-only root messages as starter context so first thread replies can still hydrate starter media. (#68594) Thanks @martingarramon. -- Google/Antigravity: resolve forward-compatible Gemini 3.1 Pro custom-tools and Flash variants from the bundled Google plugin templates, so `google-antigravity/gemini-3.1-pro-preview-customtools` no longer falls through to an unknown-model error. Fixes #35512. Thanks @steipete. +- Google/Antigravity: resolve forward-compatible Gemini 3.1 Pro custom-tools and Flash variants from the bundled Google plugin templates, so `google-antigravity/gemini-3.1-pro-preview-customtools` no longer falls through to an unknown-model error. Fixes #35512. - Active Memory: raise the blocking recall timeout ceiling to 120 seconds and reject larger config values during plugin schema validation. Fixes #68410. (#68480) Thanks @Bartok9. - Control UI/chat: keep history-backed user image uploads visible after chat reload while filtering blocked or non-image transcript media paths. (#68415) Thanks @mraleko. - Matrix/plugins: keep remaining Matrix event helpers on the canonical `matrix-js-sdk` subpath so build and plugin-load entrypoint checks stay consistent. (#68498) Thanks @masatohoshino. @@ -980,7 +989,7 @@ Docs: https://docs.openclaw.ai ### Changes -- Anthropic/models: default Anthropic selections, `opus` aliases, Claude CLI defaults, and bundled image understanding to Claude Opus 4.7. Thanks @steipete. +- Anthropic/models: default Anthropic selections, `opus` aliases, Claude CLI defaults, and bundled image understanding to Claude Opus 4.7. - Google/TTS: add Gemini text-to-speech support to the bundled `google` plugin, including provider registration, voice selection, WAV reply output, PCM telephony output, and setup/docs guidance. (#67515) Thanks @barronlroth. - Control UI/Overview: add a Model Auth status card showing OAuth token health and provider rate-limit pressure at a glance, with attention callouts when OAuth tokens are expiring or expired. Backed by a new `models.authStatus` gateway method that strips credentials and caches for 60s. (#66211) Thanks @omarshahine. - Memory/LanceDB: add cloud storage support to `memory-lancedb` so durable memory indexes can run on remote object storage instead of local disk only. (#63502) Thanks @rugvedS07. @@ -1035,10 +1044,10 @@ Docs: https://docs.openclaw.ai - Agents/context engines: keep loop-hook and final `afterTurn` prompt-cache touch metadata aligned with the current assistant turn so cache-aware context engines retain accurate cache TTL state during tool loops. (#67767) thanks @jalehman. - Memory/dreaming: strip AI-facing inbound metadata envelopes from session-corpus user turns before normalization so REM topic extraction sees the user's actual message text, including array-shaped split envelopes. (#66548) Thanks @zqchris. - Agents/errors: detect standalone Cloudflare/CDN HTML challenge pages before transport DNS classification so provider block pages no longer appear as local DNS lookup failures. (#67704) Thanks @chris-yyau. -- Security/approvals: redact secrets in exec approval prompts so inline approval review can no longer leak credential material in rendered prompt content. (#61077, #64790) Thanks @steipete. -- CLI/configure: re-read the persisted config hash after writes so config updates stop failing with stale-hash races. (#64188, #66528) Thanks @steipete. +- Security/approvals: redact secrets in exec approval prompts so inline approval review can no longer leak credential material in rendered prompt content. (#61077, #64790). +- CLI/configure: re-read the persisted config hash after writes so config updates stop failing with stale-hash races. (#64188, #66528). - CLI/update: prune stale packaged `dist` chunks after npm upgrades and keep downgrade/verify inventory checks compat-safe so global upgrades stop failing on stale chunk imports. (#66959) Thanks @obviyus. -- Onboarding/CLI: fix channel-selection crashes on globally installed CLI setups during onboarding. (#66736) Thanks @steipete. +- Onboarding/CLI: fix channel-selection crashes on globally installed CLI setups during onboarding. (#66736). - Video generation/live tests: bound provider polling for live video smoke, default to the fast non-FAL text-to-video path, and use a one-second lobster prompt so release validation no longer waits indefinitely on slow provider queues. - Memory-core/QMD `memory_get`: reject reads of arbitrary workspace markdown paths and only allow canonical memory files (`MEMORY.md`, `memory.md`, `DREAMS.md`, `dreams.md`, `memory/**`) plus exact paths of active indexed QMD workspace documents, so the QMD memory backend can no longer be used as a generic workspace-file read shim that bypasses `read` tool-policy denials. (#66026) Thanks @eleqtrizit. - Cron/agents: forward embedded-run tool policy and internal event params into the attempt layer so `--tools` allowlists, cron-owned message-tool suppression, explicit message targeting, and command-path internal events all take effect at runtime again. (#62675) Thanks @hexsprite. @@ -1069,7 +1078,7 @@ Docs: https://docs.openclaw.ai - BlueBubbles/catchup: replay missed webhook messages after gateway restart via a persistent per-account cursor and `/api/v1/message/query?after=` pass, so messages delivered while the gateway was down no longer disappear. Uses the existing `processMessage` path and is deduped by #66816's inbound GUID cache. (#66857, #66721) Thanks @omarshahine. - Telegram/native commands: keep Telegram command-sync cache process-local so gateway restarts re-register the menu instead of trusting stale on-disk sync state after Telegram cleared commands out-of-band. (#66730) Thanks @nightq. - Audio/self-hosted STT: restore `models.providers.*.request.allowPrivateNetwork` for audio transcription so private or LAN speech-to-text endpoints stop tripping SSRF blocks after the v2026.4.14 regression. (#66692) Thanks @jhsmith409. -- Auto-reply/media: allow workspace-rooted absolute media paths in auto-reply send flows so valid local media references no longer fail path validation. (#66689) Thanks @steipete. +- Auto-reply/media: allow workspace-rooted absolute media paths in auto-reply send flows so valid local media references no longer fail path validation. (#66689). - WhatsApp/Baileys media upload: harden encrypted upload handling so large outbound media sends avoid buffer spikes and reliability regressions. (#65966) Thanks @frankekn. - QQBot/cron: guard against undefined `event.content` in `parseFaceTags` and `filterInternalMarkers` so cron-triggered agent turns with no content payload no longer crash with `TypeError: Cannot read properties of undefined (reading 'startsWith')`. (#66302) Thanks @xinmotlanthua. - CLI/plugins: stop `--dangerously-force-unsafe-install` plugin installs from falling back to hook-pack installs after security scan failures, while still preserving non-security fallback behavior for real hook packs. (#58909) Thanks @hxy91819. @@ -1082,7 +1091,7 @@ Docs: https://docs.openclaw.ai - Dreaming/memory-core: use the ingestion day, not the source file day, for daily recall dedupe so repeat sweeps of the same daily note can increment `dailyCount` across days instead of stalling at `1`. (#67091) Thanks @Bartok9. - Node-host/tools.exec: let approval binding distinguish known native binaries from mutable shell payload files, while still fail-closing unknown or racy file probes so absolute-path node-host commands like `/usr/bin/whoami` no longer get rejected as unsafe interpreter/runtime commands. (#66731) Thanks @tmimmanuel. - Codex/gateway: fix gateway crash when the codex-acp subprocess terminates abruptly; an unhandled EPIPE on the child stdin stream now routes through graceful client shutdown, rejecting pending requests instead of propagating as an uncaught exception that crashes the entire gateway daemon and all connected channels. Fixes #67886. (#67947) thanks @openperf. -- Slack/streaming: resolve native streaming recipient teams from the inbound user when available, with a monitor-team fallback, so DM and shared-workspace streams target the right recipient more reliably. Thanks @steipete. +- Slack/streaming: resolve native streaming recipient teams from the inbound user when available, with a monitor-team fallback, so DM and shared-workspace streams target the right recipient more reliably. - OpenRouter/streaming: treat `reasoning_details.response.output_text` and `reasoning_details.response.text` as visible assistant output on OpenRouter-compatible completions streams, while keeping `reasoning.text` hidden and refusing to surface ambiguous bare `text` items by default so visible replies, thinking blocks, and tool calls can coexist in the same chunk. (#67410) Thanks @neeravmakwana. - Models/OpenRouter aliases: resolve `openrouter:auto` to the canonical `openrouter/auto` model and map `openrouter:free` to the first configured concrete `openrouter/...:free` model instead of mis-resolving these compatibility aliases under the default provider. (#57066) Thanks @sumiisiaran. - OpenRouter/Arcee: canonicalize stale OpenRouter `https://openrouter.ai/v1` base URLs during provider config normalization and runtime model/transport resolution, so fresh `models.json` writes and previously discovered rows self-heal back to `https://openrouter.ai/api/v1` instead of breaking OpenRouter-routed requests. (#67295) Thanks @achalkov. @@ -1151,14 +1160,14 @@ Docs: https://docs.openclaw.ai - Memory/active-memory: move recalled memory onto the hidden untrusted prompt-prefix path instead of system prompt injection, label the visible Active Memory status line fields, and include the resolved recall provider/model in gateway debug logs so trace/debug output matches what the model actually saw. (#66144) Thanks @Takhoffman. - Memory/QMD: stop treating legacy lowercase `memory.md` as a second default root collection, so QMD recall no longer searches phantom `memory-alt-*` collections and builtin/QMD root-memory fallback stays aligned. (#66141) Thanks @mbelinky. - Agents/subagents: ship `dist/agents/subagent-registry.runtime.js` in npm builds so `runtime: "subagent"` runs stop stalling in `queued` after the registry import fails. (#66189) Thanks @yqli2420 and @vincentkoc. -- Agents/OpenAI: map `minimal` thinking to OpenAI's supported `low` reasoning effort for GPT-5.4 requests, so embedded runs stop failing request validation. Thanks @steipete. +- Agents/OpenAI: map `minimal` thinking to OpenAI's supported `low` reasoning effort for GPT-5.4 requests, so embedded runs stop failing request validation. - Voice-call/media-stream: resolve the source IP from trusted forwarding headers for per-IP pending-connection limits when `webhookSecurity.trustForwardingHeaders` and `trustedProxyIPs` are configured, and reserve `maxConnections` capacity for in-flight WebSocket upgrades so concurrent handshakes can no longer momentarily exceed the operator-set cap. (#66027) Thanks @eleqtrizit. - Feishu/allowlist: canonicalize allowlist entries by explicit `user`/`chat` kind, strip repeated `feishu:`/`lark:` provider prefixes, and stop folding opaque Feishu IDs to lowercase, so allowlist matching no longer crosses user/chat namespaces or widens to case-insensitive ID matches the operator did not intend. (#66021) Thanks @eleqtrizit. - Telegram/status commands: let read-only status slash commands bypass busy topic turns, while keeping `/export-session` on the normal lane so it cannot interleave with an in-flight session mutation. (#66226) Thanks @VACInc and @vincentkoc. - TTS/reply media: persist OpenClaw temp voice outputs into managed outbound media and allow them through reply-media normalization, so voice-note replies stop silently dropping. (#63511) Thanks @jetd1. - Agents/tools: treat Windows drive-letter paths (`C:\\...`) as absolute when resolving sandbox and read-tool paths so workspace root is not prepended under POSIX path rules. (#54039) Thanks @ly85206559 and @vincentkoc. - Agents/OpenAI: recover embedded GPT-style runs when reasoning-only or empty turns need bounded continuation, with replay-safe retry gating and incomplete-turn fallback when no visible answer arrives. (#66167) thanks @jalehman. -- Outbound/relay-status: suppress internal relay-status placeholder payloads (`No channel reply.`, `Replied in-thread.`, `Replied in #...`, wiki-update status variants ending in `No channel reply.`) before channel delivery so internal housekeeping text does not leak to users. Thanks @steipete. +- Outbound/relay-status: suppress internal relay-status placeholder payloads (`No channel reply.`, `Replied in-thread.`, `Replied in #...`, wiki-update status variants ending in `No channel reply.`) before channel delivery so internal housekeeping text does not leak to users. - Slack/doctor: add a dedicated doctor-contract sidecar so config warmup paths such as `openclaw cron` no longer fall back to Slack's broader contract surface, which could trigger Slack-related config-read crashes on affected setups. (#63192) Thanks @shhtheonlyperson. - Hooks/session-memory: pass the resolved agent workspace into gateway `/new` and `/reset` session-memory hooks so reset snapshots stay scoped to the right agent workspace instead of leaking into the default workspace. (#64735) Thanks @suboss87 and @vincentkoc. - CLI/approvals: raise the default `openclaw approvals get` gateway timeout and report config-load timeouts explicitly, so slow hosts stop showing a misleading `Config unavailable.