Merge branch 'main' into fix/issue-35881-cron-perms

CHANGELOG.md

@@ -17,29 +17,78 @@ Docs: https://docs.openclaw.ai
 - Slack/DM typing feedback: add `channels.slack.typingReaction` so Socket Mode DMs can show reaction-based processing status even when Slack native assistant typing is unavailable. (#19816) Thanks @dalefrieswthat.
 - Cron/job snapshot persistence: skip backup during normalization persistence in `ensureLoaded` so `jobs.json.bak` keeps the pre-edit snapshot for recovery, while preserving backup creation on explicit user-driven writes. (#35234) Thanks @0xsline.
 - TTS/OpenAI-compatible endpoints: add `messages.tts.openai.baseUrl` config support with config-over-env precedence, endpoint-aware directive validation, and OpenAI TTS request routing to the resolved base URL. (#34321) thanks @RealKai42.
+- Plugins/before_prompt_build system-context fields: add `prependSystemContext` and `appendSystemContext` so static plugin guidance can be placed in system prompt space for provider caching and lower repeated prompt token cost. (#35177) thanks @maweibin.
+- Gateway: add SecretRef support for gateway.auth.token with auth-mode guardrails. (#35094) Thanks @joshavant.
+- Plugins/hook policy: add `plugins.entries.<id>.hooks.allowPromptInjection`, validate unknown typed hook names at runtime, and preserve legacy `before_agent_start` model/provider overrides while stripping prompt-mutating fields when prompt injection is disabled. (#36567) thanks @gumadeiras.
+- Tools/Diffs guidance: restore a short system-prompt hint for enabled diffs while keeping the detailed instructions in the companion skill, so diffs usage guidance stays out of user-prompt space. (#36904) thanks @gumadeiras.
+- Telegram/ACP topic bindings: accept Telegram Mac Unicode dash option prefixes in `/acp spawn`, support Telegram topic thread binding (`--thread here|auto`), route bound-topic follow-ups to ACP sessions, add actionable Telegram approval buttons with prefixed approval-id resolution, and pin successful bind confirmations in-topic. (#36683) Thanks @huntharo.
+- Hooks/Compaction lifecycle: emit `session:compact:before` and `session:compact:after` internal events plus plugin compaction callbacks with session/count metadata, so automations can react to compaction runs consistently. (#16788) thanks @vincentkoc.
+- CLI: make read-only SecretRef status flows degrade safely (#37023) thanks @joshavant.
+
+### Breaking
+
+- **BREAKING:** Gateway auth now requires explicit `gateway.auth.mode` when both `gateway.auth.token` and `gateway.auth.password` are configured (including SecretRefs). Set `gateway.auth.mode` to `token` or `password` before upgrade to avoid startup/pairing/TUI failures. (#35094) Thanks @joshavant.
 
