openclaw/appcast.xml

<?xml version="1.0" standalone="yes"?>
<rss xmlns:sparkle="http://www.andymatuschak.org/xml-namespaces/sparkle" version="2.0">
    <channel>
        <title>OpenClaw</title>
        <item>
            <title>2026.5.2</title>
            <pubDate>Sun, 03 May 2026 01:11:51 +0000</pubDate>
            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
            <sparkle:version>2026050290</sparkle:version>
            <sparkle:shortVersionString>2026.5.2</sparkle:shortVersionString>
            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
            <description><![CDATA[<h2>OpenClaw 2026.5.2</h2>
<h3>Highlights</h3>
<ul>
<li>External plugin installation, update, doctor repair, dependency reporting, and artifact metadata now cover the npm-first cutover, stale configured installs, missing package payloads, and beta-channel plugin fallback. Thanks @vincentkoc.</li>
<li>Gateway and agent hot paths are leaner across startup, session listing, task maintenance, prompt prep, plugin loading, tool descriptor planning, filesystem guards, and large runtime configs.</li>
<li>Control UI and WebChat are more resilient across Sessions, Cron, long-running Gateway WebSockets, grouped-message width, slash-command feedback, iOS PWA bounds, selection contrast, and Talk diagnostics.</li>
<li>Messaging fixes cover WhatsApp Channel/Newsletter targets, Telegram topic commands and networking, Discord delivery/startup edge cases, Slack threads, Signal groups/media, and visible reply routing.</li>
<li>Provider and media fixes cover OpenAI-compatible TTS/Realtime, OpenRouter/DeepSeek replay, Anthropic-compatible streaming, LM Studio reasoning metadata, Brave/SearXNG/Firecrawl web search, media paths, music, and voice-call routing.</li>
</ul>
<h3>Changes</h3>
<ul>
<li>Gateway/startup and restart: skip plugin-backed auth-profile overlays during startup secrets preflight, reducing gateway readiness latency while keeping reload and OAuth recovery paths overlay-capable; add <code>openclaw gateway restart --force</code> and <code>--wait <duration></code>, log active task run IDs before restart deferral timers, and report timeout restarts as explicit forced restarts. (#68327) Thanks @JIRBOY.</li>
<li>Plugins/ClawHub: make diagnostics, onboarding, doctor repair, and channel setup carry ClawPack metadata through install records while keeping explicit <code>clawhub:</code> installs on ClawHub and bare package installs on npm for the launch cutover. Thanks @vincentkoc.</li>
<li>Plugins/CLI: include package dependency install state in <code>openclaw plugins list --json</code> so scripts can spot missing plugin dependencies without runtime-loading plugins.</li>
<li>Plugins/update: on the beta OpenClaw update channel, default-line npm and ClawHub plugin updates try <code>@beta</code> first and fall back to default/latest when no plugin beta release exists.</li>
<li>Plugins/runtime: scope broad runtime preloads to the effective plugin ids derived from config, startup planning, configured channels, slots, and auto-enable rules instead of importing every discoverable plugin.</li>
<li>Agents/runtime: reuse the startup-loaded plugin registry for request-time providers, tools, channel actions, web/capability/memory/migration helpers, and memoized provider extra-params, and memoize transcript replay-policy resolution for stable config and process-env runs while preserving model-specific transport hook patches and custom-env provider behavior. Thanks @DmitryPogodaev.</li>
<li>Infra/path-guards: add a fast path for canonical absolute POSIX containment checks, avoiding repeated <code>path.resolve</code> and <code>path.relative</code> work in hot filesystem walkers. Refs #75895, #75575, and #68782. Thanks @Enderfga.</li>
<li>Tools/plugins: add a platform-level tool descriptor planner for descriptor-first visibility, generic availability checks, and executor references, and cache plugin tool descriptors captured from <code>api.registerTool(...)</code> so repeated prompt-time planning can skip plugin runtime loading while execution still loads the live plugin tool. (#76079) Thanks @shakkernerd.</li>
<li>Docs/Codex: clarify that ChatGPT/Codex subscription setups should use <code>openai/gpt-*</code> with <code>agentRuntime.id: "codex"</code> for native Codex runtime, while <code>openai-codex/*</code> remains the PI OAuth route. Thanks @pashpashpash.</li>
<li>Plugins/source checkout: load bundled plugins from the <code>extensions/*</code> pnpm workspace tree in source checkouts, so plugin-local dependencies and edits are used directly while packaged installs keep using the built runtime tree. Thanks @vincentkoc.</li>
<li>Plugins/beta: externalize ACPX behind <code>@openclaw/acpx</code> and diagnostics OpenTelemetry behind <code>@openclaw/diagnostics-otel</code>, keeping their heavier runtime stacks out of the core package until installed; prepare Google Chat, LINE, Matrix, Mattermost, BlueBubbles, diagnostics Prometheus, Google Meet, Nextcloud Talk, Nostr, Zalo, Zalo Personal, diagnostics OpenTelemetry, Discord, Diffs, Lobster, Memory LanceDB, Microsoft Teams, QQ Bot, Voice Call, WhatsApp, Brave, Codex, Feishu, Synology Chat, Tlon, and Twitch for <code>2026.5.1-beta.1</code>/<code>2026.5.1-beta.2</code> npm and ClawHub publishing, and keep publishable plugin dist trees out of the core npm package. Thanks @vincentkoc.</li>
<li>Providers/xAI: add Grok 4.3 to the bundled catalog and make it the default xAI chat model.</li>
<li>Google Meet: let API-created rooms set <code>accessType</code> and <code>entryPointAccess</code>, add <code>googlemeet end-active-conference</code> for closing managed spaces after a call, and add <code>googlemeet test-listen</code> plus the matching <code>google_meet</code> <code>test_listen</code> action so transcribe-mode joins wait for real caption or transcript movement before reporting listen-first health. (#74824; refs #72478) Thanks @BsnizND and @DougButdorf.</li>
<li>Plugins/ClawHub/onboarding: prefer versioned ClawPack artifacts when ClawHub publishes digest metadata, verify ClawPack response headers and downloaded bytes, persist ClawPack digest/artifact metadata on install/update records and install-on-demand provider setup entries, and allow official bundled-plugin cutovers to record ClawHub artifact metadata while preserving npm as the launch default for bare package specs and retaining npm/local fallback paths. Thanks @vincentkoc.</li>
<li>Plugins/Crestodian: add ClawHub plugin search plus Crestodian plugin list/search/install/uninstall operations, with approval and audit coverage for install and uninstall.</li>
<li>Channels/thread bindings: replace split subagent/ACP thread-spawn toggles with <code>threadBindings.spawnSessions</code>, default thread-bound spawns on, and let <code>openclaw doctor --fix</code> migrate the legacy keys. (#75943)</li>
<li>Providers/OpenAI: add <code>extraBody</code>/<code>extra_body</code> passthrough for OpenAI-compatible TTS endpoints, so custom speech servers can receive fields such as <code>lang</code> in <code>/audio/speech</code> requests. Fixes #39900. Thanks @R3NK0R.</li>
<li>Channels/WhatsApp: support explicit WhatsApp Channel/Newsletter <code>@newsletter</code> outbound message targets with channel session metadata instead of DM routing. Fixes #13417; carries forward the narrow outbound target idea from #13424. Thanks @vincentkoc and @agentz-manfred.</li>
<li>Dependencies: refresh workspace, bundled runtime, and plugin dependency pins, including TypeBox 1.1.37, AWS SDK 3.1041.0, Microsoft Teams 2.0.9, Marked 18.0.3, Pi 0.71.1, OpenAI 6.35.0, Codex 0.128.0, Zod 4.4.1, and Matrix 41.4.0. Thanks @mariozechner, @aws, and @microsoft.</li>
<li>Discord/channels: add reusable message-channel access groups plus Discord channel-audience DM authorization, so allowlists can reference <code>accessGroup:<name></code> across channel auth paths. (#75813)</li>
<li>Crabbox/scripts: print the selected Crabbox binary, version, and supported providers before <code>pnpm crabbox:*</code> commands, and reject stale binaries that lack <code>blacksmith-testbox</code> provider support.</li>
<li>Agents/Codex: add committed happy-path prompt snapshots for Codex/message-tool Telegram direct, Discord group, and heartbeat turns so prompt drift can be reviewed. Thanks @pashpashpash.</li>
<li>Agents/workspace: add <code>agents.defaults.skipOptionalBootstrapFiles</code> for skipping selected optional workspace files during bootstrap without disabling required workspace setup. (#62110) Thanks @mainstay22.</li>
<li>Plugins/CLI: add first-class <code>git:</code> plugin installs with ref checkout, commit metadata, normal scanner/staging, and <code>plugins update</code> support for recorded git sources. Thanks @badlogic.</li>
<li>Google Meet: add live caption health for Chrome transcribe mode, including caption observer state, transcript counters, last caption text, and recent transcript lines in status and doctor output. Refs #72478. Thanks @DougButdorf.</li>
<li>Voice Call/Google Meet: add Twilio Meet join phase logs around pre-connect DTMF, realtime stream setup, and initial greeting handoff for easier live-call debugging. Thanks @donkeykong91 and @PfanP.</li>
<li>macOS app: move recent session context rows into a Context submenu while keeping usage and cost details root-level, so the menu bar companion stays compact with many active sessions. Thanks @guti.</li>
<li>Gateway/SDK: add SDK-facing tools.invoke RPC with shared HTTP policy, typed approval/refusal results, and SDK helper support. Refs #74705. Thanks @BunsDev and @ai-hpc.</li>
<li>Discord: keep active buttons, selects, and forms working across Gateway restarts until they expire, so multi-step Discord interactions are less likely to break during upgrades or restarts. Thanks @amknight.</li>
<li>Messages/docs: clarify that <code>BodyForAgent</code> is the primary inbound model text while <code>Body</code> is the legacy envelope fallback, and add Signal coverage so channel hardening patches target the real prompt path. Refs #66198. Thanks @defonota3box.</li>
<li>Slack: publish a safe default App Home tab view on <code>app_home_opened</code>, include the Home tab event in setup manifests, and keep track of bot-participated threads across restarts so ongoing threaded conversations can continue auto-replying after the Gateway restarts. Fixes #11655; refs #52020. Thanks @TinyTb and @amknight.</li>
<li>Control UI/Usage: add UTC quarter-hour token buckets for the Usage Mosaic and reuse them for hour filtering, keeping the legacy session-span fallback for older summaries. (#74337) Thanks @konanok.</li>
<li>BlueBubbles: add opt-in <code>channels.bluebubbles.replyContextApiFallback</code> that fetches the original message from the BlueBubbles HTTP API when the in-memory reply-context cache misses (multi-instance deployments sharing one BB account, post-restart, after long-lived TTL/LRU eviction). Off by default; channel-level setting propagates to accounts that omit the flag through <code>mergeAccountConfig</code>; routed through the typed <code>BlueBubblesClient</code> so every fetch is SSRF-guarded by the same three-mode policy as every other BB client request; reply-id shape is validated and part-index prefixes (<code>p:0/<guid></code>) are stripped before the request; concurrent webhooks for the same <code>replyToId</code> coalesce into one fetch and successful responses populate the reply cache for subsequent hits. Also promotes BlueBubbles attachment download failures from verbose to runtime error so silently-dropped inbound images are visible at default log level, and extends <code>sanitizeForLog</code> to redact <code>?password=…</code>/<code>?token=…</code> query params and <code>Authorization:</code> headers before they reach the log sink (CWE-532). (#71820) Thanks @coletebou and @zqchris.</li>
<li>CLI/proxy: add <code>openclaw proxy validate</code> so operators can verify effective proxy configuration, proxy reachability, and expected allow/deny destination behavior before deploying proxy-routed OpenClaw commands. (#73438) Thanks @jesse-merhi.</li>
<li>Agents/Codex: default Codex app-server dynamic tools to native-first, keeping OpenClaw integration tools while leaving file, patch, exec, and process ownership to the Codex harness; default Codex-harness direct source replies to the OpenClaw <code>message</code> tool when visible reply delivery is not explicitly configured, keeping channel-visible output as a deliberate tool call. (#75308, #75765) Thanks @pashpashpash.</li>
<li>Heartbeats/agents: add a structured <code>heartbeat_respond</code> tool for tool-capable heartbeat runs so agents can record quiet outcomes or explicit notification text without relying only on <code>HEARTBEAT_OK</code> parsing. (#75765) Thanks @pashpashpash.</li>
<li>Gateway/config: allow <code>$include</code> directives to read files from operator-approved <code>OPENCLAW_INCLUDE_ROOTS</code> directories while preserving default config-directory confinement. Thanks @ificator.</li>
</ul>
<h3>Fixes</h3>
<ul>
<li>Agents/OpenAI: default GPT-5 API-key sessions to the SSE Responses transport unless WebSocket is explicitly selected, restoring replies in fresh Control UI and WebChat beta installs where the auto WebSocket path connected but produced no model events.</li>
<li>Agents/sessions: preserve terminal lifecycle state when final run metadata persists from a stale in-memory snapshot, preventing sessions from staying stuck as running after completed or timed-out turns.</li>
<li>Gateway/CLI/status: make <code>openclaw gateway start</code> repair stale managed service definitions that point at old OpenClaw versions, missing binaries, or temporary installer paths before starting; add concrete service, config, listener-owner, and log collection next steps when gateway probes fail and Bonjour finds no local gateway; avoid repeated plugin tool descriptor config hashing so large runtime configs do not block reply startup and trigger reconnect/timeouts. Refs #49012. (#75944) Thanks @vincentkoc and @joshavant.</li>
<li>Plugins/update/config: stop treating the non-plugin <code>auth</code> command root as a bundled plugin id, keep packaged upgrades and beta external plugin installs on stable runtime aliases and matching prerelease npm specs, detect tracked plugin install records whose package directories disappeared during <code>openclaw update</code>, reinstall them before normal plugin updates, fail the update if install records still point at missing disk payloads, and validate configured web-search providers plus statically suppressed model/provider pairs against the active plugin set at config load. Thanks @vincentkoc.</li>
<li>Codex/app-server: resolve managed binaries from bundled <code>dist</code> chunks and from the <code>@openai/codex</code> package bin when installs do not provide a nearby <code>.bin/codex</code> shim, avoiding false missing-binary startup failures.</li>
<li>Status: show the <code>openai-codex</code> OAuth profile for <code>openai/gpt-*</code> sessions running through the native Codex runtime instead of reporting auth as unknown. (#76197) Thanks @mbelinky.</li>
<li>Status/update: resolve beta update-channel checks from the installed version when config still says <code>stable</code>, show configured channels in <code>openclaw status</code> and config-only <code>openclaw channels status</code> output even when the Gateway is unreachable, and let <code>status --deep</code> reuse live gateway channel credential state instead of warning on command-path-only token misses. Thanks @vincentkoc.</li>
<li>Plugins/externalization: add official npm-first catalogs for externalized channel, provider, and generic plugins; install official external web-search plugins before saving provider config; repair missing configured, selected-search, and env-selected plugin installs from npm by default; keep official install docs, update examples, live Codex checks, diagnostics ClawHub packages, and persisted bundled-plugin relocation on default npm tags; keep Matrix and Mattermost bundled until their npm packages cut over; and keep ACPX, Google Chat, and LINE publishable plugin dist trees out of the core package while ClawHub pack files roll out. Thanks @vincentkoc.</li>
<li>Plugins/ClawHub/source/registry: use the ClawHub artifact resolver response as the install decision before downloading, keep bare plugin package specs on npm for the launch cutover and reserve ClawHub resolution for explicit <code>clawhub:</code> specs until ClawHub pack readiness is deployed, discover source-only plugins such as Codex from <code>extensions/*</code>, install ClawPack artifacts from the explicit npm-pack <code>.tgz</code> resolver path, persist artifact kind, npm integrity, shasum, and tarball metadata for update/diagnostics flows, fall back to version metadata when the artifact resolver route is missing, keep the Docker ClawHub fixture aligned with npm-pack artifact resolution, explain unavailable explicit ClawHub ClawPack artifact downloads with a temporary npm install hint, and hash manifest/package metadata when validating persisted plugin registries so fast same-size rewrites cannot leave stale plugin metadata trusted. Thanks @vincentkoc.</li>
<li>Control UI: add validated <code>gateway.controlUi.chatMessageMaxWidth</code> instead of patched bundled CSS, ignore malformed persisted cron rows before they enter UI state, guard stale cron render paths, and bound the default Sessions tab query to recent activity and fewer rows while keeping filters editable. Fixes #67935, #55047, #54439, and #76050; supersedes #54550 and #54552. (#76051) Thanks @xiew4589-lang and @Neomail2.</li>
<li>Gateway/channels: cap startup fanout at four channel/account handoffs and recover from Bonjour ciao self-probe races, reducing Windows startup stalls with many Telegram accounts. Fixes #75687.</li>
<li>Gateway/sessions: keep <code>sessions.list</code> polling responsive on large session stores by reusing list-safe session cache/indexes and returning a lightweight compaction checkpoint preview instead of heavyweight summaries. Thanks @rolandrscheel.</li>
<li>Control UI/Gateway: keep long-running dashboard WebSocket sessions alive with protocol pings, keep Stop available after reconnect or reload by recovering session-scoped active-run abort state, contain standalone iOS PWA viewports with safe-area-aware document locking, use high-contrast text selection colors, and show inline feedback when local slash-command dispatch is unavailable or fails unexpectedly. Fixes #70991, #60850, and #52105; supersedes #60854. Thanks @alexandre-leng, @kvncrw, @Badschaff, @efe-arv, and @MooreQiao.</li>
<li>CLI/update: treat inherited Gateway service markers as origin hints and only block package replacement when the managed Gateway is still live, so self-updates can stop the service and continue safely. (#75729) Thanks @hxy91819.</li>
<li>Agents/failover: exempt run-level timeouts that fire during tool execution from model fallback, timeout-triggered compaction, and generic timeout payload synthesis, avoiding misleading "LLM request timed out" errors after the primary model has already responded. Fixes #52147. (#75873) Thanks @simonusa.</li>
<li>Docker: copy Bun 1.3.13 from a digest-pinned image and keep CI on the same version. Fixes #74356. Thanks @fede-kamel and @sallyom.</li>
<li>Agents/compaction: keep prior context on consecutive turns against z.ai-style providers (z.ai direct, openrouter z-ai/\*, in-house GLM gateways), avoiding accidental Pi state reset after successful turns. (#76056) Thanks @openperf.</li>
<li>Doctor/plugins: run a one-time 2026.5.2 configured-plugin install repair based on <code>meta.lastTouchedVersion</code>, update stale configured plugin manifests that still declare channels without <code>channelConfigs</code>, install actively used downloadable OpenClaw plugins through the configured external source, preserve unmanaged third-party plugin <code>node_modules</code>, and then mark the config touched for the release.</li>
<li>Sessions/transcripts: use one <code>session.writeLock.acquireTimeoutMs</code> policy for session transcript lock acquisitions and raise the default wait to 60 seconds, avoiding user-visible lock timeouts during legitimate slow prep, cleanup, compaction, and mirror work. Fixes #75894. Thanks @shandutta.</li>
<li>Agents/restart recovery: match cleaned transcript locks by exact transcript lock paths plus the canonical session fallback, so interrupted main sessions using topic-suffixed transcripts resume after gateway restart. Refs #76052. Thanks @anyech.</li>
<li>Agents/runtime: cache the stable system-prompt prefix and reuse prompt-report tool schema stats during dispatch prep, reducing repeated CPU work before streaming starts. Fixes #75999; supersedes #76061. Thanks @zackchiutw and @STLI69.</li>
<li>Telegram/native commands: pass persisted session files into plugin commands for topic-bound sessions, so <code>/codex bind</code> works from Telegram forum topics. Refs #75845 and #76049. Thanks @MatthewSchleder.</li>
<li>Security audit/plugins: ignore plugin install backup, disabled, and dependency debris directories when enumerating installed plugin roots, avoiding false-positive findings for <code>.openclaw-install-backups</code> after plugin updates. Fixes #75456.</li>
<li>Telegram: honor runtime conversation bindings for native slash commands in bound top-level groups, so commands like <code>/status@bot</code> route to the active non-<code>main</code> session instead of falling back to the default route. Fixes #75405; supersedes #75558. Thanks @ziptbm and @yfge.</li>
<li>Gateway/tasks: make task registry maintenance use pass-local backing-session lookups and fresh active child-session indexes, avoiding repeated full task snapshots and session-store clones on large stale registries. Fixes #73517 and #75708; supersedes #74406 and #75709. Thanks @Lightningxxl, @glfruit, and @jared-rebel.</li>
<li>Auth/sessions: JSON-clone auth-profile cache/runtime snapshots and remaining session cleanup previews instead of using <code>structuredClone</code>, preserving mutation isolation while avoiding native-memory growth on large stores. Fixes #45438. Thanks @markus-lassfolk.</li>
<li>Models CLI: restore <code>openclaw models list --provider <id></code> catalog and registry fallback rows for unconfigured providers, so provider-specific verification commands no longer report "No models found." Fixes #75517; supersedes #75615. Thanks @lotsoftick and @koshaji.</li>
<li>Gateway/macOS: write LaunchAgent services with a canonical system PATH and stop preserving old plist PATH entries, so Volta, asdf, fnm, and pnpm shell paths no longer affect gateway child-process Node resolution. Fixes #75233; supersedes #75246. Thanks @nphyde2.</li>
<li>Slack/hooks: preserve bot alert attachment text in message-received hook content when command text is blank. Fixes #76035; refs #76036. Thanks @amsminn.</li>
<li>Sessions/agents: route Gateway session-store writes, CLI cleanup maintenance, and agent-delete session purges through a dedicated in-process writer and borrow the validated mutable cache during the writer slot, avoiding runtime file locks plus repeated <code>sessions.json</code> rereads and JSON clones on hot metadata updates. Refs #68554. Thanks @henkterharmsel.</li>
<li>Memory/markdown: replace CRLF managed blocks in place and collapse duplicate marker blocks without rewriting unmanaged markdown, so Dreaming and Memory Wiki files self-heal from repeated generated sections. Fixes #75491; supersedes #75495, #75810, and #76008. Thanks @asaenokkostya-coder, @ottodeng, @everettjf, and @lrg913427-dot.</li>
<li>Agents/tools: return critical tool-loop circuit-breaker stops as blocked tool results instead of thrown tool failures, so models see the guardrail and stop retrying the same call. Thanks @rayraiser.</li>
<li>Agents/sessions: preserve pre-existing runtime model and context window after heartbeat turns so a per-run heartbeat model override does not bleed into shared-session status. Fixes #75452. Thanks @zhangguiping-xydt.</li>
<li>Model commands: clarify direct and inline <code>/model</code> acknowledgements for non-default selections as session-scoped. Thanks @addu2612.</li>
<li>Doctor/gateway: stop warning that non-existent, unconfigured user-bin directories are required in the Gateway service PATH. Fixes #76017. Thanks @xiphis.</li>
<li>TUI/setup: skip full provider model normalization during context-window warmup and bound Terminal hatch bootstrap provider requests, avoiding cold-start stalls with large model registries and first-run hatching stuck behind the watchdog. (#76241) Thanks @547895019 and @joshavant.</li>
<li>Agents: enable malformed tool-call argument repair for Codex and Azure OpenAI Responses transports while keeping generic OpenAI Responses paths out of the repair gate. Fixes #75154. Thanks @Nimraakram22.</li>
<li>Memory Wiki: accept relative Markdown links that include the <code>.md</code> suffix during broken-wikilink validation, avoiding false positives for native render-mode links. Thanks @Kenneth8128.</li>
<li>OpenAI Codex: show the device-pairing code in the interactive SSH/headless prompt while keeping the short-lived code out of persistent runtime logs. Fixes #74212. Thanks @da22le123.</li>
<li>QA Lab: stop gateway children when the suite parent disappears, so interrupted local QA runs cannot leave hot orphaned gateways behind.</li>
<li>Codex/app-server/plugins: tolerate second connection closes during startup recovery, include retry counts plus stringified restart errors, and allow the official npm Codex plugin to install without the unsafe-install override while keeping <code>/codex</code> command ownership and covering the real npm Docker live path through managed <code>.openclaw/npm</code> dependencies plus uninstall failure proof.</li>
<li>Plugins/CLI: cache plugin CLI registration entries per command program so completion state generation does not repeat the full plugin sweep in one invocation. Thanks @ScientificProgrammer.</li>
<li>Plugins: reuse gateway-bindable plugin loader cache entries for later default-mode loads without serving default-built registries to gateway-bound requests, reducing repeated plugin registration during dispatch. Refs #61756. Thanks @DmitryPogodaev.</li>
<li>Gateway/secrets: include the caught error message in <code>secrets.reload</code> and <code>secrets.resolve</code> warning logs while keeping RPC errors generic, so operators can diagnose reload and permission failures. Thanks @davidangularme.</li>
<li>Providers/OpenRouter/LM Studio/Anthropic: fill DeepSeek V4 <code>reasoning_content</code> replay placeholders for <code>openrouter/deepseek/deepseek-v4-flash</code> and <code>openrouter/deepseek/deepseek-v4-pro</code>, normalize binary LM Studio reasoning metadata from Gemma 4 and other local models, and recover Anthropic-compatible stream text deltas that arrive before their matching content block. Fixes #76018 and #76007. Thanks @cloph-dsp and @vliuyt.</li>
<li>fix(infra): block workspace state-directory env override [AI]. (#75940) Thanks @pgondhi987.</li>
<li>MCP/OpenAI and media: normalize parameter-free MCP tool schemas before OpenAI tool submission, honor explicit short <code>[[tts:text]]...[[/tts:text]]</code> blocks while keeping untagged short auto-TTS suppressed, and accept home-relative <code>MEDIA:~/...</code> attachment paths under the existing file-read policy. Fixes #75362, #73758, and #73796. Thanks @tolkonepiu, @SymbolStar, @yfge, and @fabkury.</li>
<li>Hooks/doctor: warn when <code>hooks.transformsDir</code> points outside the canonical hooks transform directory, so invalid workspace skill paths get a direct recovery hint before the Gateway crash-loops. Fixes #75853. Thanks @midobk.</li>
<li>Proxy/audio: convert standard <code>FormData</code> bodies before proxy-backed undici fetches, so audio transcription and multipart uploads no longer send <code>[object FormData]</code> when <code>HTTP_PROXY</code> or <code>HTTPS_PROXY</code> is configured. Fixes #48554. Thanks @dco5.</li>
<li>Discord/setup/startup/native commands: write resolved guild/channel allowlist selections to the selected guild and channel, persist slash-command deploy hashes across process restarts, treat abort-time Carbon reconnect-exhausted events as expected shutdown during stale-socket restarts, allow explicit ack reactions in tool-only guild channels, and warn when slash dispatch or direct plugin execution produces no visible reply. Fixes #74922 and #58986; carries forward #58216; supersedes #47788, #73949, and #62057. Thanks @samvilian, @BlueBirdBack, @Eldersonar, @Perttulands, and @jb510.</li>
<li>Discord/delivery/media: use session-backed A2A announce target lookup for multi-account <code>sessions_send</code>, keep typing indicators alive during long tool runs and auto-compaction, preserve multipart Content-Type headers for uploads, preserve attachment and sticker filenames, and keep non-ASCII channel names in session labels while preserving ASCII-slug allowlists. Fixes #42652 and #59744; refs #51626 and #44773; supersedes #73975. Thanks @irchelper, @dpalfox, @Lanfei, @Squirbie, @FunJim, @xela92, @rockcent, and @swjeong9.</li>
<li>Discord/threads/PluralKit: canonicalize proxied webhook turns to the original message id for dedupe, inject thread starter context only on the first effective thread turn, and resolve thread <code>ownerId</code>/<code>parentId</code> from Discord API-style snake_case payload fields so bot-owned autoThreads do not require unnecessary mentions. Fixes #41355; supersedes #44447 and #44449. Thanks @acgh213, @p3nchan, and @mgh3326.</li>
<li>Gateway/diagnostics: include a bounded redacted startup error message in stability bundles, so crash-loop reports identify the failing plugin or contract without exposing secrets. Refs #75797. Thanks @ymebosma.</li>
<li>Gateway/pricing: defer optional model pricing catalog refresh until after sidecars and channels reach the ready path, so slow OpenRouter or LiteLLM pricing fetches cannot block Gateway readiness. Fixes #74128; supersedes #73486. Thanks @ctbritt and @alprclbi.</li>
<li>Gateway/pricing: abort in-flight model pricing catalog fetches when Gateway shutdown stops the refresh loop, and avoid post-stop cache writes or refresh timers. Fixes #72208. Thanks @rzcq.</li>
<li>Codex/app-server: make startup retry cleanup ownership-aware so concurrent Codex lanes cannot close another lane's freshly restarted shared app-server client. Thanks @vincentkoc.</li>
<li>Google Meet/Twilio/Voice Call: report missing dial-in details during setup, explain that Twilio needs a phone dial plan for Meet URLs, start the phone leg before Meet PIN DTMF, delay intro speech until after post-connect dialing, log each stage, and accept provider call IDs for gateway speak/continue while reporting ended-call state from history.</li>
<li>Control UI/Talk: allow the OpenAI Realtime WebRTC offer endpoint through the Control UI CSP, configure browser sessions with explicit VAD/transcription input settings, and surface OpenAI realtime error/lifecycle events instead of leaving Talk stuck as live with no diagnostic. Fixes #73427.</li>
