## 2026.4.27 ### Highlights - Codex Computer Use setup now ships with status/install commands, marketplace discovery, and fail-closed MCP checks for Codex-mode desktop control. Thanks @pash-openai. - DeepInfra joins the bundled provider set with model discovery, media generation/editing, TTS, embeddings, and provider-owned onboarding policy. Thanks @ats3v. - Tencent Yuanbao and QQBot support expand channel coverage with Yuanbao docs/catalog entries and QQBot group chat, streaming, media upload, and pipeline refactors. Thanks @loongfay and @cxyhhhhh. - Plugin startup and model catalogs move toward manifest-first metadata, reducing Gateway boot work and making provider rows/aliases/suppressions easier to audit. Thanks @shakkernerd. - Reliability fixes cover Telegram startup/sends, Slack socket/media stalls, gateway startup prewarm, session/history defaults, update sync, and Windows restart handoffs. Thanks @joerod26, @obviyus, @shivasymbl, @freerk, @bassboy2k, @jpreagan, @islandpreneur007, and @Thatgfsj. ### Changes - Sandbox/Docker: add opt-in `sandbox.docker.gpus` passthrough for Docker sandbox containers so local GPU workloads can run inside sandboxed agents when the host Docker runtime supports `--gpus`. Fixes #57976; carries forward #58124. Thanks @cyan-ember. - iOS/Gateway: add an authenticated `node.presence.alive` protocol event and `node.list` last-seen fields so background iOS wakes can mark paired nodes recently alive without treating them as connected. Carries forward #63123. Thanks @ngutman. - Android: publish authenticated `node.presence.alive` events after node connect and background transitions so paired Android nodes retain durable last-seen metadata after disconnects. Carries forward #63123. Thanks @ngutman. - Gateway/chat: accept non-image attachments through `chat.send` by staging them as agent-readable media paths, while keeping unsupported RPC attachment paths explicit instead of silently dropping files. Fixes #48123. (#67572) Thanks @samzong. - Security/networking: add opt-in operator-managed outbound proxy routing (proxy.enabled + proxy.proxyUrl/OPENCLAW_PROXY_URL) with strict http:// forward-proxy validation, loopback-only Gateway bypass, and cleanup of proxy env/dispatcher state on exit. (#70044) Thanks @jesse-merhi and @joshavant. - Dependencies: refresh provider and tooling dependencies, including AWS SDK, PI runtime packages, AJV, Feishu SDK, Anthropic SDK, tokenjuice, and native TypeScript/oxlint tooling. Thanks @dependabot. - Matrix/QA: add live Matrix approval scenarios for exec metadata, chunked fallback, plugin approvals, deny reactions, thread targeting, and `target: "both"` delivery, with redacted artifacts preserving safe approval summaries. Thanks @gumadeiras. - Codex: add Computer Use setup for Codex-mode agents, including `/codex computer-use status/install`, marketplace discovery, optional auto-install, and fail-closed MCP server checks before Codex-mode turns start. Fixes #72094. (#71842) Thanks @pash-openai. - Apps: consume Peekaboo 3.0.0-beta4 and ElevenLabsKit 0.1.1, align Swabble on Commander 0.2.2, and refresh macOS/iOS SwiftPM resolutions against the released dependency graph. Thanks @Blaizzy. - Plugin SDK: expose shared channel route normalization, parser-driven target resolution, raw-target compact keys, parsed-target types, and route comparison helpers through `openclaw/plugin-sdk/channel-route`, switch native approval origin matching onto that route contract with optional delivery and match-only target normalization, and retire the internal channel-route shim behind dated compatibility aliases for legacy key/comparable-target helpers. Thanks @vincentkoc. - Docs/Codex: document how Codex Computer Use, direct `cua-driver mcp`, and OpenClaw.app's PeekabooBridge fit together so desktop-control setup choices are clearer. Thanks @pash-openai and @trycua. - Matrix/streaming: stream tool-progress updates into live Matrix preview edits by default when preview streaming is active, with `streaming.preview.toolProgress: false` to keep answer previews while hiding interim tool lines. Thanks @gumadeiras. - Plugins/models: wire manifest `modelCatalog.aliases` and `modelCatalog.suppressions` into model-catalog planning and built-in model suppression, with stale Spark and Qwen Coding Plan suppressions now declared in plugin manifests instead of runtime fallback hooks. Thanks @shakkernerd. - Plugin SDK/models: add a shared manifest-backed provider catalog builder and move Qianfan, Xiaomi, NVIDIA, Cerebras, Mistral, Moonshot, DeepSeek, Tencent TokenHub, and StepFun provider catalogs onto their plugin manifest `modelCatalog` rows. Thanks @shakkernerd. - Plugin SDK/models: move BytePlus and Volcano Engine standard and plan-provider catalogs into plugin manifest `modelCatalog` rows and remove the now-unused Volcengine-family shared catalog SDK subpath. Thanks @shakkernerd. - CLI/models: move Fireworks and Together AI fixed provider catalogs into plugin manifest `modelCatalog` rows so provider-filtered listing can use manifest-backed static rows. Thanks @shakkernerd. - Channels/Yuanbao: register the Tencent Yuanbao external channel plugin (`openclaw-plugin-yuanbao`) in the official channel catalog, contract suites, and community plugin docs, with a new `docs/channels/yuanbao.md` quick-start guide for WebSocket bot DMs and group chats. (#72756) Thanks @loongfay. - Channels/Yuanbao: add a channel docs entrance so the Tencent Yuanbao bot appears in the channel listing and sidebar navigation. (#73443) Thanks @loongfay. - Channels/QQBot: add full group chat support (history tracking, @-mention gating, activation modes, per-group config, FIFO message queue with deliver debounce), C2C `stream_messages` streaming with a `StreamingController` lifecycle manager, unified `sendMedia` with chunked upload for large files, and refactor the engine into pipeline stages, focused outbound submodules, builtin slash-command modules, and explicit DI ports via `createEngineAdapters()`. (#70624) Thanks @cxyhhhhh. - Plugins/startup: migrate bundled plugin manifests to explicit `activation.onStartup` declarations so Gateway startup imports only the bundled plugins that intentionally register startup-time runtime surfaces. Thanks @shakkernerd. - Plugins/startup: add an opt-in future-mode gate for disabling deprecated implicit startup sidecar loading while preserving explicit startup and narrower activation triggers. Thanks @shakkernerd. - Plugins/startup: add plugin compatibility warnings for deprecated implicit startup loading so authors can migrate to explicit `activation.onStartup` metadata. Thanks @shakkernerd. - Plugins/runtime: load bundled agent tool-result middleware from manifest contracts on demand so tokenjuice stays startup-lazy without losing Pi/Codex tool-output compaction. Thanks @shakkernerd. - Plugins/startup: add explicit `activation.onStartup` metadata so plugins can declare Gateway startup import behavior while the deprecated implicit sidecar fallback remains for legacy plugins. Thanks @shakkernerd. - Gateway/startup: reuse lookup-table plugin manifests when loading startup plugins so Gateway boot avoids rebuilding plugin discovery and manifest metadata. Thanks @shakkernerd. - CLI/models: declare fixed Qianfan, Xiaomi, NVIDIA, Cerebras, Mistral, Chutes, Kilo, OpenAI, and OpenCode Go model catalogs in refreshable plugin manifests, keep broad `models list --all` on raw registry and supplement rows without runtime normalization, and avoid duplicate supplement resolution. Thanks @shakkernerd. - Gateway/runtime: reuse the current plugin metadata snapshot for provider discovery so repeated model-provider discovery avoids rebuilding plugin manifest metadata. Thanks @shakkernerd. - Gateway/startup: pass the plugin metadata snapshot from config validation into plugin bootstrap so startup reuses one manifest product instead of rebuilding plugin metadata. Thanks @shakkernerd. - Plugin SDK/testing: move core-only channel contract fixtures under the channel contract test tree and retire the old `test/helpers/channels` bridge directory so plugin tests stay on focused SDK surfaces. Thanks @vincentkoc. - Plugin SDK/testing: expose native agent-runtime contract fixtures through `plugin-sdk/agent-runtime-test-contracts`, move sandbox config fixtures into the focused generic fixture subpath, and block extension tests from importing repo-only `test/helpers` bridges. Thanks @vincentkoc. - Plugin SDK/testing: expose generic module reload, bundled-path, Node builtin mock, channel pairing/envelope, HTTP server, temp-home, replay-policy, and live STT helpers through focused SDK test subpaths so extension tests no longer depend on repo-only helper bridges. Thanks @vincentkoc. - Plugin SDK: move maintained bundled channels off the deprecated `channel-config-schema-legacy` subpath, add an explicit bundled-channel schema SDK surface, and track both remaining legacy test/config compatibility barrels with dated removal windows. Thanks @vincentkoc. - Plugin SDK/testing: expose media provider capability assertions and provider HTTP mocks through focused SDK test