` note when the approvals snapshot succeeds but the follow-up config RPC needs more time. (#66239) Thanks @neeravmakwana. @@ -1183,11 +1192,11 @@ Docs: https://docs.openclaw.ai - Gateway: split startup and runtime seams so gateway lifecycle sequencing, reload state, and shutdown behavior stay easier to maintain without changing observed behavior. (#63975) Thanks @gumadeiras. - Matrix/partial streaming: add MSC4357 live markers to draft preview sends and edits so supporting Matrix clients can render a live/typewriter animation and stop it when the final edit lands. (#63513) Thanks @TigerInYourDream. - QA/Telegram: add a live `openclaw qa telegram` lane for private-group bot-to-bot checks, harden its artifact handling, and preserve native Telegram command reply threading for QA verification. (#64303) Thanks @obviyus. -- Models/Codex: add the bundled Codex provider and plugin-owned app-server harness so `codex/gpt-*` models use Codex-managed auth, native threads, model discovery, and compaction while `openai/gpt-*` stays on the normal OpenAI provider path. (#64298) Thanks @steipete. +- Models/Codex: add the bundled Codex provider and plugin-owned app-server harness so `codex/gpt-*` models use Codex-managed auth, native threads, model discovery, and compaction while `openai/gpt-*` stays on the normal OpenAI provider path. (#64298). - Models/providers: add a bundled LM Studio provider with onboarding, runtime model discovery, stream preload support, and memory-search embeddings for local/self-hosted OpenAI-compatible models. (#53248) Thanks @rugvedS07. - Plugins/loading: narrow CLI, provider, and channel activation to manifest-declared needs, preserve explicit scope and trust boundaries, and centralize manifest-owner policy so startup, command discovery, and runtime activation avoid loading unrelated plugin runtime. (#65120, #65259, #65298, #65429, #65459) Thanks @vincentkoc. - Memory/active-memory: default QMD recall to search and surface better search-path telemetry so memory-backed recall works more predictably out of the box. (#65068) Thanks @Takhoffman. -- Docs/providers: expand bundled provider docs with richer capability, env-var, and setup guidance across provider pages. Thanks @steipete. +- Docs/providers: expand bundled provider docs with richer capability, env-var, and setup guidance across provider pages. - Docs/memory-wiki: add the recommended QMD + bridge-mode hybrid recipe plus zero-artifact troubleshooting guidance for `memory-wiki` bridge setups. (#63165) Thanks @sercada and @vincentkoc. ### Fixes @@ -1197,10 +1206,10 @@ Docs: https://docs.openclaw.ai - fix(security): broaden shell-wrapper detection and block env-argv assignment injection [AI-assisted]. (#65717) Thanks @pgondhi987. - Gateway/startup: defer scheduled services until sidecars finish, gate chat history and model listing during sidecar resume, and let Control UI retry startup-gated history loads so Sandbox wake resumes channels first. (#65365) Thanks @lml2468. - Control UI/chat: load the live gateway slash-command catalog into the composer and command palette so dock commands, plugin commands, and direct skill aliases appear in chat, while keeping trusted local commands authoritative and bounding remote command metadata. (#65620) Thanks @BunsDev. -- CLI/update: respawn tracked plugin refresh from the updated entrypoint after package self-updates so `openclaw update` stops failing on stale hashed `dist/install.runtime-*.js` chunk imports. (#65471) Thanks @steipete. +- CLI/update: respawn tracked plugin refresh from the updated entrypoint after package self-updates so `openclaw update` stops failing on stale hashed `dist/install.runtime-*.js` chunk imports. (#65471). - Memory/active-memory: keep recall runs on the resolved channel when wrappers like `mx-claw` are enabled, improve lexical fallback ranking, and keep lexical boosts out of hybrid search so recall finds the right memories more consistently. (#65049, #65395) Thanks @Takhoffman. -- Dreaming: consume managed heartbeat events exactly once, stage light-sleep confidence from all recorded short-term signals, wake scheduled jobs immediately, raise dreaming-only promotion enough to cross the durable-memory gate, and stop dreaming from re-ingesting its own narrative transcripts. Thanks @steipete. -- Dreaming/narrative: harden transient narrative cleanup by retrying timed-out deletes, scrubbing stale dreaming session artifacts through the lock-aware session-store path, and isolating transient narrative session keys per workspace. (#65320, #61674) Thanks @steipete. +- Dreaming: consume managed heartbeat events exactly once, stage light-sleep confidence from all recorded short-term signals, wake scheduled jobs immediately, raise dreaming-only promotion enough to cross the durable-memory gate, and stop dreaming from re-ingesting its own narrative transcripts. +- Dreaming/narrative: harden transient narrative cleanup by retrying timed-out deletes, scrubbing stale dreaming session artifacts through the lock-aware session-store path, and isolating transient narrative session keys per workspace. (#65320, #61674). - Memory/wiki: preserve Unicode letters, digits, and combining marks in wiki slugs and contradiction clustering, and cap Unicode filename segments to safe byte lengths so non-ASCII titles stop collapsing or overflowing path limits. (#64742) Thanks @zhouhe-xydt. - Memory/short-term recall: allow nested daily notes under `memory/**/YYYY-MM-DD.md` to feed short-term recall, while still excluding generated dream reports under `memory/dreaming/**` so dreaming does not promote its own output. (#64682) Thanks @SARAMALI15792. - UI/WebChat: hide synthetic transcript-repair tool results from chat history reloads so internal recovery markers do not leak into visible chat after reconnects. (#65247) Thanks @wangwllu. @@ -1208,40 +1217,40 @@ Docs: https://docs.openclaw.ai - Doctor/Discord: stop `openclaw doctor --fix` from rewriting legacy Discord preview-streaming config into the nested modern shape, so downgrades can still recover without hand-editing `channels.discord.streaming`. (#65035) Thanks @vincentkoc. - Gateway/auth: blank the shipped example gateway credential in `.env.example` and fail startup when a copied placeholder token or password is still configured, so operators cannot accidentally launch with a publicly known secret. (#64586) Thanks @navarrotech and @vincentkoc. -- Memory/active-memory+dreaming: keep active-memory recall runs on the strongest resolved channel, consume managed dreaming heartbeat events exactly once, stop dreaming from re-ingesting its own narrative transcripts, and add explicit repair/dedupe recovery flows in CLI, doctor, and the Dreams UI. Thanks @steipete. +- Memory/active-memory+dreaming: keep active-memory recall runs on the strongest resolved channel, consume managed dreaming heartbeat events exactly once, stop dreaming from re-ingesting its own narrative transcripts, and add explicit repair/dedupe recovery flows in CLI, doctor, and the Dreams UI. - Agents/queueing: carry orphaned active-turn user text into the next prompt before repairing transcript ordering, so follow-up messages that arrive mid-run are no longer silently dropped. (#65388) Thanks @adminfedres and @vincentkoc. - Gateway/keepalive: stop marking WebSocket tick broadcasts as droppable so slow or backpressured clients do not self-disconnect with `tick timeout` while long-running work is still alive. (#65256) Thanks @100yenadmin and @vincentkoc. - Matrix/mentions: keep room mention gating strict while accepting visible `@displayName` Matrix URI labels, so `requireMention` works for non-OpenClaw Matrix clients again. (#64796) Thanks @hclsys. - Doctor: warn when on-disk agent directories still exist under `~/.openclaw/agents//agent` but the matching `agents.list[]` entries are missing from config. (#65113) Thanks @neeravmakwana. - Telegram: route approval button callback queries onto a separate sequentializer lane so plugin approval clicks can resolve immediately instead of deadlocking behind the blocked agent turn. (#64979) Thanks @nk3750. -- Telegram/direct sessions: keep commentary-only assistant fallback payloads out of visible direct delivery, so Codex planning chatter cannot leak into Telegram DMs when a run has no `final_answer` text. Thanks @steipete. -- Gateway/keepalive: stop marking WebSocket tick broadcasts as droppable so slow or backpressured clients do not self-disconnect with `tick timeout` while long-running work is still alive. (#65436) Thanks @steipete. +- Telegram/direct sessions: keep commentary-only assistant fallback payloads out of visible direct delivery, so Codex planning chatter cannot leak into Telegram DMs when a run has no `final_answer` text. +- Gateway/keepalive: stop marking WebSocket tick broadcasts as droppable so slow or backpressured clients do not self-disconnect with `tick timeout` while long-running work is still alive. (#65436). - Gateway/plugins: always send a non-empty `idempotencyKey` for plugin subagent runs, so dreaming narrative jobs stop failing gateway schema validation. (#65354) Thanks @CodeForgeNet. - Gateway/auth: blank the shipped example gateway credential in `.env.example` and fail startup when a copied placeholder token or password is still configured, so operators cannot accidentally launch with a publicly known secret. (#64586) Thanks @navarrotech. - Plugins/memory-core dreaming: keep bundled `memory-core` loaded alongside an explicit external memory slot owner only when that owner enables dreaming, while preserving `plugins.slots.memory = "none"` disable semantics. (#65411) Thanks @pradeep7127. -- Doctor/Discord: stop `openclaw doctor --fix` from rewriting legacy Discord preview-streaming config into the nested modern shape, so downgrades can still recover without hand-editing `channels.discord.streaming`. Thanks @steipete. +- Doctor/Discord: stop `openclaw doctor --fix` from rewriting legacy Discord preview-streaming config into the nested modern shape, so downgrades can still recover without hand-editing `channels.discord.streaming`. - Doctor: warn when on-disk agent directories still exist under `~/.openclaw/agents//agent` but the matching `agents.list[]` entries are missing from config. (#65113) Thanks @neeravmakwana. -- CLI/plugins: honor `memory-wiki` when `plugins.allow` is set for `openclaw wiki`, and pass the active app config into the metadata registrar so plugin-owned wiki commands resolve the live plugin config instead of falling back to defaults. (#64779, #65012) Thanks @steipete. +- CLI/plugins: honor `memory-wiki` when `plugins.allow` is set for `openclaw wiki`, and pass the active app config into the metadata registrar so plugin-owned wiki commands resolve the live plugin config instead of falling back to defaults. (#64779, #65012). - QA/packaging: stop packaged QA helpers from crashing when optional scenario execution config is unavailable, so npm distributions can skip the repo-only scenario pack without breaking completion-cache and startup paths. (#65118) Thanks @EdderTalmor. - Media/audio transcription: surface the real provider failure when every audio transcription attempt fails, so status output and the CLI stop collapsing those errors into generic skips. (#65096) Thanks @l0cka. - Infra/net: fix multipart FormData fields (including `model`) being silently dropped when a guarded runtime fetch body crosses a FormData implementation boundary, restoring OpenAI audio transcription requests that failed with HTTP 400. (#64349) Thanks @petr-sloup. -- Dreaming/diary: use the host local timezone for diary timestamps when `dreaming.timezone` is unset, and include the timezone abbreviation so `DREAMS.md` and the UI make local or UTC time explicit. (#65034, #65057) Thanks @steipete. +- Dreaming/diary: use the host local timezone for diary timestamps when `dreaming.timezone` is unset, and include the timezone abbreviation so `DREAMS.md` and the UI make local or UTC time explicit. (#65034, #65057). - Dreaming/promotion: raise phase reinforcement enough for repeated dreaming-only revisits to clear the default durable-memory gate after multiple days, instead of stalling just below the score threshold. (#64068) Thanks @vincentkoc. - Dreaming/light-sleep: compute staged candidate confidence from all recorded short-term signals instead of recall-only counts, so dreaming-only entries stop rendering as `confidence: 0.00`. (#64599) Thanks @vincentkoc. -- Plugins/memory: restore cached memory capability public artifacts on plugin-registry cache hits so memory-backed artifact surfaces stay visible after warm loads. Thanks @steipete. -- Gateway/cron: preserve requested isolated-agent config across runtime reloads so subagent jobs and heartbeat overrides keep the right workspace and heartbeat settings when the hot-loaded snapshot is stale. Thanks @steipete. -- Cron/isolated sessions: persist the right transcript path for each isolated run, including fresh session rollovers, so cron runs stop appending to stale session files. Thanks @steipete. +- Plugins/memory: restore cached memory capability public artifacts on plugin-registry cache hits so memory-backed artifact surfaces stay visible after warm loads. +- Gateway/cron: preserve requested isolated-agent config across runtime reloads so subagent jobs and heartbeat overrides keep the right workspace and heartbeat settings when the hot-loaded snapshot is stale. +- Cron/isolated sessions: persist the right transcript path for each isolated run, including fresh session rollovers, so cron runs stop appending to stale session files. - Discord/gateway: clear stale heartbeat timers before reconnecting so zombie gateway callbacks cannot crash the