<li>Plugins: clarify config-selected duplicate plugin override diagnostics and document manifest schema updates for bundled-plugin forks. Fixes #8582. Thanks @sachah.</li>
<li>CLI backends/Claude: make live-session JSONL turn caps bounded and configurable via <code>reliability.outputLimits</code>, raising the default guard for tool-heavy Claude CLI turns while preserving memory limits. Fixes #75838. Thanks @hcordoba840.</li>
<li>Telegram/DMs/network/commands: keep incidental <code>message_thread_id</code> reply-with-quote metadata on flat DM sessions unless topic isolation is configured, raise outbound text and typing Bot API guards to 60 seconds with safe timeout overrides and typing fallback retries, and register/clear command menus in default and group-chat scopes so <code>/status</code> and plugin commands stay available in forum topics. Fixes #75975, #76013, and #74032; updates #6457. Thanks @ProjectEvolutionEVE, @iaki1206, @dae-sun, and @WouldenShyp.</li>
<li>Providers/OpenAI: resolve <code>keychain:<service>:<account></code> <code>OPENAI_API_KEY</code> refs before creating OpenAI Realtime browser sessions or voice bridges, with a bounded cached Keychain lookup. Fixes #72120. Thanks @ctbritt.</li>
<li>Discord/gateway: reconnect when the gateway socket closes while waiting for the shared IDENTIFY concurrency window, instead of silently skipping IDENTIFY and leaving the bot online but unresponsive. Fixes #74617. Thanks @zeeskdr-ai.</li>
<li>Voice Call: add <code>sessionScope: "per-call"</code> for fresh per-call agent memory while preserving the default per-phone caller history. Fixes #45280. Thanks @pondcountry.</li>
<li>Music generation: raise too-small tool timeouts to the provider-safe 10-second floor and collapse cascading abort fallback errors into a clearer root-cause summary. Thanks @shakkernerd.</li>
<li>Memory-core/dreaming: include the primary runtime workspace in multi-agent dreaming sweeps without mixing main-agent session transcripts into configured subagent workspaces. Fixes #70014. Thanks @ttomiczek.</li>
<li>Control UI: add tab/RPC timing attribution and decouple slow Overview/Cron secondary refreshes so Sessions navigation gets immediate visible feedback. Refs #64004. Thanks @WaMaSeDu.</li>
<li>Memory: retry transient SQLite index file swaps during atomic reindex on Windows, so brief <code>EBUSY</code>, <code>EPERM</code>, or <code>EACCES</code> locks do not fail memory rebuilds. Fixes #64187. Thanks @kunpeng-ai-lab.</li>
<li>Telegram/startup/models: use the existing <code>getMe</code> request guard and higher <code>timeoutSeconds</code> configs for slow Bot API paths, and make model picker confirmations say selections are session-scoped. Fixes #75783 and #75965. Thanks @tankotan and @sd1114820.</li>
<li>Control UI/slash commands: keep fallback command metadata on a browser-safe registry path, so provider thinking runtime imports cannot blank the Web UI with <code>process is not defined</code>. Fixes #75987. Thanks @novkien.</li>
<li>Heartbeat/Discord: keep async exec completion events out of the generic <code>System (untrusted)</code> prompt block and let the dedicated exec heartbeat prompt handle them, so Discord no longer receives raw exec failure tails as separate system-style messages. Fixes #66366. Thanks @Promee-ThaBossHoss.</li>
<li>Heartbeat/scheduler: make heartbeat phase scheduling active-hours-aware so the scheduler seeks forward to the first in-window phase slot instead of arming timers for quiet-hours slots and relying solely on the runtime guard. Non-UTC <code>activeHours.timezone</code> values (e.g. <code>Asia/Shanghai</code>) now correctly influence when the next heartbeat timer fires, avoiding wasted quiet-hours ticks and long dormant gaps after gateway restarts. Fixes #75487. Thanks @amknight.</li>
<li>Channels: strip plain-text MiniMax and XML tool-call scaffolding from shared user-facing reply sanitization, so messaging channels do not deliver raw model tool syntax when a provider emits it as text instead of structured tool calls. Fixes #62820. Thanks @canh0chua.</li>
<li>Infer/media: report missing image-understanding and audio-transcription provider configuration for <code>image describe</code>, <code>image describe-many</code>, and <code>audio transcribe</code> instead of blaming the input path when no provider is available. Fixes #73569 and supersedes #73593, #74288, and #74495. Thanks @bittoby, @tmimmanuel, @Linux2010, and @vyctorbrzezowski.</li>
<li>CLI/infer: reject local <code>codex/*</code> one-shot model probes before simple-completion dispatch and point operators at the Codex app-server runtime path instead of ending with an empty-output error.</li>
<li>Docs/health: clarify that session listing surfaces stored conversation rows rather than Discord/channel socket liveness, and point connectivity checks at channel status and health probes. Fixes #70420. Thanks @ashersoutherncities-art and @martingarramon.</li>
<li>WhatsApp/Cron: keep DM pairing-store approvals out of implicit cron and heartbeat recipient fallback, so scheduled automation only uses explicit targets, active configured recipients, or configured <code>allowFrom</code> entries. Fixes #62339. Thanks @kelvinisly-collab.</li>
<li>Google Meet: keep the agent-facing <code>google_meet</code> tool visible on non-macOS hosts but block local Chrome realtime actions with guidance, so Linux agents can still use transcribe, Twilio, chrome-node, and artifact flows without choosing the macOS-only BlackHole path. Refs #75950. Thanks @actual-software-inc.</li>
<li>macOS/settings: keep opening General from rewriting <code>openclaw.json</code> during Tailscale settings hydration, preserving <code>gateway</code>, <code>auth</code>, <code>meta</code>, and <code>wizard</code> until the user changes a setting. Fixes #59545. Thanks @Tengdw.</li>
<li>Discord: prioritize interaction callbacks ahead of stale background REST work without polling active REST buckets, validate oversized gateway payloads and member-intent requests before send, and forward explicit component payloads from message actions. (#75363)</li>
<li>Active Memory: use the configured recall timeout as the blocking prompt-build hook budget by default and move cold-start setup grace behind explicit <code>setupGraceTimeoutMs</code> config, so the plugin no longer silently extends 15000 ms configs to 45000 ms on the main lane. Fixes #75843. Thanks @vishutdhar.</li>
<li>Plugins/web-provider: reuse the active gateway plugin registry for runtime web provider resolution after deriving the same candidate plugin ids as the loader path, avoiding a redundant <code>loadOpenClawPlugins</code> call on every request while preserving origin and scope filters. Fixes #75513. Thanks @jochen.</li>
<li>Crestodian/CLI: exit non-zero when interactive Crestodian is invoked without a TTY, so scripts and CI no longer treat the setup error as success. Fixes #73646 and supersedes #73928 and #74059. Thanks @bittoby, @luyao618, and @Linux2010.</li>
<li>Cron: keep implicit/default isolated cron announce deliveries out of the main session awareness queue, so isolated jobs do not accumulate in the main conversation. Fixes #61426. Thanks @Lihannon.</li>
<li>Subagents: avoid duplicate parent-visible replies when a parent uses <code>sessions_send</code> on its own persistent native subagent session, while preserving announce delivery for async sends. Fixes #73550. Thanks @sylviazhang2006-design.</li>
<li>Web search/Brave: add opt-in <code>brave.http</code> diagnostics for Brave request URLs/query params, response status/timing, and cache hit/miss/write events without logging API keys or response bodies. Fixes #55196. Thanks @mecampbellsoup.</li>
<li>Web search/Brave: add <code>plugins.entries.brave.config.webSearch.baseUrl</code> for Brave-compatible proxies, including endpoint-aware cache keys for both web and LLM Context modes. Fixes #19075. Thanks @jkoprax and @vishnukool.</li>
<li>Web search/config: validate explicit <code>tools.web.search.provider</code> values against bundled and installed plugin manifests, while warning for stale third-party plugin config. Fixes #53092. Thanks @TinyTb.</li>
<li>Web search/SearXNG: retry empty non-general category searches once with the general category, so unsupported category engines do not return empty results when general search has matches. Fixes #73552. Thanks @Loukky.</li>
<li>CLI/message: skip gateway-stop hooks for read-only <code>message read</code> and bound stop-hook shutdown for other message actions, so one-shot Discord reads cannot hang behind plugin lifecycle cleanup.</li>
<li>Plugins/web-provider: cache repeated bundled web search and web fetch provider registry loads by default while preserving explicit cache opt-outs. Supersedes #75992. Thanks @DmitryPogodaev.</li>
<li>Agents/sandbox: preserve existing workspace file modes when sandbox edits atomically replace files, so 0644 files do not collapse to 0600 after Write/Edit/apply_patch. Fixes #44077. Thanks @patosullivan.</li>
<li>Control UI/WebChat: route typed <code>/new</code> through the New Chat dashboard-session creation flow instead of <code>chat.send</code>, while keeping <code>/reset</code> as the explicit current-session reset. Fixes #69599. Thanks @WolvenRA.</li>
<li>Agents/models: keep legacy CLI runtime model refs such as <code>claude-cli/*</code> in the configured allowlist after canonical runtime migration, so cron <code>payload.model</code> overrides keep working. Fixes #75753. Thanks @RyanSandoval.</li>
<li>Codex/app-server: restart the shared Codex app-server client once when it closes during startup thread resume, preserving the existing thread binding instead of retrying <code>thread/start</code> on a closed client. Thanks @vincentkoc.</li>
<li>Gateway/watch: keep colored subsystem log prefixes in the managed tmux pane even when the parent shell exports <code>NO_COLOR</code>, while preserving explicit <code>FORCE_COLOR=0</code> opt-out. Thanks @vincentkoc.</li>
<li>Agents/compaction: submit a non-empty runtime-event marker for pre-compaction memory flush turns, so strict Anthropic providers no longer reject the silent flush as an empty user message. Fixes #75305. Thanks @sableassistant3777-source.</li>
<li>Plugin SDK: re-export <code>isPrivateIpAddress</code> from <code>plugin-sdk/ssrf-runtime</code>, restoring source-checkout builds for SearXNG and Firecrawl private-network guards. Thanks @vincentkoc.</li>
<li>Discord/message actions: advertise <code>upload-file</code> and route it through Discord's send runtime with agent-scoped media reads, so agents can discover and send file attachments. Fixes #60652 and supersedes #60808, #61087, and #61100. Thanks @claw-io, @efe-arv, @joelnishanth, and @sjhddh.</li>
<li>Sessions: suppress exact inter-session control replies such as <code>NO_REPLY</code> and keep agent-to-agent announce bookkeeping out of visible transcripts. Fixes #53145. Thanks @TarahAssistant.</li>
<li>CLI/directory: report unsupported directory operations for installed channel plugins instead of prompting to reinstall the plugin when it lacks a directory adapter. Fixes #75770. Thanks @lawong888.</li>
<li>Web search/SearXNG/Firecrawl/Kimi: show the SearXNG JSON API <code>search.formats</code> prerequisite, pass through <code>img_src</code> image URLs, fail explicitly when Kimi returns ungrounded answers, keep public provider requests on strict SSRF guards, reject private/loopback/metadata/non-HTTP(S) hosted Firecrawl scrape targets, and allow explicit self-hosted private Firecrawl endpoints. Fixes #52573, #74357, and #63877; supersedes #65592, #61416, #74360, #48133, #59666, #63941, and #74013. Thanks @evanpaul14, @sghael, @wangwllu, @fede-kamel, @kn1ghtc, @jhthompson12, @jzakirov, @Mlightsnow, and @shad0wca7.</li>
<li>CLI/models: report gateway model fallback attempts in <code>infer model run --json</code> and avoid double-prefixing provider-qualified defaults such as <code>openrouter/auto</code> in <code>models status</code>. Partially fixes #69527. Thanks @alexifra.</li>
<li>Providers/OpenRouter: strip trailing assistant prefill turns from verified OpenRouter Anthropic model requests when reasoning is enabled, so Claude 4.6 routes no longer fail with Anthropic's prefill rejection through the OpenAI-compatible adapter. Fixes #75395. Thanks @sbmilburn.</li>
<li>Voice Call: add per-number inbound routing for dialed-number greetings, response agents/models/prompts, and TTS voice overrides. Fixes #56604. Thanks @healthstatus.</li>
<li>Feishu: preserve Feishu/Lark HTTP error bodies for message sends, media sends, and chat member lookups, so HTTP 400 failures include vendor code, message, log id, and troubleshooter details. Fixes #73860. Thanks @desksk.</li>
<li>Agents/transcripts: avoid reopening large Pi transcript files through the synchronous session manager for maintenance rewrites, persisted tool-result truncation, manual compaction boundary hardening, and queued compaction rotation. Thanks @mariozechner.</li>
<li>Web search/Exa/MiniMax: accept Exa <code>webSearch.baseUrl</code> overrides with endpoint-partitioned caches, include MiniMax Search in setup, and let <code>MINIMAX_API_KEY</code> participate in MiniMax Search auto-detection. Fixes #54928; supersedes #54939 and #65828. Thanks @mrpl327, @lyfuci, and @Jah-yee.</li>
<li>Plugins/ClawHub: preserve official source-linked trust through archive installs, so OpenClaw can install trusted ClawHub plugin packages that trigger the built-in dangerous-pattern scanner. Thanks @vincentkoc.</li>
<li>Plugins/ClawHub: install package runtime dependencies for archive-backed plugin installs, so ClawHub packages such as WhatsApp load declared dependencies after download. Thanks @vincentkoc.</li>
<li>Plugins/tools: cache repeated plugin tool factory results only for matching request context, reducing per-turn tool prep without leaking sandbox, session, browser, delivery, or runtime config state. Fixes #75956. Thanks @Linux2010.</li>
<li>Providers/LM Studio: allow <code>models.providers.lmstudio.params.preload: false</code> to skip OpenClaw's native model-load call so LM Studio JIT loading, idle TTL, and auto-evict can own model lifecycle. Fixes #75921. Thanks @garyd9.</li>
<li>Agents/transcripts: keep chat history, restart recovery, fork token checks, and stale-token compaction checks on bounded async transcript reads or cached async indexes instead of reparsing large session files. Thanks @mariozechner.</li>
<li>Telegram: inherit the process DNS result order for Bot API transport and downgrade recovered sticky IPv4 fallback promotions to debug logs, while keeping pinned-IP escalation warnings visible. Fixes #75904. Thanks @highfly-hi and @neeravmakwana.</li>
<li>Sessions: keep durable external conversation pointers, including group and thread-scoped chat sessions, out of age, count, and disk-budget maintenance eviction while still allowing synthetic runtime entries to age out. Fixes #58088. Thanks @drinkflav.</li>
<li>Web search/Providers MiniMax: allow <code>MINIMAX_OAUTH_TOKEN</code> to satisfy MiniMax Search credentials and derive Coding Plan usage polling from the configured MiniMax base URL, so OAuth-authorized and global setups use the right endpoint. Fixes #65768 and #65054. Thanks @kikibrian, @zhouhe-xydt, @sixone74, and @Yanhu007.</li>
<li>Control UI/WebChat: skip assistant-media transcript supplements when stale media refs resolve to no playable media, so text-only final replies are not stored a second time as gateway-injected assistant messages. Fixes #73956. Thanks @HemantSudarshan.</li>
<li>Sessions: reject <code>sessions_send</code> targets that resolve to thread-scoped chat sessions, so inter-agent coordination cannot be injected into active human-facing Slack or Discord threads. Fixes #52496. Thanks @barry-p5cc.</li>
<li>Subagents: honor <code>sessions_spawn</code> with <code>expectsCompletionMessage: false</code> by skipping parent completion handoff delivery while still running child cleanup. Fixes #75848. Thanks @alfredjbclaw.</li>
<li>Media/completions: treat media-only message-tool sends as delivered async completion output, avoiding duplicate raw <code>MEDIA:</code> fallback posts after video or music generation finishes.</li>
<li>Gateway/logging: keep deferred channel startup logs on the subsystem logger, so Slack, Discord, Telegram, and voice-call startup messages keep timestamped prefixes. Thanks @vincentkoc.</li>
<li>Codex/app-server: recover JSON-RPC frames split by raw command-output newlines and include a redacted preview when malformed app-server messages still reach the console. Thanks @vincentkoc.</li>
<li>Replies/typing: keep typing alive for queued follow-up messages that are genuinely waiting behind an active run, instead of making chat surfaces look idle while work is queued. Fixes #65685. Thanks @papag00se.</li>
<li>ACP/Discord: suppress completion announce delivery for inline thread-bound ACP session runs, so Discord thread-bound ACP replies are not delivered twice. Fixes #60780. Thanks @solavrc.</li>
<li>Discord/threads: ignore webhook-authored copies in already-bound Discord session threads even when the webhook id differs, preventing PluralKit proxy copies from creating duplicate turn pressure. Fixes #52005. Thanks @acgh213.</li>
<li>Discord/threads: return the created thread as partial success when the follow-up initial message fails, so agents do not retry thread creation and create empty duplicate threads. Fixes #48450. Thanks @dahifi.</li>
<li>Discord/components: consume every button or select in a non-reusable component message after the first authorized click, so single-use panels cannot fire sibling callbacks. Fixes #54227. Thanks @fujiwarakasei.</li>
<li>macOS/config: preserve existing <code>gateway.auth</code> and unrelated config keys during app fallback writes, so dashboard or Talk settings changes cannot strand Control UI clients by dropping persisted auth. Fixes #75631. Thanks @Fuma2013.</li>
<li>Control UI/TUI: keep reconnecting chat sends bound to the same backing session id and let TUI relaunches resume the last selected session, avoiding silent fresh sessions after refresh, reconnect, or terminal restart. Fixes #63195, #68162, and #73546. Thanks @bond260312-cmyk, @zhong18804784882, and @mtuwei.</li>
<li>Plugins/tools: let plugin manifests declare static tool availability so reply startup skips unavailable plugin tool runtimes instead of importing factories that only return <code>null</code>. Thanks @shakkernerd.</li>
<li>Discord/reactions: skip reaction listener registration when DMs and group DMs are disabled and every configured guild has <code>reactionNotifications: "off"</code>, avoiding needless reaction-event queue work. Fixes #47516. Thanks @x4v13r1120.</li>
<li>CLI sessions: preserve explicit manual-attach reuse bindings so trusted CLI sessions are not invalidated on the first turn when auth, prompt, or MCP fingerprints drift. Fixes #75849. Thanks @alfredjbclaw.</li>
<li>Telegram/streaming: keep partial preview streaming enabled for plain reply-to replies, disabling drafts only for real native quote excerpts that require Telegram quote parameters. Fixes #73505. Thanks @choury.</li>
<li>Config: log the "newer OpenClaw" version warning once per process instead of once per config snapshot read. (#75927) Thanks @romneyda.</li>
<li>Telegram/message actions: treat benign delete-message 400s as no-op warnings instead of runtime errors, so stale or already-removed messages do not create noisy delete failures. Fixes #73726. Thanks @Avicennasis.</li>
<li>Telegram: split long default markdown sends and media follow-up text into safe HTML chunks, so outbound messages over Telegram's limit no longer fail as one oversized Bot API request. Fixes #75868. Thanks @zhengsx.</li>
<li>Gateway/chat history: merge Claude CLI transcript imports for Anthropic-routed sessions that still have a Claude CLI binding, so local chat history does not hide CLI JSONL turns. Fixes #75850. Thanks @alfredjbclaw.</li>
<li>Media: trim serialized JSON suffixes after local <code>MEDIA:</code> directive file extensions, so generated-image metadata cannot pollute the parsed media path and cause false <code>ENOENT</code> delivery failures. Fixes #75182. Thanks @TnzGit and @hclsys.</li>
<li>Plugins/runtime: hot-reload Gateway plugin runtime surfaces after plugin enable/disable changes while keeping source-changing plugin install, update, and uninstall operations restart-backed so loaded module code is not reused. Fixes #72097.</li>
<li>Cron: make scheduler reload schedule comparison tolerate malformed persisted jobs, so one bad cron entry no longer aborts the whole tick. Fixes #75886. Thanks @samfox-ai.</li>
<li>Doctor/channels: warn after migrations when default Telegram or Discord accounts have no configured token and their env fallback (<code>TELEGRAM_BOT_TOKEN</code> or <code>DISCORD_BOT_TOKEN</code>) is unavailable, with secret-safe migration docs for checking state-dir <code>.env</code>. Fixes #74298. Thanks @lolaopenclaw.</li>
<li>Gateway/diagnostics: keep idle liveness samples in telemetry instead of visible warning logs unless diagnostic work is active, waiting, or queued. Thanks @vincentkoc.</li>
<li>Channels/cron: reject provider-prefixed targets for the wrong channel and let prefixed announce targets such as <code>telegram:123</code> select their channel when delivery falls back to <code>last</code>, so Telegram IDs cannot be coerced into WhatsApp phone numbers. Fixes #56839. Thanks @bencoremans.</li>
<li>Control UI/chat: keep live replies visible when a raw session alias such as <code>main</code> sends the chat turn but Gateway emits events under the canonical session key for the same run. Fixes #73716. Thanks @teebes.</li>
<li>CLI/models: reject <code>--agent</code> on <code>openclaw models set</code> and <code>set-image</code> instead of silently writing agent-scoped requests to global model defaults. Fixes #68391. Thanks @derrickabellard.</li>
<li>CLI: stop treating the legacy singular <code>openclaw tool ...</code> token as a plugin id under restrictive <code>plugins.allow</code>, so it falls through as a normal unknown/reserved command instead of suggesting a stale allowlist entry. Fixes #64732. Thanks @efe-arv, @SweetSophia, and @hashtag1974.</li>
<li>Media: write inbound media buffers through same-directory temp files before rename, so failed disk writes do not leave zero-byte artifacts for later voice transcription. Fixes #55966. Thanks @OpenCodeEngineer.</li>
<li>TTS/Telegram: keep trusted local audio generated by the TTS tool queued for voice-note delivery even when the run-level built-in tool list omits the raw <code>tts</code> name. Fixes #74752. Thanks @Loveworld3033 and @andyliu.</li>
<li>TTS: require explicit user or config audio intent for the agent speech tool so dashboard chats stay text unless audio is requested. Fixes #69777. Thanks @alexandre-leng.</li>
<li>Plugins/config: keep bundled source-checkout plugins from being runtime-gated by install-only <code>minHostVersion</code> metadata, accept prerelease host floors, trim plugin-service startup failures to one log line, and avoid broad channel-runtime loading during base config parsing. Thanks @vincentkoc.</li>
<li>Heartbeat: strip legacy <code>[TOOL_CALL]...[/TOOL_CALL]</code> and <code>[TOOL_RESULT]...[/TOOL_RESULT]</code> pseudo-call blocks from heartbeat replies before channel delivery. Fixes #54138. Thanks @Deniable9570.</li>
<li>macOS/Voice Wake: send wake-word and Push-to-Talk transcripts through the selected macOS session target instead of always falling back to main WebChat. Fixes #51040. Thanks @carl-jeffrolc.</li>
<li>Providers/xAI: give Grok <code>web_search</code> a 60s default timeout, harden malformed xAI Responses parsing, and return structured timeout errors instead of aborting the tool call. Fixes #58063 and #58733. Thanks @dnishimura, @marvcasasola-svg, and @Nanako0129.</li>
<li>Providers/configure: preserve the existing default model when adding or reauthing a provider whose plugin returns a default-model config patch. Fixes #50268. Thanks @rixcorp-oc.</li>
<li>Slack/DMs/routing: honor <code>dmHistoryLimit</code> for fresh 1:1 DMs, keep top-level DMs on stable DM sessions even when <code>replyToMode</code> targets thread replies, send text/block-only proactive DMs directly with <code>chat.postMessage(channel=<user id>)</code>, match Slack target route syntax such as <code>channel:C...</code>, <code>user:U...</code>, or <code><@U...></code>, and match public-channel allowlists against bare runtime channel IDs. Fixes #64427, #58832, #62042, #41608, and #41264; supersedes #56530. Thanks @brantley-creator, @daye-jjeong, @MarkMolina, @Winnsolutionsadmin, @babutree, and @Realworld404.</li>
<li>Slack/delivery/capabilities: preserve missing-scope details in outbound errors, read granted scopes from <code>auth.test</code> metadata before legacy APIs, retry Slack writes only for wrapped DNS request failures such as <code>EAI_AGAIN</code>, and prefer the account bound to the outbound target peer in multi-workspace sends. Fixes #62391, #44625, and #68789; supersedes #66807. Thanks @alexey-pelykh, @Qquanwei, @martingarramon, @sonnyb9, and @rijhsinghani.</li>
<li>Slack/message actions/tools: send media before follow-up Block Kit messages for file sends, forward agent-scoped media roots through the bundled upload-file path, resolve <code><!subteam^...></code> user-group mentions before waking mention-gated channels, and let <code>read</code> fetch an exact Slack message timestamp or thread reply. Fixes #51458, #64625, #73827, and #53943. Thanks @HirokiKobayashi-R, @benpchandler, @CG-Intelligence-Agent-Jack, and @zomars.</li>
<li>PDF/Gemini: send native PDF analysis API keys in the <code>x-goog-api-key</code> header instead of the request URL, keeping secrets out of proxy and access logs. Supersedes #60600. Thanks @garagon.</li>
<li>Web search/Gemini/DuckDuckGo/Brave/fetch: route abort signals into Gemini provider fetches, late-bind managed agent <code>web_search</code> calls to the current runtime config snapshot, reuse Google provider API key/base URL as lower-priority Gemini search fallbacks, pass Gemini freshness/date filters through grounding, include DuckDuckGo in setup, honor Gemini/Grok/x_search <code>baseUrl</code> overrides, point Brave metadata at canonical docs, support Brave LLM Context freshness/date ranges, resolve external <code>webFetchProviders</code> for non-sandboxed fetches, and point missing-key errors to <code>web_fetch</code> or browser where appropriate. Fixes #72995, #75420, #66498, #65862, #65870, and #74915; supersedes #57496, #65940, #61972, #65892, and #51005. Thanks @RoseKongPS, @richardmqq, @Aoiujz, @ismael-81, @Jah-yee, @Lanfei, @Magicray1217, @remusao, @ultrahighsuper, @mingmingtsao, and @zhaoyang97.</li>
<li>Slack/directory: make <code>openclaw directory peers/groups list --channel slack</code> prefer token-backed live readers and return the connected Slack account from <code>directory self</code>, so valid Slack tokens no longer produce empty directory CLI results. Fixes #50776. Thanks @pjaillon.</li>
<li>Slack: keep assistant typing status, temporary typing reactions, and status reactions active for group/channel turns that use message-tool-only visible replies, while still suppressing automatic source replies. Fixes #75877. Thanks @teosborne.</li>
<li>Slack: recover full inbound DM text from top-level rich-text blocks when Slack sends a shortened message preview, so long direct messages still reach the agent intact. Fixes #55358. Thanks @tonyjwinter.</li>
<li>Replies: strip legacy <code>[TOOL_CALL]{tool => ..., args => ...}[/TOOL_CALL]</code> pseudo-call text from user-facing replies and flag it in tool-call diagnostics instead of showing raw tool syntax in channels. Fixes #63610. Thanks @canh0chua.</li>
<li>WhatsApp: close long-lived web sockets through Baileys <code>end(error)</code> before falling back to raw websocket close, so listener teardown runs Baileys cleanup instead of leaving zombie sockets. Fixes #52442. Thanks @essendigitalgroup-cyber.</li>
<li>Twitch/plugins: emit a flat JSON Schema for Twitch channel config so single-account and multi-account configs validate before runtime load, and add source-checkout diagnostics for missing pnpm workspace dependencies. Thanks @vincentkoc.</li>
<li>Gateway/sessions: move hot transcript reads and mirror appends onto async bounded IO with serialized parent-linked writes, keeping large session histories from stalling Gateway requests and channel replies. Fixes #75656. Thanks @DerFlash.</li>
<li>macOS/Talk Mode: downmix multi-channel microphone buffers before handing them to Apple Speech across Push-to-Talk, Talk Mode, Voice Wake, and the wake-word tester, so pro audio interfaces no longer produce empty transcripts. Fixes #42533. Thanks @jbuecker.</li>
<li>macOS/Talk Mode: subscribe native WebChat to active-session transcript updates and render external spoken user turns in the chat thread instead of only showing assistant replies. Fixes #75155. Thanks @SledderBling.</li>
<li>macOS/Voice Wake: accept trigger-only phrases in the built-in Voice Wake test, matching the settings UI and runtime trigger-only path instead of requiring extra command text after the wake word. Fixes #64986. Thanks @zoiks65.</li>
<li>Cron/TTS: run cron announce payloads through the normal TTS directive transform before outbound delivery, so scheduled <code>[[tts]]</code> replies generate voice payloads instead of leaking raw tags. Fixes #52125. Thanks @kenchen3000.</li>
<li>WhatsApp: save downloadable quoted image media from reply context as inbound media, so agents can inspect an image that a user replied to instead of only seeing <code><media:image></code>. Fixes #59174. Thanks @gaffner.</li>
<li>Sessions/store: stop persisting the runtime-only <code>skillsSnapshot.resolvedSkills</code> array inside each session entry, so <code>sessions.json</code> no longer carries a copy of every parsed <code>SKILL.md</code> body for every active session; <code>ensureSkillSnapshot</code> rehydrates the array from disk on cold resume so the embedded runner, the Claude CLI skills plugin, and the Claude live-session fingerprint all see populated skills, and legacy stores self-heal on the next save. Refs #11950, #6650, #15000. Thanks @amoghasgekar.</li>
<li>Doctor/WhatsApp: warn when Linux crontabs still run the legacy <code>ensure-whatsapp.sh</code> health check, which can misreport <code>Gateway inactive</code> when cron lacks the systemd user-bus environment. Fixes #60204. Thanks @mySebbe.</li>
<li>Slack/setup: print the generated app manifest as plain JSON instead of embedding it inside the framed setup note, so it can be copied into Slack without deleting border characters. Fixes #65751. Thanks @theDanielJLewis.</li>
<li>Channels/WhatsApp: route CLI logout through the live Gateway and stop runtime-backed listeners before channel removal, so removing a WhatsApp account does not leave the old socket replying until restart. Fixes #67746. Thanks @123Mismail.</li>
