chore(release): update macOS appcast for 2026.5.2

appcast.xml

@@ -2,6 +2,406 @@
 <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>
@@ -657,240 +1057,5 @@
 ]]></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>
-        <item>
-            <title>2026.4.26</title>
-            <pubDate>Tue, 28 Apr 2026 02:40:27 +0000</pubDate>
-            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
-            <sparkle:version>2026042690</sparkle:version>
-            <sparkle:shortVersionString>2026.4.26</sparkle:shortVersionString>
-            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
-            <description><![CDATA[<h2>OpenClaw 2026.4.26</h2>
-<h3>Changes</h3>
-<ul>
-<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>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>Control UI/Talk: add a generic browser realtime transport contract, Google Live browser Talk sessions with constrained ephemeral tokens, and a Gateway relay for backend-only realtime voice plugins. Thanks @VACInc.</li>
-<li>CLI/models: route provider-filtered model listing through an explicit source plan so user config, installed manifest rows, Provider Index previews, and scoped runtime fallbacks keep a stable authority order without adding another catalog cache. Thanks @shakkernerd.</li>
-<li>Providers: add Cerebras as a bundled plugin with onboarding, static model catalog, docs, and manifest-owned endpoint metadata.</li>
-<li>Memory/OpenAI-compatible: add optional <code>memorySearch.inputType</code>, <code>queryInputType</code>, and <code>documentInputType</code> config for asymmetric embedding endpoints, including direct query embeddings and provider batch indexing. Carries forward #63313 and #60727. Thanks @HOYALIM and @prospect1314521.</li>
-<li>Ollama/memory: add model-specific retrieval query prefixes for <code>nomic-embed-text</code>, <code>qwen3-embedding</code>, and <code>mxbai-embed-large</code> memory-search queries while leaving document batches unchanged. Carries forward #45013. Thanks @laolin5564.</li>
-<li>Plugins/providers: move pre-runtime model-id normalization, endpoint host metadata, OpenAI-compatible request-family hints, model-catalog aliases/suppressions, OpenAI stale Spark suppression, and reusable startup metadata snapshots into plugin manifests so core no longer carries bundled-provider routing tables or repeated manifest rebuilds. Thanks @shakkernerd.</li>
-<li>Plugins/config: deprecate direct plugin config load/write helpers in favor of passed runtime snapshots plus transactional mutation helpers with explicit restart follow-up policy, scanner guardrails, runtime warnings, and revision-based cache invalidation.</li>
-<li>Plugins/install: allow <code>OPENCLAW_PLUGIN_STAGE_DIR</code> to contain layered runtime-dependency roots, resolving read-only preinstalled deps before installing missing deps into the final writable root. Fixes #72396. Thanks @liorb-mountapps.</li>
-<li>Control UI: add a raw config pending-changes diff panel that parses JSON5, redacts sensitive values until reveal, and avoids fake raw-edit callbacks when opening the panel. Refs #39831; supersedes #48621 and #46654. Thanks @JiajunBernoulli and @BunsDev.</li>
-<li>Control UI: polish the quick settings dashboard grid so common cards align across desktop, tablet, and mobile layouts without wasting horizontal space. Thanks @BunsDev.</li>
-<li>Matrix/E2EE: add <code>openclaw matrix encryption setup</code> to enable Matrix encryption, bootstrap recovery, and print verification status from one setup flow. Thanks @gumadeiras.</li>
-<li>Agents/compaction: add an opt-in <code>agents.defaults.compaction.maxActiveTranscriptBytes</code> preflight trigger that runs normal local compaction when the active JSONL grows too large, requiring transcript rotation so successful compaction moves future turns onto a smaller successor file instead of raw byte-splitting history. Thanks @vincentkoc.</li>
-<li>CLI/migration: add <code>openclaw migrate</code> with plan, dry-run, JSON, pre-migration backup, onboarding detection, archive-only reports, a Claude Code/Desktop importer, and a Hermes importer for configuration, memory/plugin hints, model providers, MCP servers, skills, commands, and supported credentials. Thanks @vincentkoc and @NousResearch.</li>
-</ul>
-<h3>Fixes</h3>
-<ul>
-<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>Gateway/device tokens: stop echoing rotated bearer tokens from shared/admin <code>device.token.rotate</code> responses while preserving the same-device token handoff needed by token-only clients before reconnect. (#66773) Thanks @MoerAI.</li>
-<li>Control UI/Talk: keep Google Live browser sessions on the WebSocket transport instead of falling back to WebRTC, validate browser Google Live WebSocket endpoints, cap Gateway relay sessions per browser connection, and remove stale browser-native voice buttons that did not use the configured Talk/TTS provider. Thanks @BunsDev.</li>
-<li>Gateway/startup: reuse config snapshot plugin manifests for startup auto-enable, config validation, and plugin bootstrap planning, including authored source config and disabled setup-probe handling, so restrictive allowlists avoid duplicate manifest/config passes during boot. Thanks @shakkernerd.</li>
-<li>Agents/subagents: enforce <code>subagents.allowAgents</code> for explicit same-agent <code>sessions_spawn(agentId=...)</code> calls instead of auto-allowing requester self-targets. Fixes #72827. Thanks @oiGaDio.</li>
-<li>ACP/sessions_spawn: let explicit <code>sessions_spawn(runtime="acp")</code> bootstrap turns run while <code>acp.dispatch.enabled=false</code> still blocks automatic ACP thread dispatch. Fixes #63591. Thanks @moeedahmed.</li>
-<li>CLI/update: install npm global updates into a verified temporary prefix before swapping the package tree into place, preventing mixed old/new installs and stale packaged files from breaking <code>openclaw update</code> verification. Thanks @shakkernerd.</li>
-<li>Gateway: skip CLI startup self-respawn for foreground gateway runs so low-memory Linux/Node 24 hosts start through the same path as direct <code>dist/index.js</code> without hanging before logs. Fixes #72720. Thanks @sign-2025.</li>
-<li>Google Meet: route local Chrome joins through OpenClaw browser control, grant Meet media permissions, pin local Chrome audio defaults to <code>BlackHole 2ch</code>, and use the configured OpenClaw browser profile so joined agents no longer show <code>Permission needed</code> or use raw/default Chrome state. Thanks @DougButdorf and @oromeis.</li>
-<li>Plugins/discovery: follow symlinked plugin directories in global and workspace plugin roots while keeping broken links ignored and existing package safety checks in place. Fixes #36754; carries forward #72695 and #63206. Thanks @Quackstro, @ming1523, and @xsfX20.</li>
-<li>Plugins/install: skip test files and directories during install security scans while still force-scanning declared runtime entrypoints, so packaged test mocks no longer block plugin installs. Fixes #66840; carries forward #67050. Thanks @saurabhjain1592 and @Magicray1217.</li>
-<li>Plugins/install: allow exact package-manager peer links back to the trusted OpenClaw host package during install security scans while continuing to block spoofed or nested escaping <code>node_modules</code> symlinks. Carries forward #70819. Thanks @fgabelmannjr.</li>
-<li>Plugins/install: resolve plugin install destinations from the active profile state dir across CLI, ClawHub, marketplace, local path, and channel setup installs, so <code>openclaw --profile <name> plugins install ...</code> no longer writes into the default profile. Fixes #69960; carries forward #69971. Thanks @FrancisLyman and @Sanjays2402.</li>