subpaths, and retire the repo-only media-generation test helper bridge. Thanks @vincentkoc. - Plugin SDK/testing: promote bundled plugin/provider/channel contract helpers to focused SDK test subpaths and retire the repo-only `test/helpers/plugins` TypeScript bridge. Thanks @vincentkoc. - Plugin SDK/testing: expose generic channel action, setup, status, and directory contract helpers through `plugin-sdk/channel-test-helpers` so bundled extension tests no longer import repo-only channel helper bridges. Thanks @vincentkoc. - Plugin SDK/testing: add `plugin-sdk/channel-target-testing` for shared channel target-resolution cases, document channel reaction helpers on `plugin-sdk/channel-feedback`, and keep the old `plugin-sdk/test-utils` alias as compatibility-only. Thanks @vincentkoc. - Plugin SDK/testing: add a focused generic fixture subpath for CLI capture, sandbox, skill, agent-message, system-event, terminal, chunking, auth-token, and typed-case helpers. Thanks @vincentkoc. - Plugin SDK/testing: add focused plugin runtime and environment fixture subpaths so plugin tests can avoid the broad `plugin-sdk/testing` barrel for common setup helpers. Thanks @vincentkoc. - Plugin SDK/testing: add a focused `plugin-sdk/plugin-test-api` helper subpath and move bundled plugin registration tests off the repo-only plugin API bridge. Thanks @vincentkoc. - Plugin SDK: add generic host hooks for session state, next-turn context, trusted tool policy, UI descriptors, events, scheduler cleanup, and run-scoped plugin context. (#72287) Thanks @100yenadmin. - Plugin SDK/testing: expose provider catalog, wizard, registry, manifest, public-artifact, outbound, and TTS contract helpers through documented SDK testing seams so bundled plugin tests no longer import repo `src/**` internals. Thanks @vincentkoc. - Providers/DeepInfra: add a bundled DeepInfra provider with `DEEPINFRA_API_KEY` onboarding, dynamic OpenAI-compatible model discovery, image generation/editing, image/audio media understanding, TTS, text-to-video, memory embeddings, static catalog metadata, and provider-owned base URL policy. Carries forward #53805, #48088, #37576, #43896, #11533, and #2554. Thanks @ats3v. - Matrix: attach versioned structured approval metadata to pending approval messages so capable Matrix clients can render richer approval UI while body text and reaction fallback keep working. (#72432) Thanks @kakahu2015. ### Fixes - Gateway/sessions: align `chat.history` and `sessions.list` thinking defaults with owning-agent and catalog-aware resolution so Control UI session defaults match backend runtime state. (#63418) Thanks @jpreagan. - Devices/pairing: recover array-shaped device and node pairing state files before persisting approvals, so UUID-keyed pending and paired entries no longer disappear after a malformed JSON store write. Fixes #63035. Thanks @sar618. - Gateway/auth: clear reused stale device tokens and stop reconnecting on device-token mismatch in the Control UI and Node gateway clients, avoiding rate-limit loops after scope-upgrade or token-rotation handoffs. Fixes #71609. Thanks @ricksayhi. - Gateway/approvals: treat duplicate same-decision approval resolves as idempotent during the resolved-entry grace window, including consumed `allow-once` approvals, while returning an explicit already-resolved error for conflicting repeats. Fixes #59162; refs #58479 and #65486. Thanks @wikithoughts, @sajazuniga7-coder, and @mjmai20682068-create. - Channels/Telegram: honor `approvals.exec/plugin.targets[].accountId` when routing native approvals across multi-bot Telegram accounts while preserving unscoped Telegram targets for any account. Fixes #69916. Thanks @joerod26. - Telegram/gateway: bound outbound Bot API calls and cache bundled plugin alias lookup so slow Telegram sends or WSL2 filesystem scans no longer wedge gateway replies. (#74210) Thanks @obviyus. - Agents/exec: omit the internal session-resume fallback preface from successful async exec completion messages sent directly back to chat. Fixes #67181. Thanks @raistlin88. - Agents/media: register detached `video_generate` and `music_generate` tool run contexts until terminal status, so Discord-backed provider jobs stay live in `/tasks` instead of becoming `lost` when the parent chat run context disappears. Thanks @vincentkoc. - Agents/media: prefer OpenAI image and video providers when the default model uses the OpenAI Codex auth alias, so auto media generation no longer falls through to Fal before GPT Image or Sora. Thanks @vincentkoc. - Tasks/media: infer agent ownership for session-scoped task records so `/tasks` agent-local fallback includes session-backed `video_generate` and other async media jobs even when the current chat session has no linked rows. Thanks @vincentkoc. - Agents/media: keep long-running `video_generate` and `music_generate` tasks fresh while provider jobs are still pending, so task maintenance does not mark active Discord media renders lost before completion. Thanks @vincentkoc. - CLI/status: treat scope-limited gateway probes as reachable-but-degraded in shared status scans, so `openclaw status --all` no longer reports a live gateway as unreachable after `missing scope: operator.read`. Fixes #49180; supersedes #47981. Thanks @openjay. - CLI/update: skip tracked plugins disabled in config during post-update plugin sync before npm, ClawHub, or marketplace update checks, preserving their install records without failing the update. Fixes #73880. Thanks @islandpreneur007. - Slack/Socket Mode: use a 15s Slack SDK pong timeout by default and add `channels.slack.socketMode.clientPingTimeout`, `serverPingTimeout`, and `pingPongLoggingEnabled` overrides so stale-websocket handling no longer depends on app-event health heuristics. Fixes #14248; refs #58519, #64009, and #63488. Thanks @shivasymbl and @freerk. - Slack/media: bound private file and forwarded attachment downloads with idle and total timeouts while preserving placeholder fallback, so stalled Slack `file_share` media no longer wedges inbound message handling. Fixes #61850. Thanks @bassboy2k. - Plugins/inspector: keep bundled plugin runtime capture quiet and config-tolerant for Codex, memory-lancedb, Feishu, Mattermost, QQBot, and Tlon so plugin-inspector JSON checks can validate the full bundled set. Thanks @vincentkoc. - Slack/auto-reply: keep fully consumed text reset triggers such as `new session` out of `BodyForAgent` after directive cleanup, so configured Slack reset phrases do not leak into the fresh model turn. Fixes #73137. Thanks @neeravmakwana. - Plugins/runtime deps: prune stale retained bundled runtime deps and keep doctor/secret channel contract scans on lightweight artifacts, so disabled bundled channels stop preserving old dependency trees or importing heavy plugin surfaces. Thanks @SymbolStar and @vincentkoc. - Plugins/runtime deps: cache unchanged bundled runtime mirror dist-file materialization decisions and close file-lock handles on owner-write failures, reducing repeated startup chunk scans and avoiding FileHandle-GC recovery stalls. Refs #73532. Thanks @oadiazp and @bstanbury. - Auto-reply: bound the post-run pending tool-result delivery drain with a progress-aware idle timeout, so a never-settling tool-result task no longer leaves the session active forever while slow healthy deliveries can keep draining. Fixes #53889; supersedes #64733 and #73434. Thanks @zijunl and @wujiaming88. - Gateway/startup: start chat channels without waiting for primary model prewarm, keeping model warmup bounded in the background so Slack and other channels come online promptly when provider discovery is slow. Supersedes #73420. Thanks @dorukardahan. - Gateway/install: carry env-backed config SecretRefs such as `channels.discord.token` into generated service environments when they are present only in the installing shell, while keeping gateway auth SecretRefs non-persisted. Fixes #67817; supersedes #73426. Thanks @wdimaculangan and @ztexydt-cqh. - Auto-reply/commands: stop bare `/reset` and `/new` after reset hooks acknowledge the command, so non-ACP channels no longer fall through into empty provider calls while `/reset <message>` and `/new <message>` still seed the next model turn. Fixes #73367 and #73412. Thanks @hoyanhan, @wenxu007, and @amdhelper. - Providers/DeepSeek: backfill DeepSeek V4 `reasoning_content` on plain assistant replay messages as well as tool-call turns, so thinking sessions with prior tool use no longer fail follow-up requests with missing reasoning content. Fixes #73417; refs #71372. Thanks @34262315716 and @Bartok9. - Agents/gateway tool: strip full config payloads from `config.patch` and `config.apply` tool responses while preserving direct RPC responses, so config-heavy sessions no longer replay large redacted configs into transcript history. Fixes #47610; supersedes #73439. Thanks @HanenVit and @juan-flores077. - Auto-reply: preserve voice-note media from silent turns while continuing to suppress text and non-voice media, so `NO_REPLY` TTS replies still deliver the requested audio bubble. (#73406) Thanks @zqchris. - Channels/Mattermost: stop enqueueing regular inbound posts as system events, so Mattermost user messages reach the model only as user-role inbound-envelope content instead of also appearing as `System: Mattermost message...