<li>Voice Call/Twilio: honor TTS directive text and provider voice/model overrides during telephony synthesis, so <code>[[tts:...]]</code> tags are not spoken literally and voiceId overrides reach OpenAI/ElevenLabs calls. Fixes #58114. Thanks @legonhilltech-jpg.</li>
<li>Agents/session-locks: reclaim untracked current-process session locks with matching starttime during acquisition and startup cleanup, so Gateway restarts recover from self-owned orphan <code>.jsonl.lock</code> files. Fixes #75805; refs #49603. Thanks @cdznho.</li>
<li>Agents/subagents: initialize built-in context engines before native <code>sessions_spawn</code> resolves spawn preparation, so cliBackend-only cold starts no longer fail with an unregistered <code>legacy</code> context engine. Fixes #73095. (#73904) Thanks @brokemac79.</li>
<li>Plugins/Bonjour: ship the ciao runtime dependency with packaged OpenClaw so fresh OCM envs can start default mDNS discovery without a missing-module failure. Thanks @shakkernerd.</li>
<li>Agents/tools: scope reply plugin-tool discovery to manifest-declared tool owners and already-active matching tool entries, avoiding broad plugin runtime loading for narrow or core-only tool allowlists. Thanks @shakkernerd.</li>
<li>Agents/replies: defer implicit image model discovery and keep OAuth auth-store adoption on persisted profiles during reply startup, cutting OCM MarCodex warm prep to sub-second in live checks. Thanks @shakkernerd.</li>
<li>Plugins/tools: enforce <code>contracts.tools</code> as the manifest ownership contract for plugin tool registration, rejecting undeclared runtime tool names and adding bundled plugin drift coverage. Thanks @shakkernerd.</li>
<li>Agents/Codex: stop prompting message-tool-only source turns to finish with <code>NO_REPLY</code>, so quiet turns are represented by not calling the visible message tool instead of conflicting final-text instructions. Thanks @pashpashpash.</li>
<li>Gateway/config: report failed backup restores as failed in logs and config observe audit records instead of marking them valid. (#70515) Thanks @davidangularme.</li>
<li>Compaction: use the active session model fallback chain for implicit summarization failures without persisting fallback model selection, so Azure content-filter 400s can recover. Fixes #64960. (#74470) Thanks @jalehman and @OpenCodeEngineer.</li>
<li>Gateway/config: allow <code>gateway config.patch</code> to update documented subagent thinking defaults. Fixes #75764. (#75802) Thanks @kAIborg24.</li>
<li>Plugins/CLI: keep git plugin install paths credential-free, preserve existing git checkouts until replacement succeeds, honor duplicate npm install mode, and remove managed git repos on uninstall. Thanks @vincentkoc.</li>
<li>Plugins/CLI: redact authenticated git URLs from git install command failure details, so failed clone or checkout output cannot leak credentials during plugin installs. Thanks @vincentkoc.</li>
<li>Channels/status reactions: remove stale non-terminal lifecycle reactions when a run reaches done or error, so Discord does not leave a permanent thinking emoji after completion. Fixes #75458. Thanks @davelutztx.</li>
<li>Discord/doctor: migrate unsupported per-channel <code>agentId</code> entries under guild channel config into top-level <code>bindings[]</code> routes, so <code>openclaw doctor --fix</code> preserves the intended agent route instead of stripping it as an unknown key. Fixes #62455. Thanks @lobster-biscuit.</li>
<li>Discord/DMs: set inbound direct-message <code>ctx.To</code> to the semantic <code>user:<id></code> target while keeping delivery routed through the DM channel, so mirror and recovery paths do not treat DMs as channel conversations. Fixes #68126. Thanks @illuminate0623.</li>
<li>Discord/DMs: keep no-guild inbound messages on direct-message routing when Discord channel lookup is temporarily unavailable, preventing degraded DMs from forking into channel sessions. Fixes #59817. Thanks @DooPeePey.</li>
<li>Discord: retry outbound API calls on HTTP 5xx, request-timeout, and transient transport failures instead of only Discord rate limits, reducing dropped cron and agent replies during short Discord or network outages. Fixes #52396. Thanks @sunshineo.</li>
<li>Discord: include Components v2 Text Display content from referenced replies and forwarded snapshots, so component-only messages still appear in reply context. Fixes #56228. Thanks @HollandDrive.</li>
<li>Discord: add configurable gateway READY timeouts for startup and runtime reconnects, so staggered multi-account setups can avoid false restart loops. Fixes #72273. Thanks @sergionsantos.</li>
<li>Discord: preserve native slash-command description localizations through command reconcile, so localized Discord descriptions no longer get overwritten by English defaults. Fixes #56580. Thanks @mhseo93.</li>
<li>Discord: add configured outbound mention aliases so known <code>@Name</code> references can be rewritten to real Discord user mentions instead of relying only on the transient directory cache. Fixes #67587. Thanks @McoreD.</li>
<li>Discord: avoid startup REST amplification by skipping native command deploy retries after Discord rate limits and deriving the bot id from parseable bot tokens instead of requiring a <code>/users/@me</code> lookup. Fixes #75341. Thanks @PrinceOfEgypt.</li>
<li>Plugins/hooks: derive hook <code>ctx.channelId</code> from the conversation target instead of the provider name, so Discord and other channel plugins can keep per-channel state isolated. Fixes #59881. Thanks @bradfreels.</li>
<li>Gateway/config: log config health-state write failures instead of silently hiding config observe-recovery write errors. Thanks @sallyom.</li>
<li>Diagnostics: reset stuck-session timers on reply, tool, status, block, and ACP progress events, and back off repeated <code>session.stuck</code> diagnostics while a session remains unchanged. Supersedes #72010. Thanks @rubencu.</li>
<li>Gateway/agents: avoid rebuilding core tools for plugin-only allowlists and keep the full plugin registry cache warm across scoped plugin loads, reducing per-turn latency spikes. Fixes #75882, #75907, #75906, #75887, and #75851. (#75922) Thanks @obviyus.</li>
<li>Agents/failover: classify bare <code>status: internal server error</code> provider messages as retryable server errors so model fallback can rotate instead of stopping. (#73844) Thanks @thesomewhatyou.</li>
<li>Gateway/startup: return the shared retryable startup-sidecars error for startup-gated control-plane RPCs such as sessions.create, sessions.send, sessions.abort, agent.wait, and tools.effective, so clients can retry early sidecar races. (#76012) Thanks @scoootscooob.</li>
<li>Providers/Google: fix Gemini 2.5 Flash-Lite <code>reasoning: "minimal"</code> rejections by raising its thinking-budget floor to 512 while preserving the existing Gemini 2.5 Pro and Flash minimal presets. (#70629) Thanks @ericberic.</li>
<li>Agents/status: resolve <code>session_status(sessionKey="current")</code> for sparse channel-plugin sessions after literal current lookups miss, so Scope, Slack, Discord, and other plugin-driven agents avoid retrying through <code>Unknown sessionKey: current</code>. Fixes #74141. (#72306) Thanks @bittoby.</li>
<li>Cron: retry recurring wake-now main-session jobs through temporary heartbeat busy skips before recording success, so queued cron events no longer appear as ok ghost runs while the main lane is still busy. Fixes #75964. (#76083) Thanks @kshetrajna12 and @xuruiray.</li>
<li>Providers/Google: keep Gemini thinking-signature-only stream chunks active during reasoning, so Gemini 3.1 Pro Preview replies no longer hit idle timeouts before visible text. Fixes #76071. (#76080) Thanks @marcoschierhorn and @zhangguiping-xydt.</li>
<li>CLI/skills: show per-agent model and command visibility in <code>openclaw skills check --agent</code>, and let doctor report or disable unavailable skills allowed for the default agent. (#75983) Thanks @mbelinky.</li>
<li>Agents/runtime/tools: keep reply startup on Gateway metadata, manifest catalog rows, auth-store state, and plugin loader cache-key compatibility checks so scoped runtime registries, model allowlists, thinking metadata, media/PDF/generation tools, Comfy workflows, OpenAI Codex OAuth image generation, and image/video/music tool registration avoid broad provider/runtime loads while preserving explicit config and auth-backed providers. Thanks @shakkernerd.</li>
<li>Discord: document canonical mention formatting in agent prompt hints and channel docs so outbound replies use <code><@USER_ID></code>, <code><#CHANNEL_ID></code>, and <code><@&ROLE_ID></code> instead of legacy nickname mentions. (#75173)</li>
<li>Heartbeat scheduler: gate exec-event/notification/spawn/retry wakes through a centralized cooldown so backgrounded <code>process.start</code> exit notifications can no longer self-feed runaway heartbeat runs (configured <code>every: "30m"</code> was firing every ~10s in production, pegging the gateway event loop with <code>eventLoopDelayMaxMs >6s</code> spikes that stalled control-UI asset serving and TUI handshakes). Documented wake-now paths (<code>manual</code>, <code>wake</code>, task completion, blocked-task follow-up, <code>/hooks/wake mode=now</code>, and cron <code>--wake now</code>) remain immediate; retryable busy skips no longer poison the cooldown for the next retry; per-agent flood guard caps any unexpected feedback loop at 5 runs/60s. (#64016, refs #17797 and #75436) Thanks @hexsprite.</li>
<li>fix: block workspace CLOUDSDK_PYTHON override and always set trusted interpreter for gcloud. (#74492) Thanks @pgondhi987.</li>
<li>Providers/Z.AI: move the bundled GLM catalog and auth env metadata into the plugin manifest, so <code>models list --all --provider zai</code> shows the full known catalog without duplicated runtime seed data. Thanks @shakkernerd.</li>
<li>Providers/Qianfan and Providers/Stepfun: declare setup auth metadata (<code>api-key</code> method, <code>QIANFAN_API_KEY</code>, <code>STEPFUN_API_KEY</code>) in the plugin manifest so onboarding and <code>models setup</code> surface the expected env var without falling back to legacy <code>providerAuthEnvVars</code> runtime seed data. Thanks @shakkernerd.</li>
<li>fix(infra): block ambient Homebrew env vars from brew resolution. (#74463) Thanks @pgondhi987.</li>
<li>Onboarding/configure: avoid staging every default plugin runtime dependency after config writes, so skipped setup flows only prepare config-selected plugin deps instead of pulling broad feature-plugin packages. Thanks @vincentkoc.</li>
<li>Thinking/providers: resolve bundled provider thinking profiles through lightweight provider policy artifacts when startup-lazy providers are not active, so OpenAI Codex GPT-5.x keeps xhigh available in Gateway session validation. Fixes #74796. Thanks @maxschachere.</li>
<li>Security/Windows: ignore workspace <code>.env</code> system-path variables and resolve stale-process <code>taskkill.exe</code> from the validated Windows install root, preventing repository-local env files from redirecting cleanup helpers. Thanks @pgondhi987.</li>
<li>CLI/plugins: refresh persisted plugin registry policy in place for <code>plugins enable</code> and <code>plugins disable</code>, so routine toggles no longer rebuild and hash every plugin source when the target is already indexed. Thanks @vincentkoc.</li>
<li>Windows/install: run npm from a writable installer temp directory and pin the Bedrock runtime dependency below a Windows ARM Node 24 npm resolver failure, so global OpenClaw installs no longer fail before onboarding. Thanks @mariozechner.</li>
<li>CLI/plugins: scope install and enable slot selection to the selected plugin manifest/runtime fallback, so plugin installs no longer load every plugin runtime or broad status snapshot just to update memory/context slots. Thanks @vincentkoc.</li>
<li>Plugins/TTS: keep bundled speech-provider discovery available on cold package Gateway paths and add bundled plugin matrix runtime probes for health, readiness, RPC, TTS discovery, and post-ready runtime-deps watchdog coverage. Refs #75283. Thanks @vincentkoc.</li>
<li>Google Meet/Twilio: show delegated voice call ID, DTMF, and intro-greeting state in <code>googlemeet doctor</code>, and avoid claiming DTMF was sent when no Meet PIN sequence was configured. Refs #72478. Thanks @DougButdorf.</li>
<li>Plugins/tools: prefer built bundled plugin code during tool discovery and skip channel runtime hydration while preserving companion provider registrations, reducing per-run plugin-tool prep cost without dropping executable plugin tools. Fixes #75290. Thanks @thanos-openclaw.</li>
<li>Plugins/loader: scope plugin-tool registry reuse to the enabled plugin plan and stored Gateway method keys, so embedded runner tool lookup can reuse compatible startup registries without hiding enabled non-startup plugin tools. Fixes #75520. Thanks @whtoo.</li>
<li>Voice Call/Twilio: send notify-mode initial TwiML directly in the outbound create-call request while keeping conversation and pre-connect DTMF calls webhook-driven, so one-shot notify calls do not depend on a first-answer webhook fetch. Supersedes #72758. Thanks @tyshepps.</li>
<li>Discord/Slack: defer status-reaction cleanup until run finalization so queued, thinking, tool, and terminal reactions no longer flicker during normal progress updates. (#75582)</li>
<li>Discord/voice: leave voice off for text-only configs unless explicitly configured, rerun configured voice auto-join after gateway RESUMED events, ignore already-destroyed stale voice connections during reconnect cleanup, lengthen the default voice join Ready wait with configurable timeouts, merge configured media-understanding providers such as Deepgram into partial active registries, apply per-channel <code>systemPrompt</code> overrides to voice transcript turns, and run voice-channel turns under a voice-output policy that hides the agent <code>tts</code> tool. Fixes #73753, #40665, #63098, #65687, #47095, and #61536; refs #74044, #39825, and #65039. Thanks @sanchezm86, @SecureCloudProjO, @liz709, @darealgege, @kzicherman, @ayochim, @OneMintJulep, @qearlyao, and @aounakram.</li>
<li>Plugins/CLI: reuse the cold manifest registry while building plugin status and inspect reports, so large configured plugin sets no longer rediscover the bundled/plugin registry once per inspect row. Thanks @vincentkoc.</li>
<li>Gateway/health: refresh cached health RPC snapshots when channel runtime state diverges, so Discord and other channel status reads no longer report stale running or connected values until the cache TTL expires. (#75423)</li>
<li>Gateway/sessions: keep session-store reads from running stale prune and entry-count cap maintenance during startup, so oversized stores no longer block chat history readiness after updates while writes and <code>sessions cleanup --enforce</code> still preserve the cleanup safeguards. Fixes #70050. Thanks @tangda18.</li>
<li>Security/audit: keep plain <code>security audit</code> on the cold config/filesystem path and reserve plugin runtime security collectors for <code>--deep</code>, so large plugin installs cannot execute every plugin runtime during routine audits. Thanks @vincentkoc.</li>
<li>WhatsApp: stage <code>qrcode</code> through root mirrored runtime dependencies so packaged QR pairing can render from staged plugin-runtime-deps installs. Fixes #75394. Thanks @FelipeX2001.</li>
<li>Interactive channel payloads: send Discord component-only interaction replies, Slack block-only slash replies, Telegram button/select fallback labels, and LINE quick-reply fallback option text instead of accepting empty renderable payloads. Thanks @vincentkoc.</li>
<li>Auto-reply/docking: require <code>/dock-*</code> route switches to start from direct chats, so group or channel participants cannot reroute a shared session's future replies into a linked DM. Thanks @vincentkoc.</li>
<li>Discord: keep text-DM main-session route updates pinned to the configured DM owner, matching component interactions so another direct-message sender cannot redirect future main-session replies. Thanks @vincentkoc.</li>
<li>Mattermost/Matrix: keep direct-message main-session route updates pinned to the configured DM owner so paired or temporarily allowed senders cannot redirect future shared-session replies. Thanks @vincentkoc.</li>
<li>Discord: keep SecretRef-backed bot tokens discoverable for message actions without resolving the token during schema generation, and resolve scoped channel SecretRefs before outbound agent message sends even when the tool is built from a config snapshot. Fixes #75324. Thanks @slideshow-dingo and @Conan-Scott.</li>
<li>Updates: run package post-install doctor repair with the managed Gateway service profile and state paths when a daemon is installed, so shell/profile mismatches no longer repair the caller state while the restarted Gateway keeps stale config. Thanks @vincentkoc.</li>
<li>Models/DeepInfra: declare DeepInfra manifest catalog discovery and derive its runtime fallback catalog from the manifest, restoring provider-filtered <code>models list --all --provider deepinfra</code> rows without duplicated static model data. Thanks @shakkernerd.</li>
<li>CLI/update: verify managed gateway restarts against the installed service port instead of the caller shell port, so package updates do not report a healthy daemon as failed when profiles use different gateway ports. Thanks @vincentkoc.</li>
<li>Gateway/agent: reject strict <code>openclaw agent --deliver</code> requests with missing delivery targets before starting the agent run, so users do not wait for a completed turn that cannot send anywhere. Thanks @vincentkoc.</li>
<li>Setup/import: honor non-interactive <code>--import-from</code> onboarding flags by running the migration import path instead of silently completing normal setup without importing anything. Thanks @vincentkoc.</li>
<li>Doctor/plugins: keep plain <code>doctor --non-interactive</code> from installing bundled plugin runtime dependencies, so headless health checks report missing deps while <code>doctor --fix</code> remains the explicit repair path. Thanks @vincentkoc.</li>
<li>Doctor/gateway: require an interactive confirmation before installing or rewriting the Gateway service, so <code>doctor --fix --non-interactive</code> can repair plugin/config drift without replacing the operator's launchd/systemd service from a temporary environment. Thanks @vincentkoc.</li>
<li>Plugins/runtime-deps: include packaged OpenClaw identity in bundled plugin loader cache keys, so same-path package upgrades stop reusing stale versioned runtime-deps mirrors. Fixes #75045. Thanks @sahilsatralkar.</li>
<li>Plugin SDK: restore reply-prefix and reply-pipeline helpers on the deprecated root/compat SDK surface so external plugins still using <code>openclaw/plugin-sdk</code> do not fail message dispatch after update. Fixes #75171. Thanks @zhangxiliang.</li>
<li>Plugins/runtime-deps: prune inactive same-package versioned runtime-deps roots after bundled dependency repair, so upgrades do not leave old <code>openclaw-<version>-<hash></code> package caches behind after doctor runs. Thanks @vincentkoc.</li>
<li>Plugins/runtime-deps: prune legacy version-scoped plugin runtime-deps roots during bundled dependency repair and cover the path in Package Acceptance's upgrade-survivor matrix, so upgrades from 2026.4.x no longer leave stale per-plugin runtime trees after doctor runs. Thanks @vincentkoc.</li>
<li>Plugins/runtime-deps: keep Gateway startup plugin imports and runtime plugin fallback loads verify-only after startup/config repair planning, so packaged installs no longer spawn package-manager repair from hot paths after readiness. Refs #75283 and #75069. Thanks @brokemac79 and @xiaohuaxi.</li>
<li>Plugins/runtime-deps: treat package.json runtime-deps manifests as supersets when generated materialization metadata is absent, so bundled plugin activation stops restaging already-installed dependency subsets on every activation. Fixes #75429. (#75431) Thanks @loyur.</li>
<li>iMessage: add stdin write callback and error listener to IMessageRpcClient so async EPIPE from a closed child process rejects the pending request instead of crashing the gateway with uncaughtException. Fixes #75438.</li>
<li>MCP/stdio: settle MCP stdio transport send() from the write callback instead of resolving immediately on buffer acceptance, so async write errors reject the promise instead of being lost. Refs #75438.</li>
<li>Process/exec: add stdin error listener in runCommandWithTimeout so EPIPE from a prematurely-exited child is swallowed instead of escaping to uncaughtException. Refs #75438.</li>
<li>Voice Call/realtime: add default-off fast memory/session context for <code>openclaw_agent_consult</code>, giving live calls a bounded answer-or-miss path before the full agent consult. Fixes #71849. Thanks @amzzzzzzz.</li>
<li>Google Meet: interrupt Realtime provider output when local barge-in clears playback, so command-pair audio stops model speech instead of only restarting Chrome playback. Fixes #73850. (#73834) Thanks @shhtheonlyperson.</li>
<li>Gateway/config: cap oversized plugin-owned schemas in the full <code>config.schema</code> response so large installed plugin sets cannot balloon Gateway RSS or crash schema clients. Thanks @vincentkoc.</li>
<li>Plugins/update: skip ClawHub and marketplace plugin updates when the bundled version is newer than the recorded installed version, so <code>openclaw update</code> no longer overwrites working bundled plugins with older external packages. Fixes #75447. Thanks @amknight.</li>
<li>Gateway/sessions: use bounded tail reads for sessions-list transcript usage fallbacks and cap bulk title/last-message hydration, keeping large session stores responsive when rows request derived previews. Thanks @vincentkoc.</li>
<li>Gateway/sessions: yield during bulk transcript title/preview hydration and copy compaction checkpoints asynchronously, keeping the Gateway event loop responsive for large session stores and large transcripts. Refs #75330 and #75414. Thanks @amknight.</li>
<li>Gateway/sessions: stream bounded transcript reads for session detail, history, artifacts, compaction, and send/subscribe sequence paths so small Gateway requests no longer materialize large transcripts or OOM on oversized session logs. Thanks @vincentkoc.</li>
<li>Gateway/chat: bound chat-history transcript reads to the requested display window so large session logs no longer OOM the Gateway when clients ask for a small history page. Thanks @vincentkoc.</li>
<li>BlueBubbles: detect audio attachments by Apple UTIs (<code>public.audio</code>, <code>public.mpeg-4-audio</code>, <code>com.apple.m4a-audio</code>, <code>com.apple.coreaudio-format</code>) in addition to <code>audio/*</code> MIME, so iMessage voice notes whose webhook payload only carries the UTI are now classified as audio in the inbound <code><media:audio></code> placeholder instead of falling through to the generic <code><media:attachment></code> tag. Thanks @omarshahine.</li>
<li>Voice Call/Twilio: honor stored pre-connect TwiML before realtime webhook shortcuts and reject DTMF sequences outside conversation mode, so Meet PIN entry cannot be skipped or silently dropped. Thanks @donkeykong91 and @PfanP.</li>
<li>Docs/sandboxing: clarify that sandbox setup scripts (<code>sandbox-setup.sh</code>, <code>sandbox-common-setup.sh</code>, <code>sandbox-browser-setup.sh</code>) are only available from a source checkout, and add inline <code>docker build</code> commands for npm-installed users so sandbox image setup works without cloning the repo. Fixes #75485. Thanks @amknight.</li>
<li>Google Meet/Voice Call: play Twilio Meet DTMF before opening the realtime media stream and carry the intro as the initial Voice Call message, so the greeting is generated after Meet admits the phone participant instead of racing a live-call TwiML update. Thanks @donkeykong91 and @PfanP.</li>
<li>Google Meet/Voice Call: make Twilio setup preflight honor explicit <code>--transport twilio</code> and fail local/private Voice Call webhook URLs, including IPv6 loopback and unique-local forms, before joins. Thanks @donkeykong91 and @PfanP.</li>
<li>Voice Call/Twilio: retry transient 21220 live-call TwiML updates and catch answered-path initial-greeting failures, so a fast answered callback no longer crashes the Gateway or drops the Twilio greeting/listen transition. (#74606) Thanks @Sivan22.</li>
<li>CLI/startup: preserve <code>OPENCLAW_HIDE_BANNER</code> banner suppression for route-first startup callers that rely on the default process environment while keeping read-only status/channel paths from repairing bundled plugin runtime dependencies. Refs #75183.</li>
<li>Voice Call/Twilio: register accepted media streams immediately but wait for realtime transcription readiness before speaking the initial greeting, so reconnect grace handling stays live while OpenAI STT startup is no longer starved by TTS. Fixes #75197. (#75257) Thanks @donkeykong91 and @PfanP.</li>
<li>Voice Call CLI: run gateway-delegated <code>voicecall continue</code> through operation-id polling and protocol-shaped errors, so long conversational turns keep their transcript result without blocking a single Gateway RPC. (#75459) Thanks @serrurco and @DougButdorf.</li>
<li>Voice Call CLI: delegate operational <code>voicecall</code> commands to the running Gateway runtime and skip webhook startup during CLI-only plugin loading, preventing webhook port conflicts and <code>setup --json</code> hangs. Fixes #72345. Thanks @serrurco and @DougButdorf.</li>
<li>Agents/pi-embedded-runner: extract the <code>abortable</code> provider-call wrapper from <code>runEmbeddedAttempt</code> to module scope so its promise handlers no longer close over the run lexical context, releasing transcripts, tool buffers, and subscription callbacks when a provider call hangs past abort. (#74182) Thanks @cjboy007.</li>
<li>Docker: restore <code>python3</code> in the gateway runtime image after the slim-runtime switch. Fixes #75041.</li>
<li>Agents/session-repair: fix resumed sessions failing with repeated 400 errors on Anthropic and strict OpenAI-compatible providers (Qwen, mlx-vlm) after an interrupted conversation or blank user input. Fixes #75271 and #75313. Thanks @amknight.</li>
<li>CLI/Voice Call: scope <code>voicecall</code> command activation to the Voice Call plugin so setup and smoke checks no longer broad-load unrelated plugin runtimes or hang after printing JSON. Thanks @vincentkoc.</li>
<li>Doctor/plugins: warn when restrictive <code>plugins.allow</code> is paired with wildcard or plugin-owned tool allowlists, making the exclusive plugin allowlist behavior visible before users hit empty callable-tool runs. Refs #58009 and #64982. Thanks @KR-Python and @BKF-Gitty.</li>
<li>Google Meet/Voice Call: keep Twilio Meet joins in conversation mode and reuse the realtime intro prompt when no voice-call-specific intro is configured, so answered phone bridge calls speak instead of joining silently. Refs #72478. Thanks @DougButdorf.</li>
<li>Auto-reply/group chats: keep the <code>message</code> tool available for message-tool-only visible replies and apply group-scoped tool policy before deciding fallback delivery, so Discord/Slack-style rooms reply visibly in the correct channel after upgrades. Fixes #74842; refs #75207. Thanks @davelutztx and @aa-on-ai.</li>
<li>Agents/commitments: keep inferred follow-ups internal when heartbeat target is none, strip raw source text from stored commitments, disable tools during due-commitment heartbeat turns, bound hidden extraction queue growth, expire stale commitments, and add QA/Docker safety coverage. Thanks @vignesh07.</li>
<li>Telegram/agents: keep typing indicators and optional generation tools off the reply critical path, so fresh Telegram replies no longer stall while provider catalogs and media models load. (#75360) Thanks @obviyus.</li>
<li>Agents/commitments: run hidden follow-up extraction on the configured agent/default model instead of falling back to direct OpenAI, so OpenAI Codex OAuth-only gateways no longer spam background API-key failures. Fixes #75334. Thanks @sene1337.</li>
<li>Agents/media: keep async music generation completions on the requester-session wake path even when direct-send completion is enabled, so finished audio stays agent-mediated while video can still opt into direct channel delivery. (#75335) Thanks @vincentkoc.</li>
<li>Security/config-audit: redact CLI argv and execArgv secrets before persisting config audit records, covering write, observe, and recovery paths. Fixes #60826. Thanks @koshaji.</li>
<li>Gateway/models: keep default and configured model-list views responsive when provider catalog discovery stalls, without hiding real catalog load failures, while <code>--all</code> still waits for the exact full catalog. Fixes #75297; refs #74404. Thanks @lisandromachado and @najef1979-code.</li>
<li>Plugins/runtime-deps: accept already materialized package-level runtime-deps supersets as converged, so later lazy plugin activation no longer prunes and relaunches <code>pnpm install</code> after gateway startup pre-staging, reducing event-loop pressure from repeated runtime-deps repair on packaged installs. Fixes #75283; refs #75297 and #72338. Thanks @brokemac79, @lisandromachado, and @midhunmonachan.</li>
<li>Plugins/runtime-deps: remove OpenClaw-owned legacy runtime-deps symlinks before replacing staged bundled plugin dependencies, so updates can recover from older symlinked installs instead of failing the symlink safety guard. Thanks @goldmar.</li>
<li>Discord: retry queued REST 429s against learned bucket/global cooldowns and reacquire fresh voice upload URLs after CDN upload rate limits, so outbound sends recover without reusing stale single-use upload URLs. Thanks @discord.</li>
<li>TTS/providers: keep bundled speech-provider compat fallback available when plugins are globally disabled, so cold gateway and CLI startup can still resolve fallback speech providers instead of leaving explicit TTS provider selection with no registered providers. Refs #75265. Thanks @sliekens.</li>
<li>Discord: collapse repeated native slash-command deploy rate-limit startup logs into one non-fatal warning while keeping per-request REST timing in verbose output. Thanks @discord.</li>
<li>Discord: report native slash-command deploy aborts as REST timeouts with method, path, timeout budget, and observed duration, so startup logs explain slow Discord API calls instead of showing a generic aborted operation. Thanks @discord.</li>
<li>Security/logging: redact payment credential field names such as card number, CVC/CVV, shared payment token, and payment credential across default log and tool-payload redaction patterns so wallet-style MCP tools do not expose raw payment credentials in UI events or transcripts. Thanks @stainlu.</li>
<li>Providers/OpenAI Codex: preserve existing wrapped Codex streams during OpenAI attribution so PI OAuth bearer injection reaches ChatGPT/Codex Responses, and strip native Codex-only unsupported payload fields without touching custom compatible endpoints. (#75111) Thanks @keshavbotagent.</li>