-<li>Plugins/registry: suppress duplicate-plugin startup warnings when a tracked npm-installed plugin intentionally overrides the bundled plugin with the same id. Carries forward #48673. Thanks @abdushsk.</li>
-<li>Plugins/startup: reuse canonical realpath lookups throughout each plugin discovery pass, including package and manifest boundary checks, so Windows npm-global startups no longer repeat expensive path resolution for the same plugin roots. Fixes #65733. Thanks @welfo-beo.</li>
-<li>Gateway/proxy: pass <code>ALL_PROXY</code> / <code>all_proxy</code> into the global Undici env-proxy dispatcher and provider proxy-fetch helper while keeping SSRF trusted-proxy auto-upgrade on <code>HTTP_PROXY</code> / <code>HTTPS_PROXY</code> only, so gateway/provider calls honor all-proxy setups without weakening guarded fetches. Fixes #43821; carries forward #43919. Thanks @RickyTong1.</li>
-<li>Reply/link understanding: keep media and link preprocessing on stable runtime entrypoints and continue with raw message content if optional enrichment fails, so URL-bearing messages are no longer dropped after stale runtime chunk upgrades. Fixes #68466. Thanks @songshikang0111.</li>
-<li>Discord: persist routed model-picker overrides when the hidden <code>/model</code> dispatch succeeds but the bound thread session store is still stale, including LM Studio suffixed model ids. Carries forward #61473. Thanks @Nanako0129.</li>
-<li>Nodes/CLI: add <code>openclaw nodes remove --node <id|name|ip></code> and <code>node.pair.remove</code> so stale gateway-owned node pairing records can be cleaned without hand-editing state files.</li>
-<li>Gateway: include the connecting client and fresh presence version in the initial <code>hello-ok</code> snapshot, so clients no longer need a follow-up event before seeing themselves online.</li>
-<li>Docker: install the CA certificate bundle in the slim runtime image so HTTPS calls from containerized gateways no longer fail TLS setup after the <code>bookworm-slim</code> base switch. Fixes #72787. Thanks @ryuhaneul.</li>
-<li>Providers/OpenRouter: remove retired Hunter Alpha and Healer Alpha static catalog rows and disable proxy reasoning injection for stale Hunter Alpha configs, so replies are not hidden when OpenRouter returns answer text in reasoning fields. Fixes #43942. Thanks @EvanDataForge.</li>
-<li>Providers/reasoning: let Groq and LM Studio declare provider-native reasoning effort values, so Qwen thinking models receive <code>none</code>/<code>default</code> or <code>off</code>/<code>on</code> instead of OpenAI-only <code>low</code>/<code>medium</code> values. Fixes #32638. Thanks @Aqu1bp, @mgoulart, @Norpps, and @BSTail.</li>
-<li>Local models: default custom providers with only <code>baseUrl</code> to the Chat Completions adapter and trust loopback model requests automatically, so local OpenAI-compatible proxies receive <code>/v1/chat/completions</code> without timing out. Fixes #40024. Thanks @parachuteshe.</li>
-<li>Channels/message tool: surface Discord, Slack, and Mattermost <code>user:</code>/<code>channel:</code> target syntax in the shared message target schema and Discord ambiguity errors, so DM sends by numeric id stop burning retries before finding <code>user:<id></code>. Fixes #72401. Thanks @garyd9, @hclsys, and @praveen9354.</li>
-<li>Agents/tools: scope tool-loop detection history to the active run when available, so scheduled heartbeat cycles no longer inherit stale repeated-call counts from previous runs. Fixes #40144. Thanks @mattbrown319.</li>
-<li>Agents/subagents: preserve requester delivery for completion announces across different channel accounts, keep same-channel thread completions routed to the child thread, and fail closed instead of guessing a child binding when requester conversation signal is missing. Thanks @sfuminya and @suyua9.</li>
-<li>Agents/status: persist the post-compaction token estimate from auto-compaction when providers omit usage metadata, so <code>/status</code> and session lists keep showing fresh context usage after compaction. Fixes #67667; carries forward #72822. Thanks @Jimmy-xuzimo and @skylight-9.</li>
-<li>Control UI: show loading, reload, and retry states when a lazy dashboard panel cannot load after an upgrade, so the Logs tab no longer appears blank on stale browser bundles. Fixes #72450. Thanks @sobergou.</li>
-<li>Gateway/plugins: start the Gateway in degraded mode when a single plugin entry has invalid schema config, and let <code>openclaw doctor --fix</code> quarantine that plugin config instead of crash-looping every channel. Fixes #62976 and #70371. Thanks @Doraemon-Claw and @pksidekyk.</li>
-<li>Agents/plugins: skip malformed plugin tools with missing schema objects and report plugin diagnostics, so one broken tool no longer crashes Anthropic agent runs. Fixes #69423. Thanks @jmnickels.</li>
-<li>Agents/reasoning: recover fully wrapped unclosed <code><think></code> replies that would otherwise sanitize to empty text while keeping strict stripping for closed reasoning blocks and unclosed tails after visible text. Fixes #37696; supersedes #51915. Thanks @druide67 and @okuyam2y.</li>
-<li>Control UI/Gateway: bind WebChat handshakes to their active socket and reject post-close server registrations, so aborted connects no longer leave zombie clients or misleading duplicate WebSocket connection logs. Fixes #72753. Thanks @LumenFromTheFuture.</li>
-<li>Agents/fallback: split ambiguous provider failures into <code>empty_response</code>, <code>no_error_details</code>, and <code>unclassified</code>, and add flat fallback-step fields to structured fallback logs so primary-model failures stay visible when later fallbacks also fail. Fixes #71922; refs #71744. Thanks @andyk-ms and @nikolaykazakovvs-ux.</li>
-<li>Plugins/Windows: normalize Windows absolute paths before handing bundled plugin modules to Jiti, so Feishu/Lark message sending no longer fails with unsupported <code>c:</code> ESM loader URLs. Fixes #72783. Thanks @jackychen-png.</li>
-<li>CLI/doctor: run bundled plugin runtime-dependency repairs through the async npm installer with spinner/line progress and heartbeat updates, so long <code>openclaw doctor --fix</code> installs no longer look hung in TTY or piped output. Fixes #72775. Thanks @dfpalhano.</li>
-<li>Feishu/Windows: normalize bundled channel sidecar loads before Jiti evaluates them, so Feishu outbound sends no longer fail with raw <code>C:</code> ESM loader errors on Windows. Fixes #72783. Thanks @jackychen-png.</li>
-<li>Agents/tools: ignore volatile <code>exec</code> runtime metadata when comparing tool-loop outcomes, so enabled loop detection can stop repeated identical shell-command results instead of resetting on duration, PID, session, or cwd changes. Fixes #34574; supersedes #41502. Thanks @gucasbrg and @Zcg2021.</li>
-<li>Agents/fallback: classify internal live-session model switch conflicts as unknown fallback failures instead of provider overloads, preventing local vLLM endpoints from receiving misleading overloaded cooldowns. Refs #63229. Thanks @clawdia-lobster.</li>
-<li>Discord: let thread sessions inherit the parent channel's session-level <code>/model</code> override as a model-only fallback without enabling parent transcript inheritance. Fixes #72755. Thanks @solavrc.</li>
-<li>Gateway/plugins: skip stale configured channels whose matching plugin is no longer discoverable, point cleanup at <code>openclaw doctor --fix</code>, and keep unrelated channel typos fatal so one missing channel plugin no longer crash-loops the Gateway. Fixes #53311. Thanks @futhgar.</li>