` directives. Fixes #71795. Thanks @juan-flores077. - Agents/media: qualify bare `agents.defaults.imageModel` and `pdfModel` refs from unique configured image-capable providers, so Ollama vision models such as `moondream` and `qwen2.5vl:7b` do not fall through to the default provider. Fixes #38816; supersedes #73396. Thanks @alainasclaw and @vincentkoc. - Agents/Anthropic: send implicit Anthropic beta headers only to direct public Anthropic endpoints, including OAuth, so custom Anthropic-compatible providers no longer mis-handle unsupported beta flags unless explicitly configured. Refs #73346. Thanks @byBrodowski. - Skills: require explicit `skills.entries.coding-agent.enabled` before exposing the bundled coding-agent skill, so installs with Codex on PATH but no OpenAI auth do not silently offer Codex delegation. Fixes #73358. Thanks @LaFleurAdvertising and @Sanjays2402. - Plugins/startup: treat manifestless Claude bundles as valid installed-plugin registry entries instead of stale missing manifests, so workspace bundles no longer force repeated derived registry rebuilds or noisy `plugins.entries.workspace` warnings during Gateway startup. Fixes #73433. Thanks @AnneVoss. - Agents/subagents: preserve `sessions_yield` as a paused subagent state and ignore its wait text while freezing completion output, so parent sessions wait for the final post-compaction answer instead of receiving intermediate progress or `(no output)`. Fixes #73413. Thanks @Ask-sola. - Plugins/startup: precompute bundled runtime mirror fingerprints before taking the mirror lock and keep Docker bundled plugin runtime deps/mirrors in a Docker-managed volume instead of the Windows/WSL config bind mount, so cold starts avoid slow host-volume mirror writes. Fixes #73339. Thanks @1yihui. - Plugins/runtime deps: refresh bundled runtime mirrors without deleting active import trees, so config-triggered restarts do not see transient missing plugin files during registration. Thanks @shakkernerd. - Channels/LINE: persist inbound image, video, audio, and file downloads in `~/.openclaw/media/inbound/` instead of temporary files so agents can still read LINE media after `/tmp` cleanup. Fixes #73370. Thanks @hijirii and @wenxu007. - CLI/plugins: keep bundled plugin installs out of `plugins.load.paths` while preserving install records, so install/inspect/doctor loops no longer warn about the current bundled plugin directory. Thanks @vincentkoc. - CLI/plugins: scope `plugins inspect <id>` runtime loading to the matched plugin so single-plugin inspection does not load every plugin before checking the target. Thanks @shakkernerd. - CLI/plugins: remove managed copied-path plugin directories during uninstall and plan uninstall from metadata instead of runtime-loading plugins, so plugin lifecycle commands avoid unnecessary bundled runtime-deps work. Thanks @shakkernerd. - Cron tool: infer the creating session's agentId for `cron.add` jobs when `agentId` is omitted or passed as undefined, keeping scheduled agentTurn jobs routed to the session agent; #40571 identified the guard bug and supplied the focused regression coverage. Thanks @ChanningYul. - Cron/Telegram: add `--thread-id` to `openclaw cron add` and `openclaw cron edit`, preserving Telegram forum topic delivery targets across scheduled announcements. Carries forward #51581, #60373, and #60890. Thanks @ChunHao-dev. - Cron/Telegram: preserve session-derived Telegram topic thread IDs when isolated cron delivery explicitly targets the parent chat, keeping bare chat targets in the active forum topic without leaking stale topics to other chats. Carries forward #64708. Thanks @addelh. - Memory/compaction: keep pre-compaction memory-flush prompts runtime-only so session transcripts and `chat.history` no longer expose them as normal user turns. Fixes #54408 and #58956; refs #43567. Thanks @markgong and @guoyuhang9. - Control UI/WebChat: keep large attachment payloads out of Lit state and optimistic chat messages, using object URL previews plus send-time payload serialization so PDF/image uploads no longer trigger `RangeError: Maximum call stack size exceeded`. Fixes #73360; refs #54378 and #63432. Thanks @hejunhui-73, @Ansub, and @christianhernandez3-afk. - Agents/Anthropic: cancel stalled Anthropic Messages SSE body reads when abort signals fire, so active-memory timeouts release transport resources instead of leaving hidden recall runs parked on `reader.read()`. Refs #72965 and #73120. Thanks @wdeveloper16. - Control UI/WebChat: keep pending run and typing state attached to the active client run, so unowned inject/announce/side-result finals no longer unlock unrelated active runs while completed owned runs still clear promptly. Fixes #57795; carries forward the narrow diagnosis from #57887. Thanks @haoyu-haoyu. - Sandbox/Docker: stop satisfying a missing default sandbox image by tagging plain Debian as `openclaw-sandbox:bookworm-slim`, preserving the Python tooling required by sandbox write/edit helpers and directing users to build the default image. Fixes #51185; refs #45108, #51099, #51609, and #57713. Thanks @dpalis, @Tin55FoilDev, @jbcohen2-coder, @macminihal-cyber, and @PraxoOnline. - Control UI/WebChat: confirm toolbar New Session button resets before dispatching `/new` while leaving typed `/new` and `/reset` commands immediate. Fixes #45800; refs #27065, #56611, #54499, and #27110. Thanks @aethnova, @kosta228-huli, @adambezemek, and @xss925175263 (xianshishan). - Agents/models: keep per-agent primary models strict when `fallbacks` is omitted, so probe-only custom providers are not tried as hidden fallback candidates unless the agent explicitly opts in. Fixes #73332. Thanks @haumanto. - Gateway/models: add `models.pricing.enabled` so offline or restricted-network installs can skip startup OpenRouter and LiteLLM pricing-catalog fetches while keeping explicit model costs working. Fixes #53639. Thanks @callebtc, @palewire, and @rjdjohnston. - Gateway/startup: warn when legacy `CLAWDBOT_*` or `MOLTBOT_*` environment variables are still present, pointing users to `OPENCLAW_*` names instead of failing silently. Fixes #53482; carries forward #53667. Thanks @lndyzwdxhs. - Onboarding: pin interactive and non-interactive health checks to the just-configured setup token/password so stale `OPENCLAW_GATEWAY_TOKEN` or `OPENCLAW_GATEWAY_PASSWORD` values do not produce false gateway-token-mismatch failures after setup. Fixes #72203. Thanks @galiniliev. - Doctor/state: require an interactive confirmation before archiving orphan transcript files, so `openclaw doctor --fix` no longer silently renames recoverable session history after upgrades regenerate `sessions.json`. Fixes #73106. Thanks @scottgl9. - Cron/Telegram: preserve explicit `:topic:` delivery targets over stale session-derived thread IDs when isolated cron announces to Telegram forum topics. Carries forward #59069; refs #49704 and #43808. Thanks @roytong9. - Build/runtime: write the runtime-postbuild stamp after `pnpm build` writes the build stamp, so the next CLI invocation does not re-sync runtime artifacts after a successful build. Fixes #73151. Thanks @bittoby. - Build/runtime: preserve staged bundled-plugin runtime dependency caches across source-checkout tsdown rebuilds, so local CLI and gateway-watch rebuilds no longer recreate large plugin dependency trees before starting. Refs #73205. Thanks @SymbolStar. - CLI/channels: list configured chat channel accounts from read-only setup metadata even when the standalone CLI has not loaded the runtime channel registry, so `openclaw channels list` shows Telegram accounts before auth providers. Fixes #73319 and #73322. Thanks @mlaihk. - CLI/model probes: keep `infer model run --gateway` raw by skipping prior session transcript, bootstrap context, context-engine assembly, tools, and bundled MCP servers, so local backends can be tested without full agent-context overhead. Fixes #73308. Thanks @ScientificProgrammer. - CLI/image describe: pass `--prompt` and `--timeout-ms` through `infer image describe` and `describe-many`, so custom vision instructions and slow local model budgets reach media-understanding providers such as Ollama, OpenAI, Google, and OpenRouter. Addresses #63700. Thanks @cedricjanssens. - Providers/Ollama: reject long non-linguistic Kimi/GLM symbol runs as provider failures instead of storing them as successful visible assistant replies, so fallback or error handling can recover from garbled cloud output. Fixes #64262; refs #67019. Thanks @Kloz813 and @xiaomenger123. - CLI/model probes: reject empty or whitespace-only `infer model run --prompt` values before calling local providers or the Gateway, so smoke checks do not spend provider calls on invalid turns. Fixes #73185. Thanks @iot2edge. - Gateway/media: route text-only `chat.send` image offloads through media-understanding fields so `agents.defaults.imageModel` can describe WebChat attachments instead of