<li>Plugins/runtime-deps: materialize newly required bundled plugin packages after local <code>openclaw onboard</code> and <code>openclaw configure</code> config writes, while keeping remote setup read-only, so first Gateway startup no longer discovers missing channel/provider deps after setup claimed success. Fixes #75309; refs #75069. Thanks @scottgl9 and @xiaohuaxi.</li>
<li>Plugins/runtime-deps: expire stale legacy install locks whose live PID cannot be tied to the current process incarnation, so Docker PID reuse no longer leaves bundled dependency repair stuck behind old <code>.openclaw-runtime-deps.lock</code> directories. Fixes #74948; refs #74950 and #74346. Thanks @dchekmarev.</li>
<li>Plugins/runtime-deps: recover interrupted bundled runtime-dependency installs whose package sentinels exist but generated materialization is incomplete, forcing npm/pnpm repair in Gateway startup, doctor, and lazy plugin loads instead of leaving channels crash-looping on missing packages. Fixes #75309; refs #75310, #75296, and #75304. Thanks @scottgl9.</li>
<li>Plugins/runtime-deps: treat no-main and export-map package sentinels without reachable entry files as incomplete, so Gateway startup, doctor, and lazy plugin loads repair interrupted bundled dependency installs instead of accepting package.json-only partial installs. Fixes #75309; refs #75183. Thanks @shakkernerd.</li>
<li>Plugins/runtime-deps: keep runtime inspection and channel maintenance commands from downloading bundled plugin dependencies, route explicit repairs through <code>openclaw plugins deps --repair</code>, and still allow Gateway/DO paths to repair missing deps before import. Refs #75069. Thanks @xiaohuaxi.</li>
<li>Updates: force non-deferred, no-cooldown update restarts after package-manager updates requested through the live Gateway control plane and fail release validation on post-swap stale chunk import crashes, so Telegram/Discord imports do not stay pointed at removed dist files. Fixes #75206. Thanks @xonaman and @faux123.</li>
<li>Agents/tool-result guard: use the resolved runtime context token budget for non-context-engine tool-result overflow checks, so long tool-heavy sessions no longer compact early when <code>contextTokens</code> is larger than native <code>contextWindow</code>. Fixes #74917. Thanks @kAIborg24.</li>
<li>Gateway/systemd: exit with sysexits 78 for supervised lock and <code>EADDRINUSE</code> conflicts so <code>RestartPreventExitStatus=78</code> stops <code>Restart=always</code> restart loops instead of repeatedly reloading plugins against an occupied port. Fixes #75115. Thanks @yhyatt.</li>
<li>Agents/runtime: skip blank visible user prompts at the embedded-runner boundary before provider submission while still allowing internal runtime-only turns and media-only prompts, so Telegram/group sessions no longer leak raw empty-input provider errors when replay history exists. Fixes #74137. Thanks @yelog, @Gracker, and @nhaener.</li>
<li>Agents/Codex: isolate local Codex app-server <code>CODEX_HOME</code> and <code>HOME</code> per agent and add a deliberate Codex migration path with selectable skill copies, so personal Codex CLI skills, plugins, config, and hooks no longer leak into OpenClaw agents unless the operator migrates them into the workspace. Thanks @pashpashpash.</li>
<li>Security/Nextcloud Talk: make webhook signature validation use the padded timing-safe compare path even when the supplied signature length is wrong, keep normalized header lookup behavior, and extend regression coverage for tampered bodies, wrong secrets, array-backed headers, and truncated signatures. Carries forward earlier contributor work from #50516 by teddytennant. (#58097) Thanks @gavyngong.</li>
<li>Plugins/runtime-deps: replace stale symlinked mirror target roots before writing runtime-mirror temp files and skip rewriting already materialized hardlinks, so cross-version container upgrades no longer crash-loop on read-only image-layer paths while warm mirrors do less churn. Fixes #75108; refs #75069. Thanks @coletebou and @xiaohuaxi.</li>
<li>Auto-reply/group chats: fall back to automatic source delivery when a channel precomputes message-tool-only replies but the <code>message</code> tool is unavailable, so Discord/Slack-style group turns do not silently complete without a visible reply. Fixes #74868. Thanks @kagura-agent.</li>
<li>Browser/gateway: share one browser control runtime across the HTTP control server and <code>browser.request</code>, and refresh browser profile config from the source snapshot, so CLI status/start honors configured <code>browser.executablePath</code>, <code>headless</code>, and <code>noSandbox</code> instead of falling back to stale auto-detection. Fixes #75087; repairs #73617. Thanks @civiltox and @martingarramon.</li>
<li>Agents/subagents: bound automatic orphan recovery with persisted recovery attempts and a wedged-session tombstone, and teach task maintenance/doctor to reconcile those sessions so restart loops no longer require manual <code>sessions.json</code> surgery. Fixes #74864. Thanks @solosage1.</li>
<li>Plugins/runtime-deps: keep bundled provider policy config loading from staging plugin runtime dependencies, so config reads no longer fail on locked-down <code>/var/lib/openclaw/plugin-runtime-deps</code> directories. Fixes #74971. Thanks @eurojojo.</li>
<li>Memory/runtime-deps: retain the native <code>node-llama-cpp</code> runtime only when local memory search is configured, so packaged installs can repair local embeddings without relying on unreachable global npm installs. Fixes #74777. Thanks @LLagoon3.</li>
<li>Gateway/startup: skip pre-bind web-fetch provider discovery for credential-free <code>tools.web.fetch</code> config, so Docker/Kubernetes gateways bind even when optional fetch limits are present. Fixes #74896. Thanks @KoykL.</li>
<li>Signal: match group allowlists against inbound Signal group ids as well as sender ids, and process explicitly configured Signal groups without requiring mentions unless <code>requireMention</code> is set. Fixes #53308. Thanks @minupla and @juan-flores077.</li>
<li>Signal: bound <code>signal-cli</code> installer release and archive downloads with explicit timeouts, declared and streamed size checks, and partial-file cleanup. Fixes #54153. Thanks @jinduwang1001-max and @juan-flores077.</li>
<li>Slack: require bot-authored room messages with <code>allowBots=true</code> to come from an explicitly channel-allowlisted bot or from a room where an explicit Slack owner is present, so broad bot relays cannot run unattended. Fixes #59284. Thanks @andrewhong-translucent.</li>
<li>Signal: derive <code>getAttachment</code> HTTP response caps from <code>channels.signal.mediaMaxMb</code> with base64 headroom, so inbound photos and videos no longer drop behind the 1 MiB RPC default. Fixes #73564. Thanks @heyhudson.</li>
<li>Signal: keep the long-lived receive SSE monitor open while idle instead of applying the 10s RPC/check deadline, so <code>signal-cli</code> 0.14.3 event streams no longer reconnect before inbound messages arrive. Fixes #74741. Thanks @fgabelmannjr and @k7n4n5t3w4rt.</li>
<li>CLI/progress: suppress nested progress spinners and line clears while TUI input owns raw stdin, so Crestodian <code>/status</code> no longer disturbs the active input row. (#75003) Thanks @velvet-shark.</li>
<li>Models/OpenAI Codex: restore <code>openai-codex/gpt-5.4-mini</code> for ChatGPT/Codex OAuth PI runs after live OAuth proof, and align the manifest, forward-compat metadata, docs, and regression tests so stale cron and heartbeat configs resolve again. Fixes #74451. Thanks @0xCyda, @hclsys, and @Marvae.</li>
<li>Plugins/runtime-deps: always write a dependency map in generated runtime-deps install manifests, so npm does not crash or prune staged bundled-plugin packages when the plan is empty. Fixes #74949. Thanks @hclsys.</li>
<li>Telegram: use durable message edits for streaming previews instead of native draft state, so generated replies no longer flicker through draft-to-message transitions that look like duplicates. (#75073) Thanks @obviyus.</li>
<li>Telegram: echo preflighted DM voice-note transcripts back to the originating chat, including Telegram DM topic thread metadata, instead of only echoing later media-understanding transcripts. Fixes #75084. Thanks @M-Lietz.</li>
<li>Telegram: clamp low long-polling client timeouts so configured <code>timeoutSeconds</code> values below the <code>getUpdates</code> poll window no longer force a fresh HTTPS connection every few seconds. Fixes #75114. Thanks @hpinho77.</li>
<li>Web search: describe <code>web_search</code> as using the configured provider instead of hard-coding Brave when DuckDuckGo or another provider is active. Fixes #75088. Thanks @sun-rongyang.</li>
<li>Infra/tmp: tolerate concurrent temp-dir permission repairs by rechecking directories that another process already tightened, so parallel ACP subprocess startup no longer throws <code>Unsafe fallback OpenClaw temp dir</code>. Fixes #66867. Thanks @Kane808-AI and @jarvisz8.</li>
<li>Agents/compaction: add an opt-in <code>agents.defaults.compaction.midTurnPrecheck</code> mid-turn precheck that detects tool-loop context pressure and triggers compaction before the next tool call instead of waiting for end-of-turn. (#73499) Thanks @marchpure and @haoxingjun.</li>
<li>Gateway/approvals: let loopback token/password-backed native approval clients resolve exec approvals without attaching stale paired Gateway identities, while remote and unauthenticated approval clients keep normal device identity behavior. (#74472)</li>
<li>Gateway/config: include rejected validation paths in foreground and service last-known-good recovery logs plus main-agent notices, so unsupported direct edits explain which key caused restore instead of looking like silent reversion. Fixes #75060. Thanks @amknight.</li>
<li>Plugins/runtime-deps: hash the OS-canonical <code>packageRoot</code> via <code>fs.realpathSync.native</code> (with <code>path.resolve</code> fallback) when computing the bundled runtime-deps stage key, so loader and channel <code>bundled-root</code> callers no longer derive divergent stage directories under <code>~/.openclaw/plugin-runtime-deps/openclaw-<version>-<hash>/</code> and bundled channels stop failing with <code>ENOENT</code> on shared dist chunks under Windows npm symlinks, junctions, or PM2 multi-instance worker layouts. Fixes #74963. (#75048) Thanks @openperf and @vincentkoc.</li>
<li>fix(logging): add redaction patterns for Tencent Cloud, Alibaba Cloud, HuggingFace and Replicate API keys (#58162). Thanks @gavyngong</li>
<li>Pairing: surface unexpected allowlist filesystem stat errors instead of treating the allowlist as missing, so permission and I/O failures are visible during pairing authorization checks. (#63324) Thanks @franciscomaestre.</li>
<li>macOS app: reserve layout space for exec approval command details so the allow dialog no longer overlaps the command, context, and action buttons. (#75470) Thanks @ngutman.</li>
<li>Agents/failover: carry <code>sessionId</code>, <code>lane</code>, <code>provider</code>, <code>model</code>, and <code>profileId</code> attribution through <code>FailoverError</code> and <code>describeFailoverError</code>/<code>coerceToFailoverError</code> so structured error logs (e.g. <code>gateway.err.log</code> ingestion) can attribute exhausted-fallback wrapper errors to the originating session and last-attempted provider instead of dropping the metadata after the per-profile errors. Fixes #42713. (#73506) Thanks @wenxu007.</li>
<li>Context Engine: treat assembled prompt as the default authority for preemptive overflow prechecks so engines that return a windowed, self-contained context no longer trigger false hard-fail compactions on huge raw history. Engines whose assembled view can hide overflow risk can opt back into the legacy behavior with <code>AssembleResult.promptAuthority: "preassembly_may_overflow"</code>. (#74255) Thanks @100yenadmin.</li>
<li>Mattermost: refresh current native slash command registrations before accepting callbacks so stale tokens from deleted or regenerated commands stop being accepted without a gateway restart while failed validations stay briefly cached and lookup starts are rate-limited per command, gate each callback against the resolved command's own startup token so a token leaked for one slash command cannot poison another command's failure cache, redact slash validation lookup errors, and add a body read timeout to the multi-account routing path so slow callback senders cannot tie up the dispatcher. Thanks @feynman-hou and @eleqtrizit.</li>
<li>Security/dotenv: block <code>COMSPEC</code> in workspace <code>.env</code> so a malicious repo cannot redirect Windows <code>cmd.exe</code> resolution, and lock in case-insensitive workspace-<code>.env</code> regression coverage for the full Windows shell trust-root family (<code>COMSPEC</code>, <code>PROGRAMFILES</code>, <code>PROGRAMW6432</code>, <code>SYSTEMROOT</code>, <code>WINDIR</code>). (#74460) Thanks @mmaps.</li>
<li>Gateway/install: drop stale version-manager and package-manager PATH entries preserved from old service files during <code>gateway install --force</code> and doctor repair, so the repair path no longer recreates <code>gateway-path-nonminimal</code> warnings. Fixes #75220. (#75440) Thanks @leonaIee, @renaudcerrato, and @aaajiao.</li>
</ul>
<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
]]></description>
            <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.5.2/OpenClaw-2026.5.2.zip" length="51078259" type="application/octet-stream" sparkle:edSignature="NwoecacHxJOYpltNmB/y7LV5I8ZIh5pENWSydbOM1vsfgSrcb7pRP+Zm2nih1IAq7hh1tOmQ0XWnsohic7U4DA=="/>
        </item>
        <item>
            <title>2026.4.29</title>
            <pubDate>Thu, 30 Apr 2026 21:47:22 +0000</pubDate>
            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
            <sparkle:version>2026042990</sparkle:version>
            <sparkle:shortVersionString>2026.4.29</sparkle:shortVersionString>
            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
            <description><![CDATA[<h2>OpenClaw 2026.4.29</h2>
<h3>Highlights</h3>
<ul>
<li>Messaging and automation get active-run steering by default, visible-reply enforcement, spawned subagent routing metadata, and opt-in follow-up commitments for heartbeat-delivered reminders. Thanks @vincentkoc, @scoootscooob, @samzong, and @vignesh07.</li>
<li>Memory grows into a people-aware wiki with provenance views, per-conversation Active Memory filters, partial recall on timeout, and bounded REM preview diagnostics. Thanks @vincentkoc, @quengh, @joeykrug, and @samzong.</li>
<li>Provider/model coverage expands with NVIDIA onboarding/catalogs plus faster manifest-backed model/auth paths, Bedrock Opus 4.7 thinking parity, and safer Codex/OpenAI-compatible replay and streaming behavior. Thanks @eleqtrizit, @shakkernerd, @prasad-yashdeep, @woodhouse-bot, and @LyHug.</li>
<li>Gateway and packaged-plugin reliability focuses on slow-host startup, reusable model catalogs, event-loop readiness diagnostics, runtime-dependency repair, stale-session recovery, and version-scoped update caches. Thanks @lpendeavors, @DerFlash, @vincentkoc, @pashpashpash, and @jhsmith409.</li>
<li>Channel fixes cluster around Slack Block Kit limits, Telegram proxy/webhook/polling/send resilience, Discord startup/rate-limit handling, WhatsApp delivery/liveness, and Microsoft Teams/Matrix/Feishu edge cases. Thanks @slackapi, @SymbolStar, @djgeorg3, @TinyTb, @dseravalli, @nklock, and @alex-xuweilong.</li>
<li>Security and operations add OpenGrep scanning, sharper GHSA triage policy, safer exec/pairing/owner-scope handling, Docker/onboarding automation, and web-fetch IPv6 ULA opt-in for trusted proxy stacks. Thanks @jesse-merhi, @pgondhi987, @mmaps, @jinjimz, and @jeffrey701.</li>
</ul>
<h3>Changes</h3>
<ul>
<li>Security/tools: configured tool sections (<code>tools.exec</code>, <code>tools.fs</code>) no longer implicitly widen restrictive profiles (<code>messaging</code>, <code>minimal</code>). Users who need those tools under a restricted profile must add explicit <code>alsoAllow</code> entries; a startup warning identifies affected configs. Fixes #47487. Thanks @amknight.</li>
<li>Agents/commitments: add opt-in inferred follow-up commitments with hidden batched extraction, per-agent/per-channel scoping, heartbeat delivery, CLI management, a simple <code>commitments.enabled</code>/<code>commitments.maxPerDay</code> config, and heartbeat-interval due-time clamping so magical check-ins do not echo immediately. (#74189) Thanks @vignesh07.</li>
<li>Messages/queue: make <code>steer</code> drain all pending Pi steering messages at the next model boundary, keep legacy one-at-a-time steering as <code>queue</code>, and add a dedicated steering queue docs page. Thanks @vincentkoc.</li>
<li>Messages/queue: default active-run queueing to <code>steer</code> with a 500ms followup fallback debounce, and document the queue modes, precedence, and drop policies on the command queue page. Thanks @vincentkoc.</li>
<li>Messages: add global <code>messages.visibleReplies</code> so operators can require visible output to go through <code>message(action=send)</code> for any source chat, while <code>messages.groupChat.visibleReplies</code> stays available as the group/channel override. Thanks @scoootscooob.</li>
<li>Gateway/events: surface <code>spawnedBy</code> on subagent chat and agent broadcast payloads so clients can route child session events without an extra session lookup. (#63244) Thanks @samzong.</li>
<li>Memory/wiki: add agent-facing people wiki metadata, canonical aliases, person cards, relationship graphs, privacy/provenance reports, evidence-kind drilldown, and search modes for person lookup, question routing, source evidence, and raw claims. Thanks @vincentkoc.</li>
<li>Active Memory: add optional per-conversation <code>allowedChatIds</code> and <code>deniedChatIds</code> filters so operators can enable recall only for selected direct, group, or channel conversations while keeping broad sessions skipped. (#67977) Thanks @quengh.</li>
<li>Active Memory: return bounded partial recall summaries when the hidden memory sub-agent times out, including the default temporary-transcript path, so useful recovered context is not discarded. (#73219) Thanks @joeykrug.</li>
<li>Gateway/memory: add a read-only <code>doctor.memory.remHarness</code> RPC so operator clients can preview bounded REM dreaming output without running mutation paths. (#66673) Thanks @samzong.</li>
<li>Providers/NVIDIA: add the NVIDIA provider with API-key onboarding, setup docs, static catalog metadata, and literal model-ref picker support so NVIDIA hosted models can be selected with their provider prefix intact. (#71204) Thanks @eleqtrizit.</li>
<li>Models: suppress explicitly configured openai-codex/gpt-5.4-mini inline entries so a stale models config written by <code>openclaw doctor --fix</code> cannot bypass the manifest capability block and cause repeated assistant-turn failures when the runtime switches to that model on ChatGPT-backed Codex accounts. Conditional suppressions (e.g. qwen Coding Plan endpoint guards) remain bypassable by explicit user configuration. (#74451) Thanks @0xCyda, @hclsys, and @Marvae.</li>
<li>Added SQLite-backed plugin state store (<code>api.runtime.state.openKeyedStore</code>) for restart-safe keyed registries with TTL, eviction, and automatic plugin isolation. Thanks @amknight.</li>
<li>Plugin SDK: mark remaining legacy alias exports and diffs tool/config aliases with deprecation metadata, and add a guard so future legacy alias comments require <code>@deprecated</code> tags. Thanks @vincentkoc.</li>
<li>CLI/QR/dependencies: internalize small terminal progress and QR wrapper helpers while keeping the real QR encoder dependency direct, reducing the default runtime dependency graph without changing QR output behavior. Thanks @vincentkoc.</li>
<li>Dependencies: refresh workspace runtime, plugin, and tooling packages, including ACP, Pi, AWS SDK, TypeBox, pnpm, oxlint, oxfmt, jsdom, pdfjs, ciao, and tokenjuice, while keeping patched ACP behavior and lint gates current. Thanks @mariozechner.</li>
<li>Gateway/dev: run <code>pnpm gateway:watch</code> through a named tmux session by default, with <code>gateway:watch:raw</code> and <code>OPENCLAW_GATEWAY_WATCH_TMUX=0</code> for foreground mode, so repeated starts respawn an inspectable watcher without trapping the invoking agent shell. Thanks @vincentkoc.</li>
<li>Gateway/diagnostics: emit an opt-in startup diagnostics timeline that records gateway lifecycle and plugin-load phases behind a config flag, so slow-start diagnosis no longer requires bespoke instrumentation. Thanks @shakkernerd.</li>
<li>Control UI/i18n: extend the locale registry with new Persian (fa), Dutch (nl), Vietnamese (vi), Italian (it), Arabic (ar), and Thai (th) entries and ship <code>fa</code>, <code>nl</code>, <code>vi</code>, and <code>zh-TW</code> docs glossaries, so the docs translation pipeline and the Control UI language picker stay aligned across surfaces. Thanks @vincentkoc.</li>
<li>Channels: add Yuanbao channel docs entrance so the Tencent Yuanbao bot appears in the channel listing and sidebar navigation. (#73443) Thanks @loongfay.</li>
<li>Channels/Yuanbao: update plugin GitHub location to YuanbaoTeam/yuanbao-openclaw-plugin and add "yuanbao" alias to channel catalog. (#74253) Thanks @loongfay.</li>
<li>Docker setup: add <code>OPENCLAW_SKIP_ONBOARDING</code> so automated Docker installs can skip the interactive onboarding step while still applying gateway defaults. (#55518) Thanks @jinjimz.</li>
<li>Security policy: classify media/base64 decode and format-conversion overhead after configured acceptance limits as performance-only for GHSA triage unless a report demonstrates a limit bypass, crash, exhaustion, data exposure, or another boundary bypass. (#74311)</li>
<li>Security/OpenGrep: add a precise OpenGrep rulepack, source-rule compiler, provenance metadata check, and PR/full scan workflows that validate first-party code and rulepack-only changes while uploading SARIF to GitHub Code Scanning. (#69483) Thanks @jesse-merhi.</li>
</ul>
<h3>Fixes</h3>
<ul>
<li>Providers/OpenAI Codex: preserve existing wrapped Codex streams during OpenAI attribution so PI OAuth bearer injection reaches ChatGPT/Codex Responses, and strip native Codex-only unsupported payload fields without touching custom compatible endpoints. (#75111) Thanks @keshavbotagent.</li>
<li>Agents/tool-result guard: use the resolved runtime context token budget for non-context-engine tool-result overflow checks, so long tool-heavy sessions no longer compact early when <code>contextTokens</code> is larger than native <code>contextWindow</code>. Fixes #74917. Thanks @kAIborg24.</li>
<li>Gateway/systemd: exit with sysexits 78 for supervised lock and <code>EADDRINUSE</code> conflicts so <code>RestartPreventExitStatus=78</code> stops <code>Restart=always</code> restart loops instead of repeatedly reloading plugins against an occupied port. Fixes #75115. Thanks @yhyatt.</li>
<li>Agents/runtime: skip blank visible user prompts at the embedded-runner boundary before provider submission while still allowing internal runtime-only turns and media-only prompts, so Telegram/group sessions no longer leak raw empty-input provider errors when replay history exists. Fixes #74137. Thanks @yelog, @Gracker, and @nhaener.</li>
<li>Auto-reply/group chats: fall back to automatic source delivery when a channel precomputes message-tool-only replies but the <code>message</code> tool is unavailable, so Discord/Slack-style group turns do not silently complete without a visible reply. Fixes #74868. Thanks @kagura-agent.</li>
<li>Browser/gateway: share one browser control runtime across the HTTP control server and <code>browser.request</code>, and refresh browser profile config from the source snapshot, so CLI status/start honors configured <code>browser.executablePath</code>, <code>headless</code>, and <code>noSandbox</code> instead of falling back to stale auto-detection. Fixes #75087; repairs #73617. Thanks @civiltox and @martingarramon.</li>
<li>Agents/subagents: bound automatic orphan recovery with persisted recovery attempts and a wedged-session tombstone, and teach task maintenance/doctor to reconcile those sessions so restart loops no longer require manual <code>sessions.json</code> surgery. Fixes #74864. Thanks @solosage1.</li>
<li>Gateway/startup: skip pre-bind web-fetch provider discovery for credential-free <code>tools.web.fetch</code> config, so Docker/Kubernetes gateways bind even when optional fetch limits are present. Fixes #74896. Thanks @KoykL.</li>
<li>Infra/tmp: tolerate concurrent temp-dir permission repairs by rechecking directories that another process already tightened, so parallel ACP subprocess startup no longer throws <code>Unsafe fallback OpenClaw temp dir</code>. Fixes #66867. Thanks @Kane808-AI and @jarvisz8.</li>
<li>Signal: match group allowlists against inbound Signal group ids as well as sender ids, and process explicitly configured Signal groups without requiring mentions unless <code>requireMention</code> is set. Fixes #53308. Thanks @minupla and @juan-flores077.</li>
<li>Slack: require bot-authored room messages with <code>allowBots=true</code> to come from an explicitly channel-allowlisted bot or from a room where an explicit Slack owner is present, so broad bot relays cannot run unattended. Fixes #59284. Thanks @andrewhong-translucent.</li>
<li>Signal: bound <code>signal-cli</code> installer release and archive downloads with explicit timeouts, declared and streamed size checks, and partial-file cleanup. Fixes #54153. Thanks @jinduwang1001-max and @juan-flores077.</li>
<li>Signal: derive <code>getAttachment</code> HTTP response caps from <code>channels.signal.mediaMaxMb</code> with base64 headroom, so inbound photos and videos no longer drop behind the 1 MiB RPC default. Fixes #73564. Thanks @heyhudson.</li>
<li>Signal: keep the long-lived receive SSE monitor open while idle instead of applying the 10s RPC/check deadline, so <code>signal-cli</code> 0.14.3 event streams no longer reconnect before inbound messages arrive. Fixes #74741. Thanks @fgabelmannjr and @k7n4n5t3w4rt.</li>
<li>Models/OpenAI Codex: restore <code>openai-codex/gpt-5.4-mini</code> for ChatGPT/Codex OAuth PI runs after live OAuth proof, and align the manifest, forward-compat metadata, docs, and regression tests so stale cron and heartbeat configs resolve again. Fixes #74451. Thanks @0xCyda, @hclsys, and @Marvae.</li>
<li>Memory/runtime-deps: retain the native <code>node-llama-cpp</code> runtime only when local memory search is configured, so packaged installs can repair local embeddings without relying on unreachable global npm installs. Fixes #74777. Thanks @LLagoon3.</li>
<li>Plugins/runtime-deps: replace stale symlinked mirror target roots before writing runtime-mirror temp files and skip rewriting already materialized hardlinks, so cross-version container upgrades no longer crash-loop on read-only image-layer paths while warm mirrors do less churn. Fixes #75108; refs #75069. Thanks @coletebou and @xiaohuaxi.</li>
<li>Plugins/runtime-deps: keep bundled provider policy config loading from staging plugin runtime dependencies, so config reads no longer fail on locked-down <code>/var/lib/openclaw/plugin-runtime-deps</code> directories. Fixes #74971. Thanks @eurojojo.</li>
<li>Plugins/runtime-deps: always write a dependency map in generated runtime-deps install manifests, so npm does not crash or prune staged bundled-plugin packages when the plan is empty. Fixes #74949. Thanks @hclsys.</li>
<li>Security/outbound: strip re-formed HTML tags during plain-text sanitization so nested tag fragments cannot leave a CodeQL-detected <code><script></code> sequence behind. Thanks @vincentkoc.</li>
<li>Security/secrets: compare credential bytes with padded timing-safe buffers instead of hashing candidate passwords before equality checks. Thanks @vincentkoc.</li>
<li>Security/QQBot: sanitize debug log arguments before writing to <code>console.*</code>, so gateway payload fields cannot forge extra log lines when debug logging is enabled. Thanks @vincentkoc.</li>
<li>QQBot: unify slash command auth and c2cOnly gating in the command registry, pass <code>allowQQBotDataDownloads</code> when sending slash command file attachments, align clear-storage with actual downloads directory, and add <code>/bot-me</code> to display sender user ID. (#73616) Thanks @cxyhhhhh.</li>
<li>CLI/agents/status: keep <code>openclaw agents</code>, text <code>agents list</code>, and plain text <code>status</code> on read-only metadata paths so human output no longer preloads plugin runtimes or live channel scans before printing. Fixes #74195. Thanks @NianJiuZst.</li>
<li>Agents/local models: derive context-window guard thresholds from the effective model window with 4k/8k safety floors, so small local models are no longer rejected by fixed 16k/32k preflight cutoffs. Fixes #42999. Thanks @chengjialu8888.</li>
<li>PDF extraction: resolve PDF.js standard fonts from the installed package root and pass a filesystem path to the Node fallback extractor, so built-in font PDFs render without <code>file://</code> URL lookup failures. Fixes #51455; carries forward #70936, #54447, and #62175. Thanks @anyech, @JuanRdBO, and @solomonneas.</li>
<li>Media: treat legacy Word/OLE attachments with <code>application/msword</code> or <code>application/x-cfb</code> MIME as binary so printable-looking <code>.doc</code> files are not embedded into prompts as text. Fixes #54176; carries forward #54380. Thanks @andyliu.</li>
<li>Config: accept documented <code>browser.tabCleanup</code> keys in strict root config validation, so configured tab cleanup no longer fails before runtime reads it. Fixes #74577. Thanks @lonexreb and @ezdlp.</li>
<li>Cron: validate disabled job schedule edits before persisting updates, so invalid cron changes no longer partially mutate stored jobs. Fixes #74459. Thanks @yfge.</li>
<li>CLI/cron: warn when <code>openclaw cron add --message</code> omits a nonblank <code>--agent</code>, including blank agent values and session-key jobs, so scheduled agent-turn jobs make default-agent fallback explicit while system events stay quiet. Fixes #42196; carries forward #42245. Thanks @ethanclaw.</li>
<li>CLI/progress: suppress nested progress spinners and line clears while TUI input owns raw stdin, so Crestodian <code>/status</code> no longer disturbs the active input row. (#75003) Thanks @velvet-shark.</li>
<li>Channels/status: keep Telegram, Slack, and Google Chat read-only allowlist/default-target accessors on config-only paths, so status and channel summaries do not resolve SecretRef-backed runtime credentials. Thanks @eusine.</li>
<li>Telegram: use durable message edits for streaming previews instead of native draft state, so generated replies no longer flicker through draft-to-message transitions that look like duplicates. (#75073) Thanks @obviyus.</li>