-<li>Control UI: keep session-specific assistant identity loads authoritative after WebSocket connect, so non-main agent chat sessions do not show the main agent name in the header after bootstrap refreshes. Fixes #72776. Thanks @rockytian-top.</li>
-<li>Agents/Qwen: preserve exact custom <code>modelstudio</code> provider configs with foreign <code>api</code> owners so explicit OpenAI-compatible Model Studio endpoints no longer get normalized into the bundled Qwen plugin path. Fixes #64483. Thanks @FiredMosquito831.</li>
-<li>MCP/bundle-mcp: normalize CLI-native <code>type: "http"</code> MCP server entries to OpenClaw <code>transport: "streamable-http"</code> on save, repair existing configs with doctor, and keep embedded Pi from falling back to legacy SSE GET-first startup for those servers. Fixes #72757. Thanks @Studioscale.</li>
-<li>OpenCode: expose Anthropic Opus/Sonnet 4.x thinking levels for proxied Claude models, so <code>/think xhigh</code>, <code>/think adaptive</code>, and <code>/think max</code> validate consistently with the direct Anthropic provider. Fixes #72729. Thanks @haishmg and @aaajiao.</li>
-<li>Media-understanding/audio: migrate deprecated <code>{input}</code> placeholders in legacy <code>audio.transcription.command</code> configs to <code>{{MediaPath}}</code>, so custom audio transcribers no longer receive the literal placeholder after doctor repair. Fixes #72760. Thanks @krisfanue3-hash.</li>
-<li>Ollama/WSL2: warn when GPU-backed WSL2 installs combine CUDA visibility with an autostarting <code>ollama.service</code> using <code>Restart=always</code>, and document the systemd, <code>.wslconfig</code>, and keep-alive mitigation for crash loops. Carries forward #61022; fixes #61185. Thanks @yhyatt.</li>
-<li>Ollama/onboarding: de-dupe suggested bare local models against installed <code>:latest</code> tags and skip redundant pulls, so setup shows the installed model once and no longer says it is downloading an already available model. Fixes #68952. Thanks @tleyden.</li>
-<li>Memory-core/doctor: keep <code>doctor.memory.status</code> on the cached path by default and only run live embedding pings for explicit deep probes, preventing slow local embedding backends from blocking Gateway status checks. Fixes #71568. Thanks @apex-system.</li>
-<li>Memory/QMD: group same-source collections into one QMD search invocation when the installed QMD supports multiple <code>-c</code> filters, while keeping older QMD builds on the per-collection fallback. Fixes #72484; supersedes #72485 and #69583. Thanks @BsnizND and @zeroaltitude.</li>
-<li>Memory/QMD: accept QMD status vector-count variants such as <code>Vectors = 42</code>, <code>Vectors:42</code>, and <code>Vectors: 42 embedded</code>, so <code>memory status --deep</code> no longer reports embeddings unavailable for healthy QMD wrappers. Fixes #63652; carries forward #63678. Thanks @apoapostolov and @WarrenJones.</li>
-<li>Memory/QMD: skip QMD vector status probes and embedding maintenance in lexical <code>searchMode: "search"</code>, so BM25-only QMD setups on ARM do not trigger llama.cpp/Vulkan builds during status checks or embed cycles. Fixes #59234 and #67113. Thanks @PrinceOfEgypt, @Vksh07, @Snipe76, @NomLom, @t4r3e2q1-commits, and @dmak.</li>
-<li>Memory/QMD: report the live watcher dirty state in memory status, so changed QMD-backed memory files show as dirty until the queued sync finishes. Fixes #60244. Thanks @xinzf.</li>
-<li>Compaction: skip oversized pre-compaction checkpoint snapshots and prune duplicate long user turns from compaction input and rotated successor transcripts, preventing retry storms from being preserved across checkpoint cycles. Fixes #72780. Thanks @SweetSophia.</li>
-<li>Control UI/Cron: render cron job prompts and run summaries as sanitized markdown in the dashboard, with full-width block content, safer link clicks, and no duplicate error text when a failed run has no summary. Supersedes #48504. Thanks @garethdaine.</li>
-<li>Control UI/Gateway: preserve WebChat client version labels across localhost, 127.0.0.1, and IPv6 loopback aliases on the same port, avoiding misleading <code>vcontrol-ui</code> connection logs while investigating duplicate-message reports. Refs #72753 and #72742. Thanks @LumenFromTheFuture and @allesgutefy.</li>
-<li>Agents/reasoning: treat orphan closing reasoning tags with following answer text as a privacy boundary across delivery, history, streaming, and Control UI sanitizers so malformed local-model output cannot leak chain-of-thought text. Fixes #67092. Thanks @AnildoSilva.</li>
-<li>Memory-core: run one-shot memory CLI commands through transient builtin and QMD managers so <code>memory index</code>, <code>memory status --index</code>, and <code>memory search</code> no longer start long-lived file watchers that can hit macOS <code>EMFILE</code> limits. Fixes #59101; carries forward #49851. Thanks @mbear469210-coder and @maoyuanxue.</li>
-<li>Agents/ACP: ship the Claude ACP adapter with OpenClaw and require Claude result messages before idle can complete a prompt, preventing parent agents from waking early on long-running <code>sessions_spawn(runtime: "acp", agentId: "claude")</code> children. Fixes #72080. Thanks @siavash-saki and @iannwu.</li>
-<li>CLI/tasks: route <code>tasks --json</code>, <code>tasks list --json</code>, and <code>tasks audit --json</code> through a lean JSON path so read-only task inspection no longer loads unrelated plugin/runtime command graphs. Fixes #66238. Thanks @ChuckChambers.</li>
-<li>Memory-core: re-resolve the active runtime config whenever <code>memory_search</code> or <code>memory_get</code> executes, so provider changes made by <code>config.patch</code> stop leaving stale embedding backends behind in existing tool instances. Fixes #61098. Thanks @BradGroux and @Linux2010.</li>
-<li>WebChat: keep bare <code>/new</code> and <code>/reset</code> startup instructions out of visible chat history while preserving <code>/reset <note></code> as user-visible transcript text. Fixes #72369. Thanks @collynes and @haishmg.</li>
-<li>Tasks/memory: checkpoint and truncate SQLite WAL sidecars on a timer and before close for task, Task Flow, proxy capture, and builtin memory databases, bounding long-running gateway <code>*.sqlite-wal</code> growth. Fixes #72774. Thanks @dfpalhano.</li>
-<li>CLI/doctor: remove dangling channel config, heartbeat targets, and channel model overrides when stale plugin repair removes a missing channel plugin, preventing Gateway boot loops after failed plugin reinstalls. Fixes #65293. Thanks @yidecode.</li>
-<li>Control UI/Gateway: cache, coalesce, stale-refresh, and invalidate effective tool inventory on channel registry changes while reusing the gateway-bound plugin registry and avoiding model/auth discovery, so chat runs no longer stall Control UI requests on repeated plugin/model setup. Fixes #72365; supersedes #72558. Thanks @Gabiii2398 and @1yihui.</li>
-<li>Channels/setup: treat bundled channel plugins as already bundled during <code>channels add</code> and onboarding, enabling them without writing redundant <code>plugins.load.paths</code> entries or path install records. Fixes #72740. Thanks @iCodePoet.</li>
-<li>WhatsApp: honor gateway <code>HTTPS_PROXY</code> / <code>HTTP_PROXY</code> env vars for QR-login WebSocket connections, while respecting <code>NO_PROXY</code>, so proxied networks no longer fall back to direct <code>mmg.whatsapp.net</code> connections that time out with 408. Fixes #72547; supersedes #72692. Thanks @mebusw and @SymbolStar.</li>