leaving only an opaque `media://inbound` marker. Fixes #72968. Thanks @vorajeeah. - Gateway/Windows: route no-listener restart handoffs through the Windows supervisor without leaving restart tokens in flight, so failed task scheduling can be retried and successful handoffs do not coalesce later restart requests. (#69056) Thanks @Thatgfsj. - Gateway/model pricing: skip plugin manifest discovery during background pricing refreshes when `plugins.enabled: false`, so disabled-plugin setups do not keep rebuilding plugin metadata from the Gateway hot path. Fixes #73291. Thanks @slideshow-dingo and @fishgills. - Ollama/thinking: validate `/think` commands against live Ollama catalog reasoning metadata and preserve explicit native `params.think`/`params.thinking`, so models whose `/api/show` capabilities include `thinking` expose `low`, `medium`, `high`, and `max` instead of being stuck on `off`. Fixes #73366. Thanks @cymise. - Gateway/sessions: remove automatic oversized `sessions.json` rotation backups, deprecate `session.maintenance.rotateBytes`, and teach `openclaw doctor --fix` to remove the ignored key so hot session writes no longer copy multi-MB stores. Refs #72338. Thanks @midhunmonachan and @DougButdorf. - Channels/Telegram: fail fast when Telegram rejects the startup `getMe` token probe with 401, so invalid or stale BotFather tokens are reported as token auth failures instead of misleading `deleteWebhook` cleanup failures. Fixes #47674. Thanks @samaedan-arch. - ACPX: keep generated Codex and Claude ACP wrapper startup paths working when remote or special state filesystems reject chmod, since OpenClaw invokes the wrappers through Node instead of executing them directly. Fixes #73333. Thanks @david-garcia-garcia. - CLI/onboarding: infer image input for common custom-provider vision model IDs, ask only for unknown models, and keep `--custom-image-input`/`--custom-text-input` overrides so vision-capable proxies do not get saved as text-only configs. Fixes #51869. Thanks @Antsoldier1974. - Models/OpenAI Codex: stop listing or resolving unsupported `openai-codex/gpt-5.4-mini` rows through Codex OAuth, keep stale discovery rows suppressed with a clear API-key-route hint, and leave direct `openai/gpt-5.4-mini` available. Fixes #73242. Thanks @0xCyda. - Plugin SDK: restore the root `stringEnum` and `optionalStringEnum` exports on both the published SDK entry and runtime root-alias bridge, so older external plugins can keep building and loading while migrating to focused SDK subpaths. Fixes #68279. Thanks @marzliak. - Plugin SDK: restore the root-alias bridge for `registerContextEngine` and expose missing legacy compat helpers `normalizeAccountId` and `resolvePreferredOpenClawTmpDir` so older external plugins such as `openclaw-weixin` can keep loading while migrating to focused SDK subpaths. Fixes #53497. Thanks @alanxchen85. - Auth profiles: make `openclaw doctor --fix` migrate legacy flat `auth-profiles.json` files such as `{ "ollama-windows": { "apiKey": "ollama-local" } }` to canonical provider default API-key profiles with a backup, so custom Ollama/OpenAI-compatible providers recover cleanly after upgrading. Fixes #59629; supersedes #59642. Thanks @Xsanders555 and @Linux2010. - Memory/Dreaming: retry Dream Diary once with the session default when a configured dreaming model is unavailable, while leaving subagent trust and allowlist errors visible instead of silently masking configuration problems. Refs #67409 and #69209. Thanks @Ghiggins18 and @everySympathy. - Feishu/inbound files: recover CJK filenames from plain `Content-Disposition: filename=` download headers when Feishu exposes UTF-8 bytes through Latin-1 header decoding, while leaving valid Latin-1 and JSON-derived names unchanged. (#48578, #50435, #59431) Thanks @alex-xuweilong, @lishuaigit, and @DoChaoing. - Channels/Telegram: normalize accidental full `/bot<TOKEN>` Telegram `apiRoot` values at runtime and teach `openclaw doctor --fix` to remove the suffix, so startup control calls no longer 404 when direct Bot API curl commands work. Fixes #55387. Thanks @brendanmatthewjones-cmyk, @techfindubai-ux, and @Sivlerback-Chris. - Zalo Personal: persist refreshed `zca-js` session cookies after QR login, session restore, and successful API calls so gateway restarts restore the freshest local session. (#73277) Thanks @darkamenosa. - Logging/security: redact sensitive tokens (sk-\* keys, Bearer/Authorization values, etc.) at the subsystem console sink so `createSubsystemLogger().info/warn/error` output that bypasses the patched console-capture handler still applies the same redaction the file transport already does. Fixes #73284; refs #67953 and #64046. Thanks @edwin-rivera-dev. - Plugins/runtime deps: reuse enclosing versioned cache roots when bundled plugins resolve from nested staged paths, so plugin-runtime-deps no longer mints `openclaw-unknown-*` directories or loops on `ENOTEMPTY`. Fixes #72956. (#73205) Thanks @SymbolStar. - Agents/failover: classify CJK provider transport, quota, billing, auth, and overload error text so Chinese-language provider failures trigger fallback and user-facing transport copy instead of surfacing as unclassified raw errors. (#56242) Thanks @tomcatzh. - Agents/failover: seed non-claude-cli fallback prompts with Claude Code session context when a claude-cli attempt fails, so fallback models do not restart cold after billing or quota failover. (#72069) Thanks @stainlu. - Agents/CLI runner: transfer bundle-MCP tempDir cleanup from the per-turn runner finally to the Claude live-session lifecycle, so persistent Claude CLI sessions keep their `--mcp-config` directory until the live subprocess closes. Fixes #73244. Thanks @edwin-rivera-dev. - Gateway/nodes: allow Windows companion nodes to use safe declared commands such as canvas, camera list, location, device info, and screen snapshot by default while keeping dangerous media commands opt-in. (#71884) Thanks @shanselman. - Agents/cron: clarify agent-tool and CLI cron timezone guidance so supplied `tz` values use local wall-clock cron fields and omitted cron `tz` falls back to the Gateway host local timezone. Fixes #53669; carries forward #46177. (#73372) Thanks @chen-zhang-cs-code and @maranello-o. - Providers/Qwen: allow explicitly configured `qwen/qwen3.6-plus` to resolve on Qwen Coding Plan endpoints while keeping the built-in catalog from advertising it there. Fixes #63654; carries forward #63987. Thanks @jepson-liu. - Channels/Telegram: keep Bot API network fallbacks sticky after failed attempts and retry timed-out startup control calls once on the fallback route, so `deleteWebhook` IPv6 stalls no longer trigger slow multi-account retry storms. Fixes #73255. Thanks @ttomiczek and @sktbrd. - Gateway/agents: accept heartbeat, cron, and webhook as internal channel hints for agent runs so `sessions_spawn` works from non-delivery parent sessions while unknown channel hints still fail closed. Fixes #73237. Thanks @KeWang0622. - Gateway/models: merge explicit `models.providers.*.models` rows into the Gateway model catalog with normalized provider/model dedupe, and use normalized image-capability lookup so custom vision models keep native image attachments even when Pi discovery omits them or model ID casing differs. Fixes #64213 and #65165. Thanks @billonese and @202233a. - Gateway/reload: publish canonical post-write source config to in-process reloaders so simple config saves no longer create phantom plugin diffs or trigger unnecessary Gateway restarts. (#73267) Thanks @szsip239. - Gateway/Docker: keep config-triggered restarts in-process inside containers instead of spawning a detached child and exiting PID 1 cleanly, so Docker Swarm and other on-failure supervisors do not leave the service stuck at 0/1 replicas. Fixes #73178. Thanks @du-nguyen-IT007. - CLI/tasks: ship the task-registry control runtime in npm packages so `openclaw tasks cancel` can load ACP/subagent cancellation helpers from published builds. Fixes #68997. Thanks @1OAKDesign. - Channels/Telegram: preserve unsent generated media after partial reply streaming has already delivered the text, so `image_generate` outputs still reach Telegram as photos instead of being dropped from the final payload. Fixes #73253. Thanks @mlaihk. - Memory-core/dreaming: cap detached Dream Diary narrative subagents across cron sweeps so multi-workspace dreaming no longer fans out unbounded subagent sessions, lock contention, and cascading narrative timeouts. Fixes #73198. (#73287) Thanks @KeWang0622. - CLI/agents: close local one-shot Claude live stdio sessions and bundled MCP loopback resources after embedded `openclaw agent --local` runs, while keeping gateway-owned MCP loopback cleanup internal to the Gateway. Thanks @frankekn. - Export/session: keep inline export HTML scripts and vendor libraries injected after template formatting so generated session exports open with the app code, markdown renderer, and syntax highlighter present. Fixes #41862 and #49957; carries forward #41861 and #68947. Thanks @briannewman, @martenzi, and @armanddp. - Agents/ACPX: stage the patched Claude ACP