<li>Telegram: clamp low long-polling client timeouts so configured <code>timeoutSeconds</code> values below the <code>getUpdates</code> poll window no longer force a fresh HTTPS connection every few seconds. Fixes #75114. Thanks @hpinho77.</li>
<li>Active Memory: clarify the deprecated <code>modelFallbackPolicy</code> warning and config help so <code>modelFallback</code> is described as a chain-resolution last resort, not runtime failover. (#74602) Thanks @jeffrey701.</li>
<li>Channels/Discord: keep read-only allowlist/default-target accessors from resolving SecretRef-backed bot tokens, so status and channel summaries no longer fail when tokens are only available in gateway runtime. (#74737) Thanks @eusine.</li>
<li>Gateway/sessions: align session abort wait semantics across <code>chat</code>, <code>agent</code>, and <code>sessions</code> server methods so abort RPCs return after the targeted sessions actually halt instead of resolving early while runs are still draining. (#74751) Thanks @BunsDev.</li>
<li>Agents/output: drop copied inbound metadata-only assistant replay turns before provider replay instead of synthesizing a placeholder, so Telegram and other channels cannot receive <code>[assistant copied inbound metadata omitted]</code> as model output. Fixes #74745. Thanks @adamwdear and @Marvae.</li>
<li>Doctor/memory: suppress skipped embedding-readiness warnings for key-optional providers such as Ollama and LM Studio while preserving timeout and not-ready diagnostics. Fixes #74608 and #73882. Thanks @hclsys.</li>
<li>Channels/groups: preserve observe-only turn suppression for prepared dispatch paths and restore deprecated channel turn runtime aliases, so passive observer/group flows stay silent while older plugins keep compiling. Thanks @vincentkoc.</li>
<li>Feishu: skip empty-text messages (e.g. <code>{"text":""}</code>) that carry no media, so no blank user turn is written to the session and downstream LLM providers cannot reject the request with "messages must not be empty". (#74634) Thanks @xdengli and @hclsys.</li>
<li>Feishu/Bitable: clean up newly created placeholder rows whose fields contain only default empty values while preserving meaningful link, attachment, user, number, boolean, and location values during create-app cleanup. (#73920) Carries forward #40602. Thanks @boat2moon.</li>
<li>macOS app: keep attach-only mode and the Debug Settings launchd toggle marker-only, so launching with <code>--attach-only</code>/<code>--no-launchd</code> no longer uninstalls the Gateway LaunchAgent or drops active sessions. (#72174) Thanks @DolencLuka.</li>
<li>macOS Canvas: stop auto-reloading the current A2UI host during push/eval/snapshot flows, so pushed A2UI content remains visible instead of returning to the empty Canvas shell. Fixes #73337. Thanks @Gr4via.</li>
<li>Plugin SDK: restore the deprecated <code>plugin-sdk/zalouser</code> command-auth facade so published Lark/Zalo plugins that import it load on current hosts. Fixes #74702. Thanks @Goron01.</li>
<li>Plugins/runtime-deps: include bundled provider plugins when <code>models.providers</code>, auth profiles, agent defaults, or subagent model refs configure that provider, while keeping inactive default-enabled provider plugins out of doctor repair. Refs #74307. Thanks @Skeptomenos.</li>
<li>Plugins/runtime: resolve relative plugin <code>api.resolvePath</code> inputs against the plugin root instead of the host working directory, while keeping absolute and home paths user-resolved. Fixes #74718. Thanks @jimdawdy-hub.</li>
<li>Plugins/runtime-deps: refresh mirrored root chunks through a temporary file before replacing the active copy, so failed refreshes do not delete chunks that running plugin imports still need. Thanks @shakkernerd.</li>
<li>Plugins/runtime-deps: prefer <code>require</code> conditional exports when building staged dependency aliases, so CommonJS-only plugin runtime deps such as <code>ws</code> do not resolve to ESM wrappers under Jiti. Fixes #74547. Thanks @aderius.</li>
<li>Bonjour/Gateway: cap flapping advertiser restarts in a sliding window, so mDNS probing/name-conflict loops disable discovery instead of churning indefinitely on constrained hosts. Refs #74209 and #74242. Thanks @ndj888 and @Sanjays2402.</li>
<li>Plugins/runtime-deps: verify staged package entry files before reusing mirrored runtime roots, so browser-control repairs incomplete <code>ajv</code>/MCP SDK installs after update instead of failing after restart on a missing <code>ajv/dist/ajv.js</code>. Refs #74630. Thanks @spickeringlr.</li>
<li>Heartbeat: resolve <code>responsePrefix</code> template variables with the selected provider, model, and thinking context before delivering alerts or suppressing prefixed <code>HEARTBEAT_OK</code> replies. Fixes #43064; repairs #43065; supersedes #46858. Thanks @yweiii and @JunJD.</li>
<li>Memory/LanceDB: show full memory UUIDs in the <code>memory_forget</code> candidate list so agents can pass the displayed ID back to targeted deletion without hitting the full-UUID validator. (#66913) Thanks @amittell.</li>
<li>File-transfer plugin: require canonical read-path preflight authorization for <code>file.fetch</code>, fail closed when <code>dir.fetch</code> preflight entries are missing, absolute, or traversing, and recheck returned archive entries before handing archive bytes to callers. Carries forward #74134. Thanks @omarshahine.</li>
<li>Channels/Feishu: retry file-typed iOS video resource downloads as <code>media</code> after a Feishu/Lark HTTP 502 and preserve the original 502 when the fallback also fails. Fixes #49855; carries forward #50164 and #73986. Thanks @alex-xuweilong.</li>
<li>Providers/Amazon Bedrock: expose the full Claude Opus 4.7 thinking profile (<code>xhigh</code>, <code>adaptive</code>, and <code>max</code>) for Bedrock model refs, while keeping Opus/Sonnet 4.6 on adaptive-by-default, so <code>/think</code> menus and validation match the Anthropic transport behavior. Fixes #74701. Thanks @prasad-yashdeep, @sparkleHazard, @Sanjays2402, and @hclsys.</li>
<li>Plugins/tokenjuice: compile the bundled plugin against tokenjuice 0.7.0's published OpenClaw host types instead of a local compatibility shim, so package contract drift fails in OpenClaw validation before release. Thanks @vincentkoc.</li>
<li>OAuth/secrets: ignore root-level Google OAuth <code>client_secret_*.json</code> downloads so local client-secret files do not appear as commit candidates. (#74689) Thanks @jeongdulee.</li>
<li>Memory: mirror <code>sqlite-vec</code> into packaged bundled-plugin runtime deps for the default memory plugin, so builtin vector search does not lose its SQLite extension after upgrading to 2026.4.27. Fixes #74692. Thanks @mozi1924.</li>
<li>Gateway/startup: bound local discovery advertisement during startup, so a stuck discovery plugin can no longer keep the Gateway from reaching ready. Fixes #73865; refs #74630 and #74633. Thanks @lpendeavors, @moltar-bot, and @Saboor711.</li>
<li>Gateway/models: serve the last successful model catalog while stale reloads refresh in the background, so Gateway control-plane and OpenAI-compatible requests no longer block behind model-provider rediscovery after model config changes. Refs #74135, #74630, and #74633. Thanks @DerFlash, @moltar-bot, and @Saboor711.</li>
<li>CLI/status: resolve read-only channel setup runtime fallback from the packaged OpenClaw dist root, so <code>status --all</code>, <code>status --deep</code>, channel, and doctor paths do not crash when an external channel plugin needs setup metadata. Fixes #74693. Thanks @giangthb.</li>
<li>SDK/events: keep per-run SDK event streams from surfacing duplicate raw chat projection frames, while normalizing chat-only projection frames and preserving raw access through <code>rawEvents</code>. Refs #74704. Thanks @BunsDev.</li>
<li>SDK: report Gateway terminal <code>agent.wait</code> timeout snapshots with lifecycle metadata as <code>timed_out</code> while keeping bare wait deadlines non-terminal. Thanks @clawsweeper.</li>
<li>Google Meet: block managed Chrome intro/test speech until browser health proves the participant is in-call, and expose <code>speechReady</code> diagnostics so login, admission, permission, and audio-bridge blockers no longer look like successful speech. Refs #72478. Thanks @DougButdorf.</li>
<li>Slack/commands: keep native command argument menus on select controls for encoded choice values up to Slack's option limit and truncate fallback button labels to Slack's button-text limit, so long valid choices no longer render invalid Slack blocks. Thanks @slackapi.</li>
<li>Agents/Codex: flush accepted debounced steering messages before normal app-server turn cleanup, so inbound follow-ups acknowledged as queued are not dropped when the turn completes before the debounce fires. Thanks @vincentkoc.</li>
<li>Slack/interactive replies: keep rendered buttons and selects within Slack Block Kit value and count limits, and align command argument select values with Slack's option limit, so overlong agent-authored choices no longer make Slack reject the whole block payload. Thanks @slackapi.</li>
<li>Slack/interactive replies: drop overlong Block Kit button URLs while preserving valid callback values, so malformed link buttons no longer make Slack reject the whole interactive reply. Thanks @slackapi.</li>
<li>Slack/commands: truncate native command argument-menu confirmation text to Slack's dialog limit, so long plugin arg names no longer make fallback buttons render invalid Block Kit payloads. Thanks @slackapi.</li>
<li>Slack/exec approvals: cap native approval metadata context to Slack's element and text limits, so large approval details no longer make Slack reject the approval card. Thanks @slackapi.</li>
<li>Slack/exec approvals: cap native approval update fallback text to Slack's message limit while preserving the rendered approval blocks, so long commands no longer make resolved or expired approval cards stay stale after <code>chat.update</code> rejects <code>msg_too_long</code>. Thanks @slackapi.</li>
<li>Slack/commands: cap native command argument-menu fallback rows to Slack's message block limit, so large plugin choice lists no longer make Slack reject the generated menu. Thanks @slackapi.</li>
<li>Slack/commands: drop fallback command argument buttons whose encoded values exceed Slack's button-value limit, so one oversized plugin choice no longer makes Slack reject the whole menu. Thanks @slackapi.</li>
<li>Slack/messages: merge message-tool presentation and interactive blocks on Slack sends, so buttons and selects are no longer dropped when a structured message body is also present. Thanks @slackapi.</li>
<li>Slack/messages: cap Block Kit fallback text to Slack's send limit while preserving the rendered blocks, so long context fallbacks no longer make rich Slack messages fail with <code>msg_too_long</code>. Thanks @slackapi.</li>
<li>Slack/messages: cap Block Kit fallback text on message edits while preserving the rendered blocks, so long context fallbacks no longer make Slack reject <code>chat.update</code> calls with <code>msg_too_long</code>. Thanks @slackapi.</li>
<li>Channels/WhatsApp: require Baileys outbound message ids before marking auto-replies delivered, so transcript text and ack reactions no longer make failed group replies look sent. Fixes #49225. Thanks @TinyTb.</li>
<li>CLI/update: scope packaged Node compile caches by OpenClaw version and install metadata, so global installs no longer reuse stale compiled chunks after package updates. Thanks @pashpashpash.</li>
<li>Channels/Voice call: keep pre-auth webhook in-flight limiting active when socket remote address metadata is missing, so slow-body requests from stripped-IP proxy paths still share the fallback bucket. (#74453) Thanks @davidangularme.</li>
<li>Plugin SDK/testing: lazy-load TypeScript from the plugin test-contract runtime and add release checks for critical SDK contract entrypoint imports and bundle size, so published packages fail preflight before shipping ESM-incompatible or oversized contract helpers. Thanks @vincentkoc.</li>
<li>Channels/Microsoft Teams: treat configured <code>19:...@thread.tacv2</code> and legacy <code>19:...@thread.skype</code> team/channel IDs as already resolved during startup, avoiding false <code>channels unresolved</code> warnings while preserving Graph name lookup for display-name entries. Fixes #74683. Thanks @dseravalli.</li>
<li>CLI/browser: preserve parent flags while lazy-loading browser subcommands, so <code>openclaw browser --json open</code> and <code>openclaw browser --json tabs</code> keep machine-readable output after reparsing. Fixes #74574. Thanks @devintegeritsm.</li>
<li>Exec/elevated: preserve <code>turnSourceChannel</code> as <code>messageProvider</code> on approval-followup runs so <code>tools.elevated.allowFrom.<provider></code> checks no longer fail with <code>provider=null</code> after the user approves an async elevated command. Fixes #74646. Thanks @xhd2015.</li>
<li>Plugins/runtime-deps: add <code>openclaw plugins deps</code> inspection and repair with script-free package-manager defaults shared across plugin installers, so operators can repair missing bundled runtime deps without corrupting JSON output or blocking unrelated conflict-free deps. Thanks @vincentkoc.</li>
<li>Agents/output: strip internal <code>[tool calls omitted]</code> replay placeholders from user-facing replies while preserving visible reply whitespace. Fixes #74573. Thanks @blaspat.</li>
<li>Providers/Google Vertex: route authorized_user ADC credentials through OpenClaw's REST transport so Docker installs using gcloud application-default credentials no longer crash in the Google SDK before requests are sent. Fixes #74628. Thanks @frankhal2001-design.</li>
<li>ACP/resolver: fall through to thread-bound session resolution when an explicit <code>--session</code> token cannot be resolved while preserving the bad-token diagnostic when no thread binding exists, so Discord slash commands that auto-fill the current thread ID as the positional ACP target no longer return "Unable to resolve session target" errors. Fixes #66299. Thanks @hclsys, @kindomLee, and @martingarramon.</li>
<li>Agents/sessions: emit a terminal lifecycle backstop when embedded timeout/error turns return without <code>agent_end</code>, so Gateway sessions no longer stay stuck in <code>running</code> after failover surfaces a timeout. Fixes #74607. Thanks @millerc79.</li>
<li>Gateway/diagnostics: include stuck-session reason hints and recovery skip causes in warnings, so operators can tell whether a lane is waiting on active work, queued work, or stale bookkeeping. Thanks @vincentkoc.</li>
<li>Providers/DeepSeek: expose native DeepSeek V4 <code>xhigh</code> and <code>max</code> thinking levels through the provider <code>resolveThinkingProfile</code> hook so <code>/think xhigh|max</code> applies the intended effort instead of falling back to base levels. (#73008) Thanks @ai-hpc.</li>
<li>Agents/Codex: bound embedded-run cleanup, trajectory flushing, and command-lane task timeouts after runtime failures, so Discord and other chat sessions return to idle instead of staying stuck in processing. Thanks @vincentkoc.</li>
<li>Heartbeat/exec: consume successful metadata-only async exec completions silently so Telegram and other chat surfaces no longer ask users for missing command logs after <code>No session found</code>. Fixes #74595. Thanks @gkoch02.</li>
<li>Web fetch: add a documented <code>tools.web.fetch.ssrfPolicy.allowIpv6UniqueLocalRange</code> opt-in and thread it through cache keys and DNS/IP checks so trusted fake-IP proxy stacks using <code>fc00::/7</code> can work without broad private-network access. Fixes #74351. Thanks @jeffrey701.</li>
<li>OpenAI Codex: restore <code>/verbose full</code> persistence and app-server tool-output forwarding, and retry Gateway E2E temp-home cleanup so debug runs do not regress on stale validation or cleanup flakes. Thanks @vincentkoc.</li>
<li>Anthropic/Meridian: preserve text and thinking content seeded on <code>content_block_start</code> in anthropic-messages streams, so <code>[thinking, text]</code> replies no longer persist as empty turns or trigger empty-response fallbacks. Fixes #74410. Thanks @vyctorbrzezowski.</li>
<li>Channels/Matrix: complete the cross-signing handshake on <code>openclaw matrix verify confirm-sas</code> so the operator's other Matrix device clears its <code>Verifying…</code> loop instead of staying stuck after the agent confirms. (#74542) Thanks @nklock.</li>
<li>CLI/status: honor channel-specific model context-window overrides when reporting effective context, so channel-scoped sessions reflect the active window in <code>openclaw status</code>. Thanks @HemantSudarshan.</li>
<li>Sandbox/Docker: tolerate Docker daemon unavailability when sandbox mode is off, so doctor and preflight checks no longer fail on installs that do not run the Docker daemon. Fixes #73671. Thanks @kaseonedge.</li>
<li>Control UI/mobile: persist mobile chat settings through Lit-managed state and route mobile navigation through the same view-state path so chat panel toggles survive transitions on small viewports. Thanks @BunsDev.</li>
<li>Control UI/exports: align sidebar trigger affordances across the resizable divider, mobile layout, and exported-HTML transcript template so the sidebar toggle and exported transcript sidebar render with consistent hit areas and styling. Thanks @BunsDev.</li>
<li>Control UI/chat: disable the page refresh affordance while a chat run is active so accidental refreshes do not abort an in-flight reply. Thanks @Angfr95 and @BunsDev.</li>
<li>Memory/LanceDB: return real memory records from <code>openclaw ltm list</code> (with optional <code>--limit</code> and createdAt ordering) instead of an empty placeholder, so the CLI surface matches the documented LTM listing contract. (#67952) Thanks @zhangyue19921010.</li>
<li>Media: include redacted per-attempt resize failures and resolved model input capabilities in vision-pipeline errors so ARM64 image failures are diagnosable without closing the remaining routing investigation. Refs #74552. Thanks @1yihui.</li>
<li>Control UI/i18n: route zh-CN agent, debug, channel-refresh, and exec-approval copy through the locale source while preserving the English <code>Cron Jobs</code> agent tab label and the security-audit command styling. Carries forward #39692 repair context. Thanks @hepeng154833488 and @vincentkoc.</li>
<li>Auto-reply: honor explicit <code>silentReply.direct: "allow"</code> for clean empty or reasoning-only direct chat turns while keeping the default direct-chat empty-response guard conservative. Fixes #74409. Thanks @jesuskannolis.</li>
<li>OpenAI Codex: send a non-empty Responses input item when a Codex turn only has systemPrompt-backed instructions, avoiding ChatGPT backend 400s from <code>input: []</code>. Fixes #73820. Thanks @woodhouse-bot.</li>
<li>Ollama: normalize provider-prefixed tool-call names at the native stream boundary so Kimi/Ollama calls such as <code>functions.exec</code> dispatch as <code>exec</code> instead of missing configured tools. Fixes #74487. Thanks @afurm and @carreipeia.</li>
<li>Security/audit: resolve configured model aliases before model-tier and small-parameter checks, so alias-based GPT-5/Codex configs no longer report false weak-model warnings. Fixes #74455. Thanks @blaspat.</li>
<li>CLI/agent: isolate Gateway-timeout embedded fallback runs under explicit <code>gateway-fallback-*</code> sessions so accepted Gateway runs cannot race transcript locks or replace the routed conversation session. Fixes #62981. Thanks @HemantSudarshan.</li>
<li>CLI/QR/device-pair: reject malformed public setup URLs before issuing mobile pairing bootstrap tokens, while keeping valid bare host:port setup URLs supported. Thanks @Lucenx9.</li>
<li>Models/UI: hide unauthenticated providers from the default Web chat, <code>/models</code>, and model setup pickers while keeping explicit full-catalog browse paths through <code>view: "all"</code>, <code>/models <provider> all</code>, and <code>models list --all</code>. Fixes #74423. Thanks @guarismo and @SymbolStar.</li>
<li>Ollama: keep explicit local model runs on target-provider runtime hooks when PI discovery is skipped, so one-shot Ollama calls no longer cold-load unrelated provider runtimes before streaming. Fixes #74078. Thanks @sakalaboator.</li>
<li>Slack/prompts: rely on Slack <code>interactiveReplies</code> guidance instead of generic <code>inlineButtons</code> config hints so enabled Slack button directives are not contradicted. Fixes #46647. Thanks @jeremykoerber.</li>
<li>Slack/reactions: treat duplicate <code>already_reacted</code> responses as idempotent success so repeated agent reaction adds no longer surface as tool failures. Fixes #69005. Thanks @shipitsteven and @martingarramon.</li>
<li>Channels/Discord: cool down Cloudflare/Error 1015 HTML 429 REST failures during startup application lookup and gateway metadata fetches, add <code>channels.discord.applicationId</code> as an app-id lookup bypass, sanitize HTML bodies before logging, and honor Retry-After before falling back to a conservative cooldown. Fixes #38853. (#74489) Thanks @djgeorg3 and @Garyko0730.</li>
<li>Slack/tools: expose <code>fileId</code> in the shared message tool schema so <code>download-file</code> can receive Slack attachment IDs from inbound placeholders. Fixes #45574. Thanks @chadvegas.</li>
<li>Exec: reject invalid per-call <code>host</code> values instead of silently falling back to the default target, so hostname-like values fail before commands run. Fixes #74426. Thanks @scr00ge-00 and @vyctorbrzezowski.</li>
<li>Google/Gemini: send non-empty placeholder content when a Gemini run is triggered with empty or filtered user content, avoiding <code>contents is not specified</code> API errors. Thanks @CaoYuhaoCarl.</li>
<li>Heartbeat: preserve non-task <code>HEARTBEAT.md</code> context around <code>tasks:</code> blocks and apply <code>agents.defaults.heartbeat</code> to all agents unless per-agent heartbeat entries restrict scope. Thanks @Sekhar03.</li>
<li>Markdown: preserve paragraph breaks inside loose list items in shared outbound formatting while keeping tight list spacing stable. Thanks @Lucenx9.</li>
<li>Build/Gateway: route restart, shutdown, respawn, diagnostics, command-queue cleanup, and runtime cleanup through one stable gateway lifecycle runtime entry so rebuilt packages do not strand long-running gateways on stale hashed chunks. Carries forward #73964. Thanks @pashpashpash.</li>
<li>Memory/wiki: keep broad shared-source and generated related-link blocks from turning every page into a search hit, cap noisy backlinks, support all-term searches such as people-routing queries, and prefer readable page body snippets over generated metadata. Thanks @vincentkoc.</li>
<li>Cron/Gateway: abort and bounded-clean up timed-out isolated agent turns before recording the timeout, so stale cron sessions cannot leave Discord or other chat lanes stuck in <code>processing</code> after a timeout. Thanks @vincentkoc.</li>
<li>Agents/errors: suppress malformed streaming tool-call JSON fragments before they reach chat surfaces while preserving provider request-validation diagnostics. Fixes #59076; keeps #59080 as duplicate coverage. (#59118) Thanks @singleGanghood.</li>
<li>CLI/models: restore provider-filtered <code>models list --all --provider <id></code> rows for providers without manifest/static catalog coverage, including Anthropic and Amazon Bedrock, while keeping the compatibility fallback off expensive availability and resolver paths. Thanks @shakkernerd.</li>
<li>CLI/models: keep manifest auth-evidence credentials visible across <code>models status</code>, auth probes, and PI model discovery so workspace-scoped provider auth does not disagree between listing, probing, and execution. Thanks @shakkernerd.</li>
<li>CLI/models: move local credential evidence such as Google Vertex ADC into generic plugin manifest setup metadata so the model-list auth index stays declarative without provider-specific runtime branches. Thanks @shakkernerd.</li>
<li>CLI/models: compute the <code>models list</code> Auth column through one command-local provider auth index so row rendering no longer repeats auth profile, env, configured-provider, AWS, or synthetic-auth checks per model row. Thanks @shakkernerd.</li>
<li>CLI/models: move the OpenAI listable catalog into the plugin manifest so <code>models list --all --provider openai</code> uses the manifest fast path instead of loading provider runtime normalization hooks. Thanks @shakkernerd.</li>
<li>CLI/tools: keep the Gateway <code>tools.*</code> RPC namespace out of plugin command discovery and managed proxy startup, so stray commands like <code>openclaw tools effective</code> fail quickly instead of cold-loading plugin metadata. Refs #73477. Thanks @oromeis.</li>
<li>CLI/status: keep default text <code>openclaw status --usage</code> on metadata-only channel scans unless <code>--deep</code> or <code>--all</code> is set, and send stray <code>openclaw tools --help</code> through the precomputed root-help fast path so latency-triage commands avoid plugin/runtime cold loads before printing. Refs #73477 and #74220. Thanks @oromeis and @NianJiuZst.</li>
<li>Agents/diagnostics: trace embedded-run startup and preparation stage timings before model I/O, and warn only on severe slow stages, so Docker/VPS latency reports can identify whether plugin loading, auth/model resolution, tool inventory, bootstrap, MCP/LSP, resource loading, or stream setup is dominating pre-run latency without noisy normal logs. Refs #73428. Thanks @Dimaoggg, @quangtran88, and @Heyvhuang.</li>
<li>Agents/subagents: cache persisted subagent run registry reads by file signature while preserving fresh-parse isolation, so busy gateways stop reparsing unchanged <code>subagents/runs.json</code> on controller/list/status hot paths. Refs #72338. Thanks @argus-as.</li>
<li>Gateway/clients: wait for the event loop to become responsive before opening Gateway WebSocket RPC/probe/client connections while charging that readiness wait to caller timeouts, so Windows deferred module-evaluation stalls no longer turn healthy loopback gateways into false handshake timeouts across status, TUI, ACP, MCP, node-host, and plugin client paths. Refs #74279 and #48270. Thanks @wongcode and @joost-heijden.</li>
<li>Gateway/Windows: read listener command lines via PowerShell before falling back to <code>wmic</code>, so restart health can recognize OpenClaw listeners on modern Windows installs and avoid long anonymous-port waits. Refs #74280. Thanks @zym951223.</li>
<li>Plugins/runtime-deps: record process start-time in bundled dependency install locks and expire recycled-PID locks, so Docker gateway restarts recover from stale <code>.openclaw-runtime-deps.lock</code> directories without waiting through repeated five-minute timeouts. Fixes #74346. (#74361) Thanks @jhsmith409.</li>
<li>Plugins/runtime-deps: memoize packaged bundled runtime dist-mirror preparation after the first successful pass while keeping source-checkout mirrors refreshable, so constrained Docker/VPS installs avoid repeated root scans before chat turns. Refs #73428, #73421, #73532, and #73477. Thanks @Dimaoggg, @oromeis, @oadiazp, @jmfraga, @bstanbury, @antoniusfelix, and @jkobject.</li>
<li>Channels/Discord: treat bare numeric outbound targets that match the effective Discord DM allowlist as user DMs while preserving account-specific legacy <code>dm.allowFrom</code> precedence over inherited root <code>allowFrom</code>. (#74303) Thanks @Squirbie.</li>
<li>Channels/Discord/Slack: share one DM policy/allowlist resolver across runtime, setup, allowlist editing, and doctor repair, so legacy <code>dm.policy</code> / <code>dm.allowFrom</code> compatibility migrates to canonical <code>dmPolicy</code> / <code>allowFrom</code> without divergent access checks. Thanks @Squirbie.</li>
<li>Control UI: make the chat sidebar split divider focusable, keyboard-resizable, ARIA-described, and pointer-event based so sidebar resizing works without a mouse. Thanks @BunsDev.</li>
<li>Agents/usage: keep PI embedded-run telemetry attributed to the resolved model provider instead of the PI harness label, so OpenRouter and other provider-backed turns report the right provider in session usage and traces. Thanks @vincentkoc.</li>
<li>Agents/attribution: send OpenClaw attribution headers on native OpenAI and Codex traffic, including SDK transports, realtime voice and TTS, device-code auth, WHAM usage, and remote embeddings, so PI-origin defaults no longer leak into provider requests. Thanks @vincentkoc.</li>
<li>Agents/auth: keep OAuth auth profiles inherited from the main agent read-through instead of copying refresh tokens into secondary agents, and refresh Codex app-server tokens against the owning store so multi-agent swarms avoid reused refresh-token failures. Fixes #74055. Thanks @ClarityInvest.</li>
<li>Channels/Telegram: honor <code>ALL_PROXY</code> / <code>all_proxy</code> and service-level <code>OPENCLAW_PROXY_URL</code> when constructing the HTTP/1-only Telegram Bot API transport, so Windows and service installs that rely on those proxy settings no longer fall back to direct egress. Fixes #74014; refs #74086. Thanks @SymbolStar.</li>
<li>Channels/Telegram: keep raw host/network-unreachable Bot API connect failures non-fatal and route tagged polling uncaught exceptions through the Telegram restart path, so transient reachability failures no longer kill the Gateway or leave long polling stuck. Fixes #60515; refs #74540. Thanks @HemantSudarshan, @thacid22, and @ewimsatt.</li>
<li>Channels/Telegram: continue polling when <code>deleteWebhook</code> hits a transient network failure but <code>getWebhookInfo</code> confirms no webhook is configured, so startup does not retry cleanup forever after the webhook was already removed. Refs #74086; carries forward #47384. Thanks @clovericbot.</li>
<li>Channels/Telegram: retry native quote replies without <code>reply_parameters.quote</code> when Telegram returns <code>QUOTE_TEXT_INVALID</code>, so stale or truncated quote excerpts no longer drop the whole reply. Fixes #74581. Thanks @moeedahmed.</li>
<li>Channels/Telegram: apply strict safe-send retry to inbound final replies when grammY wraps a pre-connect failure, while leaving ambiguous plain network envelopes single-shot to avoid duplicate visible messages. Fixes #74203. Thanks @nanli2000cn.</li>
<li>Channels/Telegram: surface polling liveness warnings in channel status and doctor when a running long-poller has not completed <code>getUpdates</code> after startup grace or its transport activity is stale, so silent polling failures no longer look clean. Refs #74299. Thanks @lolaopenclaw.</li>
<li>Channels/Telegram: publish webhook runtime state and warn when <code>setWebhook</code> has not completed after startup grace, so webhook-mode accounts no longer look healthy while registration is still failing or retrying. Refs #74299. Thanks @lolaopenclaw and @martingarramon.</li>