-<li>Bonjour: default mDNS advertisements to the system hostname when it is DNS-safe, avoiding <code>openclaw.local</code> probing conflicts and Gateway restart loops on hosts such as <code>Lobster</code> or <code>ubuntu</code>. Fixes #72355 and #72689; supersedes #72694. Thanks @mscheuerlein-bot, @gcusms, @moyuwuhen601, @pavan987, @zml-0912, @hhq365, and @SymbolStar.</li>
-<li>Agents/OpenAI-compatible: retry replay-safe empty <code>stop</code> turns once for <code>openai-completions</code> endpoints, so transient empty local backend responses no longer surface as “Agent couldn't generate a response” when a continuation succeeds, and restore <code>openclaw agent --model</code> for one-shot CLI runs. Fixes #72751. Thanks @moooV252.</li>
-<li>Git hooks: skip ignored staged paths when formatting and restaging pre-commit files, so merge commits no longer abort when <code>.gitignore</code> newly ignores staged merged content. Fixes #72744. Thanks @100yenadmin.</li>
-<li>Memory-core/dreaming: add a supported <code>dreaming.model</code> knob for Dream Diary narrative subagents, wired through phase config and the existing plugin subagent model-override trust gate. Refs #65963. Thanks @esqandil and @mjamiv.</li>
-<li>Agents/Anthropic: remove trailing assistant prefill payloads when extended thinking is enabled, so Opus 4.7/Sonnet 4.6 requests do not fail Anthropic's user-final-turn validation. Fixes #72739. Thanks @superandylin.</li>
-<li>Agents/vLLM/Qwen: add plugin-owned Qwen thinking controls for vLLM chat-template kwargs and DashScope-style top-level <code>enable_thinking</code> flags, including preserved thinking for agent loops. Fixes #72329. Thanks @stavrostzagadouris.</li>
-<li>Memory-core/dreaming: treat request-scoped narrative fallback as expected, skip session cleanup when no subagent run was created, and remove duplicate phase-level cleanup so fallback no longer emits warning noise. Fixes #67152. Thanks @jsompis.</li>
-<li>Agents/exec: apply configured <code>tools.exec.timeoutSec</code> to background, <code>yieldMs</code>, and node <code>system.run</code> commands when no per-call timeout is set, preventing auto-backgrounded and remote node commands from running indefinitely. Fixes #67600; supersedes #67603. Thanks @dlmpx and @kagura-agent.</li>
-<li>Config/doctor: stop masking unknown-key validation diagnostics such as <code>agents.defaults.llm</code>, and have <code>openclaw doctor --fix</code> remove the retired <code>agents.defaults.llm</code> timeout block. Thanks @aidiffuser.</li>
-<li>CLI/startup: keep the built pre-dispatch CLI graph free of package-level imports and extend packaged CLI smoke coverage to onboard and doctor help paths, preventing missing runtime dependencies such as tslog from killing onboarding before repair code can run. Fixes #63024. Thanks @hu19940121.</li>
-<li>CLI/plugins: preserve unversioned ClawHub install specs so <code>plugins update</code> can follow newer ClawHub releases instead of pinning to the initially resolved version. Fixes #63010; supersedes #58426. Thanks @kangsen1234 and @robinspt.</li>
-<li>Memory-core/subagents: tag plugin-created subagent sessions with their plugin owner so dreaming narrative cleanup can delete its own ephemeral sessions without granting broad admin session deletion. Fixes #72712. Thanks @BSG2000.</li>
-<li>Gateway/models: move local-provider pricing opt-outs, OpenRouter/LiteLLM aliases, and proxy passthrough pricing lookup into plugin manifest metadata so core no longer carries extension-specific pricing tables.</li>
-<li>CLI/update: honor <code>OPENCLAW_NO_AUTO_UPDATE=1</code> as a gateway startup kill-switch for configured background package auto-updates, so operators can hold a deliberate downgrade during incident recovery without editing config first. Fixes #72715. Thanks @Xivi08.</li>
-<li>Agents/Claude CLI: force live-session launches to include <code>--output-format stream-json</code> whenever OpenClaw adds <code>--input-format stream-json</code>, so new Claude CLI sessions no longer fail immediately while reusable sessions keep working. Fixes #72206. Thanks @kwangwonkoh and @Xivi08.</li>
-<li>CLI/plugins: accept ClawHub plugin API wildcard ranges such as <code>*</code> without rejecting compatible plugin installs, while still requiring a valid runtime API version. Fixes #56446; supersedes #56466. Thanks @darconada and @claygeo.</li>
-<li>CLI/plugins: add an explicit <code>npm:<package></code> install prefix that skips ClawHub lookup for known npm packages while keeping bare package specs ClawHub-first. Fixes #55805; supersedes #54377. Thanks @Zeoy2020 and @vagusX.</li>
-<li>CLI/plugins: let config-gated bundled plugins install without persisting invalid placeholder config entries, so install/uninstall sweeps can cover plugins such as memory-lancedb before the user configures credentials. Thanks @vincentkoc.</li>
-<li>CLI/plugins: reject malformed ClawHub plugin specs with trailing <code>@</code> before registry lookup, so empty-version typos report as invalid specs instead of package-not-found errors. Fixes #56579; supersedes #56582. Thanks @Kansodata.</li>
-<li>Agents/sessions: acquire the session write lock only after cold bootstrap, plugin, and tool setup so fallback runs are not blocked by stalled pre-model startup work.</li>
-<li>Browser/plugins: auto-start the bundled browser plugin when root <code>browser</code> config is present, including restrictive plugin allowlists, and ignore stale persisted plugin registries whose package paths no longer exist.</li>
-<li>Browser: circuit-break repeated managed Chrome launch failures per profile so browser requests stop spawning Chromium indefinitely when CDP cannot start. Fixes #64271. Thanks @TheophilusChinomona.</li>
-<li>Gateway/models: skip external OpenRouter and LiteLLM pricing refreshes for local/self-hosted model endpoints so startup does not wait on remote pricing catalogs for local-only Ollama, vLLM, and compatible providers.</li>
-<li>CLI/plugins: stop security-blocked plugin installs from retrying as hook packs, so normal plugin packages report the scanner failure without a misleading "not a valid hook pack" follow-up. Fixes #61175; supersedes #64102. Thanks @KonsultDigital and @ziyincody.</li>
-<li>Agents/Anthropic: strip stale trailing assistant prefill turns from outbound replay so context-engine short circuits cannot send unsupported assistant-prefill payloads to provider APIs. Fixes #72556. Thanks @Veda-openclaw.</li>
-<li>Agents/Google: strip stale trailing assistant/model prefill turns from Gemini outbound replay so Google Generative AI requests end with a user turn or function response. Follow-up to #72556. Thanks @Veda-openclaw.</li>
-<li>Control UI/Dreaming: require explicit confirmation before applying restart-impacting Dreaming mode changes, with restart warning copy and loading feedback. Fixes #63804. (#63807) Thanks @bbddbb1.</li>
-<li>CLI/agent: mark Gateway-to-embedded fallback runs with <code>meta.transport: "embedded"</code> and <code>meta.fallbackFrom: "gateway"</code> in JSON output, and make the terminal diagnostic explicit so scripts and operators can distinguish fallback runs from Gateway runs. Fixes #71416. Thanks @amknight.</li>
-<li>Agents/tools: normalize <code>null</code> or missing tool-call arguments to <code>{}</code> for parameterless object schemas before Pi validation, so empty-argument tools run instead of failing argument validation. Fixes #72587. Thanks @amknight.</li>