adapter as an ACPX runtime dependency and route known Codex/Claude ACP commands through local wrappers, so Gateway runtime no longer depends on live `npx` adapter resolution. Fixes #73202. Thanks @joerod26. - Memory/compaction: let pre-compaction memory flush use an exact `agents.defaults.compaction.memoryFlush.model` override such as `ollama/qwen3:8b` without inheriting the active session fallback chain, so local housekeeping can avoid paid conversation models. Fixes #53772. Thanks @limen96. - macOS/update: stop managed Gateway services before package replacement and keep LaunchAgent service secrets out of world-readable plist metadata by loading them from owner-only env files. Fixes #72996. Thanks @Mathewb7. - Google Meet: keep observe-only Chrome joins and setup checks from requiring BlackHole or audio bridge commands, avoid granting or selecting the microphone in observe-only mode, and make `test_speech` report fresh realtime output-byte verification instead of only confirming a queued utterance. Refs #72478. Thanks @DougButdorf. - Gateway/hooks: route non-delivered hook completion and error summaries to the target agent's main session instead of the default agent session, preserving multi-agent hook isolation. Fixes #24693; carries forward #68667. Thanks @abersonFAC and @bluesky6868. - Control UI/models: request the configured Gateway model-list view so dashboards with only `models.providers.*.models` show those configured models first instead of flooding the picker with the full built-in catalog. Fixes #65405. Thanks @wbyanclaw. - CLI/models: keep default-model and allowlist pickers on explicit `models.providers.*.models` entries when `models.mode` is `replace` instead of loading the full built-in catalog. Fixes #64950. Thanks @mrozentsvayg. - Media/security: tighten media-understanding MIME sanitization so parameterized MIME values stay end-anchored and malformed whitespace or suffix payloads are rejected before file-context handling. Fixes #9795; carries forward #68225 with related review/test context from #61016/#68456. Thanks @ymaxgit, @bluesky6868, and @shamsulalam1114. - Discord: own the Carbon interaction listener and hand off Discord slash/component handling asynchronously, so compaction or long session locks no longer trip `InteractionEventListener` listener timeouts. Fixes #73204. Thanks @slideshow-dingo. - Compaction/diagnostics: keep unknown compaction failure classifications stable while logging sanitized detail for unclassified provider errors such as missing Ollama provider adapters. Thanks @gzsiang. - Models/fallbacks: record first-class `model.fallback_step` trajectory events with from/to models, failure detail, chain position, and final outcome so support exports preserve the primary model failure even when a later fallback also fails. Fixes #71744. Thanks @nikolaykazakovvs-ux. - Gateway/agents: block agent `exec` from launching interactive `openclaw channels login` flows and abort active agent runs after invalid-config recovery restores last-known-good config, preventing known channel-login and reload paths from wedging replies. Refs #72338. Thanks @midhunmonachan. - Gateway/diagnostics: emit payload-free liveness warnings with event-loop delay, event-loop utilization, CPU-core ratio, active-session counts, and OTEL warning metrics/spans so live-but-stalled Gateways capture CPU-spin context in stability bundles and telemetry. Refs #72338. Thanks @midhunmonachan and @DougButdorf. - Gateway/startup: keep value-option foreground starts on the gateway fast path and skip proxy bootstrap unless proxy env is configured, reducing normal gateway startup RSS and avoiding full CLI graph loading. Thanks @vincentkoc. - Heartbeat/models: show heartbeat model bleed guidance on context-overflow resets when the last runtime model matches configured `heartbeat.model`, so smaller local heartbeat models point users to `isolatedSession` or `lightContext` instead of only compaction-buffer tuning. Fixes #67314. Thanks @Knightmare6890. - Subagents/models: persist `sessions_spawn.model` and configured subagent models as child-session model overrides before the first turn, so spawned subagents actually run on the requested provider/model instead of reverting to the target agent default. Fixes #73180. Thanks @danielzinhu99. - Channels/Telegram: keep webhook-mode local listeners alive and retry Telegram `setWebhook` registration after recoverable startup network failures, so transient Bot API timeouts no longer leave reverse proxies pointing at a closed listener. Fixes #71834. Thanks @jinon86. - Agents/ACPX: bundle the Codex ACP adapter and launch it from the isolated `CODEX_HOME` wrapper before falling back to npm, so Codex ACP startup no longer depends on live `npx` resolution or the stale `@zed-industries/codex-acp@^0.11.1` range. Fixes #72037; refs #73202. Thanks @jasonftl, @sazora, and @joerod26. - Agents/ACPX: register the embedded ACP backend at Gateway startup through a lightweight ACP backend SDK path and without importing the heavy ACPX runtime until an ACP session or explicit startup probe needs it, reducing baseline Gateway RSS. Thanks @vincentkoc. - CLI/update: keep restart health polling when the restarted Gateway is reachable but has not reported its version yet, so macOS service restarts do not fail early with `actual unavailable`. Thanks @ProspectOre. - Backup: skip installed plugin `extensions/*/node_modules` dependency trees while keeping plugin manifests and source files in archives, so local backups avoid rebuildable npm payload bloat. Fixes #64144. Thanks @BrilliantWang. - Cron/models: fail isolated cron runs closed when an explicit `payload.model` is not allowed or cannot be resolved, so scheduled jobs do not silently fall back to an unrelated agent default or paid route before configured provider proxies such as LiteLLM can run. Fixes #73146. Thanks @oneandrewwang. - Memory/QMD: back off repeated chat-turn QMD open failures while still letting memory status and CLI probes recheck immediately, so a broken sidecar dependency cannot trigger active-memory or cron retry storms. Fixes #73188 and #73176. Thanks @leonlushgit and @w3i-William. - Talk Mode: resolve `messages.tts.providers.<id>.apiKey` through the active runtime snapshot for `talk.config`, so Talk overlays can discover SecretRef-backed speech providers without falling back to local speech. Fixes #73109. (#73111) Thanks @omarshahine. - Memory/Ollama: resolve `memorySearch.provider` custom provider ids through their configured `models.providers.<id>.api` owner, so multi-GPU Ollama setups can dedicate embeddings to providers such as `ollama-5080` without losing the Ollama adapter or local auth semantics. Fixes #73150. Thanks @oneandrewwang. - CLI/memory: skip eager context-window warmup for `openclaw memory` commands so memory search does not race unrelated model metadata discovery. Fixes #73123. Thanks @oalansilva and @neeravmakwana. - CLI/Telegram: route Telegram `message send` and poll actions through the running Gateway when available, so packaged installs use the staged `grammy` runtime deps and CLI sends return instead of hanging after the Telegram channel is active. Fixes #73140. Thanks @oalansilva. - Plugins/runtime deps: prepare staged bundled plugin dependencies before loading packaged public surfaces, so OpenClaw's Telegram runtime/test facade loads resolve `grammy` from the managed runtime-deps stage without copying dependencies into the global package root. Refs #73140. Thanks @oalansilva. - Agents/exec: emit `(no output)` for silent exec update and node-host result blocks so Anthropic-compatible providers no longer reject empty tool-result text after quiet commands. Fixes #73117. Thanks @pfrederiksen and @Sanjays2402. - Cron/providers: preflight local Ollama and OpenAI-compatible provider endpoints before isolated cron agent turns, record unreachable local providers as skipped runs, and cache dead-endpoint probes so many jobs do not hammer the same stopped local server. Fixes #58584. Thanks @jpeghead. - Gateway/config: let config reload continue in degraded mode when invalidity is scoped to plugin entries, so incompatible plugin configs can be skipped and the Gateway restart can still pick up the rest of the config after rollbacks. Fixes #73131. Thanks @Adam-Researchh. - Doctor/channels: suppress disabled bundled-plugin blocker warnings when a trusted external plugin owns the configured channel, so Lark/Feishu installs no longer get Feishu repair noise after switching to `openclaw-lark`. Fixes #56794. Thanks @wuji-tech-dev. - CLI/status: show skipped fast-path memory checks as `not checked` and report active custom memory plugin runtime status from `status --json --all` without requiring built-in `agents.defaults.memorySearch`, so plugins such as memory-lancedb-pro and memory-cms no longer look unavailable when their own runtime is healthy. Fixes #56968. Thanks @Tony-ooo and @aderius. - Gateway/channels: record and log unexpected clean channel monitor exits so channels that return without throwing no longer appear stopped with no error. Fixes #73099. Thanks @balaji1968-kingler. - Discord/group chats: keep group/channel replies private by default unless the agent explicitly uses the message tool, so always-on rooms can lurk without leaking automatic final, block, preview, or status-reaction output; `messages.groupChat.visibleReplies: "automatic"` restores legacy auto-posting. (#73046) Thanks @scoootscooob. - Plugins/package: force nested bundled-plugin runtime dependency installs out of inherited npm dry-run mode during prepack and package smoke checks, so packed installs materialize required plugin modules instead of reporting missing bundled files. Refs #73128. Thanks @Adam-Researchh. - Discord: skip reaction events before REST channel fetch when notifications are off, guild reactions are disabled, or allowlist mode cannot match without channel overrides, reducing reconnect bursts that caused slow listener warnings. Fixes #73133. Thanks @isaacsummers. - Channels/Telegram: centralize polling update tracking so accepted offsets remain durable across restarts, same-process handler failures can still retry, and slow offset writes cannot overwrite newer accepted watermarks. Refs #73115. Thanks @vdruts. - Agents/models: classify empty, reasoning-only, and planning-only terminal agent runs before accepting a model fallback candidate, so invalid or incompatible models can advance to the next configured fallback instead of returning a 30-second terminal failure. Fixes #73115. Thanks @vdruts. - Memory/LanceDB: let embedding config use provider-backed auth profiles, environment credentials, or provider config without a separate plugin `embedding.apiKey`, so OAuth-capable embedding providers can power auto-recall/capture. Fixes #68950. Thanks @malshaalan-ai. - CLI/parents: invoking `openclaw <parent>` (memory, channels, plugins, approvals, devices, cron, mcp) without a subcommand now prints the parent's help and exits `0`, matching `<parent> --help` and the existing `agents` / `sessions` defaults so shell `&&` chains and pnpm wrappers no longer surface a misleading `ELIFECYCLE Command failed with exit code 1.` line. Fixes #73077. Thanks @hclsys. - Plugins/hooks: time out never-settling `agent_end` observation hooks after 30 seconds and log the plugin failure, so hung embedding endpoints no longer leave memory capture silently pending forever. Fixes #65544. Thanks @ghoc0099. - Gateway/config: serve runtime config schemas from the current plugin metadata snapshot and generated bundled channel schema metadata instead of rebuilding plugin channel config modules on every `config.get`/`config.schema`, preventing idle plugin-discovery CPU churn after upgrades. Fixes #73088. Thanks @sleitor and @geovansb. - Memory/LanceDB: call OpenAI-compatible embedding endpoints through the raw SDK transport without sending `encoding_format`, then normalize float-array or base64 responses so providers such as ZhiPu and DashScope no longer fail recall with wrong vector dimensions or rejected parameters. Fixes #63655. Thanks @kinthaiofficial. - Plugins/install: run dependency installs with npm error-level logging instead of silent mode so failed plugin or hook installs surface actionable npm errors such as EUNSUPPORTEDPROTOCOL instead of `npm install failed:` with no detail. (#73093) Thanks @sanctrl. - Memory/LanceDB: bound memory recall embedding queries with a new `recallMaxChars` setting, prefer the latest user message over channel prompt metadata during auto-recall, and document the knob so small Ollama embedding models avoid context-length failures. Fixes #56780. Thanks @rungmc357 and @zak-collaborator. - CLI/skills: resolve workspace-backed skills commands from `--agent`, then the current agent workspace, before falling back to the default agent, so multi-agent ClawHub installs, updates, and status checks stay scoped to the active workspace. Fixes #56161; carries forward #72726. Thanks @langbowang and @luyao618. - Plugin SDK: fall back from partial bundled plugin directory overrides to package source public surfaces while preserving `OPENCLAW_DISABLE_BUNDLED_PLUGINS` as a hard disable. (#72817) Thanks @serkonyc. - Agents/ACPX: stop forwarding Codex ACP timeout config controls that Codex rejects while preserving OpenClaw's run-timeout watchdog for ACP subagents. Fixes #73052. Thanks @pfrederiksen and @richa65. - Memory Core: stream fallback vector search scoring with a bounded top-K result set so large indexes do not materialize every chunk embedding when sqlite-vec is unavailable. (#73069) Thanks @parkertoddbrooks. - Memory Core: stream embedding-cache seeding during safe reindex so large local caches do not materialize every row into the V8 heap before the atomic rebuild. (#73067) Thanks @parkertoddbrooks. - Memory/Ollama: add `memorySearch.remote.nonBatchConcurrency` for inline embedding indexing, default Ollama non-batch indexing to one request at a time, and keep batch concurrency separate from non-batch concurrency so local embedding backfills avoid timeout storms on smaller hosts. Carries forward #57733. Thanks @itilys. - macOS app: update Peekaboo, ElevenLabsKit, and MLX TTS helper dependencies, make canvas file watching and config/exec-approval state writes reliable under concurrent app/test activity, and keep the app plus helper builds warning-free. Thanks @Blaizzy. - iOS app: refresh SwiftPM/XcodeGen source hygiene, make app, extension, watch, and curated shared Swift files pass the prebuild SwiftFormat and SwiftLint checks, move relay registration off deprecated StoreKit receipt APIs, and keep simulator builds and logic tests warning-free. Thanks @ngutman. - Agents/models: keep `models.json` readiness and provider-hook caches warm across repeated agent and subagent model resolution while preserving external `models.json` invalidation, reducing repeated provider-plugin loads on slower ARM64 hosts. Fixes #73075. Thanks @jochen. - Docs/tools: clarify that `tools.profile: "messaging"` is intentionally narrow and that `tools.profile: "full"` is the unrestricted baseline for broader command/control access. Carries forward #39954. Thanks @posigit. - Control UI/Agents: redact tool-call args, partial/final results, derived exec output, and configured custom secret patterns before streaming tool events to the Control UI, so tool output cannot expose provider or channel credentials. Fixes #72283. (#72319) Thanks @volcano303 and @BunsDev. - Agents/sessions: keep `sessions_history` recall redaction enabled even when general log redaction is disabled, and clarify that safety-boundary UI/tool/diagnostic payloads still redact independently of `logging.redactSensitive`. Carries forward #72319. Thanks @volcano303 and @BunsDev. - Providers/Codex: pass agent and workspace directories into provider stream wrappers so Codex native `web_search` activation can evaluate the correct auth context, and smoke-test the built status-message runtime by resolving the emitted bundle name. Carries forward #67843; refs #65909. Thanks @neilofneils404. - Cron/models: keep `payload.model` as a per-job primary that can use configured fallbacks, while still letting `payload.fallbacks: []` make cron runs strict and avoid hidden agent-primary retries. Refs #73023. Thanks @pavelyortho-cyber. - Models/fallbacks: treat user-selected session models as exact choices, so `/model ollama/...` and model-picker switches fail visibly when the selected provider is unreachable instead of answering from an unrelated configured fallback. Fixes #73023. Thanks @pavelyortho-cyber. - Codex harness: keep ChatGPT subscription app-server runs from inheriting `CODEX_API_KEY` or `OPENAI_API_KEY`, and fall back to `CODEX_API_KEY` / `OPENAI_API_KEY` app-server login only when no Codex account is available. Fixes #73057. Thanks @holgergruenhagen and @pashpashpash. - CLI/model probes: fail local `infer model run` probes when the provider returns no text output, so unreachable local providers and empty completions no longer look like successful smoke tests. Refs #73023. Thanks @pavelyortho-cyber. - CLI/Ollama: run local `infer model run` through the lean provider completion path and skip global model discovery for one-shot local probes, so Ollama smoke tests no longer pay full chat-agent/tool startup cost or hang before the native `/api/chat` request. Fixes #72851. Thanks @TotalRes2020. - Doctor/gateway services: ignore launchd/systemd companion services that only reference the gateway as a dependency, suppress inactive Linux extra-service warnings, and avoid rewriting a running systemd gateway command/entrypoint during doctor repair. Carries forward #39118. Thanks @therk. - Daemon/service: only emit hard-coded version-manager paths such as `~/.volta/bin`, `~/.asdf/shims`, `~/.bun/bin`, and fnm/pnpm fallbacks into gateway and node service PATHs when the directories exist, so `openclaw doctor` no longer flags `gateway.path.non-minimal` against a PATH the daemon just wrote. Env-driven roots and stable user-bin dirs remain unconditional. Fixes #71944; carries forward #71964. Thanks @Sanjays2402. - CLI/startup: disable Node's module compile cache automatically for live source-checkout launchers so in-place `pnpm build` updates are visible to the next `openclaw` CLI invocation. Fixes #73037. Thanks @LouisGameDev. - Agents/group chat: keep silent-allowed empty and reasoning-only turns on the `NO_REPLY` path without injecting visible-answer retry prompts, and clarify the group prompt so agents use the exact silent token instead of prose. Thanks @vincentkoc. - Agents/group chat: move `NO_REPLY` mechanics into channel-aware direct/group prompts and suppress the duplicate generic silent-reply section for auto-reply runs, so always-on group agents get one consistent stay-silent instruction. Thanks @vincentkoc. - Providers/OpenAI: preserve encrypted empty-summary Responses reasoning items in WebSocket replay and request `reasoning.encrypted_content` on reasoning turns so GPT-5.4/GPT-5.5 sessions do not lose required `rs_*` state beside `msg_*` items. Fixes #73053. Thanks @odb36777. - Gateway/startup: treat `plugins.enabled=false` as an early plugin fast path, skipping plugin auto-enable discovery, gateway plugin lookup/runtime-dependency staging, and stale-plugin cleanup warnings while preserving channel blocker warnings. (#73041) Thanks @WuKongAI-CMU. - Channels/commands: make generated `/dock-*` commands switch the active session reply route through `session.identityLinks` instead of falling through to normal chat. Fixes #69206; carries forward #73033. Thanks @clawbones and @michaelatamuk. - Providers/Cloudflare AI Gateway: strip assistant prefill turns from Anthropic Messages payloads when thinking is enabled, so Claude requests through Cloudflare AI Gateway no longer fail Anthropic conversation-ending validation. Fixes #72905; carries forward #73005. Thanks @AaronFaby and @sahilsatralkar. - Gateway/startup: keep primary-model startup prewarm on scoped metadata preparation, let native approval bootstraps retry outside channel startup, and skip the global hook runner when no `gateway_start` hook is registered, so clean post-ready sidecar work stays off the critical path. Refs #72846. Thanks @RayWoo, @livekm0309, and @mrz1836. - Gateway/channels: start bundled channel accounts with a lightweight `runtimeContexts` surface instead of importing the full reply/routing/session channel runtime before `startAccount`, so Discord, Telegram, Slack, Matrix, and QQBot startup no longer block on unrelated channel helper graphs. Refs #72846 and #72960. Thanks @mrz1836, @RayWoo, and @rollingshmily. - Gateway/supervisor: exit cleanly when a supervised restart finds an existing healthy gateway and bound retries when the existing gateway stays unhealthy, so stale lock contention cannot loop indefinitely. Refs #72846. Thanks @azgardtek. - Gateway/startup: scope primary-model provider discovery during channel prewarm to the configured provider owner and add split startup trace timings, so boot avoids staging unrelated bundled provider dependencies while setup discovery remains broad. Fixes #73002. Thanks @Schnup03. - Plugins/runtime deps: declare retained staged bundled plugin dependencies in the npm staging manifest while installing only newly missing packages, so Gateway restarts avoid reinstalling the full retained dependency set when one runtime dependency is absent. Fixes #73055. Thanks @GCorp2026. - CLI/status: keep default `openclaw status` off the heavyweight security audit, plugin compatibility, and memory-vector probes while still showing configured Telegram channels through setup metadata, so routine health checks stay fast and no longer render an empty Channels table. Fixes #72993. Thanks @comick1. - Channels/Telegram: send a best-effort native typing cue immediately after an inbound message is accepted, so slow pre-dispatch turns show Telegram liveness before queueing, compaction, model, or tool work starts. Fixes #63759. Thanks @alessandropcostabr. - Channels/Telegram: stop native approval startup auth failures from retrying every second, while still waiting through retryable Gateway auth handoffs, so Telegram approval setup problems no longer create a reconnect/log loop during channel startup. Refs #72846 and #72867. Thanks @kiranvk-2011 and @porly1985. - Channels/Microsoft Teams: unwrap staged CommonJS JWT runtime dependencies before Bot Connector token validation so inbound Teams messages no longer 401 after the bundled runtime-deps move. Fixes #73026. Thanks @kbrown10000. - Gateway/auth: allow local direct callers in trusted-proxy mode to use the configured gateway password as an internal fallback while keeping token fallback rejected. Fixes #17761. Thanks @dashed, @vincentkoc, and @jetd1. - Gateway/auth: add explicit `trustedProxy.allowLoopback` support for same-host loopback reverse proxies while keeping loopback trusted-proxy auth fail-closed by default and preserving required-header and allowlist checks. Fixes #59167; carries forward #63379. Thanks @Matir, @jeremyakers, and @mrosmarin. - Channels/sessions: prevent guarded inbound session recording from creating route-only phantom sessions while still allowing last-route updates for sessions that already exist. Carries forward #73009. Thanks @jzakirov. - Cron: accept `delivery.threadId` in Gateway cron add/update schemas so scheduled announce delivery can target Telegram forum topics and other threaded channel destinations through the documented delivery path. Fixes #73017. Thanks @coachsootz. - Plugins/runtime deps: stage bundled plugin dependencies imported by mirrored root dist chunks, so packaged memory and status commands do not miss `chokidar` or similar root-chunk dependencies after update. Fixes #72882 and #72970; carries forward #72992. Thanks @shrimpy8, @colin-chang, and @Schnup03. - Plugins/runtime deps: reuse unchanged bundled plugin runtime mirrors instead of rebuilding plugin trees on every load, cutting avoidable writes and restart/reconnect I/O on slow storage. Fixes #72933. Thanks @jasonftl. - Agents/runtime context: deliver hidden runtime context through prompt-local system context while keeping the transcript-only custom entry out of provider user turns, and strip stale copied runtime-context prefaces from user-facing replies. Fixes #72386; carries forward #72969. Thanks @jhsmith409. - Channels/Telegram: skip the optional webhook-info API call during polling-mode status checks and startup bot-label probes so long-polling setups avoid an unnecessary Telegram round trip. Carries forward #72990. Thanks @danielgruneberg. - CLI/message: resolve targeted `openclaw message` channels to their owning plugin before loading the registry, and fall back to configured channel plugins when the channel must be inferred, so scripted sends avoid full bundled plugin registry scans without assuming channel ids match plugin ids. Fixes #73006. Thanks @jasonftl. - Plugins/startup: parse strict JSON plugin manifests with native JSON first and keep JSON5 as the compatibility fallback, reducing manifest registry CPU during Gateway boot and CLI startup. Fixes #73011. Thanks @jasonftl. - CLI/models: keep route-first `models status --json` stdout reserved for the JSON payload by routing auth-profile and startup diagnostics to stderr. Fixes #72962. Thanks @vishutdhar. - Gateway/runtime: keep dirty-tree status calls from rebuilding live `dist`, clear stale task and restart state across in-process restarts, retry transient Discord lazy imports, and let channel startup continue after slow model warmup so browser, Discord, and voice-call sidecars come online. Thanks @vincentkoc. - Security/CodeQL: replace file SecretRef id gateway schema regex validation with segment-aligned predicates and set empty permissions on release summary/backfill jobs so the narrowed CodeQL profile stays clean. Thanks @vincentkoc. - Sessions: ignore future-dated session activity timestamps during reset freshness checks and cap future `updatedAt` values at the merge boundary so clock-skewed messages cannot keep stale sessions alive forever. Fixes #72989. Thanks @martingarramon. - Sessions: apply search, activity filters, and limits before gateway row enrichment so bounded session lists avoid scanning discarded transcripts. Carries forward #72978. Thanks @yeager. - Sessions: remove trajectory runtime and pointer sidecars when session maintenance prunes, caps, or disk-evicts their owning session, while preserving sidecars still referenced by live rows. Fixes #73000. Thanks @jared-rebel. - Plugins/CLI: allow managed plugin installs when the active extensions root is a symlink to a real state directory, while keeping nested target symlinks blocked and suppressing misleading hook-pack fallback errors for install-boundary failures. Fixes #72946. Thanks @mayank6136. - Providers/Ollama: mark discovered Ollama catalog models as supporting streaming usage metadata so token accounting stays enabled for local models. (#72976) Thanks @sdeyang. - Media understanding: reject malformed MIME values with trailing junk while preserving standard parameter tails before enrichment uses them. (#72914) Thanks @volcano303. - WebChat: keep bare `/new` and `/reset` prompts from producing empty transcript text by inserting the hidden session marker when the visible tail is blank. (#72863) Thanks @mahopan. - CLI/update: explain completion-cache refresh timeouts with manual refresh guidance instead of surfacing a raw low-level timeout. Fixes #72842. (#72850) Thanks @iot2edge. - Memory-core/dreaming: give narrative generation a 60-second timeout so slower local or remote models can finish instead of timing out at 15 seconds. Fixes #72837. (#72852) Thanks @RayWoo. - Plugins/hooks: inject each plugin's resolved config into internal hook event context without mutating the shared event object. (#72888) Thanks @jalapeno777. - Agents/ACP: pass the resolved ACP agent directory into media understanding so per-agent media caches and config are used for ACP-dispatched image turns. (#72832) Thanks @luyao618. - Gateway/Bonjour: truncate mDNS service names and host labels to the 63-byte DNS label limit at valid UTF-8 boundaries. (#72809) Thanks @luyao618. - Feishu: treat groups explicitly configured under channels.feishu.groups as admitted even when groupAllowFrom is empty, while preserving groupPolicy: "disabled" as a hard group block and keeping groups.