<li>Channels/Telegram: bound native command menu <code>deleteMyCommands</code> and <code>setMyCommands</code> Bot API calls and allow the same timeout-triggered transport fallback retry as other startup control calls, so Windows/WSL network stalls cannot leave command sync hanging behind an otherwise running provider. Refs #74086. Thanks @SymbolStar.</li>
<li>ACP/commands: accept forwarded ACP timeout config controls in the OpenClaw bridge, treat unsupported discard-close controls as recoverable cleanup, and restore native <code>/verbose full</code> plus no-arg status behavior, so Discord command menus and nested ACP turns no longer fail on supported session controls. Thanks @vincentkoc.</li>
<li>Codex harness: interrupt and release native app-server turns that go quiet after an OpenClaw dynamic-tool response without sending <code>turn/completed</code>, so Discord and other chat lanes do not stay stuck in <code>processing</code>. Thanks @vincentkoc.</li>
<li>Codex harness: bound OpenClaw dynamic tool responses to 30 seconds and fail closed with an explicit tool result when the app-server bridge would otherwise strand the turn in <code>processing</code>. Thanks @vincentkoc.</li>
<li>TUI/status: clear stale <code>streaming</code> footer state when a final event arrives after the active run was already cleared and no tracked runs remain, while preserving concurrent-run ownership and inactive local <code>/btw</code> terminal handling. Fixes #64825; carries forward #64842, #64843, #64847, and #64862. Thanks @briandevans and @Yanhu007.</li>
<li>Channels/Discord: fail startup closed when Discord cannot resolve the bot's own identity and keep mention gating active when only configured mention patterns can detect mentions, so the provider no longer continues with a missing bot id. Fixes #42219; carries forward #46856 and #49218. Thanks @education-01 and @BenediktSchackenberg.</li>
<li>Channels/Discord: split long CJK replies at punctuation and code-point-safe fallback boundaries so Discord chunking stays readable without corrupting astral characters. Fixes #38597; repairs #71384. Thanks @p3nchan.</li>
<li>TUI: keep the streaming watchdog alive across active tool/lifecycle proof-of-life, pause it during disconnects, and reload history after stale reconnect runs so long-running chats stop flipping to false idle or hanging on stale streaming. Fixes #69081. Thanks @EenvoudJasper.</li>
<li>Browser/gateway: ignore Playwright dialog-close races from <code>Page.handleJavaScriptDialog</code> so browser automation no longer crashes the Gateway when a dialog disappears before Playwright accepts it. (#40067) Thanks @randyjtw.</li>
<li>Cron/Gateway: defer missed isolated agent-turn catch-up out of the channel startup window, so overdue cron work cannot starve Discord or Telegram while providers connect after a restart. Thanks @vincentkoc.</li>
<li>Heartbeat/cron: defer heartbeat turns while cron work is active or queued, add opt-in <code>heartbeat.skipWhenBusy</code> for subagent/nested lane pressure, and retry busy skips without advancing the schedule so local Ollama hosts do not run heartbeat and cron prompts concurrently. Fixes #50773. Thanks @scottgl9.</li>
<li>Agents/thinking: honor configured model <code>compat.supportedReasoningEfforts</code> entries that include <code>xhigh</code>, so custom OpenAI-compatible provider refs expose and validate <code>/think xhigh</code> consistently across command menus, Gateway sessions, agent CLI, and <code>llm-task</code>. Carries forward #48904. Thanks @Milchstrassse and @wufunc.</li>
<li>Vercel AI Gateway: expose provider-owned <code>/think xhigh</code> for trusted OpenAI/Codex upstream refs and Claude adaptive thinking for Anthropic upstream refs, while leaving untrusted namespaced refs on base levels. Carries forward #41561. Thanks @Zcg2021.</li>
<li>Plugins/runtime-deps: prune stale <code>openclaw-unknown-*</code> bundled runtime dependency roots during Gateway startup while keeping recent or locked roots, so old staging debris cannot keep growing across restarts. Thanks @vincentkoc.</li>
<li>Plugins/runtime-deps: include ten more root-package runtime dependencies (<code>@agentclientprotocol/sdk</code>, <code>@lydell/node-pty</code>, <code>croner</code>, <code>dotenv</code>, <code>jiti</code>, <code>json5</code>, <code>jszip</code>, <code>markdown-it</code>, <code>tar</code>, <code>web-push</code>) in <code>MIRRORED_CORE_RUNTIME_DEP_NAMES</code> so they are mirrored into the runtime-deps tree alongside <code>semver</code> and <code>tslog</code>, preventing <code>Cannot find package 'X'</code> failures from core dist code (for example <code>qmd-manager</code>, <code>cron/schedule</code>, <code>infra/archive</code>, <code>infra/push-web</code>, <code>infra/backup-create</code>, <code>process/supervisor/adapters/pty</code>) when no enabled extension owns the dependency. Adds a static drift guard test that scans <code>src/</code> for value imports of root-package deps and fails CI when one is missing from the mirror allowlist or extension-owned set. Refs #74199. Thanks @maxpuppet.</li>
<li>Ollama: compose caller abort signals with guarded-fetch timeouts for native <code>/api/chat</code> streams, so <code>/stop</code> and early cancellation still interrupt local Ollama requests that also carry provider timeout budgets. Refs #74133. Thanks @obviyus.</li>
<li>Doctor/TTS: migrate legacy <code>messages.tts.enabled</code>, agent TTS, channel TTS, and voice-call plugin TTS toggles to <code>auto</code> mode during <code>openclaw doctor --fix</code>, matching the documented TTS config contract. Thanks @vincentkoc.</li>
<li>CLI/logs: fall back to the configured Gateway file log when implicit loopback Gateway connections close or time out before or during <code>logs.tail</code>, so <code>openclaw logs</code> still works while diagnosing local-model Gateway disconnects. Refs #74078. Thanks @sakalaboator.</li>
<li>MCP/plugins: stringify non-array plugin tool results with chat-content coercion instead of default object stringification, so MCP callers receive useful JSON/text content from plugin tools. Thanks @vincentkoc.</li>
<li>Active Memory/QMD: make gateway-start QMD refresh opt-in via <code>memory.qmd.update.startup</code>, keep normal memory access lazy, preserve interactive file watching, and align watcher dependency/build ignores with QMD's scanner so cold gateway startup no longer imports or initializes QMD by default. Thanks @codexGW.</li>
<li>Channels/Discord: remove Discord-owned queued-run timeout replies through the shared channel lifecycle queue while preserving message ordering and compatibility timeout constants, so long Discord turns stay governed by session/tool/runtime lifecycle instead of channel fallback errors. Thanks @codexGW.</li>
<li>Agents/tools: clamp <code>process.poll</code> waits to 30 seconds, advertise that cap in the tool schema, and honor abort signals while waiting, so long command polls cannot pin agent responsiveness after cancellation. Thanks @vincentkoc.</li>
<li>Plugin SDK: add tracked Discord component-message helpers and a Telegram account-resolution compatibility facade, so existing plugins using those subpaths resolve while new plugins stay on generic channel SDK contracts. Thanks @vincentkoc.</li>
<li>Shared labels: preserve Unicode combining marks and NFC-equivalent accented text in group/channel slug normalization so non-Latin labels no longer lose meaningful characters. Fixes #58932; carries forward #58942 and #58995. Thanks @fengqing-git, @Starhappysh, and @koen666.</li>
<li>Channels/Telegram: include probed video width and height when sending regular Telegram videos, so portrait clips render with the correct orientation instead of being stretched by clients. (#18915) Thanks @storyarcade.</li>
<li>Docs/Hetzner: clarify that SSH tunnel access requires <code>AllowTcpForwarding local</code> before running <code>ssh -L</code>, so hardened VPS sshd configs do not block loopback Gateway access. Fixes #54557; carries forward #54564; refs #54954. Thanks @satishkc7, @blackstrype, and @Aftabbs.</li>
<li>Agents/config: preserve authored <code>agents.defaults.params</code> and per-model <code>agents.defaults.models[].params</code> during narrowed internal config writes, so OpenAI transport overrides such as <code>transport: "sse"</code> and <code>openaiWsWarmup: false</code> are not stripped from <code>openclaw.json</code>. Fixes #73607; refs #73428. Thanks @quangtran88.</li>
<li>Agents/model config: resolve per-model extra params through canonical model keys while preserving legacy double-prefixed fallback entries, so provider-prefixed model ids such as <code>openrouter/auto</code> keep their configured runtime params. (#44319) Thanks @HenryXiaoYang.</li>
<li>Gateway/shutdown: report structured shutdown warnings and HTTP close timeout warnings through <code>ShutdownResult</code> while preserving lifecycle hook hardening. Carries forward #41296. Thanks @edenfunf.</li>
<li>Control UI: keep Agents Overview and config-form select dropdowns on their configured value after options render while preserving inherited agent model placeholders. Fixes #40352; carries forward #52948. Thanks @xiaoquanidea.</li>
<li>Agents/exec: launch zsh, bash, and fish host exec shells with startup files suppressed while preserving existing PATH fallbacks, so daemon env is not overridden by shell startup files. Carries forward #40200; fixes #40179. Thanks @NewdlDewdl.</li>
<li>Plugins/QA: prebuild the private QA channel runtime before plugin gauntlet source runs so wrapper CPU/RSS measurements are not polluted by private QA dist rebuild work. Thanks @vincentkoc.</li>
<li>Plugins/QA: add a Kitchen Sink plugin gauntlet that installs the external package, checks command inventory, MCP tools, channel status, provider turns, gateway RSS, CPU, and fatal log anomalies. Thanks @vincentkoc.</li>
<li>Plugins/config: reuse the bundled plugin alias scan within a single config normalization pass, so Kitchen Sink-style plugin configs no longer peg Gateway CPU by repeatedly rescanning bundled metadata before agent turns. Thanks @vincentkoc.</li>
<li>Plugins/channels: reject malformed runtime channel registrations that omit required config helpers before they can poison channel status. Thanks @vincentkoc.</li>
<li>MCP/plugins: serialize raw plugin tool return values through the plugin-tools MCP bridge so Kitchen Sink-style tools no longer surface <code>undefined</code> content. Thanks @vincentkoc.</li>
<li>Gateway/reload: bound default restart deferral and SIGUSR1 restart drain to five minutes while preserving explicit <code>deferralTimeoutMs: 0</code> indefinite waits, so stale active work accounting cannot block config reloads forever. Thanks @vincentkoc.</li>
<li>Active Memory: register the prompt-build hook with the configured recall timeout plus setup grace instead of the 150s maximum budget, so default memory recall cannot delay turn startup for multiple minutes. Thanks @vincentkoc.</li>
<li>Gateway/readiness: include an <code>eventLoop</code> diagnostic block in local or authenticated <code>/readyz</code> responses with event-loop delay (p99 and max), event-loop utilization, CPU core ratio, and a <code>degraded</code> flag, so operators can see when slow startups or runaway turns stall the event loop. Thanks @vincentkoc.</li>
<li>Gateway/agents: schedule accepted agent runs after the accepted RPC frame has a chance to flush, so pre-turn prompt/context work is less likely to starve immediate <code>agent.wait</code> callers. Thanks @vincentkoc.</li>
<li>CLI/update: tolerate stale memory-runtime import failures during best-effort CLI process teardown, so <code>openclaw update</code> replacing hashed runtime chunks before the finalizer runs no longer surfaces as exit-time <code>Cannot find module</code> noise. Thanks @vincentkoc.</li>
<li>CLI/channels logs: reuse the rolling log-file resolver so <code>openclaw channels logs</code> falls back to the active dated log across date boundaries without reading unrelated custom log files. Fixes #42875; carries forward #42904 and #43043. Thanks @ethanclaw and @wdskuki.</li>
<li>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.</li>
<li>Control UI: fix Peak Error Hours showing incorrect hourly rates when the browser's timezone observes DST, by storing hourly message counts with UTC date keys and using DST-aware <code>Date.getHours()</code> for local conversion. Also extract <code>accumulateMessageCounts</code> helper to reduce duplicated daily/hourly aggregation logic. (#49396) Thanks @konanok.</li>
<li>iMessage: normalize known leading attributedBody corruption markers on sent-message echo text keys so delayed reflected echoes with U+FFFD/U+FFFE/U+FFFF/FEFF prefixes are dropped without collapsing interior text. Fixes #59973; carries forward #59980 and #62191. Thanks @neeravmakwana and @maguilar631697.</li>
<li>Security/audit: recognize dangerous node command IDs as valid <code>gateway.nodes.denyCommands</code> entries, so audit only warns on real typos or unsupported patterns. (#56923) Thanks @chziyue.</li>
<li>Cron: treat implicit text payloads with agent-turn overrides as agent turns, preserving model overrides for scheduled text prompts instead of pruning them as system events. Fixes #28905. (#64060) Thanks @liaoandi.</li>
<li>Telegram/exec approvals: stop treating general Telegram chat allowlists and <code>defaultTo</code> routes as native exec approvers; Telegram now uses explicit <code>execApprovals.approvers</code> or owner identity from <code>commands.ownerAllowFrom</code>, matching the first-pairing owner bootstrap path. Thanks @pashpashpash.</li>
<li>Plugins/providers: keep Gateway startup primary-model discovery on metadata-only provider entries and reuse active non-speech capability providers even with explicit plugin entries, avoiding unnecessary provider registry loads during startup and media capability checks. Fixes #73729, #73835, and #73793; carries forward #73853 and #73794. Thanks @sg1416-zg, @brokemac79, and @poolside-ventures.</li>
<li>Chat commands: route sensitive group <code>/diagnostics</code> and <code>/export-trajectory</code> approvals and results to a private owner route, preferring same-surface DMs before falling back to the first configured owner route, so Discord group invocations can land in Telegram when that is the primary owner interface. Thanks @pashpashpash.</li>
<li>Gateway/hooks: keep successful <code>deliver:false</code> agent hooks silent, log a hook audit record for suppressed success announcements, and suppress fallback summaries after attempted hook delivery while still surfacing failed hook runs. Repairs #55761; builds on #36332 and #49234. Thanks @EffortlessSteven, @cioclawcode, and @BrennerSpear.</li>
<li>Plugin SDK/Discord: restore a deprecated <code>openclaw/plugin-sdk/discord</code> compatibility facade and the legacy compat group-policy warning export for the published <code>@openclaw/discord@2026.3.13</code> package, covering its config, account, directory, status, and thread-binding imports while keeping new plugins on generic SDK subpaths. Fixes #73685; supersedes #73703. Thanks @rderickson9 and @SymbolStar.</li>
<li>Channels/Discord: suppress duplicate gateway monitors when multiple enabled accounts resolve to the same bot token, preferring config tokens over default env fallback and reporting skipped duplicates as disabled. Supersedes #73608. Thanks @kagura-agent.</li>
<li>CLI/health: build channel health summaries from inspected credential metadata plus runtime state, so <code>openclaw health --json</code> reports Discord <code>running</code>, <code>connected</code>, and <code>tokenSource</code> consistently with channel status. Fixes #44354. Thanks @ferenc-acs.</li>
<li>Control UI/Talk: decode Google Live binary WebSocket JSON frames and stop queued browser audio on interruption or shutdown, so browser Talk leaves <code>Connecting Talk...</code> and barge-in no longer plays stale audio. Fixes #73601 and #73460; supersedes #73466. Thanks @Spolen23 and @WadydX.</li>
<li>Channels/Discord: ignore stale route-shaped conversation bindings after a Discord channel is reconfigured to another agent, while preserving explicit focus and subagent bindings. Fixes #73626. Thanks @ramitrkar-hash.</li>
<li>Agents/bootstrap: pass pending BOOTSTRAP.md contents through the first-run user prompt while keeping them out of privileged system context, and show limited bootstrap guidance when workspace file access is unavailable. Fixes #73622. Thanks @mark1010.</li>
<li>ACP/tasks: classify parent-owned ACP sessions as background work regardless of persistent runtime mode, and close terminal stale ACP sessions when no active binding remains, so delegated ACP output reports through the parent task notifier instead of acting like a normal foreground chat session. Refs #73609. Thanks @joerod26.</li>
<li>Tasks: keep terminal mirrored TaskFlow timestamps pinned to task completion time and let maintenance repair stale mirrors, so ACP terminal delivery updates no longer leave inconsistent flow audits. Refs #73609. Thanks @joerod26.</li>
<li>Gateway/sessions: add conservative stuck-session recovery that releases only stale session lanes while active embedded runs, reply operations, and lane tasks remain serialized, so queued follow-ups can drain without aborting legitimate long-running turns. Refs #73581, #73655, #73652, #73705, #73647, #73602, #73592, and #73601. Thanks @WS-Q0758, @bryangauvin, @spenceryang1996-dot, @bmilne1981, @mattmcintyre, @Vksh07, and @Spolen23.</li>
<li>Plugins: cache unchanged plugin manifest loads by file signature, reducing repeated JSON/JSON5 parsing and manifest normalization in bursty startup and runtime registry paths. Refs #73532 and #73647; carries forward #73678. Thanks @TheDutchRuler.</li>
<li>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.</li>
<li>Plugins/runtime-deps: retry and defer transient cleanup failures for owned runtime staging directories so CLI startup no longer aborts after a successful bundled dependency swap. Refs #73903. Thanks @bobfreeman1989.</li>
<li>Plugins/runtime-deps: cache bundled runtime-deps JSON/package files by file signature, reducing repeated staged-runtime metadata reads during bundled channel startup. Refs #73647 and #73705. Thanks @mattmcintyre and @bmilne1981.</li>
<li>Plugins/runtime-deps: delegate bundled plugin dependency staging to complete npm/pnpm install plans with durable runtime state, removing retained-manifest and source-checkout cache reconciliation from Gateway startup. Refs #73532. Thanks @oadiazp, @bstanbury, and @jmfraga.</li>
<li>Plugins/runtime-deps: replace Gateway-start root chunk dependency inference with explicit mirrored-root dependency metadata, reducing staged runtime scans while preserving lazy per-plugin installs. Refs #73532. Thanks @oadiazp and @bstanbury.</li>
<li>Plugins/runtime-deps: run pnpm staged installs outside the repository workspace and disable pnpm release-age gates for exact bundled runtime dependency materialization, so bundled plugin dependency repair writes packages into the generated stage without blocking fresh packaged dependencies. Refs #73532. Thanks @oadiazp and @bstanbury.</li>
<li>CLI/TUI: keep <code>chat.history</code> off model-catalog discovery so initial Gateway-backed TUI history loads cannot block behind slow provider/plugin model scans on low-core hosts. Refs #73524. Thanks @harshcatsystems-collab.</li>
<li>Channels/WhatsApp: flag recently reconnected linked accounts in channel status even when the socket is currently healthy, so flapping WhatsApp Web sessions no longer look clean after a brief reconnect. Refs #73602. Thanks @Vksh07.</li>
<li>Channels/WhatsApp: log shared dispatcher delivery failures with reply kind, message id, chat id, and connection id, so typing-without-send reports can identify whether the WhatsApp send path rejected a generated reply. Refs #74269. Thanks @tomcosta-git.</li>
<li>Feishu: suppress distinct late <code>final</code> text deliveries after a streaming card has already closed, while keeping media attachments deliverable, so late-finals no longer reopen duplicate Feishu cards. Fixes #71977. (#72294) Thanks @MonkeyLeeT.</li>
<li>Gateway: expose <code>gateway.handshakeTimeoutMs</code> in config, schema, and docs while preserving <code>OPENCLAW_HANDSHAKE_TIMEOUT_MS</code> precedence, so loaded or low-powered hosts can tune local WebSocket pre-auth handshakes without patching dist files. Supersedes #51282; refs #73592 and #73652. Thanks @henry-the-frog.</li>
<li>Gateway/TUI/status: align configured and env-based WebSocket handshake budgets across local clients, probes, and fallback RPCs while preserving explicit status timeouts and paired-device auth fallback, so slow local gateways are not marked unreachable by a shorter client watchdog. Refs #73524, #73535, #73592, and #73602. Thanks @harshcatsystems-collab, @DJBlackhawk, and @Vksh07.</li>
<li>Gateway/startup: return retryable <code>UNAVAILABLE</code> during the sidecar startup window and keep CLI/TUI/status clients retrying inside their existing timeout budget, so early connects no longer surface as terminal handshake failures. Fixes #73652. Thanks @spenceryang1996-dot.</li>
<li>Gateway/proxy: bypass inherited proxy environment for local Gateway control-plane WebSockets to <code>localhost</code> as well as loopback IPs, so Windows/WSL proxy settings cannot intercept local CLI/TUI Gateway connections. Supersedes #73474; refs #73602. Thanks @DhtIsCoding.</li>
<li>Doctor/Gateway: use a lightweight <code>status</code> RPC without channel summary work for doctor Gateway liveness, so slow health snapshots do not falsely drive service restart repair. Fixes #64400; supersedes #64511. Thanks @CHE10X and @EronFan.</li>
<li>Agents/auth: scope external CLI credential discovery to configured providers during model auth status and startup prewarm, so opencode-only and other single-provider gateways do not block on unrelated Claude CLI Keychain probes. Fixes #73908. Thanks @Ailuras.</li>
<li>Agents/model selection: resolve slash-form aliases before provider/model parsing and keep alias-resolved primary models subject to transient provider cooldowns, so cron and persisted sessions do not retry cooled-down raw aliases. Fixes #73573 and #73657. Thanks @akai-shuuichi and @hashslingers.</li>
<li>Agents/Claude CLI: reuse already-cached macOS Keychain credentials for no-prompt Claude credential reads, so doctor/runtime checks do not miss fresh interactive Claude auth. Fixes #73682. Thanks @RyanSandoval.</li>
<li>Agents/Claude CLI doctor: scope workspace and project-dir checks to agents that actually use the Claude CLI runtime, so non-default Claude agents no longer make the default agent look Claude-backed. Fixes #73903. Thanks @bobfreeman1989.</li>
<li>Gateway/sessions: expose effective agent runtime metadata on session rows, <code>sessions.patch</code>, and local <code>openclaw sessions --json</code>, while keeping Claude CLI-backed rows on the canonical model provider so runtime backend and model identity are no longer conflated. Fixes #73090. Thanks @vishutdhar.</li>
<li>Gateway/auth status: scope external CLI credential overlays to configured providers, runtimes, or profiles and keep status reads off new Keychain prompts, so single-provider Gateway configs no longer probe unrelated Claude/Codex/MiniMax auth on startup. Fixes #73908. Thanks @Ailuras.</li>
<li>Agents/runtime status: expose effective agent runtime metadata in <code>agents.list</code>, Control UI agent panels, and <code>/agents</code>, and avoid rendering stale or cumulative CLI token totals as live context usage. Fixes #73660, #73578, and #45268. Thanks @spartman, @DashLabsDev, and @xyooz.</li>
<li>Agents/transcripts: strip empty assistant text blocks while preserving valid text, images, and signatures, so Anthropic-style providers no longer reject sanitized transcript turns. Fixes #73640. Thanks @jowhee327.</li>
<li>Gateway/sessions: preserve session keys on hidden lifecycle events so channel-routed runs still persist terminal session state and do not strand session status as running after Codex turn completion. Thanks @cathrynlavery.</li>
<li>Providers/Bedrock: omit deprecated <code>temperature</code> for Claude Opus 4.7 Bedrock model ids, named and application inference profiles, including dotted <code>opus-4.7</code> refs, and classify the nested validation response for failover. Fixes #73663. Thanks @bstanbury.</li>
<li>Gateway: raise the preauth/connect-challenge timeout to 15s so cold CLI starts on slower hosts have more time to process the WebSocket challenge before the Gateway closes the connection. Fixes #51469; refs #73592 and #62060. Thanks @GothicFox and @jackychen-png.</li>
<li>CLI/status: fall back to a bounded local <code>status</code> RPC when loopback detail probes time out or report unknown capability, so reachable local gateways are no longer marked unreachable by slow read diagnostics. Fixes #73535; refs #48360, #62762, #51357, and #42019. Thanks @RacecarGuy, @justinschille, @DJBlackhawk, @tianyaqpzm, and @0xrsydn.</li>
<li>CLI/gateway: reuse cached paired-device auth during <code>gateway probe</code> and report post-connect diagnostic failures as degraded reachability, so healthy local gateways are no longer marked unreachable after loopback auth or read timeouts. Fixes #48360. Thanks @RacecarGuy.</li>
<li>Channels/Discord: give Discord Gateway WebSocket handshakes a 30s timeout so stalled TLS/network transitions emit an error and Carbon can continue its reconnect loop instead of leaving the bot silent until restart. Refs #50046. Thanks @codexGW.</li>
<li>Mattermost/WebSocket: send protocol ping/pong keepalives and terminate stale sessions when pongs stop arriving, so silent TCP drops reconnect instead of leaving monitoring idle. Fixes #41837; carries forward #57621; refs #50138, #44160, and #51104. Thanks @JasonWang1124.</li>
<li>Channels/Telegram: suppress standalone failed edit/write warning payloads when a user-facing assistant error reply already covers the turn, while keeping unresolved mutating failures visible behind success-looking or suppressed-error replies. Fixes #39631; refs #73750; carries forward #39636 and #39717; leaves #39406 for configurable delivery policy. Thanks @Bartok9 and @Bortlesboat.</li>
<li>Control UI/agents: persist the Set Default action through <code>agents.list[].default</code> instead of writing the unsupported <code>agents.defaultId</code> field, so saved default-agent changes survive config validation. Fixes #65565; carries forward #72585. Thanks @luyao618.</li>
<li>NVIDIA/NIM: persist the <code>NVIDIA_API_KEY</code> provider marker and mark bundled NVIDIA Chat Completions models as string-content compatible, so NIM models load from <code>models.json</code> and OpenAI-compatible subagent calls send plain text content. Fixes #73013 and #50107; refs #73014. Thanks @bautrey, @iot2edge, @ifearghal, and @futhgar.</li>
<li>Channels/Discord: let text-only configs drop the <code>GuildVoiceStates</code> gateway intent and expose a bounded <code>/gateway/bot</code> metadata timeout with rate-limited fallback logs, reducing idle CPU and warning floods. Fixes #73709 and #73585. Thanks @sanchezm86 and @trac3r00.</li>
<li>Agents/sessions: mark same-turn <code>sessions_send</code> and A2A reply prompts with an inter-session <code>isUser=false</code> envelope before they reach the model, so foreign session output no longer lands as bare active user text. Fixes #73702; refs #73698, #73609, #73595, and #73622. Thanks @alvelda.</li>
<li>Channels/Telegram: fail closed when account-level public DM settings conflict with a restrictive top-level <code>allowFrom</code>, and require an effective wildcard before <code>dmPolicy="open"</code> behaves as public access. Fixes #73756; refs #73698. Thanks @Hilo-Hilo and @xace1825.</li>
<li>Channels/security: move open-DM allowlist semantics into the shared policy helpers and align Discord, Slack, Mattermost, Matrix, Feishu, LINE, IRC, Google Chat, Zalo, Zalo User, QQ Bot, and Synology Chat so <code>dmPolicy="open"</code> is public only with an effective wildcard and otherwise still respects sender allowlists. Refs #73756 and #73698. Thanks @Hilo-Hilo and @xace1825.</li>
<li>ACP/tasks: sweep orphaned parent-owned ACP sessions whose task records are gone, preserving bound persistent sessions but clearing unbound stale ACPX metadata so old child sessions cannot silently respawn into chat. Fixes #73609. Thanks @joerod26.</li>
<li>Outbound/security: strip known internal runtime scaffolding such as <code><system-reminder></code> and <code><previous_response></code> at the final channel delivery boundary and keep Discord output on targeted tag stripping, so degraded harness replies cannot leak those tags to users. Fixes #73595. Thanks @gabrielexito-stack and @martingarramon.</li>
<li>Security/Telegram: load Telegram security adapters in read-only audit/doctor, audit malformed Telegram DM <code>allowFrom</code> entries even when groups are disabled, and keep allowlist DM audits from counting stale pairing-store senders, so public/shared-DM risk checks stay accurate. Refs #73698. Thanks @xace1825.</li>
<li>Plugins: remove hidden manifest, provider-owner, bootstrap, and channel metadata caches so plugin installs, manifest edits, and bundled-root changes are visible on the next metadata read while keeping runtime/module loader caches for actual plugin code. Thanks @shakkernerd.</li>
<li>CLI/plugins: use plugin metadata snapshots for install slot selection and add opt-in plugin lifecycle timing traces, so plugin install avoids runtime-loading the plugin registry for metadata-only decisions. Thanks @shakkernerd.</li>
<li>fix(plugins): restrict bundled plugin dir resolution to trusted package roots. (#73275) Thanks @pgondhi987.</li>
<li>fix(security): prevent workspace PATH injection via service env and trash helpers. (#73264) Thanks @pgondhi987.</li>
<li>Active Memory: allow <code>allowedChatTypes</code> to include explicit portal/webchat sessions and classify <code>agent:...:explicit:...</code> session keys before opaque session ids can shadow the chat type. Fixes #65775. (#66285) Thanks @Lidang-Jiang.</li>
<li>Active Memory: allow the hidden recall sub-agent to use both <code>memory_recall</code> and the legacy <code>memory_search</code>/<code>memory_get</code> memory tool contract, so bundled <code>memory-lancedb</code> recall works without breaking the default <code>memory-core</code> path. Fixes #73502. (#73584) Thanks @Takhoffman.</li>
<li>fix(device-pairing): validate callerScopes against resolved token scopes on repair [AI]. (#72925) Thanks @pgondhi987.</li>
<li>Active Memory docs: document the <code>cacheTtlMs</code> 1000-120000 ms range and 15000 ms default so setup snippets do not lead users past the schema limit. Fixes #65708. (#65737) Thanks @WuKongAI-CMU.</li>
<li>fix(agents): canonicalize provider aliases in byProvider tool policy lookup [AI]. (#72917) Thanks @pgondhi987.</li>
<li>fix(security): block npm_execpath injection from workspace .env [AI-assisted]. (#73262) Thanks @pgondhi987.</li>