-<li>Agents/subagents: clear active embedded-run state before terminal lifecycle events so post-completion cleanup no longer treats finished child runs as still active and skips archive or announcement bookkeeping. (#70187) Thanks @amknight.</li>
-<li>CLI/update: keep the automatic post-update completion refresh on the core-command tree so it no longer stages bundled plugin runtime deps before the Gateway restart path, avoiding <code>.24</code> update hangs and 1006 disconnect cascades. Fixes #72665. Thanks @sakalaboator and @He-Pin.</li>
-<li>Control UI: make explicit Reload Config actions discard stale local config edits while passive refreshes and failed-save recovery keep pending drafts intact. Fixes #40352; carries forward #40443. Thanks @realmikechong-dotcom.</li>
-<li>Agents/Bedrock: stop heartbeat runs from persisting blank user transcript turns and repair existing blank user text messages before replay, preventing AWS Bedrock <code>ContentBlock</code> blank-text validation failures. Fixes #72640 and #72622. Thanks @goldzulu.</li>
-<li>Agents/LM Studio: promote standalone bracketed local-model tool requests into registered tool calls and hide unsupported bracket blocks from visible replies, so MemPalace MCP lookups do not print raw <code>[tool]</code> JSON scaffolding in chat. Fixes #66178. Thanks @detroit357.</li>
-<li>Local models: warn when an assistant reply looks like a tool call but the provider emitted plain text instead of a structured tool invocation, making fake/non-executed tool calls visible in logs. Fixes #51332. Thanks @emilclaw.</li>
-<li>Local models: accept persisted non-secret local auth markers for private-LAN custom OpenAI-compatible providers, so LAN Ollama configs no longer fail with missing auth when <code>ollama-local</code> is saved as the key. Fixes #49736. Thanks @charles-zh.</li>
-<li>TUI/local models: treat visible gateway client labels such as <code>openclaw-tui</code> as the current requester session for session-aware tools, so Ollama tool calls no longer fail by resolving the UI label as a session id. Fixes #66391. Thanks @kickingzebra.</li>
-<li>Local models: route self-hosted OpenAI-compatible model discovery through the guarded fetch path pinned to the configured host, covering vLLM and SGLang setup without reopening local/LAN SSRF probes. Supersedes #46359. Thanks @cdxiaodong.</li>
-<li>Local models: classify terminated, reset, closed, timeout, and aborted model-call failures and attach a process memory snapshot to the diagnostic event, making LM Studio/Ollama RAM-pressure failures easier to prove from stability bundles. Refs #65551. Thanks @BigWiLLi111.</li>
-<li>Local models: pass configured provider request timeouts through OpenAI SDK transports and the model idle watchdog so long-running local or custom OpenAI-compatible streams use one timeout knob instead of hitting the SDK's 10-minute default or the 120s idle default. Fixes #63663. Thanks @aidiffuser.</li>
-<li>LM Studio: trust configured LM Studio loopback, LAN, and tailnet endpoints for guarded model requests by default, preserving explicit private-network opt-outs. Refs #60994. Thanks @tnowakow.</li>
-<li>Docker/setup: route Docker onboarding defaults for host-side LM Studio and Ollama through <code>host.docker.internal</code> and add the Linux host-gateway mapping to the bundled Compose file, so containerized gateways can reach local providers without using container loopback. Fixes #68684; supersedes #68702. Thanks @safrano9999 and @skolez.</li>
-<li>Agents/LM Studio: strip prior-turn Gemma 4 reasoning from OpenAI-compatible replay while preserving active tool-call continuation reasoning. Fixes #68704. Thanks @chip-snomo and @Kailigithub.</li>
-<li>LM Studio: allow interactive onboarding to leave the API key blank for unauthenticated local servers, using local synthetic auth while clearing stale LM Studio auth profiles. Fixes #66937. Thanks @olamedia.</li>
-<li>Plugins/startup/registry: reuse a Gateway <code>PluginLookUpTable</code> and one manifest registry pass across startup plugin IDs, plugin loading, deferred channel reloads, model pricing, read-only channel defaults, capability/provider/media resolution, manifest contracts, extractors, web fallback discovery, owner maps, and cold provider-discovery caches, with new startup-trace timing/count metrics for installed-index, manifest, startup-plan, and owner-map work. Thanks @shakkernerd and @mcaxtr.</li>
-<li>Mattermost: keep direct-message replies top-level by suppressing reply roots for DM delivery while preserving channel and group thread roots, and derive inbound chat kind from the trusted channel lookup instead of the websocket event channel type. Carries forward #60115, #55186, #72305, and #72659; refs #59758, #59981, #59791, and #57565. Thanks @vincentkoc, @jwchmodx, and @hnykda.</li>
-<li>Docker: pre-create <code>/home/node/.openclaw</code> with node ownership and private permissions so first-run Docker Compose named volumes no longer fail startup with EACCES. (#48072, #63959; fixes #61279) Thanks @timoxue and @jeanibarz.</li>
-<li>CLI/Gateway: treat local restart probe policy closes for connect, exact <code>device required</code>, pairing, and auth failures as Gateway reachability proof without accepting empty, broad standalone token/password/scope/role, or pair-substring 1008 close reasons. Fixes #48771; carries forward #48801; related #63491. Thanks @MarsDoge and @genoooool.</li>
-<li>Feishu: send outgoing interactive reply payloads as native cards with clickable buttons while preserving text, media, and document-comment fallbacks. Fixes #13175 and #58298; carries forward #47891. Thanks @Horacehxw.</li>
-<li>Process/Windows: decode command stdout and stderr from raw bytes with console-codepage awareness, while preserving valid UTF-8 output and multibyte characters split across chunks. Fixes #50519. Thanks @iready, @kevinten10, @zhangyongjie1997, @knightplat-blip, @heiqishi666, and @slepybear.</li>
-<li>Bonjour/Windows: hide the bundled mDNS advertiser's Windows ARP shell probe so Gateway startup no longer flashes command-prompt windows. Fixes #70238. Thanks @alexandre-leng, @PratikRai0101, @infinitypacific, and @tomerpeled.</li>
-<li>Agents/bootstrap: dedupe hook-injected bootstrap context files by workspace-relative path and store normalized resolved paths so duplicate relative and absolute hook paths no longer depend on the process cwd. (#59344; fixes #59319; related #56721, #56725, and #57587) Thanks @koen666.</li>
-<li>Agents/bootstrap: refresh cached workspace bootstrap snapshots on long-lived main-session turns when <code>AGENTS.md</code>, <code>SOUL.md</code>, <code>MEMORY.md</code>, or <code>TOOLS.md</code> change on disk, while preserving unchanged snapshot identity through the workspace file cache. (#64871; related #43901, #26497, #28594, #30896) Thanks @aimqwest and @mikejuyoon.</li>
-<li>macOS Gateway: detect installed-but-unloaded LaunchAgent split-brain states during status, doctor, and restart, and re-bootstrap launchd supervision before falling back to unmanaged listener restarts. Fixes #67335, #53475, and #71060; refs #58890, #60885, and #70801. Thanks @ze1tgeist88, @dafacto, and @vishutdhar.</li>
-<li>Plugins/install: treat mirrored core logger dependencies as staged bundled runtime deps so packaged Gateway starts do not crash when the external plugin-runtime-deps root is missing <code>tslog</code>. Fixes #72228; supersedes #72493. Thanks @deepujain.</li>
-<li>Build/plugins: preserve active bundled runtime-dependency staging temp directories owned by live build processes so overlapping postbuild runs no longer delete each other's staged deps mid-prune. Supersedes #72220. Thanks @VACInc.</li>