process and drop in-flight replies. (#65009) Thanks @SARAMALI15792. - Matrix/mentions: keep room mention gating strict while accepting visible `@displayName` Matrix URI labels, so `requireMention` works for non-OpenClaw Matrix clients again. (#64796) Thanks @hclsys. - Agents/Anthropic replay: preserve immutable signed-thinking replay safety across stored and live reruns, keep non-thinking embedded `tool_result` user blocks intact, and drop conflicting preserved tool IDs before validation so retries stop degrading into omitted tool calls. (#65126) Thanks @shakkernerd. -- Memory/QMD: allow channel sessions in the shipped default QMD scope, while still denying groups. Thanks @steipete. -- Memory/QMD: stop registering the legacy lowercase root memory file as a separate default collection, so QMD now prefers `MEMORY.md` and the `memory/` tree without duplicate collection-add warnings. Thanks @steipete. +- Memory/QMD: allow channel sessions in the shipped default QMD scope, while still denying groups. +- Memory/QMD: stop registering the legacy lowercase root memory file as a separate default collection, so QMD now prefers `MEMORY.md` and the `memory/` tree without duplicate collection-add warnings. - Memory/memory-core: watch the `memory` directory directly and ignore non-markdown churn so nested note changes still sync on macOS + Node 25 environments where recursive `memory/**/*.md` glob watching fails. (#64711) Thanks @jasonxargs-boop and @vincentkoc. - WhatsApp: centralize per-account connection ownership so reconnects, login recovery, and outbound readiness stay attached to the live socket instead of drifting across monitor and login paths. (#65290) Thanks @mcaxtr and @vincentkoc. - iMessage: retry transient `watch.subscribe` startup failures before tearing down the monitor, and sanitize startup error logging so brief local transport stalls do not immediately bounce the channel or leak raw imsg RPC payloads into logs. (#65393) Thanks @vincentkoc. - CLI/audio providers: report env-authenticated providers as configured in `openclaw infer audio providers --json`, while keeping trusted workspace provider env lookup defaults stable during auth setup. (#65491) Thanks @scoootscooob. -- Plugins/install: reinstall bundled runtime packages when the matching platform native optional child is missing, so packaged Windows installs can recover dependencies that were packed on another host OS. Thanks @steipete. -- Memory/QMD: preserve explicit `memory.qmd.command` paths, create missing agent workspaces before QMD probes, and keep the current Node binary on QMD subprocess PATH so service and gateway environments do not fall back to builtin search unnecessarily. Thanks @steipete. +- Plugins/install: reinstall bundled runtime packages when the matching platform native optional child is missing, so packaged Windows installs can recover dependencies that were packed on another host OS. +- Memory/QMD: preserve explicit `memory.qmd.command` paths, create missing agent workspaces before QMD probes, and keep the current Node binary on QMD subprocess PATH so service and gateway environments do not fall back to builtin search unnecessarily. - Plugins/Lobster: load the published `@clawdbot/lobster/core` runtime in process so bundled Lobster runs stop depending on private package internals. (#64755) Thanks @mbelinky. - Agents/CLI: keep unrelated config, session, transcript, and MCP bootstrap runtime off common `openclaw agent` cold paths so provider selection and agent startup stop stalling on heavyweight imports. Thanks @vincentkoc. - Setup/config/install: stop setup, config dry-runs, and daemon install from eagerly booting auth-profile and plugin repair runtime when those paths are not needed, so onboarding and local service setup avoid long cold-start stalls. Thanks @vincentkoc. @@ -1254,12 +1263,12 @@ Docs: https://docs.openclaw.ai ### Changes -- Dreaming/memory-wiki: add ChatGPT import ingestion plus new `Imported Insights` and `Memory Palace` diary subtabs so Dreaming can inspect imported source chats, compiled wiki pages, and full source pages directly from the UI. (#64505) Thanks @steipete. -- Control UI/webchat: render assistant media/reply/voice directives as structured chat bubbles, add the `[embed ...]` rich output tag, and gate external embed URLs behind config. (#64104) Thanks @steipete. +- Dreaming/memory-wiki: add ChatGPT import ingestion plus new `Imported Insights` and `Memory Palace` diary subtabs so Dreaming can inspect imported source chats, compiled wiki pages, and full source pages directly from the UI. (#64505). +- Control UI/webchat: render assistant media/reply/voice directives as structured chat bubbles, add the `[embed ...]` rich output tag, and gate external embed URLs behind config. (#64104). - Tools/video_generate: add URL-only generated asset delivery, typed `providerOptions`, reference audio inputs, per-asset role hints, `adaptive` aspect-ratio support, and a higher image-input cap so video providers can expose richer generation modes without forcing large files into memory. (#61987, #61988) Thanks @xieyongliang. -- Feishu: improve document comment sessions with richer context parsing, comment reactions, and typing feedback so document-thread conversations behave more like chat conversations. (#63785) Thanks @steipete. -- Microsoft Teams: add reaction support, reaction listing, Graph pagination, and delegated OAuth setup for sending reactions while preserving application-auth read paths. (#51646) Thanks @steipete. -- Plugins: allow plugin manifests to declare activation and setup descriptors so plugin setup flows can describe required auth, pairing, and configuration steps without hardcoded core special cases. (#64780) Thanks @steipete. +- Feishu: improve document comment sessions with richer context parsing, comment reactions, and typing feedback so document-thread conversations behave more like chat conversations. (#63785). +- Microsoft Teams: add reaction support, reaction listing, Graph pagination, and delegated OAuth setup for sending reactions while preserving application-auth read paths. (#51646). +- Plugins: allow plugin manifests to declare activation and setup descriptors so plugin setup flows can describe required auth, pairing, and configuration steps without hardcoded core special cases. (#64780). - Ollama: cache `/api/show` context-window and capability metadata during model discovery so repeated picker refreshes stop refetching unchanged models, while still retrying after empty responses and invalidating on digest changes. (#64753) Thanks @ImLukeF. - Models/providers: surface how configured OpenAI-compatible endpoints are classified in embedded-agent debug logs, so local and proxy routing issues are easier to diagnose. (#64754) Thanks @ImLukeF. - QA/parity: add the GPT-5.4 vs Opus 4.6 agentic parity report gate with shared scenario coverage checks, stricter evidence heuristics, and skipped-scenario accounting for maintainer review. (#64441) Thanks @100yenadmin. @@ -1273,8 +1282,8 @@ Docs: https://docs.openclaw.ai - Control UI/webchat: persist agent-run TTS audio replies into webchat history and preserve interleaved tool card pairing so generated audio and mixed tool output stay attached to the right messages. (#63514) Thanks @bittoby. - WhatsApp: honor the configured default account when the active listener helper is used without an explicit account id, so named default accounts do not get registered under `default`. (#53918) Thanks @yhyatt. - ACP/agents: suppress commentary-phase child assistant relay text in ACP parent stream updates, so spawned child runs stop leaking internal progress chatter into the parent session. Thanks @vincentkoc. -- Agents/timeouts: honor explicit run timeouts in the LLM idle watchdog and align default timeout config so slow models can keep working until the configured limit instead of using the wrong idle window. Thanks @steipete. -- Config: include `asyncCompletion` in the generated zod schema so documented async completion config no longer fails with an unrecognized-key error. (#63618) Thanks @steipete. +- Agents/timeouts: honor explicit run timeouts in the LLM idle watchdog and align default timeout config so slow models can keep working until the configured limit instead of using the wrong idle window. +- Config: include `asyncCompletion` in the generated zod schema so documented async completion config no longer fails with an unrecognized-key error. (#63618). - Google/Veo: stop sending the unsupported `numberOfVideos` request field so Gemini Developer API Veo runs do not fail before OpenClaw can complete the intended Google video generation path. (#64723) Thanks @velvet-shark. - QA/packaging: stop packaged CLI startup and completion cache generation from reading repo-only QA scenario markdown, ship the bundled QA scenario pack in npm releases, and keep `openclaw completion --write-state` working even if QA setup is broken. (#64648) Thanks @obviyus. - Codex/QA: keep Codex app-server coordination chatter out of visible replies, add a live QA leak scenario, and classify leaked harness meta text as a QA failure instead of a successful reply. Thanks @vincentkoc. @@ -1291,10 +1300,10 @@ Docs: https://docs.openclaw.ai ### Changes -- Models/Codex: add the bundled Codex provider and plugin-owned app-server harness so `codex/gpt-*` models use Codex-managed auth, native threads, model discovery, and compaction while `openai/gpt-*` stays on the normal OpenAI provider path. (#64298) Thanks @steipete. +- Models/Codex: add the bundled Codex provider and plugin-owned app-server harness so `codex/gpt-*` models use Codex-managed auth, native threads, model discovery, and compaction while `openai/gpt-*` stays on the normal OpenAI provider path. (#64298). - Memory/Active Memory: add a new optional Active Memory plugin that gives OpenClaw a dedicated memory sub-agent right before the main reply, so ongoing chats can automatically pull in relevant preferences, context, and past details without making users remember to manually say "remember this" or "search memory" first. Includes configurable message/recent/full context modes, live `/verbose` inspection, advanced prompt/thinking overrides for tuning, and opt-in transcript persistence for debugging. Docs: https://docs.openclaw.ai/concepts/active-memory. (#63286) Thanks @Takhoffman. - macOS/Talk: add an experimental local MLX speech provider for Talk Mode, with explicit provider selection, local utterance playback, interruption handling, and system-voice fallback. (#63539) Thanks @ImLukeF. -- Tools/video generation: add Seedance 2.0 model refs to the bundled fal provider and submit the provider-specific duration, resolution, audio, and seed metadata fields needed for live Seedance 2.0 runs. Thanks @steipete. +- Tools/video generation: add Seedance 2.0 model refs to the bundled fal provider and submit the provider-specific duration, resolution, audio, and seed metadata fields needed for live Seedance 2.0 runs. - Microsoft Teams: add message actions for pin, unpin, read, react, and listing reactions. (#53432) Thanks @sudie-codes. - QA/Matrix: add a live `openclaw qa matrix` lane backed by a disposable Matrix homeserver, shared live-transport seams, and Matrix-specific transport coverage for threading, reactions, restart, and allowlist behavior. (#64489) Thanks @gumadeiras. - QA/Telegram: add a live `openclaw qa telegram` lane for private-group bot-to-bot checks, harden its artifact handling, and preserve native Telegram command reply threading for QA verification. (#64303) Thanks @obviyus. @@ -1310,31 +1319,31 @@ Docs: https://docs.openclaw.ai - Control UI/dreaming: simplify the Scene and Diary surfaces, preserve unknown phase state for partial status payloads, and stabilize waiting-entry recency ordering so Dreaming status and review lists stay clear and deterministic. (#64035) Thanks @davemorin. - Agents: add an opt-in strict-agentic embedded Pi execution contract for GPT-5-family runs so plan-only or filler turns keep acting until they hit a real blocker. (#64241) Thanks @100yenadmin. - Agents/OpenAI: add provider-owned OpenAI/Codex tool schema compatibility and surface embedded-run replay/liveness state for long-running runs. (#64300) Thanks @100yenadmin. -- Dreaming/memory-wiki: add ChatGPT import ingestion plus new `Imported Insights` and `Memory Palace` diary subtabs so Dreaming can inspect imported source chats, compiled wiki pages, and full source pages directly from the UI. (#64505) Thanks @steipete. +- Dreaming/memory-wiki: add ChatGPT import ingestion plus new `Imported Insights` and `Memory Palace` diary subtabs so Dreaming can inspect imported source chats, compiled wiki pages, and full source pages directly from the UI. (#64505). ### Fixes -- Browser/security: tighten browser and sandbox navigation defenses across strict SSRF defaults, hostname allowlists, interaction-driven redirects, subframes, CDP discovery, existing sessions, tab actions, noVNC, marker-span sanitization, and Docker CDP source-range enforcement. (#61404, #63332, #63882, #63885, #63889, #64367, #64370, #64371) Thanks @steipete. -- Security/tools: harden exec preflight reads, host env denylisting, node output boundaries, outbound host-media reads, profile-mutation authorization, plugin install dependency scanning, ACPX tool hooks, Gmail watcher token redaction, and oversized realtime WebSocket frame handling. (#62333, #62661, #62662, #63277, #63551, #63553, #63886, #63890, #63891, #64459) Thanks @steipete. +- Browser/security: tighten browser and sandbox navigation defenses across