<li>Tools/web_fetch: decode response bodies from raw bytes using declared HTTP, XML, or HTML meta charsets before extraction, so Shift_JIS and other legacy-charset pages no longer return mojibake. Fixes #72916. Thanks @amknight.</li>
<li>Active Memory: skip payload-less <code>memory_search</code> transcript tool results when building debug telemetry, so newer empty entries no longer hide the latest useful debug payload. (#68773) Thanks @SimbaKingjoe.</li>
<li>Active Memory: keep recall setup time from consuming the configured model timeout while giving the hook runner an explicit bounded budget for the plugin, so slow embedded-run setup no longer causes immediate recall timeouts. Fixes #72606. (#72620) Thanks @hyspacex.</li>
<li>Channels/Discord: bound message read/search REST calls, route those actions through Gateway execution, and fall back to <code>CommandTargetSessionKey</code> for inbound hook session keys so Discord reads do not hang and hooks still fire when <code>SessionKey</code> is empty. Fixes #73431. (#73521) Thanks @amknight.</li>
<li>Plugins/media: auto-enable provider plugins referenced by <code>agents.defaults.imageGenerationModel</code>, <code>videoGenerationModel</code>, and <code>musicGenerationModel</code> primary/fallback refs, so configured Google and MiniMax media providers do not stay disabled behind a restrictive plugin allowlist. Thanks @vincentkoc.</li>
<li>Memory-core/dreaming: retry managed dreaming cron registration after startup when the cron service is not reachable yet, so the scheduled Memory Dreaming Promotion sweep recovers without waiting for heartbeat traffic. Fixes #72841. Thanks @amknight.</li>
<li>Acpx/runtime: validate the runtime session mode at the <code>AcpxRuntime.ensureSession</code> wrapper boundary so callers that pass anything other than <code>persistent</code> or <code>oneshot</code> get a clear <code>ACP_INVALID_RUNTIME_OPTION</code> error instead of silently round-tripping through the encoded handle as a default <code>persistent</code> mode and later throwing <code>SessionResumeRequiredError</code>. Investigation context: #73071. (#73548) Thanks @amknight.</li>
<li>CLI/infer: keep web-search fallback on missing provider API keys, preserve structured validation errors from the selected provider, and let per-request image describe prompts override configured media-entry prompts. (#63263) Thanks @Spolen23.</li>
<li>Chat commands: include configured model-catalog reasoning metadata when building <code>/think</code> argument menus so Ollama Cloud and other provider-owned reasoning models show supported levels instead of only <code>off</code>. Fixes #73515; supersedes #73568. Thanks @danielzinhu99 and @neeravmakwana.</li>
<li>Channels/Telegram: suppress generic tool-progress chatter when preview streaming is off, so non-streaming Telegram turns only deliver final replies while approvals, media, and errors still route normally. Refs #72363 and #72482. Thanks @neeravmakwana and @SweetSophia.</li>
<li>CLI/model probes: add repeatable image <code>--file</code> inputs to <code>infer model run</code> for local and gateway multimodal model smokes, so vision models such as Ollama Qwen VL and Gemini can be tested through the raw model-probe surface. Fixes #63700. Thanks @cedricjanssens.</li>
<li>CLI/model probes: request trusted operator scope for <code>infer model run --gateway --model <provider/model></code> so Gateway raw model smokes can use one-off provider/model overrides instead of being rejected before provider auth resolution. Fixes #73759. Thanks @chrislro.</li>
<li>CLI/image describe: pass <code>--prompt</code> and <code>--timeout-ms</code> through <code>infer image describe</code> and <code>describe-many</code>, so custom vision instructions and slow local model budgets reach media-understanding providers such as Ollama, OpenAI, Google, and OpenRouter. Refs #63700. Thanks @cedricjanssens.</li>
<li>Model selection: include the rejected provider/model ref and allowlist recovery hint when a stored session override is cleared, so local model selections such as Gemma GGUF variants do not fall back to the default with a generic message. Refs #71069. Thanks @CyberRaccoonTeam.</li>
<li>OpenAI-compatible providers: drop malformed event-only or blank-data SSE frames before the OpenAI SDK stream parser sees them, so proxies that split <code>event:</code> from <code>data:</code> no longer crash streaming runs with <code>Unexpected end of JSON input</code>. Fixes #52802. Thanks @LyHug.</li>
<li>Gateway/OpenAI-compatible streaming: strip <code><final></code> tags split across streamed model deltas before they reach SSE clients, so <code>/v1/chat/completions</code> no longer emits tag remnants or drops content when final-answer wrappers cross chunk boundaries. Fixes #63325. Thanks @tzwickl.</li>
<li>Ollama: resolve explicitly selected signed-in <code>:cloud</code> models through <code>/api/show</code> when <code>/api/tags</code> omits them, so working models such as <code>gemini-3-flash-preview:cloud</code> and <code>deepseek-v4-pro:cloud</code> do not fail dynamic model resolution before the native <code>/api/chat</code> transport runs. Fixes #73909. Thanks @chtse53.</li>
<li>Discord/exec approvals: keep the local <code>/approve</code> prompt when no native Discord approval runtime is active, and send a manual fallback notice when native approval delivery reaches no targets, so failed DM cards no longer leave approval turns silent or dependent on model-written shell commands. Fixes #73954; carries forward #74027. Thanks @guarismo and @brokemac79.</li>
<li>Local model prompt caching: keep stable Project Context above volatile channel/session prompt guidance and stop embedding current channel names in the message tool description, so Ollama, MLX, llama.cpp, and other prefix-cache backends avoid avoidable full prompt reprocessing across channel turns. Fixes #40256; supersedes #40296. Thanks @rhclaw and @sriram369.</li>
<li>Gateway/OpenAI-compatible API: guard provider policy lookup against runtime providers with non-array <code>models</code> values, so <code>/v1/chat/completions</code> no longer fails with <code>provider?.models?.some is not a function</code>. Fixes #66744; carries forward #66761. Thanks @MightyMoud, @MukundaKatta.</li>
<li>WhatsApp/Web: pass explicit Baileys socket timings into every WhatsApp Web socket and expose <code>web.whatsapp.*</code> keepalive, connect, and query timeout settings so unstable networks can avoid repeated 408 disconnect and opening-handshake timeout loops. Fixes #56365. (#73580) Thanks @velvet-shark.</li>
<li>WhatsApp/Web: recover recently active listeners when a post-408 reconnect keeps receiving transport frames but stops delivering app messages, while keeping group metadata fallback off Baileys sends. Fixes #63855 and #66920; refs #7433, #67986, #70856, #60007, and #72621. Thanks @legonhilltech-jpg, @octopuslabs-fl, @Kanorin-chan, and @stuswan.</li>
<li>Channels/Telegram: persist native command metadata on target sessions so topic, helper, and ACP-bound slash commands keep their session metadata attached to the routed conversation. (#57548) Thanks @GaosCode.</li>
<li>Channels/native commands: keep validated native slash command replies visible in group chats while preserving explicit owner allowlists for command authorization. (#73672) Thanks @obviyus.</li>
<li>Pairing/doctor: bootstrap <code>commands.ownerAllowFrom</code> from the first approved DM pairing when no command owner exists, and have doctor explain missing owners so privileged slash commands are not accidentally unusable after onboarding. Thanks @pashpashpash.</li>
<li>Telegram/exec: infer native exec approvers from <code>commands.ownerAllowFrom</code> and auto-enable the Telegram approval client when an owner is resolvable, so owner-only commands such as <code>/diagnostics</code> can be approved in Telegram without duplicate per-channel approver config. Thanks @pashpashpash.</li>
<li>Auto-reply/session: carry the tail of user/assistant turns into the freshly-rotated transcript on silent in-reply session resets (compaction failure, role-ordering conflict) so direct-chat continuity survives the rebind. Fixes #70853. (#70898) Thanks @neeravmakwana.</li>
<li>Skills: load grouped skill directories such as <code>skills/<group>/<skill>/SKILL.md</code> from configured skill roots while keeping grouped discovery capped for large directories. Fixes #56915. (#72534) Thanks @ottodeng, @MoerAI, and @i010542.</li>
<li>Config: skip malformed non-string <code>env.vars</code> entries before env-reference checks, so config loading no longer crashes on JSON values like numbers or booleans. (#42402) Thanks @MiltonHeYan.</li>
<li>Docker Compose: default missing config and workspace bind mounts to <code>${HOME:-/tmp}/.openclaw</code> so manual compose runs do not create invalid empty-source volume specs. (#64485) Thanks @jlapenna.</li>
<li>Agents/context engines: preserve the child agent's configured <code>agentDir</code> when subagent cleanup re-resolves a context engine, so <code>onSubagentEnded</code> hooks keep operating on the correct per-agent state. (#67243) Thanks @jarimustonen.</li>
<li>Channels/WhatsApp: restrict pairing verification replies to real inbound user content, preventing unsolicited prompts from receipts, typing indicators, presence updates, and other non-message Baileys upserts. Fixes #73797. (#73823) Thanks @hclsys.</li>
<li>Configure/Ollama: show the configured Ollama model allowlist after Cloud only or Cloud + Local setup and skip slow per-model cloud metadata fetches. (#73995) Thanks @obviyus.</li>
<li>Channels/WhatsApp: detect explicit group <code>@mentions</code> again when the bot's own E.164 is in <code>allowFrom</code>, so shared-number setups no longer skip group pings that directly mention the bot. Fixes #49317. (#73453) Thanks @juan-flores077.</li>
<li>WhatsApp/reliability: publish real transport-liveness into WhatsApp channel status and force earlier reconnects on silent transport stalls, so quiet healthy sessions stay connected while wedged sockets recover before the later remote 408 path. (#72656) Thanks @Sathvik-1007.</li>
<li>Core/channels: tighten selected runtime, media, and plugin edge-case handling while preserving existing behavior. Thanks @jesse-merhi.</li>
<li>Channels/WhatsApp: strip leaked plural tool-call XML wrappers on every WhatsApp-visible outbound path and keep channel error payloads out of WhatsApp chats. (#71830) Thanks @rubencu.</li>
<li>Agents/embedded-runner: inject the resolved OAuth bearer (and forward the run abort signal) on the boundary-aware embedded stream fallback so models that route through <code>openai-codex-responses</code> and other boundary-aware transports stop failing with <code>401 Unauthorized: Missing bearer or basic authentication in header</code>. Fixes #73559. (#73588) Thanks @openperf.</li>
<li>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.</li>
<li>Configure/GitHub Copilot: reuse existing Copilot auth during configure and show the provider's manifest model catalog in the model picker. (#74276) Thanks @obviyus.</li>
<li>Configure/models: keep the model picker scoped to the selected manifest provider and enable its bundled plugin before catalog lookup, so choosing GitHub Copilot no longer falls back to Ollama or skips the catalog. (#74322) Thanks @obviyus.</li>
<li>Auto-reply/subagents: reject <code>/focus</code> from leaf subagents and scope fallback target resolution to the requesting subagent's children, so subagents cannot bind conversations outside their control boundary. (#73613) Thanks @drobison00.</li>
<li>Gateway/startup: skip inherited workspace startup memory for sandboxed spawned sessions without real-workspace write access, so <code>/new</code> no longer preloads host workspace memory into isolated child runs. (#73611) Thanks @drobison00.</li>
<li>Agents/tool policy: validate caller group IDs against session or spawned context before applying group-scoped tool policies or persisting gateway group metadata, so forged group IDs cannot unlock more permissive tools. (#73720) Thanks @mmaps.</li>
<li>Commands: keep channel-prefixed owner allowlist entries scoped to matching providers so webchat command contexts cannot inherit external channel owners. Thanks @zsxsoft.</li>
<li>Auth/device pairing: bound bootstrap handoff token issuance, redemption, and approved pairing baselines to the documented per-role scope allowlist, so bootstrap approvals cannot persistently grant <code>operator.admin</code>, <code>operator.pairing</code>, or <code>node.exec</code> scopes. Thanks @eleqtrizit.</li>
<li>Providers/GitHub Copilot: support the GUI/RPC wizard device-code auth flow so onboarding from non-TTY clients (gateway RPC bridge, GUI wizards) completes instead of returning empty profiles. Dangerous-state handling now distinguishes <code>access_denied</code> and <code>expired_token</code> from transport errors. (#73290) Thanks @indierawk2k2.</li>
<li>Installer/Linux: warn before switching an unwritable npm global prefix to <code>~/.npm-global</code>, then tell users to run future global updates with <code>npm i -g openclaw@latest</code> without <code>sudo</code> so npm keeps using the redirected user prefix. Fixes #44365; carries forward #50479. Thanks @Sayeem3051.</li>
<li>Gateway/plugins: enable the native <code>require()</code> fast path on Windows for bundled plugin modules so plugin loading uses <code>require()</code> instead of Jiti's transform pipeline, reducing startup from ~39s to ~2s on typical 6-plugin setups. Fixes #68656. (#74173) Thanks @galiniliev.</li>
<li>macOS app: detect stale Gateway TLS certificate pins, automatically repair trusted Tailscale Serve rotations, and surface paired-but-disconnected Mac companion nodes so partial Gateway connections no longer look healthy. Thanks @guti.</li>
</ul>
<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
]]></description>
            <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.4.29/OpenClaw-2026.4.29.zip" length="50896802" type="application/octet-stream" sparkle:edSignature="YfQ25zMGgDv8XvHbdlL/s0SMJXyu763l5ppnfjiKOjSyxZY9sfoLaoXthcctFQDXA8isR1EEb/EEausu+XkFCA=="/>
        </item>
        <item>
            <title>2026.4.27</title>
            <pubDate>Wed, 29 Apr 2026 23:53:26 +0000</pubDate>
            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
            <sparkle:version>2026042790</sparkle:version>
            <sparkle:shortVersionString>2026.4.27</sparkle:shortVersionString>
            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
            <description><![CDATA[<h2>OpenClaw 2026.4.27</h2>
<h3>Changes</h3>
<ul>
<li>Sandbox/Docker: add opt-in <code>sandbox.docker.gpus</code> passthrough for Docker sandbox containers so local GPU workloads can run inside sandboxed agents when the host Docker runtime supports <code>--gpus</code>. Fixes #57976; carries forward #58124. Thanks @cyan-ember.</li>
<li>iOS/Gateway: add an authenticated <code>node.presence.alive</code> protocol event and <code>node.list</code> last-seen fields so background iOS wakes can mark paired nodes recently alive without treating them as connected. Carries forward #63123. Thanks @ngutman.</li>
<li>Android: publish authenticated <code>node.presence.alive</code> events after node connect and background transitions so paired Android nodes retain durable last-seen metadata after disconnects. Carries forward #63123. Thanks @ngutman.</li>
<li>Gateway/chat: accept non-image attachments through <code>chat.send</code> 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.</li>
<li>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.</li>
<li>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.</li>
<li>Matrix/QA: add live Matrix approval scenarios for exec metadata, chunked fallback, plugin approvals, deny reactions, thread targeting, and <code>target: "both"</code> delivery, with redacted artifacts preserving safe approval summaries. Thanks @gumadeiras.</li>
<li>Codex: add Computer Use setup for Codex-mode agents, including <code>/codex computer-use status/install</code>, marketplace discovery, optional auto-install, and fail-closed MCP server checks before Codex-mode turns start. Fixes #72094. (#71842) Thanks @pash-openai.</li>
<li>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.</li>
<li>Plugin SDK: expose shared channel route normalization, parser-driven target resolution, raw-target compact keys, parsed-target types, and route comparison helpers through <code>openclaw/plugin-sdk/channel-route</code>, 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.</li>
<li>Docs/Codex: document how Codex Computer Use, direct <code>cua-driver mcp</code>, and OpenClaw.app's PeekabooBridge fit together so desktop-control setup choices are clearer. Thanks @pash-openai and @trycua.</li>
<li>Matrix/streaming: stream tool-progress updates into live Matrix preview edits by default when preview streaming is active, with <code>streaming.preview.toolProgress: false</code> to keep answer previews while hiding interim tool lines. Thanks @gumadeiras.</li>
<li>Plugins/models: wire manifest <code>modelCatalog.aliases</code> and <code>modelCatalog.suppressions</code> 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.</li>
<li>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 <code>modelCatalog</code> rows. Thanks @shakkernerd.</li>
<li>Plugin SDK/models: move BytePlus and Volcano Engine standard and plan-provider catalogs into plugin manifest <code>modelCatalog</code> rows and remove the now-unused Volcengine-family shared catalog SDK subpath. Thanks @shakkernerd.</li>
<li>CLI/models: move Fireworks and Together AI fixed provider catalogs into plugin manifest <code>modelCatalog</code> rows so provider-filtered listing can use manifest-backed static rows. Thanks @shakkernerd.</li>
<li>Channels/Yuanbao: register the Tencent Yuanbao external channel plugin (<code>openclaw-plugin-yuanbao</code>) in the official channel catalog, contract suites, and community plugin docs, with a new <code>docs/channels/yuanbao.md</code> quick-start guide for WebSocket bot DMs and group chats. (#72756) Thanks @loongfay.</li>
<li>Channels/Yuanbao: add a channel docs entrance so the Tencent Yuanbao bot appears in the channel listing and sidebar navigation. (#73443) Thanks @loongfay.</li>
<li>Channels/QQBot: add full group chat support (history tracking, @-mention gating, activation modes, per-group config, FIFO message queue with deliver debounce), C2C <code>stream_messages</code> streaming with a <code>StreamingController</code> lifecycle manager, unified <code>sendMedia</code> 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 <code>createEngineAdapters()</code>. (#70624) Thanks @cxyhhhhh.</li>
<li>Plugins/startup: migrate bundled plugin manifests to explicit <code>activation.onStartup</code> declarations so Gateway startup imports only the bundled plugins that intentionally register startup-time runtime surfaces. Thanks @shakkernerd.</li>
<li>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.</li>
<li>Plugins/startup: add plugin compatibility warnings for deprecated implicit startup loading so authors can migrate to explicit <code>activation.onStartup</code> metadata. Thanks @shakkernerd.</li>
<li>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.</li>
<li>Plugins/startup: add explicit <code>activation.onStartup</code> metadata so plugins can declare Gateway startup import behavior while the deprecated implicit sidecar fallback remains for legacy plugins. Thanks @shakkernerd.</li>
<li>Gateway/startup: reuse lookup-table plugin manifests when loading startup plugins so Gateway boot avoids rebuilding plugin discovery and manifest metadata. Thanks @shakkernerd.</li>
<li>CLI/models: declare fixed Qianfan, Xiaomi, NVIDIA, Cerebras, Mistral, Chutes, Kilo, OpenAI, and OpenCode Go model catalogs in refreshable plugin manifests, keep broad <code>models list --all</code> on raw registry and supplement rows without runtime normalization, and avoid duplicate supplement resolution. Thanks @shakkernerd.</li>
<li>Gateway/runtime: reuse the current plugin metadata snapshot for provider discovery so repeated model-provider discovery avoids rebuilding plugin manifest metadata. Thanks @shakkernerd.</li>
<li>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.</li>
<li>Plugin SDK/testing: move core-only channel contract fixtures under the channel contract test tree and retire the old <code>test/helpers/channels</code> bridge directory so plugin tests stay on focused SDK surfaces. Thanks @vincentkoc.</li>
<li>Plugin SDK/testing: expose native agent-runtime contract fixtures through <code>plugin-sdk/agent-runtime-test-contracts</code>, move sandbox config fixtures into the focused generic fixture subpath, and block extension tests from importing repo-only <code>test/helpers</code> bridges. Thanks @vincentkoc.</li>
<li>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.</li>
<li>Plugin SDK: move maintained bundled channels off the deprecated <code>channel-config-schema-legacy</code> subpath, add an explicit bundled-channel schema SDK surface, and track both remaining legacy test/config compatibility barrels with dated removal windows. Thanks @vincentkoc.</li>
<li>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.</li>
<li>Plugin SDK/testing: promote bundled plugin/provider/channel contract helpers to focused SDK test subpaths and retire the repo-only <code>test/helpers/plugins</code> TypeScript bridge. Thanks @vincentkoc.</li>
<li>Plugin SDK/testing: expose generic channel action, setup, status, and directory contract helpers through <code>plugin-sdk/channel-test-helpers</code> so bundled extension tests no longer import repo-only channel helper bridges. Thanks @vincentkoc.</li>
<li>Plugin SDK/testing: add <code>plugin-sdk/channel-target-testing</code> for shared channel target-resolution cases, document channel reaction helpers on <code>plugin-sdk/channel-feedback</code>, and keep the old <code>plugin-sdk/test-utils</code> alias as compatibility-only. Thanks @vincentkoc.</li>
<li>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.</li>
<li>Plugin SDK/testing: add focused plugin runtime and environment fixture subpaths so plugin tests can avoid the broad <code>plugin-sdk/testing</code> barrel for common setup helpers. Thanks @vincentkoc.</li>
<li>Plugin SDK/testing: add a focused <code>plugin-sdk/plugin-test-api</code> helper subpath and move bundled plugin registration tests off the repo-only plugin API bridge. Thanks @vincentkoc.</li>
<li>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.</li>
<li>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 <code>src/**</code> internals. Thanks @vincentkoc.</li>
<li>Providers/DeepInfra: add a bundled DeepInfra provider with <code>DEEPINFRA_API_KEY</code> 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.</li>
<li>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.</li>
</ul>
<h3>Fixes</h3>
<ul>
<li>Gateway/sessions: align <code>chat.history</code> and <code>sessions.list</code> thinking defaults with owning-agent and catalog-aware resolution so Control UI session defaults match backend runtime state. (#63418) Thanks @jpreagan.</li>
<li>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.</li>
<li>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.</li>
<li>Gateway/approvals: treat duplicate same-decision approval resolves as idempotent during the resolved-entry grace window, including consumed <code>allow-once</code> approvals, while returning an explicit already-resolved error for conflicting repeats. Fixes #59162; refs #58479 and #65486. Thanks @wikithoughts, @sajazuniga7-coder, and @mjmai20682068-create.</li>
<li>Channels/Telegram: honor <code>approvals.exec/plugin.targets[].accountId</code> when routing native approvals across multi-bot Telegram accounts while preserving unscoped Telegram targets for any account. Fixes #69916. Thanks @joerod26.</li>
<li>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.</li>
<li>Agents/exec: omit the internal session-resume fallback preface from successful async exec completion messages sent directly back to chat. Fixes #67181. Thanks @raistlin88.</li>
<li>Agents/media: register detached <code>video_generate</code> and <code>music_generate</code> tool run contexts until terminal status, so Discord-backed provider jobs stay live in <code>/tasks</code> instead of becoming <code>lost</code> when the parent chat run context disappears. Thanks @vincentkoc.</li>
<li>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.</li>
<li>Tasks/media: infer agent ownership for session-scoped task records so <code>/tasks</code> agent-local fallback includes session-backed <code>video_generate</code> and other async media jobs even when the current chat session has no linked rows. Thanks @vincentkoc.</li>
<li>Agents/media: keep long-running <code>video_generate</code> and <code>music_generate</code> tasks fresh while provider jobs are still pending, so task maintenance does not mark active Discord media renders lost before completion. Thanks @vincentkoc.</li>
<li>CLI/status: treat scope-limited gateway probes as reachable-but-degraded in shared status scans, so <code>openclaw status --all</code> no longer reports a live gateway as unreachable after <code>missing scope: operator.read</code>. Fixes #49180; supersedes #47981. Thanks @openjay.</li>
<li>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.</li>
<li>Slack/Socket Mode: use a 15s Slack SDK pong timeout by default and add <code>channels.slack.socketMode.clientPingTimeout</code>, <code>serverPingTimeout</code>, and <code>pingPongLoggingEnabled</code> overrides so stale-websocket handling no longer depends on app-event health heuristics. Fixes #14248; refs #58519, #64009, and #63488. Thanks @shivasymbl and @freerk.</li>
<li>Slack/media: bound private file and forwarded attachment downloads with idle and total timeouts while preserving placeholder fallback, so stalled Slack <code>file_share</code> media no longer wedges inbound message handling. Fixes #61850. Thanks @bassboy2k.</li>
<li>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.</li>
<li>Slack/auto-reply: keep fully consumed text reset triggers such as <code>new session</code> out of <code>BodyForAgent</code> after directive cleanup, so configured Slack reset phrases do not leak into the fresh model turn. Fixes #73137. Thanks @neeravmakwana.</li>
<li>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.</li>
<li>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.</li>
<li>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.</li>
<li>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.</li>
<li>Gateway/install: carry env-backed config SecretRefs such as <code>channels.discord.token</code> 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.</li>
<li>Auto-reply/commands: stop bare <code>/reset</code> and <code>/new</code> after reset hooks acknowledge the command, so non-ACP channels no longer fall through into empty provider calls while <code>/reset <message></code> and <code>/new <message></code> still seed the next model turn. Fixes #73367 and #73412. Thanks @hoyanhan, @wenxu007, and @amdhelper.</li>
<li>Providers/DeepSeek: backfill DeepSeek V4 <code>reasoning_content</code> 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.</li>
<li>Agents/gateway tool: strip full config payloads from <code>config.patch</code> and <code>config.apply</code> 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.</li>
<li>Auto-reply: preserve voice-note media from silent turns while continuing to suppress text and non-voice media, so <code>NO_REPLY</code> TTS replies still deliver the requested audio bubble. (#73406) Thanks @zqchris.</li>
<li>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 <code>System: Mattermost message...</code> directives. Fixes #71795. Thanks @juan-flores077.</li>
<li>Agents/media: qualify bare <code>agents.defaults.imageModel</code> and <code>pdfModel</code> refs from unique configured image-capable providers, so Ollama vision models such as <code>moondream</code> and <code>qwen2.5vl:7b</code> do not fall through to the default provider. Fixes #38816; supersedes #73396. Thanks @alainasclaw and @vincentkoc.</li>
<li>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.</li>
<li>Skills: require explicit <code>skills.entries.coding-agent.enabled</code> 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.</li>
<li>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 <code>plugins.entries.workspace</code> warnings during Gateway startup. Fixes #73433. Thanks @AnneVoss.</li>
<li>Agents/subagents: preserve <code>sessions_yield</code> 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 <code>(no output)</code>. Fixes #73413. Thanks @Ask-sola.</li>
<li>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.</li>
<li>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.</li>
<li>Channels/LINE: persist inbound image, video, audio, and file downloads in <code>~/.openclaw/media/inbound/</code> instead of temporary files so agents can still read LINE media after <code>/tmp</code> cleanup. Fixes #73370. Thanks @hijirii and @wenxu007.</li>
<li>CLI/plugins: keep bundled plugin installs out of <code>plugins.load.paths</code> while preserving install records, so install/inspect/doctor loops no longer warn about the current bundled plugin directory. Thanks @vincentkoc.</li>
<li>CLI/plugins: scope <code>plugins inspect <id></code> runtime loading to the matched plugin so single-plugin inspection does not load every plugin before checking the target. Thanks @shakkernerd.</li>
<li>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.</li>
<li>Cron tool: infer the creating session's agentId for <code>cron.add</code> jobs when <code>agentId</code> 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.</li>
<li>Cron/Telegram: add <code>--thread-id</code> to <code>openclaw cron add</code> and <code>openclaw cron edit</code>, preserving Telegram forum topic delivery targets across scheduled announcements. Carries forward #51581, #60373, and #60890. Thanks @ChunHao-dev.</li>
<li>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.</li>
<li>Memory/compaction: keep pre-compaction memory-flush prompts runtime-only so session transcripts and <code>chat.history</code> no longer expose them as normal user turns. Fixes #54408 and #58956; refs #43567. Thanks @markgong and @guoyuhang9.</li>
<li>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 <code>RangeError: Maximum call stack size exceeded</code>. Fixes #73360; refs #54378 and #63432. Thanks @hejunhui-73, @Ansub, and @christianhernandez3-afk.</li>
<li>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 <code>reader.read()</code>. Refs #72965 and #73120. Thanks @wdeveloper16.</li>
<li>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.</li>
<li>Sandbox/Docker: stop satisfying a missing default sandbox image by tagging plain Debian as <code>openclaw-sandbox:bookworm-slim</code>, 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.</li>