-<li>Plugins/install: hide bundled runtime-dependency npm child windows on Windows across Gateway startup, postinstall, and packaged staging paths so Telegram/Anthropic dependency repair no longer flashes shell windows. Fixes #72315. Thanks @athuljayaram and @joshfeng.</li>
-<li>Agents/Windows: normalize lazy agent runtime imports before Node ESM loading so Windows drive-letter <code>subagent-registry</code> runtime paths no longer fail every agent task with <code>ERR_UNSUPPORTED_ESM_URL_SCHEME</code>. Fixes #72636; carries forward #72716. Thanks @Andyz-CData and @xialonglee.</li>
-<li>Plugins/Windows: normalize lazy plugin service override imports before Node ESM loading so drive-letter browser-control module paths no longer fail with <code>ERR_UNSUPPORTED_ESM_URL_SCHEME</code>. Fixes #72573; supersedes #72599 and #72582. Thanks @llzzww316, @feineryonah-byte, and @WuKongAI-CMU.</li>
-<li>Browser/plugins: load <code>playwright-core</code> through the browser runtime shim so packaged installs can run Playwright actions from staged plugin runtime deps after doctor/startup repair. Fixes #72168; supersedes #72238. Thanks @zdg1110 and @yetval.</li>
-<li>Plugins/install: stage bundled plugin runtime dependencies before Gateway startup, drain update restarts, and materialize plugin-owned root chunks in external mirrors so staged deps resolve under native ESM. Fixes #72058; supersedes #72084. Thanks @amnesia106 and @drvoss.</li>
-<li>TTS/SecretRef: resolve <code>messages.tts.providers.*.apiKey</code> from the active runtime snapshot so SecretRef-backed MiniMax and other TTS provider keys work in runtime reply/audio paths. Fixes #68690. Thanks @joshavant.</li>
-<li>Gateway/install: surface systemd user-bus recovery hints during Linux service activation and retry via the target user scope when <code>systemctl --user</code> reports no-medium bus failures, without letting stale <code>SUDO_USER</code> override <code>sudo -u</code> installs. Fixes #39673; refs #44417 and #63561. Thanks @Arbor4, @myrsu, @mssteuer, and @boyuaner.</li>
-<li>CLI/nodes: make unfiltered <code>openclaw nodes list</code> prefer the effective paired-node view used by <code>nodes status</code> while preserving pending rows, pairing-scope fallback, terminal-safe table rendering, and paired JSON metadata. Fixes #46871; carries forward #65772 through the ProjectClownfish #72619 repair. Thanks @skainguyen1412.</li>
-<li>CLI/startup: read generated startup metadata from the bundled <code>dist</code> layout before falling back to live help rendering, so root/browser help and channel-option bootstrap stay on the fast path. Thanks @vincentkoc.</li>
-<li>Feishu/Lark: stop treating broadcast-only <code>@all</code>/<code>@_all</code> messages as bot mentions while preserving direct bot mentions, including messages that also include <code>@all</code>. Fixes #37706. Thanks @JosepLee.</li>
-<li>CLI/help: treat positional <code>help</code> invocations like <code>openclaw channels help</code> as help paths for startup gating, avoiding model/auth warmup while preserving positional arguments such as <code>openclaw docs help</code>. Thanks @gumadeiras.</li>
-<li>Web search: route plugin-scoped web_search SecretRefs through the active runtime config snapshot so provider execution receives resolved credentials across app/runtime paths, including <code>plugins.entries.brave.config.webSearch.apiKey</code>. Fixes #68690. Thanks @VACInc.</li>
-<li>Voice Call: allow SecretRef-backed Twilio auth tokens and call-specific OpenAI/ElevenLabs TTS API keys through the plugin config surface. Fixes #68690. Thanks @joshavant.</li>
-<li>Google Meet/Voice Call: clean stale chrome-node realtime bridges before rejoining, expose bridge inspection, tolerate transient node input pull failures, default Chrome command-pair audio to 24 kHz PCM16 while preserving legacy 8 kHz G.711 mu-law pairs, handle Gemini Live interruptions/VAD and function-response names correctly, route stateful <code>google_meet</code> tools through the gateway runtime, support <code>realtime.agentId</code>, and send non-blocking consult continuations before long tool-backed answers finish. Fixes #72371, #72525, #72523, #72440, and #72425; (#72372, #72524, #72381, #72441, #72189, #72426) Thanks @BsnizND and @VACInc.</li>
-<li>Discord/media: keep incidental Markdown image badges in final replies as text unless a channel opts into Markdown-image media extraction, while preserving Telegram Markdown-image media replies and explicit <code>MEDIA:</code> attachments. Fixes #72642. Thanks @solavrc and @Bartok9.</li>
-<li>Matrix/E2EE: stabilize recovery and broken-device QA flows while avoiding Matrix device-cleanup sync races that could leave shutdown-time crypto work running. Thanks @gumadeiras.</li>
-<li>Cron: apply <code>cron.maxConcurrentRuns</code> to the nested isolated-agent lane, start isolated execution timeouts only after the runner enters that lane, keep legacy flat <code>jobs.json</code> rows loadable, invalidate stale pending runtime slots after schedule edits, and preserve due slots for formatting-only rewrites. Fixes #72707, #27996, #71607, and #41783; carries forward #71651. Thanks @kagura-agent, @xialonglee, @fagnersouza666, @ayanesakura, and @Hurray0.</li>
-<li>Cron/delivery: classify isolated successes, quiet <code>NO_REPLY</code> turns, model/provider failures, execution denials, <code>--no-deliver</code> traces, skipped-job alerts, and verified delivery outcomes correctly so cron history, retries, and failure counters reflect what actually happened. Fixes #72732, #50170, #43604, #68452, #60846, #72210, and #67172; follow-up to #54188; carries forward #43631, #68453, #72219, and #67186. Thanks @zNatix, @pixeldyn, @ChickenEggRoll, @SPFAdvisors, @anyech, @slideshow-dingo, @hatemclawbot-collab, @xydigit-sj, @oc-gh-dr, @hclsys, and @1yihui.</li>
-<li>Cron/routing: preserve direct Telegram thread/account IDs, explicit Discord <code>user:</code>/<code>channel:</code> delivery targets, and <code>session:<id></code> failure-destination routing so reminders, cron announcements, and failure alerts keep the intended recipient kind across direct and group chats. Fixes #44270; refs #62777; carries forward #44325, #44351, #44412, #72657, #68535, and #62798. Thanks @RunMintOn, @arkyu2077, @0xsline, @vincentkoc, @slideshow-dingo, @likewen-tech, and @neeravmakwana.</li>
-<li>Subagents: keep the delegated task only in the subagent system prompt and send a short initial kickoff message, avoiding duplicate task tokens while preserving multiline task formatting. Fixes #72019; carries forward #72053. Thanks @Wizongod and @ly85206559.</li>
-<li>Onboarding/GitHub Copilot: add manifest-owned <code>--github-copilot-token</code> support for non-interactive setup, including env fallback, tokenRef storage in ref mode, saved-profile reuse, and current Copilot default-model wiring. Refs #50002 and supersedes #50003. Thanks @scottgl9.</li>
-<li>Gateway/install: add a validated <code>--wrapper</code>/<code>OPENCLAW_WRAPPER</code> service install path that persists executable LaunchAgent/systemd wrappers across forced reinstalls, updates, and doctor repairs instead of falling back to raw node/bun <code>ProgramArguments</code>. Fixes #69400. (#72445) Thanks @willtmc.</li>
-<li>Plugins: fail plugin registration when loader-owned acceptance gates reject missing hook names or memory-only capability registration from non-memory plugins, surfacing the issue through plugin status and doctor instead of silently dropping the registration. Fixes #72459. Thanks @amknight.</li>