strict SSRF defaults, hostname allowlists, interaction-driven redirects, subframes, CDP discovery, existing sessions, tab actions, noVNC, marker-span sanitization, and Docker CDP source-range enforcement. (#61404, #63332, #63882, #63885, #63889, #64367, #64370, #64371). +- Security/tools: harden exec preflight reads, host env denylisting, node output boundaries, outbound host-media reads, profile-mutation authorization, plugin install dependency scanning, ACPX tool hooks, Gmail watcher token redaction, and oversized realtime WebSocket frame handling. (#62333, #62661, #62662, #63277, #63551, #63553, #63886, #63890, #63891, #64459). - OpenAI/Codex: add required Codex OAuth scopes, classify provider/runtime failures more clearly, stop suggesting `/elevated full` when auto-approved host exec is unavailable, add OpenAI/Codex tool-schema compatibility, and preserve embedded-run replay/liveness truth across compaction retries and mutating side effects. (#64300, #64439) Thanks @100yenadmin. - CLI/WhatsApp media sends: route gateway-mode outbound sends with `--media` through the channel `sendMedia` path and preserve media access context, so WhatsApp document and attachment sends stop silently dropping the file while still delivering the caption. (#64478, #64492) Thanks @ShionEria. -- Microsoft Teams: restore media downloads for personal DMs, Bot Framework `a:` conversations, OneDrive/SharePoint shared files, and Graph-backed chat IDs; accept Bot Framework audience tokens; prevent feedback-learning filename collisions; keep long tool chains alive with typing indicators; add SSO sign-in callbacks; inject parent context for thread replies; and deliver cron announcements to Teams conversation IDs. (#54932, #55383, #55386, #58001, #58249, #58774, #59731, #60956, #62219, #62674, #63063, #63942, #63945, #63949, #63951, #63953, #64087, #64088, #64089) Thanks @steipete. -- Gateway/tailscale: start Tailscale exposure and the gateway update check before awaiting channel and plugin sidecar startup so remote operators are not locked out when startup sidecars stall. Thanks @steipete. +- Microsoft Teams: restore media downloads for personal DMs, Bot Framework `a:` conversations, OneDrive/SharePoint shared files, and Graph-backed chat IDs; accept Bot Framework audience tokens; prevent feedback-learning filename collisions; keep long tool chains alive with typing indicators; add SSO sign-in callbacks; inject parent context for thread replies; and deliver cron announcements to Teams conversation IDs. (#54932, #55383, #55386, #58001, #58249, #58774, #59731, #60956, #62219, #62674, #63063, #63942, #63945, #63949, #63951, #63953, #64087, #64088, #64089). +- Gateway/tailscale: start Tailscale exposure and the gateway update check before awaiting channel and plugin sidecar startup so remote operators are not locked out when startup sidecars stall. - Gateway/startup: keep WebSocket RPC available while channels and plugin sidecars start, hold `chat.history` unavailable until startup sidecars finish so synchronous history reads cannot stall startup (reported in #63450), refresh advertised gateway methods after deferred plugin reloads, and enforce the pre-auth WebSocket upgrade budget before the no-handler 503 path so upgrade floods cannot bypass connection limits during that window. (#63480) Thanks @neeravmakwana. - WhatsApp: keep inbound replies, media, composing indicators, and queued outbound deliveries attached to the current socket across reconnect gaps, including fresh retry-eligible sends after the listener comes back. (#30806, #46299, #62892, #63916) Thanks @mcaxtr. -- Gateway/thread routing: preserve Slack, Telegram, Mattermost, Matrix, ACP, restart-sentinel, and agent announce delivery targets so subagent, cron, stream-relay, session fallback, and restart messages land back in the originating thread, topic, or room casing. (#54840, #57056, #63143, #63228, #63506, #64343, #64391) Thanks @steipete. -- Models/fallback: preserve `/models` selection across transient primary-model failures and config reloads, allow timeout cooldown probes, classify OpenRouter no-endpoints responses, detect llama.cpp context overflows, and keep provider/runtime context metadata stable through reloads. (#61472, #64196, #64471) Thanks @steipete. +- Gateway/thread routing: preserve Slack, Telegram, Mattermost, Matrix, ACP, restart-sentinel, and agent announce delivery targets so subagent, cron, stream-relay, session fallback, and restart messages land back in the originating thread, topic, or room casing. (#54840, #57056, #63143, #63228, #63506, #64343, #64391). +- Models/fallback: preserve `/models` selection across transient primary-model failures and config reloads, allow timeout cooldown probes, classify OpenRouter no-endpoints responses, detect llama.cpp context overflows, and keep provider/runtime context metadata stable through reloads. (#61472, #64196, #64471). - Agents/BTW: keep `/btw` side questions working after tool-use turns by stripping replayed tool blocks, hidden reasoning, and malformed image payloads, omitting empty tool arrays, allowing Bedrock `auth: "aws-sdk"`, and routing Feishu `/btw` plus `/stop` through bounded out-of-band lanes. (#64218, #64219, #64225, #64324) Thanks @ngutman. - Control UI/BTW: render `/btw` side results as dismissible ephemeral cards in the browser, send `/btw` immediately during active runs, and clear stale BTW cards on reset flows so webchat matches the intended detached side-question behavior. (#64290) Thanks @ngutman. -- Commands/targeting: use the selected agent or session for command output, send policy, usage/cost, context reports, model lists, bash sandbox hints, BTW/compact working directories, plugin commands, and session exports so multi-agent commands describe and mutate the intended target instead of the requester. Thanks @steipete. -- Conversation bindings: normalize focused/current conversation ids, preserve binding metadata on account and Discord rebinds, avoid stale Discord lifecycle windows, and keep generic activity touches persisted so reply routing survives rebinds and restarts. Thanks @steipete. +- Commands/targeting: use the selected agent or session for command output, send policy, usage/cost, context reports, model lists, bash sandbox hints, BTW/compact working directories, plugin commands, and session exports so multi-agent commands describe and mutate the intended target instead of the requester. +- Conversation bindings: normalize focused/current conversation ids, preserve binding metadata on account and Discord rebinds, avoid stale Discord lifecycle windows, and keep generic activity touches persisted so reply routing survives rebinds and restarts. - iMessage/self-chat: distinguish normal DM outbound rows from true self-chat using `destination_caller_id` plus chat participants, preserve multi-handle self-chat aliases, drop ambiguous reflected echoes, and strip wrapped imsg RPC text fields. (#61619, #63868, #63980, #63989, #64000) Thanks @neeravmakwana. - Matrix: keep multi-account room scoping consistent, keep packaged crypto migrations warning-only when appropriate, preserve ordered block streaming, add explicit Matrix block-streaming opt-in, and resolve verification/bootstrap from the packaged runtime entry. (#58449, #59249, #59266, #64373) Thanks @gumadeiras. -- Telegram/security: tighten Telegram `allowFrom` sender validation and keep `/whoami` allowlist reporting in sync with command auth checks. Thanks @steipete. -- Agents/timeouts: extend the default LLM idle window to 120s and keep silent no-token idle timeouts on recovery paths, so slow models can retry or fall back before users see an error. Thanks @steipete. +- Telegram/security: tighten Telegram `allowFrom` sender validation and keep `/whoami` allowlist reporting in sync with command auth checks. +- Agents/timeouts: extend the default LLM idle window to 120s and keep silent no-token idle timeouts on recovery paths, so slow models can retry or fall back before users see an error. - Gateway/agents: preserve configured model selection and richer `IDENTITY.md` content across agent create/update flows and workspace moves, and fail safely instead of silently overwriting unreadable identity files. (#61577) Thanks @samzong. - Skills/TaskFlow: restore valid frontmatter fences for the bundled `taskflow` and `taskflow-inbox-triage` skills and copy bundled `SKILL.md` files as hard dist-runtime copies so skills stay discoverable and loadable after updates. (#64166, #64469) Thanks @extrasmall0. -- Skills: respect overridden home directories when loading personal skills so service, test, and custom launch environments read the intended user skill directory instead of the process home. Thanks @steipete. +- Skills: respect overridden home directories when loading personal skills so service, test, and custom launch environments read the intended user skill directory instead of the process home. - Windows/exec: settle supervisor waits from child exit state after stdout and stderr drain even when `close` never arrives, so CLI commands stop hanging or dying with forced `SIGKILL` on Windows. (#64072) Thanks @obviyus. - Browser/sandbox: prevent sandbox browser CDP startup hangs by recreating containers when the browser security hash changes and by waiting on the correct sandbox browser lifecycle. (#62873) Thanks @Syysean. - QQBot/streaming: make block streaming configurable per QQ bot account via `streaming.mode` (`"partial"` | `"off"`, default `"partial"`) instead of hardcoding it off, so responses can be delivered incrementally. (#63746) Thanks @WideLee. @@ -1344,7 +1353,7 @@ Docs: https://docs.openclaw.ai - Browser/control: auto-generate browser-control auth tokens for `none` and `trusted-proxy` modes, and route browser auth/profile/doctor helpers through the public browser plugin facades. (#63280, #63957) Thanks @pgondhi987. - Browser/act: centralize `/act` request normalization and execution dispatch while adding stable machine-readable route-level error codes for invalid requests, selector misuse, evaluate-disabled gating, target mismatch, and existing-session unsupported actions. (#63977) Thanks @joshavant. - Security/QQBot: enforce media storage boundaries for all outbound local file paths and route image-size probes through SSRF-guarded media fetching instead of raw `fetch()`. (#63271, #63495) Thanks @pgondhi987. -- Channel setup: ignore workspace plugin shadows when resolving trusted channel setup catalog entries so onboarding and setup flows keep using the bundled, trusted setup contract. Thanks @steipete. +- Channel setup: ignore workspace plugin shadows when resolving trusted channel setup catalog entries so onboarding and setup flows keep using the bundled, trusted setup contract. - Gateway/memory startup: load the explicitly selected memory-slot plugin during gateway startup, while keeping restrictive allowlists and implicit default memory slots from auto-starting unrelated memory plugins. (#64423) Thanks @EronFan. - Config/plugins: let config writes keep disabled plugin entries without forcing required plugin config schemas or crashing raw plugin validation, and avoid re-activating plugin registry state during schema checks. (#54971, #63296) Thanks @fuller-stack-dev. - Config validation: surface the actual offending field for strict-schema union failures in bindings, including top-level unexpected keys on the matching ACP branch. (#40841) Thanks @Hollychou924. @@ -1360,13 +1369,13 @@ Docs: https://docs.openclaw.ai - Gateway/session reset: emit the typed `before_reset` hook for gateway `/new` and `/reset`, preserving reset-hook behavior even when the previous transcript has already been archived. (#53872) Thanks @VACInc. - Plugins/commands: pass the active host `sessionKey` into plugin command contexts, and include `sessionId` when it is already available from the active session entry, so bundled and third-party commands can resolve the current conversation reliably. (#59044) Thanks @jalehman. - Agents/auth: honor `models.providers.