<li>Control UI/WebChat: confirm toolbar New Session button resets before dispatching <code>/new</code> while leaving typed <code>/new</code> and <code>/reset</code> commands immediate. Fixes #45800; refs #27065, #56611, #54499, and #27110. Thanks @aethnova, @kosta228-huli, @adambezemek, and @xss925175263 (xianshishan).</li>
<li>Agents/models: keep per-agent primary models strict when <code>fallbacks</code> is omitted, so probe-only custom providers are not tried as hidden fallback candidates unless the agent explicitly opts in. Fixes #73332. Thanks @haumanto.</li>
<li>Gateway/models: add <code>models.pricing.enabled</code> 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.</li>
<li>Gateway/startup: warn when legacy <code>CLAWDBOT_*</code> or <code>MOLTBOT_*</code> environment variables are still present, pointing users to <code>OPENCLAW_*</code> names instead of failing silently. Fixes #53482; carries forward #53667. Thanks @lndyzwdxhs.</li>
<li>Onboarding: pin interactive and non-interactive health checks to the just-configured setup token/password so stale <code>OPENCLAW_GATEWAY_TOKEN</code> or <code>OPENCLAW_GATEWAY_PASSWORD</code> values do not produce false gateway-token-mismatch failures after setup. Fixes #72203. Thanks @galiniliev.</li>
<li>Doctor/state: require an interactive confirmation before archiving orphan transcript files, so <code>openclaw doctor --fix</code> no longer silently renames recoverable session history after upgrades regenerate <code>sessions.json</code>. Fixes #73106. Thanks @scottgl9.</li>
<li>Cron/Telegram: preserve explicit <code>:topic:</code> 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.</li>
<li>Build/runtime: write the runtime-postbuild stamp after <code>pnpm build</code> writes the build stamp, so the next CLI invocation does not re-sync runtime artifacts after a successful build. Fixes #73151. Thanks @bittoby.</li>
<li>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.</li>
<li>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 <code>openclaw channels list</code> shows Telegram accounts before auth providers. Fixes #73319 and #73322. Thanks @mlaihk.</li>
<li>CLI/model probes: keep <code>infer model run --gateway</code> 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.</li>
<li>CLI/image describe: pass <code>--prompt</code> and <code>--timeout-ms</code> through <code>infer image describe</code> and <code>describe-many</code>, so custom vision instructions and slow local model budgets reach media-understanding providers such as Ollama, OpenAI, Google, and OpenRouter. Addresses #63700. Thanks @cedricjanssens.</li>
<li>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.</li>
<li>CLI/model probes: reject empty or whitespace-only <code>infer model run --prompt</code> values before calling local providers or the Gateway, so smoke checks do not spend provider calls on invalid turns. Fixes #73185. Thanks @iot2edge.</li>
<li>Gateway/media: route text-only <code>chat.send</code> image offloads through media-understanding fields so <code>agents.defaults.imageModel</code> can describe WebChat attachments instead of leaving only an opaque <code>media://inbound</code> marker. Fixes #72968. Thanks @vorajeeah.</li>
<li>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.</li>
<li>Gateway/model pricing: skip plugin manifest discovery during background pricing refreshes when <code>plugins.enabled: false</code>, so disabled-plugin setups do not keep rebuilding plugin metadata from the Gateway hot path. Fixes #73291. Thanks @slideshow-dingo and @fishgills.</li>
<li>Ollama/thinking: validate <code>/think</code> commands against live Ollama catalog reasoning metadata and preserve explicit native <code>params.think</code>/<code>params.thinking</code>, so models whose <code>/api/show</code> capabilities include <code>thinking</code> expose <code>low</code>, <code>medium</code>, <code>high</code>, and <code>max</code> instead of being stuck on <code>off</code>. Fixes #73366. Thanks @cymise.</li>
<li>Gateway/sessions: remove automatic oversized <code>sessions.json</code> rotation backups, deprecate <code>session.maintenance.rotateBytes</code>, and teach <code>openclaw doctor --fix</code> to remove the ignored key so hot session writes no longer copy multi-MB stores. Refs #72338. Thanks @midhunmonachan and @DougButdorf.</li>
<li>Channels/Telegram: fail fast when Telegram rejects the startup <code>getMe</code> token probe with 401, so invalid or stale BotFather tokens are reported as token auth failures instead of misleading <code>deleteWebhook</code> cleanup failures. Fixes #47674. Thanks @samaedan-arch.</li>
<li>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.</li>
<li>CLI/onboarding: infer image input for common custom-provider vision model IDs, ask only for unknown models, and keep <code>--custom-image-input</code>/<code>--custom-text-input</code> overrides so vision-capable proxies do not get saved as text-only configs. Fixes #51869. Thanks @Antsoldier1974.</li>
<li>Models/OpenAI Codex: stop listing or resolving unsupported <code>openai-codex/gpt-5.4-mini</code> rows through Codex OAuth, keep stale discovery rows suppressed with a clear API-key-route hint, and leave direct <code>openai/gpt-5.4-mini</code> available. Fixes #73242. Thanks @0xCyda.</li>
<li>Plugin SDK: restore the root <code>stringEnum</code> and <code>optionalStringEnum</code> 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.</li>
<li>Plugin SDK: restore the root-alias bridge for <code>registerContextEngine</code> and expose missing legacy compat helpers <code>normalizeAccountId</code> and <code>resolvePreferredOpenClawTmpDir</code> so older external plugins such as <code>openclaw-weixin</code> can keep loading while migrating to focused SDK subpaths. Fixes #53497. Thanks @alanxchen85.</li>
<li>Auth profiles: make <code>openclaw doctor --fix</code> migrate legacy flat <code>auth-profiles.json</code> files such as <code>{ "ollama-windows": { "apiKey": "ollama-local" } }</code> 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.</li>
<li>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.</li>
<li>Feishu/inbound files: recover CJK filenames from plain <code>Content-Disposition: filename=</code> 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.</li>
<li>Channels/Telegram: normalize accidental full <code>/bot<TOKEN></code> Telegram <code>apiRoot</code> values at runtime and teach <code>openclaw doctor --fix</code> 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.</li>
<li>Zalo Personal: persist refreshed <code>zca-js</code> session cookies after QR login, session restore, and successful API calls so gateway restarts restore the freshest local session. (#73277) Thanks @darkamenosa.</li>
<li>Logging/security: redact sensitive tokens (sk-\* keys, Bearer/Authorization values, etc.) at the subsystem console sink so <code>createSubsystemLogger().info/warn/error</code> 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.</li>
<li>Plugins/runtime deps: reuse enclosing versioned cache roots when bundled plugins resolve from nested staged paths, so plugin-runtime-deps no longer mints <code>openclaw-unknown-*</code> directories or loops on <code>ENOTEMPTY</code>. Fixes #72956. (#73205) Thanks @SymbolStar.</li>
<li>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.</li>
<li>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.</li>
<li>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 <code>--mcp-config</code> directory until the live subprocess closes. Fixes #73244. Thanks @edwin-rivera-dev.</li>
<li>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.</li>
<li>Agents/cron: clarify agent-tool and CLI cron timezone guidance so supplied <code>tz</code> values use local wall-clock cron fields and omitted cron <code>tz</code> falls back to the Gateway host local timezone. Fixes #53669; carries forward #46177. (#73372) Thanks @chen-zhang-cs-code and @maranello-o.</li>
<li>Providers/Qwen: allow explicitly configured <code>qwen/qwen3.6-plus</code> 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.</li>
<li>Channels/Telegram: keep Bot API network fallbacks sticky after failed attempts and retry timed-out startup control calls once on the fallback route, so <code>deleteWebhook</code> IPv6 stalls no longer trigger slow multi-account retry storms. Fixes #73255. Thanks @ttomiczek and @sktbrd.</li>
<li>Gateway/agents: accept heartbeat, cron, and webhook as internal channel hints for agent runs so <code>sessions_spawn</code> works from non-delivery parent sessions while unknown channel hints still fail closed. Fixes #73237. Thanks @KeWang0622.</li>
<li>Gateway/models: merge explicit <code>models.providers.*.models</code> 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.</li>
<li>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.</li>
<li>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.</li>
<li>CLI/tasks: ship the task-registry control runtime in npm packages so <code>openclaw tasks cancel</code> can load ACP/subagent cancellation helpers from published builds. Fixes #68997. Thanks @1OAKDesign.</li>
<li>Channels/Telegram: preserve unsent generated media after partial reply streaming has already delivered the text, so <code>image_generate</code> outputs still reach Telegram as photos instead of being dropped from the final payload. Fixes #73253. Thanks @mlaihk.</li>
<li>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.</li>
<li>CLI/agents: close local one-shot Claude live stdio sessions and bundled MCP loopback resources after embedded <code>openclaw agent --local</code> runs, while keeping gateway-owned MCP loopback cleanup internal to the Gateway. Thanks @frankekn.</li>
<li>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.</li>
<li>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 <code>npx</code> adapter resolution. Fixes #73202. Thanks @joerod26.</li>
<li>Memory/compaction: let pre-compaction memory flush use an exact <code>agents.defaults.compaction.memoryFlush.model</code> override such as <code>ollama/qwen3:8b</code> without inheriting the active session fallback chain, so local housekeeping can avoid paid conversation models. Fixes #53772. Thanks @limen96.</li>
<li>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.</li>
<li>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 <code>test_speech</code> report fresh realtime output-byte verification instead of only confirming a queued utterance. Refs #72478. Thanks @DougButdorf.</li>
<li>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.</li>
<li>Control UI/models: request the configured Gateway model-list view so dashboards with only <code>models.providers.*.models</code> show those configured models first instead of flooding the picker with the full built-in catalog. Fixes #65405. Thanks @wbyanclaw.</li>
<li>CLI/models: keep default-model and allowlist pickers on explicit <code>models.providers.*.models</code> entries when <code>models.mode</code> is <code>replace</code> instead of loading the full built-in catalog. Fixes #64950. Thanks @mrozentsvayg.</li>
<li>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.</li>
<li>Discord: own the Carbon interaction listener and hand off Discord slash/component handling asynchronously, so compaction or long session locks no longer trip <code>InteractionEventListener</code> listener timeouts. Fixes #73204. Thanks @slideshow-dingo.</li>
<li>Compaction/diagnostics: keep unknown compaction failure classifications stable while logging sanitized detail for unclassified provider errors such as missing Ollama provider adapters. Thanks @gzsiang.</li>
<li>Models/fallbacks: record first-class <code>model.fallback_step</code> 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.</li>
<li>Gateway/agents: block agent <code>exec</code> from launching interactive <code>openclaw channels login</code> 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.</li>
<li>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.</li>
<li>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.</li>
<li>Heartbeat/models: show heartbeat model bleed guidance on context-overflow resets when the last runtime model matches configured <code>heartbeat.model</code>, so smaller local heartbeat models point users to <code>isolatedSession</code> or <code>lightContext</code> instead of only compaction-buffer tuning. Fixes #67314. Thanks @Knightmare6890.</li>
<li>Subagents/models: persist <code>sessions_spawn.model</code> 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.</li>
<li>Channels/Telegram: keep webhook-mode local listeners alive and retry Telegram <code>setWebhook</code> 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.</li>
<li>Agents/ACPX: bundle the Codex ACP adapter and launch it from the isolated <code>CODEX_HOME</code> wrapper before falling back to npm, so Codex ACP startup no longer depends on live <code>npx</code> resolution or the stale <code>@zed-industries/codex-acp@^0.11.1</code> range. Fixes #72037; refs #73202. Thanks @jasonftl, @sazora, and @joerod26.</li>
<li>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.</li>
<li>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 <code>actual unavailable</code>. Thanks @ProspectOre.</li>
<li>Backup: skip installed plugin <code>extensions/*/node_modules</code> dependency trees while keeping plugin manifests and source files in archives, so local backups avoid rebuildable npm payload bloat. Fixes #64144. Thanks @BrilliantWang.</li>
<li>Cron/models: fail isolated cron runs closed when an explicit <code>payload.model</code> 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.</li>
<li>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.</li>
<li>Talk Mode: resolve <code>messages.tts.providers.<id>.apiKey</code> through the active runtime snapshot for <code>talk.config</code>, so Talk overlays can discover SecretRef-backed speech providers without falling back to local speech. Fixes #73109. (#73111) Thanks @omarshahine.</li>
<li>Memory/Ollama: resolve <code>memorySearch.provider</code> custom provider ids through their configured <code>models.providers.<id>.api</code> owner, so multi-GPU Ollama setups can dedicate embeddings to providers such as <code>ollama-5080</code> without losing the Ollama adapter or local auth semantics. Fixes #73150. Thanks @oneandrewwang.</li>
<li>CLI/memory: skip eager context-window warmup for <code>openclaw memory</code> commands so memory search does not race unrelated model metadata discovery. Fixes #73123. Thanks @oalansilva and @neeravmakwana.</li>
<li>CLI/Telegram: route Telegram <code>message send</code> and poll actions through the running Gateway when available, so packaged installs use the staged <code>grammy</code> runtime deps and CLI sends return instead of hanging after the Telegram channel is active. Fixes #73140. Thanks @oalansilva.</li>
<li>Plugins/runtime deps: prepare staged bundled plugin dependencies before loading packaged public surfaces, so OpenClaw's Telegram runtime/test facade loads resolve <code>grammy</code> from the managed runtime-deps stage without copying dependencies into the global package root. Refs #73140. Thanks @oalansilva.</li>
<li>Agents/exec: emit <code>(no output)</code> 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.</li>
<li>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.</li>
<li>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.</li>
<li>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 <code>openclaw-lark</code>. Fixes #56794. Thanks @wuji-tech-dev.</li>
<li>CLI/status: show skipped fast-path memory checks as <code>not checked</code> and report active custom memory plugin runtime status from <code>status --json --all</code> without requiring built-in <code>agents.defaults.memorySearch</code>, 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.</li>
<li>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.</li>
<li>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; <code>messages.groupChat.visibleReplies: "automatic"</code> restores legacy auto-posting. (#73046) Thanks @scoootscooob.</li>
<li>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.</li>
<li>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.</li>
<li>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.</li>
<li>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.</li>
<li>Memory/LanceDB: let embedding config use provider-backed auth profiles, environment credentials, or provider config without a separate plugin <code>embedding.apiKey</code>, so OAuth-capable embedding providers can power auto-recall/capture. Fixes #68950. Thanks @malshaalan-ai.</li>
<li>CLI/parents: invoking <code>openclaw <parent></code> (memory, channels, plugins, approvals, devices, cron, mcp) without a subcommand now prints the parent's help and exits <code>0</code>, matching <code><parent> --help</code> and the existing <code>agents</code> / <code>sessions</code> defaults so shell <code>&&</code> chains and pnpm wrappers no longer surface a misleading <code>ELIFECYCLE Command failed with exit code 1.</code> line. Fixes #73077. Thanks @hclsys.</li>
<li>Plugins/hooks: time out never-settling <code>agent_end</code> 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.</li>
<li>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 <code>config.get</code>/<code>config.schema</code>, preventing idle plugin-discovery CPU churn after upgrades. Fixes #73088. Thanks @sleitor and @geovansb.</li>
<li>Memory/LanceDB: call OpenAI-compatible embedding endpoints through the raw SDK transport without sending <code>encoding_format</code>, 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.</li>
<li>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 <code>npm install failed:</code> with no detail. (#73093) Thanks @sanctrl.</li>
<li>Memory/LanceDB: bound memory recall embedding queries with a new <code>recallMaxChars</code> 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.</li>
<li>CLI/skills: resolve workspace-backed skills commands from <code>--agent</code>, 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.</li>
<li>Plugin SDK: fall back from partial bundled plugin directory overrides to package source public surfaces while preserving <code>OPENCLAW_DISABLE_BUNDLED_PLUGINS</code> as a hard disable. (#72817) Thanks @serkonyc.</li>
<li>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.</li>
<li>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.</li>
<li>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.</li>
<li>Memory/Ollama: add <code>memorySearch.remote.nonBatchConcurrency</code> 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.</li>
<li>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.</li>
<li>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.</li>
<li>Agents/models: keep <code>models.json</code> readiness and provider-hook caches warm across repeated agent and subagent model resolution while preserving external <code>models.json</code> invalidation, reducing repeated provider-plugin loads on slower ARM64 hosts. Fixes #73075. Thanks @jochen.</li>
<li>Docs/tools: clarify that <code>tools.profile: "messaging"</code> is intentionally narrow and that <code>tools.profile: "full"</code> is the unrestricted baseline for broader command/control access. Carries forward #39954. Thanks @posigit.</li>
<li>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.</li>
<li>Agents/sessions: keep <code>sessions_history</code> recall redaction enabled even when general log redaction is disabled, and clarify that safety-boundary UI/tool/diagnostic payloads still redact independently of <code>logging.redactSensitive</code>. Carries forward #72319. Thanks @volcano303 and @BunsDev.</li>
<li>Providers/Codex: pass agent and workspace directories into provider stream wrappers so Codex native <code>web_search</code> 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.</li>
<li>Cron/models: keep <code>payload.model</code> as a per-job primary that can use configured fallbacks, while still letting <code>payload.fallbacks: []</code> make cron runs strict and avoid hidden agent-primary retries. Refs #73023. Thanks @pavelyortho-cyber.</li>
<li>Models/fallbacks: treat user-selected session models as exact choices, so <code>/model ollama/...</code> 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.</li>
<li>Codex harness: keep ChatGPT subscription app-server runs from inheriting <code>CODEX_API_KEY</code> or <code>OPENAI_API_KEY</code>, and fall back to <code>CODEX_API_KEY</code> / <code>OPENAI_API_KEY</code> app-server login only when no Codex account is available. Fixes #73057. Thanks @holgergruenhagen and @pashpashpash.</li>
<li>CLI/model probes: fail local <code>infer model run</code> 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.</li>
<li>CLI/Ollama: run local <code>infer model run</code> 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 <code>/api/chat</code> request. Fixes #72851. Thanks @TotalRes2020.</li>
<li>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.</li>
<li>Daemon/service: only emit hard-coded version-manager paths such as <code>~/.volta/bin</code>, <code>~/.asdf/shims</code>, <code>~/.bun/bin</code>, and fnm/pnpm fallbacks into gateway and node service PATHs when the directories exist, so <code>openclaw doctor</code> no longer flags <code>gateway.path.non-minimal</code> against a PATH the daemon just wrote. Env-driven roots and stable user-bin dirs remain unconditional. Fixes #71944; carries forward #71964. Thanks @Sanjays2402.</li>
<li>CLI/startup: disable Node's module compile cache automatically for live source-checkout launchers so in-place <code>pnpm build</code> updates are visible to the next <code>openclaw</code> CLI invocation. Fixes #73037. Thanks @LouisGameDev.</li>
<li>Agents/group chat: keep silent-allowed empty and reasoning-only turns on the <code>NO_REPLY</code> path without injecting visible-answer retry prompts, and clarify the group prompt so agents use the exact silent token instead of prose. Thanks @vincentkoc.</li>
<li>Agents/group chat: move <code>NO_REPLY</code> 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.</li>
<li>Providers/OpenAI: preserve encrypted empty-summary Responses reasoning items in WebSocket replay and request <code>reasoning.encrypted_content</code> on reasoning turns so GPT-5.4/GPT-5.5 sessions do not lose required <code>rs_*</code> state beside <code>msg_*</code> items. Fixes #73053. Thanks @odb36777.</li>
<li>Gateway/startup: treat <code>plugins.enabled=false</code> 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.</li>
<li>Channels/commands: make generated <code>/dock-*</code> commands switch the active session reply route through <code>session.identityLinks</code> instead of falling through to normal chat. Fixes #69206; carries forward #73033. Thanks @clawbones and @michaelatamuk.</li>
<li>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.</li>
<li>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 <code>gateway_start</code> hook is registered, so clean post-ready sidecar work stays off the critical path. Refs #72846. Thanks @RayWoo, @livekm0309, and @mrz1836.</li>
<li>Gateway/channels: start bundled channel accounts with a lightweight <code>runtimeContexts</code> surface instead of importing the full reply/routing/session channel runtime before <code>startAccount</code>, 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.</li>
<li>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.</li>
<li>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.</li>
<li>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.</li>
<li>CLI/status: keep default <code>openclaw status</code> 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.</li>
<li>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.</li>
<li>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.</li>
<li>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.</li>
<li>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.</li>
<li>Gateway/auth: add explicit <code>trustedProxy.allowLoopback</code> 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.</li>
<li>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.</li>
<li>Cron: accept <code>delivery.threadId</code> 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.</li>
<li>Plugins/runtime deps: stage bundled plugin dependencies imported by mirrored root dist chunks, so packaged memory and status commands do not miss <code>chokidar</code> or similar root-chunk dependencies after update. Fixes #72882 and #72970; carries forward #72992. Thanks @shrimpy8, @colin-chang, and @Schnup03.</li>
<li>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.</li>
<li>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.</li>
<li>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.</li>
<li>CLI/message: resolve targeted <code>openclaw message</code> 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.</li>
<li>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.</li>
<li>CLI/models: keep route-first <code>models status --json</code> stdout reserved for the JSON payload by routing auth-profile and startup diagnostics to stderr. Fixes #72962. Thanks @vishutdhar.</li>
<li>Gateway/runtime: keep dirty-tree status calls from rebuilding live <code>dist</code>, 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.</li>
<li>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.</li>
<li>Sessions: ignore future-dated session activity timestamps during reset freshness checks and cap future <code>updatedAt</code> values at the merge boundary so clock-skewed messages cannot keep stale sessions alive forever. Fixes #72989. Thanks @martingarramon.</li>
<li>Sessions: apply search, activity filters, and limits before gateway row enrichment so bounded session lists avoid scanning discarded transcripts. Carries forward #72978. Thanks @yeager.</li>
<li>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.</li>
<li>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.</li>
<li>Providers/Ollama: mark discovered Ollama catalog models as supporting streaming usage metadata so token accounting stays enabled for local models. (#72976) Thanks @sdeyang.</li>
<li>Media understanding: reject malformed MIME values with trailing junk while preserving standard parameter tails before enrichment uses them. (#72914) Thanks @volcano303.</li>
<li>WebChat: keep bare <code>/new</code> and <code>/reset</code> prompts from producing empty transcript text by inserting the hidden session marker when the visible tail is blank. (#72863) Thanks @mahopan.</li>
<li>CLI/update: explain completion-cache refresh timeouts with manual refresh guidance instead of surfacing a raw low-level timeout. Fixes #72842. (#72850) Thanks @iot2edge.</li>
<li>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.</li>
<li>Plugins/hooks: inject each plugin's resolved config into internal hook event context without mutating the shared event object. (#72888) Thanks @jalapeno777.</li>
<li>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.</li>
<li>Gateway/Bonjour: truncate mDNS service names and host labels to the 63-byte DNS label limit at valid UTF-8 boundaries. (#72809) Thanks @luyao618.</li>
<li>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.</li>
<li>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.</li>
<li>WebChat: read <code>chat.history</code> 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.</li>
<li>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.</li>
<li>Agents/LSP: terminate bundled stdio LSP process trees during runtime disposal and Gateway shutdown, so nested children such as <code>tsserver</code> do not survive stop or restart. Fixes #72357. Thanks @ai-hpc and @bittoby.</li>
<li>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.</li>
<li>Logging: write validated diagnostic trace context as top-level <code>traceId</code>, <code>spanId</code>, <code>parentSpanId</code>, and <code>traceFlags</code> fields in file-log JSONL records so traced requests and model calls are easier to correlate in log processors. Refs #40353. Thanks @liangruochong44-ui.</li>
<li>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.</li>
<li>Providers/Ollama: honor <code>/api/show</code> 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.</li>
<li>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.</li>
<li>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.</li>
<li>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.</li>
<li>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.</li>
<li>Plugins/startup: load the default <code>memory-core</code> slot during Gateway startup when permitted so active-memory recall can call <code>memory_search</code> and <code>memory_get</code> without requiring an explicit <code>plugins.slots.memory</code> entry, while preserving <code>plugins.slots.memory: "none"</code>. Thanks @vincentkoc.</li>
<li>Gateway/plugins: resolve <code>gateway_start</code> cron hooks from live Gateway runtime state before the legacy deps fallback, so memory-core dreaming cron reconciliation keeps working on installs where <code>deps.cron</code> is not populated during service startup. Fixes #72835. Thanks @RayWoo.</li>
<li>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.</li>
<li>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.</li>
<li>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.</li>
<li>Plugins/CLI: refresh the persisted registry after managed plugin files are removed so ClawHub uninstall cannot leave stale <code>plugins list</code> entries. Thanks @vincentkoc.</li>
<li>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.</li>
<li>Plugins: fail <code>plugins update</code> 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.</li>
<li>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.</li>
<li>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.</li>
<li>Gateway/chat: keep duplicate attachment-backed <code>chat.send</code> retries with the same idempotency key on the documented in-flight path so aborts still target the real active run. Fixes #70139. Thanks @Feelw00.</li>
<li>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.</li>
<li>Plugins: share package entrypoint resolution between install and discovery, reject mismatched <code>runtimeExtensions</code>, and cache bundled runtime-dependency manifest reads during scans. Thanks @vincentkoc.</li>
<li>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.</li>
<li>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.</li>
<li>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 <code>tts.voice.preferAudioFileFormat</code> channel capability and a magic-byte sniff for the CAF container so the host-local-media validator (which uses <code>file-type</code> 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.</li>
<li>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.</li>
</ul>
<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
]]></description>
            <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.4.27/OpenClaw-2026.4.27.zip" length="50595360" type="application/octet-stream" sparkle:edSignature="X8DQNQNWVcvtpYLkhZcsKNpnA78ycyzgGlZaG0XBY1GIph3oZNUIpAszGGocJVqTK7+F89Au5ZPb60mOqJQ6DQ=="/>
        </item>
    </channel>
</rss>