\* wildcard defaults non-admitting. Fixes #67687. (#72789) Thanks @MoerAI. - Gateway/startup: keep hot Gateway boot paths on leaf config imports and add max-RSS reporting to the gateway startup bench so low-memory startup regressions are visible before release. Thanks @vincentkoc. - WebChat: read `chat.history` from active transcript branches, drop stale streamed assistant tails once final history catches up, and coalesce duplicate in-flight Control UI submits, so rewritten prompts, completed replies, and rapid send events no longer render or process twice. Fixes #72975, #72963, and #72974. Thanks @dmagdici, @lhtpluto, and @Benjamin5281999. - WebChat/TTS: persist automatic final-mode TTS audio as a supplemental audio-only transcript update instead of adding a second assistant message with the same visible text. Fixes #72830. Thanks @lhtpluto. - Agents/LSP: terminate bundled stdio LSP process trees during runtime disposal and Gateway shutdown, so nested children such as `tsserver` do not survive stop or restart. Fixes #72357. Thanks @ai-hpc and @bittoby. - Diagnostics/OTEL: capture privacy-safe model-call request payload bytes, streamed response bytes, first-response latency, and total duration in diagnostic events, plugin hooks, stability snapshots, and OTEL model-call spans/metrics without logging raw model content. Fixes #33832. Thanks @wwh830. - Logging: write validated diagnostic trace context as top-level `traceId`, `spanId`, `parentSpanId`, and `traceFlags` fields in file-log JSONL records so traced requests and model calls are easier to correlate in log processors. Refs #40353. Thanks @liangruochong44-ui. - Logging/sessions: apply configured redaction patterns to persisted session transcript text and accept escaped character classes in safe custom redaction regexes, so transcript JSONL no longer keeps matching sensitive text in the clear. Fixes #42982. Thanks @panpan0000. - Providers/Ollama: honor `/api/show` capabilities when registering local models so non-tool Ollama models no longer receive the agent tool surface, and keep native Ollama thinking opt-in instead of enabling it by default. Fixes #64710 and duplicate #65343. Thanks @yuan-b, @netherby, @xilopaint, and @Diyforfun2026. - Control UI/Agents: remount the Overview model controls when switching agents so the primary-model picker cannot retain stale per-agent selection. Fixes #39392; carries forward #39401, notes the duplicate #39495 approach, and keeps #46275/#54724 broader stabilization out of scope. Thanks @daijunyi002, @SergioChan, @aworki, and @wsyjh8. - Auto-reply: poison inbound message dedupe after replay-unsafe provider/runtime failures so retries stay safe before visible progress but cannot duplicate messages after block output, tool side effects, or session progress. Fixes #69303; keeps #58549 and #64606 as duplicate validation. Thanks @martingarramon, @NikolaFC, and @zeroth-blip. - Agents/model fallback: jump directly to a known later live-session model redirect instead of walking unrelated fallback candidates, while preserving the already-landed live-session/fallback loop guard. Fixes #57471; related loop family already closed via #58496. Thanks @yuxiaoyang2007-prog. - Gateway/Bonjour: keep @homebridge/ciao cancellation handlers registered across advertiser restarts so late probing cancellations cannot crash Linux and other mDNS-churned gateways. Thanks @vincentkoc. - Plugins/startup: load the default `memory-core` slot during Gateway startup when permitted so active-memory recall can call `memory_search` and `memory_get` without requiring an explicit `plugins.slots.memory` entry, while preserving `plugins.slots.memory: "none"`. Thanks @vincentkoc. - Gateway/plugins: resolve `gateway_start` cron hooks from live Gateway runtime state before the legacy deps fallback, so memory-core dreaming cron reconciliation keeps working on installs where `deps.cron` is not populated during service startup. Fixes #72835. Thanks @RayWoo. - Plugins/CLI: prefer native require for compiled bundled plugin JavaScript before jiti so read-only config, status, device, and node commands avoid unnecessary transform overhead on slow hosts. Fixes #62842. Thanks @Effet. - Plugins/compat: inventory doctor-side deprecation migrations separately from runtime plugin compatibility so release sweeps preserve needed repairs while enforcing dated removal windows. Thanks @vincentkoc. - Plugins/compat: add missing dated compatibility records for legacy extension-api, memory registration, provider hook/type aliases, runtime aliases, channel SDK helpers, and approval/test utility shims. Thanks @vincentkoc. - Plugins/CLI: refresh the persisted registry after managed plugin files are removed so ClawHub uninstall cannot leave stale `plugins list` entries. Thanks @vincentkoc. - Plugins/CLI: make plugin install and uninstall config writes conflict-aware, clear stale denylist entries on explicit reinstall/removal, and delete managed plugin files only after config/index commit succeeds. Thanks @vincentkoc. - Plugins: fail `plugins update` when tracked plugin or hook updates error, keep bundled runtime-dependency repair behind restrictive allowlists, and reject package installs with unloadable extension entries. Thanks @vincentkoc. - WebChat/Control UI: support non-video file attachments in chat uploads while preserving the existing image attachment path and MIME-sniff fallback for generic image uploads. (#70947) Thanks @IAMSamuelRodda. - Skills/memory: restore Chokidar v5 hot reloads by watching concrete skill and memory roots with filters, including SKILL.md removals and deleted skill folders without broad workspace recursion. Fixes #27404, #33585, and #41606. Thanks @shelvenzhou, @08820048, and @rocke2020. - Gateway/chat: keep duplicate attachment-backed `chat.send` retries with the same idempotency key on the documented in-flight path so aborts still target the real active run. Fixes #70139. Thanks @Feelw00. - Gateway/chat: preserve repeated boundary characters while merging assistant chat stream deltas, including repeated digits, CJK characters, and markdown/table tokens. Fixes #63769; carries forward #63994 and #65457. Thanks @yon950905 and @mohuaxiao. - Plugins: share package entrypoint resolution between install and discovery, reject mismatched `runtimeExtensions`, and cache bundled runtime-dependency manifest reads during scans. Thanks @vincentkoc. - WhatsApp/Web: keep quiet but healthy linked-device sessions connected by basing the watchdog on WhatsApp Web transport activity, while retaining a longer app-silence cap so frame activity cannot mask a stuck session forever. Fixes #70678; carries forward the focused #71466 approach and keeps #63939 as related configurable-timeout follow-up. Thanks @vincentkoc and @oromeis. - Discord/gateway: count failed health-monitor restart attempts toward cooldown and hourly caps, and evict stale account lifecycle state during channel reloads so repeated Discord gateway recovery cannot loop on old status. Fixes #38596. (#40413) Thanks @jellyAI-dev and @vashquez. - TTS/BlueBubbles: pre-transcode synthesized MP3 audio to opus-in-CAF (mono, 24 kHz — validated against macOS 15.x Messages.app's native voice-memo CAF descriptor) on macOS hosts before handing the file to BlueBubbles, so iMessage renders the result as a native voice-memo bubble with proper duration and waveform UI instead of a plain file attachment. Adds an opt-in `tts.voice.preferAudioFileFormat` channel capability and a magic-byte sniff for the CAF container so the host-local-media validator (which uses `file-type` and didn't recognize CAF natively) can verify the pre-transcoded buffer. Channels that don't opt in are unaffected. (#72586) Fixes #72506. Thanks @omarshahine. - Feishu: retry WebSocket startup failures with monitor-owned backoff while preserving SDK-local heartbeat defaults, so persistent-connection startup failures no longer leave the monitor hung. Fixes #68766; related #42354 and #55532. Thanks @alex-xuweilong, @120106835, @sirfengyu, and @tianhaocui.