*.authHeader` for pi embedded runner model requests by injecting `Authorization: Bearer ` when requested. (#54390) Thanks @lndyzwdxhs. -- Claude CLI: clear inherited Anthropic auth/header environment aliases before spawning Claude Code and add sanitized CLI backend auth-env diagnostics for debugging gateway-run provider selection. Thanks @steipete. +- Claude CLI: clear inherited Anthropic auth/header environment aliases before spawning Claude Code and add sanitized CLI backend auth-env diagnostics for debugging gateway-run provider selection. - Agents/failover: classify AbortError and stream-abort messages as timeout so Ollama NDJSON stream aborts stop showing `reason=unknown` in model fallback logs. (#58324) Thanks @yelog. - Fireworks/FirePass: disable Kimi K2.5 Turbo reasoning output by forcing thinking off on the FirePass path and hardening the provider wrapper so hidden reasoning no longer leaks into visible replies. (#63607) Thanks @frankekn. - Discord: update Carbon to v0.15.0. Thanks @thewilloftheshadow. - Config/Discord: coerce safe integer numeric Discord IDs to strings during config validation, keep unsafe or precision-losing numeric snowflakes rejected, and align `openclaw doctor` repair guidance with the same fail-closed behavior. (#45125) Thanks @moliendocode. - BlueBubbles/config: accept `enrichGroupParticipantsFromContacts` in the core strict config schema so gateways no longer fail validation or startup when the BlueBubbles plugin writes that field. (#56889) Thanks @zqchris. -- Feishu/webhooks: read webhook bodies through the pre-auth guard so unauthenticated webhook traffic stays under the same body budget as other protected channel ingress paths. Thanks @steipete. +- Feishu/webhooks: read webhook bodies through the pre-auth guard so unauthenticated webhook traffic stays under the same body budget as other protected channel ingress paths. - Tools/web_fetch: add an opt-in `tools.web.fetch.ssrfPolicy.allowRfc2544BenchmarkRange` config so fake-IP proxy environments that resolve public sites into `198.18.0.0/15` can use `web_fetch` without weakening the default SSRF block. (#61830) Thanks @xing-xing-coder. - Dreaming/cron: reconcile managed dreaming cron from startup config and runtime lifecycle changes, but only recover managed dreaming cron state during heartbeat-triggered dreaming checks so ordinary chat traffic does not recreate removed jobs. (#63873, #63929, #63938) Thanks @mbelinky. - Memory/lancedb: accept `dreaming` config when `memory-lancedb` owns the memory slot so Dreaming surfaces can read slot-owner settings without schema rejection. (#63874) Thanks @mbelinky. @@ -1377,13 +1386,13 @@ Docs: https://docs.openclaw.ai - Gateway/run cleanup: fix stale run-context TTL cleanup so the new maintenance sweep resets orphaned run sequence state and prevents unbounded run-context growth. (#52731) Thanks @artwalker. - UI/compaction: keep the compaction indicator in a retry-pending state until the run actually finishes, so the UI does not show `Context compacted` before compaction actually finishes. (#55132) Thanks @mpz4life. - Cron/tool schemas: keep cron tool schemas strict-model-friendly while still preserving `failureAlert=false`, nullable `agentId`/`sessionKey`, and flattened add/update recovery for the newly exposed cron job fields. (#55043) Thanks @brunolorente. -- Git metadata: read commit ids from packed refs as well as loose refs so version and status metadata stay accurate after repository maintenance. (#63943) Thanks @steipete. -- Gateway: keep `commands.list` skill entries categorized under tools and include provider-aware plugin `nativeName` metadata even when `scope=text`, so remote clients can group skills correctly and map text-surface plugin commands back to native aliases. (#64147) Thanks @steipete. +- Git metadata: read commit ids from packed refs as well as loose refs so version and status metadata stay accurate after repository maintenance. (#63943). +- Gateway: keep `commands.list` skill entries categorized under tools and include provider-aware plugin `nativeName` metadata even when `scope=text`, so remote clients can group skills correctly and map text-surface plugin commands back to native aliases. (#64147). - TUI: reset footer activity to idle when switching sessions so a stale streaming indicator cannot persist after the selection changes. (#63988) Thanks @neeravmakwana. - Claude CLI: stop marking spawned Claude Code runs as host-managed so they keep using normal CLI subscription behavior. (#64023) Thanks @Alex-Alaniz. -- Codex auth: brand Codex OAuth flows as OpenClaw in user-visible auth prompts and diagnostics. Thanks @steipete. -- Gateway/pairing: fail closed for paired device records that have no device tokens, and reject pairing approvals whose requested scopes do not match the requested device roles. Thanks @steipete. -- ACP/gateway chat: classify lifecycle errors before forwarding them to ACP clients so refusals use ACP's refusal stop reason while transient backend errors continue to finish as normal turns. Thanks @steipete. +- Codex auth: brand Codex OAuth flows as OpenClaw in user-visible auth prompts and diagnostics. +- Gateway/pairing: fail closed for paired device records that have no device tokens, and reject pairing approvals whose requested scopes do not match the requested device roles. +- ACP/gateway chat: classify lifecycle errors before forwarding them to ACP clients so refusals use ACP's refusal stop reason while transient backend errors continue to finish as normal turns. - Claude CLI/skills: pass eligible OpenClaw skills into CLI runs, including native Claude Code skill resolution via a temporary plugin plus per-run skill env/API key injection. (#62686, #62723) Thanks @zomars. - Discord: keep generated auto-thread names working with reasoning models by giving title generation enough output budget for thinking plus visible title text. (#64172) Thanks @hanamizuki. - Heartbeat: ignore doc-only Markdown fence markers in the default `HEARTBEAT.md` template so comment-only heartbeat scaffolds skip API calls again. (#61690, #63434) Thanks @ravyg. @@ -1439,10 +1448,10 @@ Docs: https://docs.openclaw.ai - Memory/dreaming: add a grounded REM backfill lane with historical `rem-harness --path`, diary commit/reset flows, cleaner durable-fact extraction, and live short-term promotion integration so old daily notes can replay into Dreams and durable memory without a second memory stack. Thanks @mbelinky. - Control UI/dreaming: add a structured diary view with timeline navigation, backfill/reset controls, traceable dreaming summaries, and a grounded Scene lane with promotion hints plus a safe clear-grounded action for staged backfill signals. (#63395) Thanks @mbelinky. -- QA/lab: add character-vibes evaluation reports with model selection and parallel runs so live QA can compare candidate behavior faster. Thanks @steipete. -- Plugins/provider-auth: let provider manifests declare `providerAuthAliases` so provider variants can share env vars, auth profiles, config-backed auth, and API-key onboarding choices without core-specific wiring. Thanks @steipete. +- QA/lab: add character-vibes evaluation reports with model selection and parallel runs so live QA can compare candidate behavior faster. +- Plugins/provider-auth: let provider manifests declare `providerAuthAliases` so provider variants can share env vars, auth profiles, config-backed auth, and API-key onboarding choices without core-specific wiring. - iOS: pin release versioning to an explicit CalVer in `apps/ios/version.json`, keep TestFlight iteration on the same short version until maintainers intentionally promote the next gateway version, and add the documented `pnpm ios:version:pin -- --from-gateway` workflow for release trains. (#63001) Thanks @ngutman. -- Tools/video_generate: extend the tool and the Plugin SDK with `providerOptions` (vendor-specific options forwarded as a JSON object), `inputAudios` / `audioRef` / `audioRefs` reference audio inputs, per-asset semantic role hints (`imageRoles` / `videoRoles` / `audioRoles`) using a typed `VideoGenerationAssetRole` union, a new `"adaptive"` aspect-ratio sentinel, and `maxInputAudios` provider capability declarations. Providers opt into `providerOptions` by declaring a typed `capabilities.providerOptions` schema (`{ seed: "number", draft: "boolean", ... }`); unknown keys and type mismatches cause the runtime fallback loop to skip the candidate with a visible warning and an `attempts` entry, so vendor-specific options never silently reach the wrong provider. Also raises the in-tool image input cap to 9 and updates the docs table to list all new parameters. (#61987) Thanks @xieyongliang. +- Tools/video_generate: extend the tool and the Plugin SDK with `providerOptions` (vendor-specific options forwarded as a JSON object), `inputAudios` / `audioRef` / `audioRefs` reference audio inputs, per-asset semantic role hints (`imageRoles` / `videoRoles` / `audioRoles`) using a typed `VideoGenerationAssetRole` union, a new `"adaptive"` aspect-ratio sentinel, and `maxInputAudios` provider capability declarations. Providers opt into `providerOptions` by declaring a typed `capabilities.providerOptions` schema (`{ seed: "number", draft: "boolean", .. }`); unknown keys and type mismatches cause the runtime fallback loop to skip the candidate with a visible warning and an `attempts` entry, so vendor-specific options never silently reach the wrong provider. Also raises the in-tool image input cap to 9 and updates the docs table to list all new parameters. (#61987) Thanks @xieyongliang. ### Fixes @@ -1450,7 +1459,7 @@ Docs: https://docs.openclaw.ai - Security/dotenv: block runtime-control env vars plus browser-control override and skip-server env vars from untrusted workspace `.env` files, and reject unsafe URL-style browser control override specifiers before lazy loading. (#62660, #62663) Thanks @eleqtrizit. - Gateway/node exec events: mark remote node `exec.started`, `exec.finished`, and `exec.denied` summaries as untrusted system events and sanitize node-provided command/output/reason text before enqueueing them, so remote node output cannot inject trusted `System:` content into later turns. (#62659) Thanks @eleqtrizit. - Plugins/onboarding auth choices: prevent untrusted workspace plugins from colliding with bundled provider auth-choice ids during non-interactive onboarding, so bundled provider setup keeps operator secrets out of untrusted workspace plugin handlers unless those plugins are explicitly trusted. (#62368) Thanks @pgondhi987. -- Security/dependency audit: force `basic-ftp` to `5.2.1` for the CRLF command-injection fix and bump Hono plus `@hono/node-server` in production resolution paths. Thanks @steipete. +- Security/dependency audit: force `basic-ftp` to `5.2.1` for the CRLF command-injection fix and bump Hono plus `@hono/node-server` in production resolution paths. - Android/pairing: clear stale setup-code auth on new QR scans, bootstrap operator and node sessions from fresh pairing, prefer stored device tokens after bootstrap handoff, and pause pairing auto-retry while the app is backgrounded so scan-once Android pairing recovers reliably again. (#63199) Thanks @obviyus. - Matrix/gateway: wait for Matrix sync readiness before marking startup successful, keep Matrix background handler failures contained, and route fatal Matrix sync stops through channel-level restart handling instead of crashing the whole gateway. (#62779) Thanks @gumadeiras. - Slack/media: preserve bearer auth across same-origin `files.slack.com` redirects while still stripping it on cross-origin Slack CDN hops, so `url_private_download` image attachments load again. (#62960) Thanks @vincentkoc. @@ -1465,18 +1474,18 @@ Docs: https://docs.openclaw.ai - Matrix/doctor: migrate legacy `channels.matrix.dm.policy: "trusted"` configs back to compatible DM policies during `openclaw doctor --fix`, preserving explicit `allowFrom` boundaries as `allowlist` and defaulting empty legacy configs to `pairing`. (#62942) Thanks @lukeboyett. - npm packaging: mirror bundled channel runtime deps, stage Nostr runtime deps, derive required root mirrors from manifests and built chunks, and test packed release tarballs without repo `node_modules` so fresh installs fail fast on missing plugin deps instead of crashing at runtime. (#63065) Thanks @scoootscooob. - QA/live auth: fail fast when live QA scenarios hit classified auth or runtime failure replies, including raw scenario wait paths, and sanitize missing-key guidance so gateway auth problems surface as actionable errors instead of timeouts. (#63333) Thanks @shakkernerd. -- Providers/OpenAI: default missing reasoning effort to `high` on OpenAI Responses, WebSocket, and compatible completions transports, while still honoring explicit per-run reasoning levels. Thanks @steipete. +- Providers/OpenAI: default missing reasoning effort to `high` on OpenAI Responses, WebSocket, and compatible completions transports, while still honoring explicit per-run reasoning levels. - Providers/Ollama: allow Ollama models using the native `api: "ollama"` path to optionally display thinking output when `/think` is set to a non-off level. (#62712) Thanks @hoyyeva. -- Codex CLI: pass OpenClaw's system prompt through Codex's `model_instructions_file` config override so fresh Codex CLI sessions receive the same prompt guidance as Claude CLI sessions. Thanks @steipete. -- Auth/profiles: persist explicit auth-profile upserts directly and skip external CLI sync for local writes so profile changes are saved without stale external credential state. Thanks @steipete. +- Codex CLI: pass OpenClaw's system prompt through Codex's `model_instructions_file` config override so fresh Codex CLI sessions receive the same prompt guidance as Claude CLI sessions. +- Auth/profiles: persist explicit auth-profile upserts directly and skip external CLI sync for local writes so profile changes are saved without stale external credential state. - Agents/timeouts: make the LLM idle timeout inherit `agents.defaults.timeoutSeconds` when configured, disable the unconfigured idle watchdog for cron runs, and point idle-timeout errors at `agents.defaults.llm.idleTimeoutSeconds`. Thanks @drvoss. - Agents/failover: classify Z.ai vendor code `1311` as billing and `1113` as auth, including long wrapped `1311` payloads, so these errors stop falling through to generic failover handling. (#49552) Thanks @1bcMax. - QQBot/media-tags: support HTML entity-encoded angle brackets (`<`/`>`), URL slashes in attributes, and self-closing media tags so upstream `` payloads are correctly parsed and normalized. (#60493) Thanks @ylc0919. - Memory/dreaming: harden grounded backfill inputs, diary writes, status payloads, and diary action classification by preserving source-day labels, rejecting missing or symlinked targets cleanly, normalizing diary headings in gateway backfills, and tightening claim splitting plus diary source metadata. Thanks @mbelinky. -- Memory/dreaming: accept embedded heartbeat trigger tokens so light and REM dreaming still run when runtime wrappers include extra heartbeat text. Thanks @steipete. +- Memory/dreaming: accept embedded heartbeat trigger tokens so light and REM dreaming still run when runtime wrappers include extra heartbeat text. - Android/manual connect: allow blank port input only for TLS manual gateway endpoints so standard HTTPS Tailscale hosts default to `443` without silently changing cleartext manual connects. (#63134) Thanks @Tyler-RNG. -- Windows/update: add heap headroom to Windows `pnpm build` steps during dev updates so update preflight builds stop failing on low default Node memory. Thanks @steipete. -- Plugin SDK: export the channel plugin base and web-search config contract through the public package so plugins can use them without private imports. Thanks @steipete. +- Windows/update: add heap headroom to Windows `pnpm build` steps during dev updates so update preflight builds stop failing on low default Node memory. +- Plugin SDK: export the channel plugin base and web-search config contract through the public package so plugins can use them without private imports. - Plugins/contracts: keep test-only helpers out of production contract barrels, load shared contract harnesses through bundled test surfaces, and harden guardrails so indirect re-exports and canonical `*.test.ts` files stay blocked. (#63311) Thanks @altaywtf. - Control UI/models: preserve provider-qualified refs for OpenRouter catalog models whose ids already contain slashes so picker selections submit allowlist-compatible model refs instead of dropping the `openrouter/` prefix. (#63416) Thanks @sallyom. - Plugin SDK/command auth: split command status builders onto the lightweight `openclaw/plugin-sdk/command-status` subpath while preserving deprecated `command-auth` compatibility exports, so auth-only plugin imports no longer pull status/context warmup into CLI onboarding paths. (#63174) Thanks @hxy91819. @@ -1487,11 +1496,11 @@ Docs: https://docs.openclaw.ai ### Fixes -- Telegram/setup: load setup and secret contracts through packaged top-level sidecars so installed npm builds no longer try to import missing `dist/extensions/telegram/src/*` files during gateway startup. Thanks @steipete. -- Bundled channels/setup: load shared secret contracts through packaged top-level sidecars across BlueBubbles, Feishu, Google Chat, IRC, Matrix, Mattermost, Microsoft Teams, Nextcloud Talk, Slack, and Zalo so installed npm builds no longer rely on missing `dist/extensions/*/src/*` files during gateway startup. Thanks @steipete. -- Bundled plugins: align packaged plugin compatibility metadata with the release version so bundled channels and providers load on OpenClaw 2026.4.8. Thanks @steipete. -- Agents/progress: keep `update_plan` available for OpenAI-family runs while returning compact success payloads and allowing `tools.experimental.planTool=false` to opt out. Thanks @steipete. -- Agents/exec: keep `/exec` current-default reporting aligned with real runtime behavior so `host=auto` sessions surface the correct host-aware fallback policy (`full/off` on gateway or node, `deny/off` on sandbox) instead of stale stricter defaults. Thanks @steipete. +- Telegram/setup: load setup and secret contracts through packaged top-level sidecars so installed npm builds no longer try to import missing `dist/extensions/telegram/src/*` files during gateway startup. +- Bundled channels/setup: load shared secret contracts through packaged top-level sidecars across BlueBubbles, Feishu, Google Chat, IRC, Matrix, Mattermost, Microsoft Teams, Nextcloud Talk, Slack, and Zalo so installed npm builds no longer rely on missing `dist/extensions/*/src/*` files during gateway startup. +- Bundled plugins: align packaged plugin compatibility metadata with the release version so bundled channels and providers load on OpenClaw 2026.4.8. +- Agents/progress: keep `update_plan` available for OpenAI-family runs while returning compact success payloads and allowing `tools.experimental.planTool=false` to opt out. +- Agents/exec: keep `/exec` current-default reporting aligned with real runtime behavior so `host=auto` sessions surface the correct host-aware fallback policy (`full/off` on gateway or node, `deny/off` on sandbox) instead of stale stricter defaults. - Slack: honor ambient HTTP(S) proxy settings for Socket Mode WebSocket connections, including NO_PROXY exclusions, so proxy-only deployments can connect without a monkey patch. (#62878) Thanks @mjamiv. - Slack/actions: pass the already resolved read token into `downloadFile` so SecretRef-backed bot tokens no longer fail after a raw config re-read. (#62097) Thanks @martingarramon. - Network/fetch guard: skip target DNS pinning when trusted env-proxy mode is active so proxy-only sandboxes can let the trusted proxy resolve outbound hosts. (#59007) Thanks @cluster2600. @@ -1503,19 +1512,19 @@ Docs: https://docs.openclaw.ai ### Changes - CLI/infer: add a first-class `openclaw infer ...` hub for provider-backed inference workflows across model, media, web, and embedding tasks. Thanks @Takhoffman. -- Tools/media generation: auto-fallback across auth-backed image, music, and video providers by default, preserve intent during provider switches, remap size/aspect/resolution/duration hints to the closest supported option, and surface provider capabilities plus mode-aware video-to-video support. Thanks @steipete. +- Tools/media generation: auto-fallback across auth-backed image, music, and video providers by default, preserve intent during provider switches, remap size/aspect/resolution/duration hints to the closest supported option, and surface provider capabilities plus mode-aware video-to-video support. - Memory/wiki: restore the bundled `memory-wiki` stack with plugin, CLI, sync/query/apply tooling, memory-host integration, structured claim/evidence fields, compiled digest retrieval, claim-health linting, contradiction clustering, staleness dashboards, and freshness-weighted search. Thanks @vincentkoc. - Plugins/webhooks: add a bundled webhook ingress plugin so external automation can create and drive bound TaskFlows through per-route shared-secret endpoints. (#61892) Thanks @mbelinky. - Gateway/sessions: add persisted compaction checkpoints plus Sessions UI branch/restore actions so operators can inspect and recover pre-compaction session state. (#62146) Thanks @scoootscooob. - Compaction: add pluggable compaction provider registry so plugins can replace the built-in summarization pipeline. Configure via `agents.defaults.compaction.provider`; falls back to LLM summarization on provider failure. (#56224) Thanks @DhruvBhatia0. -- Agents/system prompt: add `agents.defaults.systemPromptOverride` for controlled prompt experiments plus heartbeat prompt-section controls so heartbeat runtime behavior can stay enabled without injecting heartbeat instructions every turn. Thanks @steipete. +- Agents/system prompt: add `agents.defaults.systemPromptOverride` for controlled prompt experiments plus heartbeat prompt-section controls so heartbeat runtime behavior can stay enabled without injecting heartbeat instructions every turn. - Providers/Google: add Gemma 4 model support and keep Google fallback resolution on the requested provider path so native Google Gemma routes work again. (#61507) Thanks @eyjohn. - Providers/Google: preserve explicit thinking-off semantics for Gemma 4 while still enabling Gemma reasoning support in compatibility wrappers. (#62127) Thanks @romgenie. - Providers/Arcee AI: add a bundled Arcee AI provider plugin with Trinity catalog entries, OpenRouter support, and updated onboarding/auth guidance. (#62068) Thanks @arthurbr11. -- Providers/Anthropic: restore Claude CLI as the preferred local Anthropic path in onboarding, model-auth guidance, doctor flows, and Docker Claude CLI live lanes again. Thanks @steipete. +- Providers/Anthropic: restore Claude CLI as the preferred local Anthropic path in onboarding, model-auth guidance, doctor flows, and Docker Claude CLI live lanes again. - Providers/Ollama: detect vision capability from the `/api/show` response and set image input on models that support it so Ollama vision models accept image attachments. (#62193) Thanks @BruceMacD. - Memory/dreaming: ingest redacted session transcripts into the dreaming corpus with per-day session-corpus notes, cursor checkpointing, and promotion/doctor support. (#62227) Thanks @vignesh07. -- Providers/inferrs: add string-content compatibility for stricter OpenAI-compatible chat backends, document `inferrs` setup with a full config example, and add troubleshooting guidance for local backends that pass direct probes but fail on full agent-runtime prompts. Thanks @steipete. +- Providers/inferrs: add string-content compatibility for stricter OpenAI-compatible chat backends, document `inferrs` setup with a full config example, and add troubleshooting guidance for local backends that pass direct probes but fail on full agent-runtime prompts. - Agents/context engine: expose prompt-cache runtime context to context engines and keep current-turn prompt-cache usage aligned with the active attempt instead of stale prior-turn assistant state. (#62179) Thanks @jalehman. - Plugin SDK/context engines: pass `availableTools` and `citationsMode` into `assemble()`, and expose memory-artifact and memory-prompt seams so companion plugins and non-legacy context engines can consume active memory state without reaching into internals. Thanks @vincentkoc. - ACP/ACPX plugin: bump the bundled `acpx` pin to `0.5.1` so plugin-local installs and strict version checks pick up the latest published runtime release. (#62148) Thanks @onutc. @@ -1534,8 +1543,8 @@ Docs: https://docs.openclaw.ai - Agents/context overflow: combine oversized and aggregate tool-result recovery in one pass and restore a total-context overflow backstop so recoverable sessions retry instead of failing early. (#61651) Thanks @Takhoffman. - Auth/OpenAI Codex OAuth: reload fresh on-disk credentials inside the locked refresh path and retry once after `refresh_token_reused` rotates only the stored refresh token, so relogin/restart recovery stops getting stuck on stale cached auth state. Thanks @owen-ever. - Auth/OpenAI Codex OAuth: keep native `/model ...@profile` selections on the target session and honor explicit user-locked auth profiles even when per-agent auth order excludes them. (#62744) Thanks @jalehman. -- Providers/Anthropic: preserve thinking blocks for Claude Opus 4.5+, Sonnet 4.5+, and newer Claude 4-family models so prompt-cache prefixes keep matching, and skip `service_tier` injection on OAuth-authenticated stream wrapper requests so Claude OAuth streaming stops failing with HTTP 401. (#60356, #61793) Thanks @steipete. -- Agents/Claude CLI: surface nested API error messages from structured CLI output so billing/auth/provider failures show the real provider error instead of an opaque CLI failure. Thanks @steipete. +- Providers/Anthropic: preserve thinking blocks for Claude Opus 4.5+, Sonnet 4.5+, and newer Claude 4-family models so prompt-cache prefixes keep matching, and skip `service_tier` injection on OAuth-authenticated stream wrapper requests so Claude OAuth streaming stops failing with HTTP 401. (#60356, #61793). +- Agents/Claude CLI: surface nested API error messages from structured CLI output so billing/auth/provider failures show the real provider error instead of an opaque CLI failure. - Agents/exec: preserve explicit `host=node` routing under elevated defaults when `tools.exec.host=auto`, fail loud on invalid elevated cross-host overrides, and keep `strictInlineEval` commands blocked after approval timeouts instead of falling through to automatic execution. (#61739) Thanks @obviyus. - Nodes/exec approvals: keep `host=node` POSIX transport shell wrappers (`/bin/sh -lc ...