-<li>macOS Gateway: write launchd services with a state-dir <code>WorkingDirectory</code>, use a durable state-dir temp path instead of freezing macOS session <code>TMPDIR</code>, create that temp directory before bootstrap, and label abort-shaped launchd exits as <code>SIGABRT/abort</code> in status output. Fixes #53679 and #70223; refs #71848. Thanks @dlturock, @stammi922, and @palladius.</li>
-<li>Control UI/update: make <code>Update now</code> require a real gateway process replacement, report skipped/error update outcomes with stable reasons, and verify the running gateway version after restart so global installs cannot silently keep old code in memory. Fixes #62492; addresses #64892 and #63562. Thanks @IAMSamuelRodda.</li>
-<li>Exec approvals: accept runtime-owned <code>source: "allow-always"</code> and <code>commandText</code> allowlist metadata in gateway and node approval-set payloads so Control UI round-trips no longer fail with <code>unexpected property 'source'</code>. Fixes #60000; carries forward #60064. Thanks @sd1471123, @sharkqwy, and @luoyanglang.</li>
-<li>Exec/node: skip approval-plan preparation for full-trust <code>host=node</code> runs so interpreter and script commands no longer fail with <code>SYSTEM_RUN_DENIED: approval cannot safely bind</code> when effective policy is <code>security=full</code> and <code>ask=off</code>. Fixes #48457 and duplicate #69251. Thanks @ajtran303, @jaserNo1, @Blakeshannon, @lesliefag, and @AvIsBeastMC.</li>
-<li>Exec/node: synthesize a local approval plan when a paired node advertises <code>system.run</code> without <code>system.run.prepare</code>, unblocking approval-required <code>host=node</code> exec on current macOS companion nodes while preserving remote prepare for node hosts that support it. Fixes #37591 and duplicate #66839; carries forward #69725. Thanks @soloclz.</li>
-<li>Memory/QMD: prefer QMD's <code>--mask</code> collection pattern flag so root memory indexing stays scoped to <code>MEMORY.md</code> instead of widening to every markdown file in the workspace. Fixes #65480; supersedes #65481 and #66259. Thanks @ccage-simp, @Bortlesboat, @seank-com, and @crazyscience.</li>
-<li>Memory/doctor: treat the specific <code>gateway timeout after ...</code> gateway memory probe result as inconclusive instead of reporting embeddings not ready, while preserving warnings for explicit failures. Fixes #44426; carries forward #46576 with the Greptile review feedback applied. Thanks Cengiz (@ghost).</li>
-<li>Gateway/startup: defer QMD, core request handlers, setup wizard, CLI outbound senders, plugin HTTP routes, chat/session projection, node session runtime validation, embedded-run activity reads, MCP loopback server imports, channel runtime helpers, HTTP/canvas/plugin auth helpers, isolated cron imports, and hook dispatch parsing until their request or shutdown paths, while making plain <code>gateway status</code> use a parse-only config snapshot so no-plugin boots and status reads avoid broad runtime fanout. Thanks @vincentkoc.</li>
-<li>Lobster/Gateway: memoize repeated Ajv schema compilation before loading the embedded Lobster runtime so scheduled workflows and <code>llm.invoke</code> loops stop growing gateway heap on content-identical schemas. Fixes #71148. Thanks @cmi525, @vsolaz, and @vincentkoc.</li>
-<li>Codex harness: normalize cached input tokens before session/context accounting so prompt cache reads are not double-counted in <code>/status</code>, <code>session_status</code>, or persisted <code>sessionEntry.totalTokens</code>. Fixes #69298. Thanks @richardmqq.</li>
-<li>Hooks/session-memory: use the host local timezone for memory filenames, fallback timestamp slugs, and markdown headers instead of UTC dates. Fixes #46703. (#46721) Thanks @Astro-Han.</li>
-<li>Gateway health: preserve live runtime-backed channel/account state in <code>gateway.health</code> snapshots and cached refreshes while keeping raw probe payloads on sensitive/admin paths only. (#39921, #42586, #46527, #52770, #42543) Thanks @FAL1989, @rstar327, @0xble, and @ajayr.</li>
-<li>Feishu: extract quoted/replied interactive-card text across schema 1.0, schema 2.0, i18n, template-variable, and post-format fallback shapes without carrying broad generated/config churn from related parser experiments. (#38776, #60383, #42218, #45936) Thanks @lishuaigit, @lskun, @just2gooo, and @Br1an67.</li>
-<li>Telegram/agents: hide raw failed write/edit warning messages in Telegram when the assistant already explicitly acknowledges the failed action, while keeping warnings when the reply claims success or omits the failure; #39406 remains the broader configurable delivery-policy follow-up. Fixes #51065; covers #39631. Thanks @Bartok9 and @Bortlesboat.</li>
-<li>Exec approvals: accept a symlinked <code>OPENCLAW_HOME</code> as the trusted approvals root while still rejecting symlinked <code>.openclaw</code> path components below it. (#64663) Thanks @FunJim.</li>
-<li>Logging: add top-level <code>hostname</code>, flattened <code>message</code>, and available <code>agent_id</code>, <code>session_id</code>, and <code>channel</code> fields to file-log JSONL records for multi-agent filtering without removing existing structured log arguments. Fixes #51075. Thanks @stevengonsalvez.</li>
-<li>ACP: route server logs to stderr before Gateway config/bootstrap work so ACP stdout remains JSON-RPC only for IDE integrations. Fixes #49060. Thanks @Hollychou924.</li>
-<li>Logging: propagate internal request trace scopes through Gateway HTTP requests and WebSocket frames so file logs, diagnostic events, agent run traces, model-call traces, OTEL spans, and trusted provider <code>traceparent</code> headers share a correlatable <code>traceId</code> without logging raw request or model content. Fixes #40353. Thanks @liangruochong44-ui.</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>Agents/sessions: let <code>sessions_spawn runtime="subagent"</code> ignore ACP-only <code>streamTo</code> and <code>resumeSessionId</code> fields while keeping ACP passthrough and documenting <code>streamTo</code> as ACP-only. Fixes #43556 and #63120; covers #56326, #61724, #64714, and #67248; carries forward #68397, #65282, #58686, #56342, and #40102. Thanks @skernelx, @damselem, @Br1an67, @Mintalix, @IsaacAPerez, @vvitovec, @Sanjays2402, @shenkq97, and @1034378361.</li>
-<li>Providers/Ollama: honor <code>/api/show</code> capabilities, custom Modelfile <code>PARAMETER num_ctx</code>, configured provider/model context defaults, whitelisted native params such as <code>temperature</code>, <code>top_p</code>, and <code>think</code>, and native thinking effort levels so local models get accurate tools, context, and thinking behavior without forcing full-context VRAM use. Fixes #64710, duplicate #65343, #68344, #44550, #52206, #49684, #68662, #48010, #71584, and #44786; supersedes #69464; carries forward #44955. Thanks @yuan-b, @netherby, @xilopaint, @Diyforfun2026, @neeravmakwana, @taitruong, @armi0024, @LokiCode404, @zhouZcong, @dshenster-byte, @tangzhi, @pandego, @maweibin, @Adam-Researchh, @EmpireCreator, @g0st1n, and @voltwake.</li>
-<li>Image tool/media: honor <code>tools.media.image.timeoutSeconds</code> and matching per-model image timeouts in explicit image analysis, including the MiniMax VLM fallback path, so slow local vision models are not capped by hardcoded 30s/60s aborts. Fixes #67889; supersedes #67929. Thanks @AllenT22 and @alchip.</li>