`) aligned with inner-command allowlist analysis so allowlisted scripts stop prompting unnecessarily, while Windows `cmd.exe` wrapper runs stay approval-gated. (#62401) Thanks @ngutman. - Nodes/exec approvals: keep Windows `cmd.exe /c` wrapper runs approval-gated even when `env` carriers, including env-assignment carriers, wrap the shell invocation. (#62439) Thanks @ngutman. @@ -1545,18 +1554,18 @@ Docs: https://docs.openclaw.ai - Feishu/docx uploads: honor `tools.fs.workspaceOnly` for local `upload_file` and `upload_image` paths by forwarding workspace-constrained `localRoots` into the media loader, so docx uploads can no longer read host-local files outside the workspace when workspace-only mode is active. (#62369) Thanks @pgondhi987. - Network/fetch guard: drop request bodies and body-describing headers on cross-origin `307` and `308` redirects by default, so attacker-controlled redirect hops cannot receive secret-bearing POST payloads from SSRF-guarded fetch flows unless a caller explicitly opts in. (#62357) Thanks @pgondhi987. - Browser/SSRF: treat main-frame `document` redirect hops as navigations even when Playwright does not flag them as `isNavigationRequest()`, so strict private-network blocking still stops forbidden redirect pivots before the browser reaches the internal target. (#62355) Thanks @pgondhi987. -- Browser/node invoke: block persistent browser profile create, reset, and delete mutations through `browser.proxy` on both gateway-forwarded `node.invoke` and the node-host proxy path, even when no profile allowlist is configured. (#60489) Thanks @steipete. +- Browser/node invoke: block persistent browser profile create, reset, and delete mutations through `browser.proxy` on both gateway-forwarded `node.invoke` and the node-host proxy path, even when no profile allowlist is configured. (#60489). - Gateway/node pairing: require a fresh pairing request when a previously paired node reconnects with additional declared commands, and keep the live session pinned to the earlier approved command set until the upgrade is approved. (#62658) Thanks @eleqtrizit. - Gateway/auth: invalidate existing shared-token and password WebSocket sessions when the configured secret rotates, so stale authenticated sockets cannot stay attached after token or password changes. (#62350) Thanks @pgondhi987. -- MS Teams/security: validate file-consent upload URLs against HTTPS, Microsoft/SharePoint host allowlists, and private-IP DNS checks before uploading attachments, blocking SSRF-style consent-upload abuse. (#23596) Thanks @steipete. +- MS Teams/security: validate file-consent upload URLs against HTTPS, Microsoft/SharePoint host allowlists, and private-IP DNS checks before uploading attachments, blocking SSRF-style consent-upload abuse. (#23596). - Media/base64 decode guards: enforce byte limits before decoding missed base64-backed Teams, Signal, QQ Bot, and image-tool payloads so oversized inbound media and data URLs no longer bypass pre-decode size checks. (#62007) Thanks @eleqtrizit. -- Runtime event trust: mark background `notifyOnExit` summaries, ACP parent-stream relays, and wake-hook payloads as untrusted system events so lower-trust runtime output no longer re-enters later turns as trusted `System:` text. (#62003) Thanks @steipete. -- Auto-reply/media: allow managed generated-media `MEDIA:` paths from normal reply text again while still blocking arbitrary host-local media and document paths, so generated media keep delivering without reopening host-path injection holes. Thanks @steipete. +- Runtime event trust: mark background `notifyOnExit` summaries, ACP parent-stream relays, and wake-hook payloads as untrusted system events so lower-trust runtime output no longer re-enters later turns as trusted `System:` text. (#62003). +- Auto-reply/media: allow managed generated-media `MEDIA:` paths from normal reply text again while still blocking arbitrary host-local media and document paths, so generated media keep delivering without reopening host-path injection holes. - Gateway/status and containers: auto-bind to `0.0.0.0` inside Docker and Podman environments, and probe local TLS gateways over `wss://` with self-signed fingerprint forwarding so container startup and loopback TLS status checks work again. (#61818, #61935) Thanks @openperf and contributors. - Gateway/OpenAI-compatible HTTP: abort in-flight `/v1/chat/completions` and `/v1/responses` turns when clients disconnect so abandoned HTTP requests stop wasting agent runtime. (#54388) Thanks @Lellansin. - macOS/gateway version: strip trailing commit metadata from CLI version output before semver parsing so the Mac app recognizes installed gateway versions like `OpenClaw 2026.4.2 (d74a122)` again. (#61111) Thanks @oliviareid-svg. -- Sessions/model selection: resolve the explicitly selected session model separately from runtime fallback resolution so session status and live model switching stay aligned with the chosen model. Thanks @steipete. -- Discord/ACP bindings: canonicalize DM conversation identity across inbound messages, component interactions, native commands, and current-conversation binding resolution so `--bind here` in Discord DMs keeps routing follow-up replies to the bound agent instead of falling back to the default agent. Thanks @steipete. +- Sessions/model selection: resolve the explicitly selected session model separately from runtime fallback resolution so session status and live model switching stay aligned with the chosen model. +- Discord/ACP bindings: canonicalize DM conversation identity across inbound messages, component interactions, native commands, and current-conversation binding resolution so `--bind here` in Discord DMs keeps routing follow-up replies to the bound agent instead of falling back to the default agent. - Discord: recover forwarded referenced message text and attachments when snapshots are missing, use `ws://` again for gateway monitor sockets, stop forcing a hardcoded temperature for Codex-backed auto-thread titles, and harden voice receive recovery so rapid speaker restarts keep their next utterance. (#41536, #61670) Thanks @artwalker and contributors. - Slack/thread mentions: add `channels.slack.thread.requireExplicitMention` so Slack channels that already require mentions can also require explicit `@bot` mentions inside bot-participated threads. (#58276) Thanks @praktika-engineer. - Slack/threading: keep legacy thread stickiness for real replies when older callers omit `isThreadReply`, while still honoring `replyToMode` for Slack's auto-created top-level `thread_ts`. (#61835) Thanks @kaonash. @@ -1567,10 +1576,10 @@ Docs: https://docs.openclaw.ai - Plugins/loaders: centralize bundled `dist/**` Jiti native-load policy and keep channel, public-surface, facade, and config-metadata loader seams off native Jiti on Windows so onboarding and configure flows stop tripping `ERR_UNSUPPORTED_ESM_URL_SCHEME`. (#62286) Thanks @chen-zhang-cs-code. - Plugins/channels: keep bundled channel artifact and secret-contract loading stable under lazy loading, preserve plugin-schema defaults during install, and fix Windows `file://` plus native-Jiti plugin loader paths so onboarding, doctor, `openclaw secret`, and bundled plugin installs work again. (#61832, #61836, #61853, #61856) Thanks @Zeesejo and contributors. - Plugins/ClawHub: verify downloaded plugin archives against version metadata SHA-256, fail closed when archive integrity metadata is missing or malformed, and tighten fallback ZIP verification so plugin installs cannot proceed on mismatched or incomplete ClawHub package metadata. (#60517) Thanks @mappel-nv. -- Plugins/provider hooks: stop recursive provider snapshot loads from overflowing the stack during plugin initialization, while still preserving cached nested provider-hook results. (#61922, #61938, #61946, #61951) Thanks @steipete. +- Plugins/provider hooks: stop recursive provider snapshot loads from overflowing the stack during plugin initialization, while still preserving cached nested provider-hook results. (#61922, #61938, #61946, #61951). - Docker/plugins: stop forcing bundled plugin discovery to `/app/extensions` in runtime images so packaged installs use compiled `dist/extensions` artifacts again and Node 24 containers do not boot through source-only plugin entry paths. Fixes #62044. (#62316) Thanks @gumadeiras. -- Providers/Ollama: honor the selected provider's `baseUrl` during streaming so multi-Ollama setups stop routing every stream to the first configured Ollama endpoint. (#61678) Thanks @steipete. -- Providers/Ollama: stop warning that Ollama could not be reached when discovery only sees empty default local stubs, while still keeping real explicit Ollama overrides loud when the endpoint is unreachable. Thanks @steipete. +- Providers/Ollama: honor the selected provider's `baseUrl` during streaming so multi-Ollama setups stop routing every stream to the first configured Ollama endpoint. (#61678). +- Providers/Ollama: stop warning that Ollama could not be reached when discovery only sees empty default local stubs, while still keeping real explicit Ollama overrides loud when the endpoint is unreachable. - Providers/xAI: recognize `api.grok.x.ai` as an xAI-native endpoint again and keep legacy `x_search` auth resolution working so older xAI web-search configs continue to load. (#61377) Thanks @jjjojoj. - Providers/Mistral: send `reasoning_effort` for `mistral/mistral-small-latest` (Mistral Small 4) with thinking-level mapping, and mark the catalog entry as reasoning-capable so adjustable reasoning matches Mistral’s Chat Completions API. (#62162) Thanks @neeravmakwana. - OpenAI TTS/Groq: send `wav` to Groq-compatible speech endpoints, honor explicit `responseFormat` overrides on OpenAI-compatible paths, and only mark voice-note output as voice-compatible when the actual format is `opus`. (#62233) Thanks @neeravmakwana. @@ -1578,7 +1587,7 @@ Docs: https://docs.openclaw.ai - Tools/web search/Exa: show Exa Search in onboarding and configure provider pickers again by marking the bundled Exa provider as setup-visible. Thanks @vincentkoc. - Memory/vector recall: surface explicit warnings when `sqlite-vec` is unavailable or vector writes are degraded, and strip managed Light Sleep and REM blocks before daily-note ingestion so memory indexing and dreaming stop reporting false-success or re-ingesting staged output. (#61720) Thanks @MonkeyLeeT. - Memory/dreaming: make Dreams config reads and writes respect the selected memory slot plugin instead of always targeting `memory-core`. (#62275) Thanks @SnowSky1. -- QQ Bot/media: route gateway-side attachment and fallback downloads through guarded QQ/Tencent HTTPS fetches so QQ media handling no longer follows arbitrary remote hosts. Thanks @steipete. +- QQ Bot/media: route gateway-side attachment and fallback downloads through guarded QQ/Tencent HTTPS fetches so QQ media handling no longer follows arbitrary remote hosts. - Browser/remote CDP: retry the DevTools websocket once after remote browser restarts so healthy remote browser profiles do not fail availability checks during CDP warm-up. (#57397) Thanks @ThanhNguyxn07. - UI/light mode: target both root and nested WebKit scrollbar thumbs in the light theme so page-level and container scrollbars stay visible on light backgrounds. (#61753) Thanks @chziyue. - Agents/subagents: honor `sessions_spawn(lightContext: true)` for spawned subagent runs by preserving lightweight bootstrap context through the gateway and embedded runner instead of silently falling back to full workspace bootstrap injection. (#62264) Thanks @theSamPadilla. @@ -1586,7 +1595,7 @@ Docs: https://docs.openclaw.ai - Agents/model fallback: classify minimal HTTP 404 API errors (for example `404 status code (no body)`) as `model_not_found` so assistant failures throw into the fallback chain instead of stopping at the first fallback candidate. (#62119) Thanks @neeravmakwana. - BlueBubbles/network: respect explicit private-network opt-out for loopback and private `serverUrl` values across account resolution, status probes, monitor startup, and attachment downloads, while keeping public-host attachment hostname pinning intact. (#59373) Thanks @jpreagan. - Agents/heartbeat: keep heartbeat runs pinned to the main session so active subagent transcripts are not overwritten by heartbeat status messages. (#61803) Thanks @100yenadmin. -- Agents/heartbeat: respect disabled heartbeat prompt guidance so operators can suppress heartbeat prompt instructions without disabling heartbeat runtime behavior. Thanks @steipete. +- Agents/heartbeat: respect disabled heartbeat prompt guidance so operators can suppress heartbeat prompt instructions without disabling heartbeat runtime behavior. - Agents/compaction: stop compaction-wait aborts from re-entering prompt failover and replaying completed tool turns. (#62600) Thanks @i-dentifier. - Approvals/runtime: move native approval lifecycle assembly into shared core bootstrap/runtime seams driven by channel capabilities and runtime contexts, and remove the legacy bundled approval fallback wiring. (#62135) Thanks @gumadeiras. - Security/fetch-guard: stop rejecting operator-configured proxy hostnames against the target-scoped hostname allowlist in SSRF-guarded fetches, restoring proxy-based media downloads for Telegram and other channels. (#62312) Thanks @ademczuk. @@ -1594,7 +1603,7 @@ Docs: https://docs.openclaw.ai - Agents/sessions_send: pass `threadId` through announce delivery so cross-session notifications land in the correct Telegram forum topic instead of the group's general thread. (#62758) Thanks @jalehman. - Daemon/systemd: keep sudo systemctl calls scoped to the invoking user when machine-scoped systemctl fails, while still avoiding machine fallback for permission-denied user bus errors. (#62337) Thanks @Aftabbs. - Docs/i18n: relocalize final localized-page links after translation and remove the zh-CN homepage redirect override so localized Mintlify pages resolve to the correct language roots again. (#61796) Thanks @hxy91819. -- Agents/exec: keep timed-out shell-backgrounded commands on the failed path and point long-running jobs to exec background/yield sessions so process polling is only suggested for registered sessions. Thanks @steipete. +- Agents/exec: keep timed-out shell-backgrounded commands on the failed path and point long-running jobs to exec background/yield sessions so process polling is only suggested for registered sessions. - Agents/model resolution: let explicit `openai-codex/gpt-5.4` selection prefer provider runtime metadata when it reports a larger context window, keeping configured Codex runs aligned with the live provider limits. (#62694) Thanks @ruclaw7. - Agents/model resolution: keep explicit-model runtime comparisons on the configured workspace plugin registry, so workspace-installed providers do not silently fall back to stale explicit metadata during runtime model lookup. Thanks @obviyus. - Providers/Z.AI: default onboarding and endpoint detection to GLM-5.1 instead of GLM-5. (#61998) Thanks @serg0x. @@ -1617,42 +1626,42 @@ Docs: https://docs.openclaw.ai ### Changes -- Agents/video generation: add the built-in `video_generate` tool so agents can create videos through configured providers and return the generated media directly in the reply. Thanks @steipete. -- Agents/music generation: ignore unsupported optional hints such as `durationSeconds` with a warning instead of hard-failing requests on providers like Google Lyria. Thanks @steipete. +- Agents/video generation: add the built-in `video_generate` tool so agents can create videos through configured providers and return the generated media directly in the reply. +- Agents/music generation: ignore unsupported optional hints such as `durationSeconds` with a warning instead of hard-failing requests on providers like Google Lyria. - Providers/Arcee AI: add a bundled Arcee AI provider plugin with `ARCEEAI_API_KEY` onboarding, Trinity model catalog (mini, large-preview, large-thinking), OpenAI-compatible API support, and OpenRouter as an alternative auth path. (#62068) Thanks @arthurbr11. -- Providers/ComfyUI: add a bundled `comfy` workflow media plugin for local ComfyUI and Comfy Cloud workflows, including shared `image_generate`, `video_generate`, and workflow-backed `music_generate` support, with prompt injection, optional reference-image upload, live tests, and output download. Thanks @steipete. -- Tools/music generation: add the built-in `music_generate` tool with bundled Google (Lyria) and MiniMax providers plus workflow-backed Comfy support, including async task tracking and follow-up delivery of finished audio. Thanks @steipete. -- Providers: add bundled Qwen, Fireworks AI, and StepFun providers, plus MiniMax TTS, Ollama Web Search, and MiniMax Search integrations for chat, speech, and search workflows. (#60032, #55921, #59318, #54648) Thanks @steipete. +- Providers/ComfyUI: add a bundled `comfy` workflow media plugin for local ComfyUI and Comfy Cloud workflows, including shared `image_generate`, `video_generate`, and workflow-backed `music_generate` support, with prompt injection, optional reference-image upload, live tests, and output download. +- Tools/music generation: add the built-in `music_generate` tool with bundled Google (Lyria) and MiniMax providers plus workflow-backed Comfy support, including async task tracking and follow-up delivery of finished audio. +- Providers: add bundled Qwen, Fireworks AI, and StepFun providers, plus MiniMax TTS, Ollama Web Search, and MiniMax Search integrations for chat, speech, and search workflows. (#60032, #55921, #59318, #54648). - Providers/Amazon Bedrock: add bundled Mantle support plus inference-profile discovery and automatic request-region injection so Bedrock-hosted Claude, GPT-OSS, Qwen, Kimi, GLM, and similar routes work with less manual setup. (#61296, #61299) Thanks @wirjo. - Control UI/multilingual: add localized control UI support for Simplified Chinese, Traditional Chinese, Brazilian Portuguese, German, Spanish, Japanese, Korean, French, Turkish, Indonesian, Polish, and Ukrainian. Thanks @vincentkoc. -- Plugins: add plugin-config TUI prompts to guided onboarding/setup flows, and add `openclaw plugins install --force` so existing plugin and hook-pack targets can be replaced without using the dangerous-code override flag. (#60590, #60544) Thanks @steipete. +- Plugins: add plugin-config TUI prompts to guided onboarding/setup flows, and add `openclaw plugins install --force` so existing plugin and hook-pack targets can be replaced without using the dangerous-code override flag. (#60590, #60544). - Control UI/skills: add ClawHub search, detail, and install flows directly in the Skills panel. (#60134) Thanks @samzong. - iOS/exec approvals: add generic APNs approval notifications that open an in-app exec approval modal, fetch command details only after authenticated operator reconnect, and clear stale notification state when the approval resolves. (#60239) Thanks @ngutman. - Matrix/exec approvals: add Matrix-native exec approval prompts with account-scoped approvers, channel-or-DM delivery, and room-thread aware resolution handling. (#58635) Thanks @gumadeiras. -- Channels/context visibility: add configurable `contextVisibility` per channel (`all`, `allowlist`, `allowlist_quote`) so supplemental quote, thread, and fetched history context can be filtered by sender allowlists instead of always passing through as received. Thanks @steipete. +- Channels/context visibility: add configurable `contextVisibility` per channel (`all`, `allowlist`, `allowlist_quote`) so supplemental quote, thread, and fetched history context can be filtered by sender allowlists instead of always passing through as received. - Providers/request overrides: add shared model and media request transport overrides across OpenAI-, Anthropic-, Google-, and compatible provider paths, including headers, auth, proxy, and TLS controls. (#60200) Thanks @vincentkoc. -- Providers/OpenAI: add forward-compat `openai-codex/gpt-5.4-mini`, an opt-in GPT personality, and provider-owned GPT-5 prompt contributions so Codex/GPT runs stay cache-stable and compatible with bundled catalog lag. Thanks @steipete. +- Providers/OpenAI: add forward-compat `openai-codex/gpt-5.4-mini`, an opt-in GPT personality, and provider-owned GPT-5 prompt contributions so Codex/GPT runs stay cache-stable and compatible with bundled catalog lag. - Agents/Claude CLI: expose OpenClaw tools to background Claude CLI runs through a loopback MCP bridge and switch bundled runs to stdin + `stream-json` partial-message streaming so prompts stop riding argv, long replies show live progress, and final session/usage metadata still land cleanly. (#35676) Thanks @mylukin. -- ACPX/runtime: embed the ACP runtime directly in the bundled `acpx` plugin, remove the extra external ACP CLI hop, harden live ACP session binding and reuse, and add a generic `reply_dispatch` hook so bundled plugins like ACPX can own reply interception without hardcoded ACP paths in core auto-reply routing. (#61319) Thanks @steipete. -- Agents/progress: add experimental structured plan updates and structured execution item events so compatible UIs can show clearer step-by-step progress during long-running runs. Thanks @steipete. -- Providers/Anthropic: remove the Claude CLI backend and setup-token from new onboarding, keep existing configured legacy profiles runnable, and have `openclaw doctor` repair or remove stale `anthropic:claude-cli` state during migration. Thanks @steipete. -- Tools/video generation: add bundled xAI (`grok-imagine-video`), Alibaba Model Studio Wan, and Runway video providers, plus live-test/default model wiring for all three. Thanks @steipete. +- ACPX/runtime: embed the ACP runtime directly in the bundled `acpx` plugin, remove the extra external ACP CLI hop, harden live ACP session binding and reuse, and add a generic `reply_dispatch` hook so bundled plugins like ACPX can own reply interception without hardcoded ACP paths in core auto-reply routing. (#61319). +- Agents/progress: add experimental structured plan updates and structured execution item events so compatible UIs can show clearer step-by-step progress during long-running runs. +- Providers/Anthropic: remove the Claude CLI backend and setup-token from new onboarding, keep existing configured legacy profiles runnable, and have `openclaw doctor` repair or remove stale `anthropic:claude-cli` state during migration. +- Tools/video generation: add bundled xAI (`grok-imagine-video`), Alibaba Model Studio Wan, and Runway video providers, plus live-test/default model wiring for all three. - Memory/search: add Amazon Bedrock embeddings for Titan, Cohere, Nova, and TwelveLabs models, with AWS credential-chain auto-detection for `provider: "auto"` and provider-specific dimension controls. Thanks @wirjo. - Providers/Amazon Bedrock Mantle: generate bearer tokens from the AWS credential chain so Mantle auto-discovery can use IAM auth without manually exporting `AWS_BEARER_TOKEN_BEDROCK`. Thanks @wirjo. - Memory/dreaming (experimental): add weighted short-term recall promotion, a `/dreaming` command, Dreams UI, multilingual conceptual tagging, and doctor/status repair support, while refactoring dreaming from competing modes into three cooperative phases (light, deep, REM) with independent schedules and recovery behavior so durable memory promotion can run in the background with less manual setup. (#60569, #60697) Thanks @vignesh07. -- Memory/dreaming: add configurable aging controls (`recencyHalfLifeDays`, `maxAgeDays`) plus optional verbose logging so operators can tune recall decay and inspect promotion decisions more easily. Thanks @steipete. -- Memory/dreaming: add REM preview tooling (`openclaw memory rem-harness`, `promote-explain`), surface possible lasting truths during REM staging, and make deep promotion replay-safe so reruns reconcile instead of duplicating `MEMORY.md` entries. Thanks @steipete. +- Memory/dreaming: add configurable aging controls (`recencyHalfLifeDays`, `maxAgeDays`) plus optional verbose logging so operators can tune recall decay and inspect promotion decisions more easily. +- Memory/dreaming: add REM preview tooling (`openclaw memory rem-harness`, `promote-explain`), surface possible lasting truths during REM staging, and make deep promotion replay-safe so reruns reconcile instead of duplicating `MEMORY.md` entries. - Memory/dreaming: write dreaming trail content to top-level `dreams.md` instead of daily memory notes, update `/dreaming` help text to point there, and keep `dreams.md` available for explicit reads without pulling it into default recall. Thanks @davemorin. - Memory/dreaming: add the Dream Diary surface in Dreams, simplify user-facing dreaming config to `enabled` plus optional `frequency`, treat phases as implementation detail in docs/UI, and keep the lobster animation visible above diary content. Thanks @vignesh07. - Prompt caching: keep prompt prefixes more reusable across transport fallback, deterministic MCP tool ordering, compaction, embedded image history, normalized system-prompt fingerprints, `openclaw status --verbose` cache diagnostics, and the removal of duplicate in-band tool inventories from agent system prompts so follow-up turns hit cache more reliably. (#58036, #58037, #58038, #59054, #60603, #60691) Thanks @bcherny and @vincentkoc. - Agents/cache: diagnostics: add prompt-cache break diagnostics, trace live cache scenarios through embedded runner paths, and show cache reuse explicitly in `openclaw status --verbose`. Thanks @vincentkoc. - Agents/cache: stabilize cache-relevant system prompt fingerprints by normalizing equivalent structured prompt whitespace, line endings, hook-added system context, and runtime capability ordering so semantically unchanged prompts reuse KV/cache more reliably. Thanks @vincentkoc. -- Agents/tool prompts: remove the duplicate in-band tool inventory from agent system prompts so tool-calling models rely on the structured tool definitions as the single source of truth, improving prompt stability and reducing stale tool guidance. Thanks @steipete. +- Agents/tool prompts: remove the duplicate in-band tool inventory from agent system prompts so tool-calling models rely on the structured tool definitions as the single source of truth, improving prompt stability and reducing stale tool guidance. - Config/schema: enrich the exported `openclaw config schema` JSON Schema with field titles and descriptions so editors, agents, and other schema consumers receive the same config help metadata. (#60067) Thanks @solavrc. - Matrix/exec approvals: clarify unavailable-approval replies so Matrix no longer claims chat approvals are unsupported when native exec approvals are merely unconfigured. (#61424) Thanks @gumadeiras. -- Providers/OpenAI Codex: add forward-compat `openai-codex/gpt-5.4-mini` synthesis across provider runtime, model catalog, and model listing so Codex mini works before bundled Pi catalog updates land. Thanks @steipete. -- Providers/OpenAI: add an opt-in GPT personality and move GPT-5 prompt tuning onto provider-owned system-prompt contributions so cache-stable guidance stays above the prompt cache boundary and embedded runner paths reuse the same provider-specific prompt behavior. Thanks @steipete. -- Docs/IRC: replace public IRC hostname examples with `irc.example.com` and recommend private servers for bot coordination while listing common public networks for intentional use. Thanks @steipete. +- Providers/OpenAI Codex: add forward-compat `openai-codex/gpt-5.4-mini` synthesis across provider runtime, model catalog, and model listing so Codex mini works before bundled Pi catalog updates land. +- Providers/OpenAI: add an opt-in GPT personality and move GPT-5 prompt tuning onto provider-owned system-prompt contributions so cache-stable guidance stays above the prompt cache boundary and embedded runner paths reuse the same provider-specific prompt behavior. +- Docs/IRC: replace public IRC hostname examples with `irc.example.com` and recommend private servers for bot coordination while listing common public networks for intentional use. - Memory/dreaming: group nearby daily-note lines into short coherent chunks before staging them for dreaming, so one-off context from recent notes reaches REM/deep with better evidence and less line-level noise (#61583). Thanks @mbelinky. - Memory/dreaming: drop generic date/day headings from daily-note chunk prefixes while keeping meaningful section labels, so staged snippets stay cleaner and more reusable. (#61597) Thanks @mbelinky. - Plugins/Lobster: run bundled Lobster workflows in process instead of spawning the external CLI, reducing transport overhead and unblocking native runtime integration. (#61523) Thanks @mbelinky. @@ -1663,8 +1672,8 @@ Docs: https://docs.openclaw.ai - Control UI/chat: show `/tts` and other local audio-only slash replies in webchat by embedding local audio in the assistant message and rendering `