-<li>Providers/Ollama: strip custom provider prefixes before native chat/embedding requests, skip ambient localhost discovery unless config/auth opts in, handle custom remote <code>api: "ollama"</code> providers, accept OpenAI SDK-style <code>baseURL</code>, scope synthetic local auth and embedding bearer headers to declared host boundaries, resolve custom-named local providers for subagents, add provider-scoped model request timeouts, preserve explicit input modalities, and document <code>params.keep_alive</code> plus local/LAN/cloud/multi-host/web-search/embedding/thinking setup recipes. Fixes #72353, #56939, #62533, #43945, #64541, #68796, and #39690; supersedes #57116, #62549, #69261, #69857, #65143, and #66511; refs #43945; carries forward #43224 and #39785. Thanks @maximus-dss, @hclsys, @IanxDev, @tsukhani, @issacthekaylon, @Julien-BKK, @Linux2010, @hyspacex, @maxramsay, @Meli73, @LittleJakub, @Juankcba, @uninhibite-scholar, @yfge, @Skrblik, and @Mriris.</li>
-<li>Providers/Ollama: move memory embeddings to <code>/api/embed</code> with batched <code>input</code>, route local web search through Ollama's signed daemon proxy while keeping cloud auth scoped, treat Ollama memory embeddings as key-optional in doctor, and keep model usage visible by estimating native transcript usage when <code>/api/chat</code> omits counters. Fixes #39983, #69132, and #46584; carries forward #39112. Thanks @sskkcc, @LiudengZhang, @yoon1012, @hyspacex, @fengly78, and @TylonHH.</li>
-<li>Agents/Ollama: parse stringified native tool-call arguments, retry native empty/thinking-only turns, accept already-prefixed LLM task model overrides, apply provider-owned replay normalization for Cloud models, validate explicit <code>--thinking max</code>, show resolved thinking defaults in Control UI, and include configured provider models in <code>models list --provider</code>. Fixes #69735, #50052, #71697, #71584, #72407, and #65207; supersedes #69910; carries forward #66552 and #61223. Thanks @rongshuzhao, @yfge, @L3G, @ralphy-maplebots, @Hollychou924, @ismael-81, @g0st1n, @NotecAG, and @drzeast-png.</li>
-<li>Providers/PDF/Ollama: add bounded network timeouts for Ollama model pulls and native Anthropic/Gemini PDF analysis requests so unresponsive provider endpoints no longer hang sessions indefinitely. Fixes #54142; supersedes #54144 and #54145. Thanks @jinduwang1001-max and @arkyu2077.</li>
-<li>Docker/QA: add observability coverage to the normal Docker aggregate so QA-lab OTEL and Prometheus diagnostics run inside Docker. Thanks @vincentkoc.</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: keep auto-persisted fallback model overrides selected across turns until <code>/new</code> or reset clears them, avoiding repeated probes of a known-bad primary while <code>/status</code> shows the selected and active models. Thanks @kibedu.</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.</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>.</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/CLI: inventory doctor-side deprecation migrations separately from runtime plugin compatibility, add dated records for legacy extension-api, memory registration, provider hook/type aliases, runtime aliases, channel SDK helpers, and approval/test utility shims, refresh the persisted registry after managed plugin removals, make plugin install/uninstall writes conflict-aware, clear stale denylists, and fail tracked plugin/hook updates or unloadable package installs instead of leaving stale state. 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/session rows: report the same config-resolved thinking default that runtime sessions use, including global and per-agent defaults, so Control UI and TUI default labels stay aligned. (#71779, #70981, #71033, #70302) Thanks @chen-zhang-cs-code, @SymbolStar, and @cholaolu-boop.</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.</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>Cron/context engine: run isolated cron jobs under run-scoped context-engine session keys so prior runs of the same job are not inherited unless the job is explicitly session-bound. (#72292) Thanks @jalehman.</li>
-<li>Control UI: localize command palette labels, categories, skill shortcuts, footer hints, and connect-command copy labels while preserving localized command palette search matching. (#61130, #61119) Thanks @rubensfox20.</li>
-<li>Plugins/memory-lancedb: request float embedding responses from OpenAI-compatible servers so local providers that default SDK requests to base64 no longer return dimension-mismatched LanceDB vectors while preserving configured dimensions. Fixes #45982. (#59048, #46069, #45986) Thanks @deep-introspection, @xiaokhkh, @caicongyang, and @thiswind.</li>
-<li>Plugins/memory-lancedb: advance auto-capture cursors per session only after messages are processed or intentionally skipped, retry failed messages, survive compacted histories, and clear cursor state on session end. Fixes #71349; carries forward #42083. Thanks @as775116191.</li>
-<li>Plugins/memory-core: respect configured memory-search embedding concurrency during non-batch indexing so local Ollama embedding backends can serialize indexing instead of flooding the server. Fixes #66822. (#66931) Thanks @oliviareid-svg and @LyraInTheFlesh.</li>
-<li>Docker/update smoke: keep the package-derived update-channel fixture on package-shipped files and make its UI build stub create the asset the updater verifies. Thanks @vincentkoc.</li>
-<li>Gateway/models: repair legacy <code>models.providers.*.api = "openai"</code> config values to <code>openai-completions</code>, and skip providers with future stale API enum values during startup instead of bricking the gateway. Fixes #72477. (#72542) Thanks @JooyoungChoi14 and @obviyus.</li>
-<li>Gateway/skills: redact <code>apiKey</code> and secret-named <code>env</code> values from the <code>skills.update</code> RPC response to prevent leaking credentials into WebSocket traffic, client logs, or session transcripts. Config is still written to disk in full; only the response payload is redacted. (#69998) Thanks @Ziy1-Tan.</li>
-<li>Plugins/CLI: let flag-driven <code>openclaw channels add</code> install the selected channel plugin from its default source without opening an interactive prompt, fixing published npm Telegram setup in stdin-closed automation.</li>
-<li>Onboarding/setup: keep first-run config reads, plugin compatibility notices, OpenAI Codex auth, post-auth default-model policy lookup, skip-auth, provider-scoped model pickers, and post-model sanity checks on cold manifest/setup metadata unless the user chooses to browse all models, avoiding full plugin/provider runtime loads between prompts. Thanks @shakkernerd.</li>
-<li>Gateway/Bonjour: suppress known @homebridge/ciao cancellation and network assertion failures through scoped process handlers so malformed mDNS packets or restricted VPS networking disable/restart Bonjour instead of crashing the gateway. Fixes #67578. Thanks @zenassist26-create.</li>
-<li>Discord: keep late clicks on already-resolved exec approval buttons quiet when elevated mode auto-resolved the request, while still surfacing real approval submission failures. Fixes #66906. Thanks @rlerikse.</li>
-<li>Telegram: send a fresh final message for long-lived preview-streamed replies so the visible Telegram timestamp reflects completion time instead of the preview creation time. Thanks @rubencu.</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/v2026.4.26/OpenClaw-2026.4.26.zip" length="48222029" type="application/octet-stream" sparkle:edSignature="6wgFZUyyU09Y6nvD9T1Ufq7Plo0Wzfg+L9r80DCaNMMuwebcKWAsMVSP3RvhRhTxVMax8toUDYg3gb/vOiE5BA=="/>
-        </item>
     </channel>
 </rss>