 ### Fixes
 
+- Models/openai-completions streaming compatibility: force `compat.supportsUsageInStreaming=false` for non-native OpenAI-compatible endpoints during model normalization, preventing usage-only stream chunks from triggering `choices[0]` parser crashes in provider streams. (#8714) Thanks @nonanon1.
+- Tools/xAI native web-search collision guard: drop OpenClaw `web_search` from tool registration when routing to xAI/Grok model providers (including OpenRouter `x-ai/*`) to avoid duplicate tool-name request failures against provider-native `web_search`. (#14749) Thanks @realsamrat.
+- TUI/token copy-safety rendering: treat long credential-like mixed alphanumeric tokens (including quoted forms) as copy-sensitive in render sanitization so formatter hard-wrap guards no longer inject visible spaces into auth-style values before display. (#26710) Thanks @jasonthane.
+- WhatsApp/self-chat response prefix fallback: stop forcing `"[openclaw]"` as the implicit outbound response prefix when no identity name or response prefix is configured, so blank/default prefix settings no longer inject branding text unexpectedly in self-chat flows. (#27962) Thanks @ecanmor.
+- Memory/QMD search result decoding: accept `qmd search` hits that only include `file` URIs (for example `qmd://collection/path.md`) without `docid`, resolve them through managed collection roots, and keep multi-collection results keyed by file fallback so valid QMD hits no longer collapse to empty `memory_search` output. (#28181) Thanks @0x76696265.
+- Memory/QMD collection-name conflict recovery: when `qmd collection add` fails because another collection already occupies the same `path + pattern`, detect the conflicting collection from `collection list`, remove it, and retry add so agent-scoped managed collections are created deterministically instead of being silently skipped; also add warning-only fallback when qmd metadata is unavailable to avoid destructive guesses. (#25496) Thanks @Ramsbaby.
+- Slack/app_mention race dedupe: when `app_mention` dispatch wins while same-`ts` `message` prepare is still in-flight, suppress the later message dispatch so near-simultaneous Slack deliveries do not produce duplicate replies; keep single-retry behavior and add regression coverage for both dropped and successful message-prepare outcomes. (#37033) Thanks @Takhoffman.
+- Gateway/chat streaming tool-boundary text retention: merge assistant delta segments into per-run chat buffers so pre-tool text is preserved in live chat deltas/finals when providers emit post-tool assistant segments as non-prefix snapshots. (#36957) Thanks @Datyedyeguy.
+- TUI/model indicator freshness: prevent stale session snapshots from overwriting freshly patched model selection (and reset per-session freshness when switching session keys) so `/model` updates reflect immediately instead of lagging by one or more commands. (#21255) Thanks @kowza.
+- TUI/final-error rendering fallback: when a chat `final` event has no renderable assistant content but includes envelope `errorMessage`, render the formatted error text instead of collapsing to `"(no output)"`, preserving actionable failure context in-session. (#14687) Thanks @Mquarmoc.
+- OpenAI Codex OAuth/login hardening: fail OAuth completion early when the returned token is missing `api.responses.write`, and allow `openclaw models auth login --provider openai-codex` to use the built-in OAuth path even when no provider plugins are installed. (#36660) Thanks @driesvints.
+- OpenAI Codex OAuth/scope request parity: augment the OAuth authorize URL with required API scopes (`api.responses.write`, `model.request`, `api.model.read`) before browser handoff so OAuth tokens include runtime model/request permissions expected by OpenAI API calls. (#24720) Thanks @Skippy-Gunboat.
+- Onboarding/API key input hardening: strip non-Latin1 Unicode artifacts from normalized secret input (while preserving Latin-1 content and internal spaces) so malformed copied API keys cannot trigger HTTP header `ByteString` construction crashes; adds regression coverage for shared normalization and MiniMax auth header usage. (#24496) Thanks @fa6maalassaf.
+- Kimi Coding/Anthropic tools compatibility: normalize `anthropic-messages` tool payloads to OpenAI-style `tools[].function` + compatible `tool_choice` when targeting Kimi Coding endpoints, restoring tool-call workflows that regressed after v2026.3.2. (#37038) Thanks @mochimochimochi-hub.
+- Heartbeat/workspace-path guardrails: append explicit workspace `HEARTBEAT.md` path guidance (and `docs/heartbeat.md` avoidance) to heartbeat prompts so heartbeat runs target workspace checklists reliably across packaged install layouts. (#37037) Thanks @stofancy.
+- Subagents/kill-complete announce race: when a late `subagent-complete` lifecycle event arrives after an earlier kill marker, clear stale kill suppression/cleanup flags and re-run announce cleanup so finished runs no longer get silently swallowed. (#37024) Thanks @cmfinlan.
+- Agents/tool-result cleanup timeout hardening: on embedded runner teardown idle timeouts, clear pending tool-call state without persisting synthetic `missing tool result` entries, preventing timeout cleanups from poisoning follow-up turns; adds regression coverage for timeout clear-vs-flush behavior. (#37081) Thanks @Coyote-Den.
+- Agents/openai-completions stream timeout hardening: ensure runtime undici global dispatchers use extended streaming body/header timeouts (including env-proxy dispatcher mode) before embedded runs, reducing forced mid-stream `terminated` failures on long generations; adds regression coverage for dispatcher selection and idempotent reconfiguration. (#9708) Thanks @scottchguard.
+- Agents/fallback cooldown probe execution: thread explicit rate-limit cooldown probe intent from model fallback into embedded runner auth-profile selection so same-provider fallback attempts can actually run when all profiles are cooldowned for `rate_limit` (instead of failing pre-run as `No available auth profile`), while preserving default cooldown skip behavior and adding regression tests at both fallback and runner layers. (#13623) Thanks @asfura.
+- Cron/OpenAI Codex OAuth refresh hardening: when `openai-codex` token refresh fails specifically on account-id extraction, reuse the cached access token instead of failing the run immediately, with regression coverage to keep non-Codex and unrelated refresh failures unchanged. (#36604) Thanks @laulopezreal.
+- Gateway/remote WS break-glass hostname support: honor `OPENCLAW_ALLOW_INSECURE_PRIVATE_WS=1` for `ws://` hostname URLs (not only private IP literals) across onboarding validation and runtime gateway connection checks, while still rejecting public IP literals and non-unicast IPv6 endpoints. (#36930) Thanks @manju-rn.
+- Routing/binding lookup scalability: pre-index route bindings by channel/account and avoid full binding-list rescans on channel-account cache rollover, preventing multi-second `resolveAgentRoute` stalls in large binding configurations. (#36915) Thanks @songchenghao.
+- Browser/session cleanup: track browser tabs opened by session-scoped browser tool runs and close tracked tabs during `sessions.reset`/`sessions.delete` runtime cleanup, preventing orphaned tabs and unbounded browser memory growth after session teardown. (#36666) Thanks @Harnoor6693.
+- Slack/local file upload allowlist parity: propagate `mediaLocalRoots` through the Slack send action pipeline so workspace-rooted attachments pass `assertLocalMediaAllowed` checks while non-allowlisted paths remain blocked. (synthesis: #36656; overlap considered from #36516, #36496, #36493, #36484, #32648, #30888) Thanks @2233admin.
+- Agents/compaction safeguard pre-check: skip embedded compaction before entering the Pi SDK when a session has no real conversation messages, avoiding unnecessary LLM API calls on idle sessions. (#36451) thanks @Sid-Qin.
+- Config/schema cache key stability: build merged schema cache keys with incremental hashing to avoid large single-string serialization and prevent `RangeError: Invalid string length` on high-cardinality plugin/channel metadata. (#36603) Thanks @powermaster888.
+- iMessage/cron completion announces: strip leaked inline reply tags (for example `[[reply_to:6100]]`) from user-visible completion text so announcement deliveries do not expose threading metadata. (#24600) Thanks @vincentkoc.
+- Sessions/daily reset transcript archival: archive prior transcript files during stale-session scheduled/daily resets by capturing the previous session entry before rollover, preventing orphaned transcript files on disk. (#35493) Thanks @byungsker.
+- Feishu/group slash command detection: normalize group mention wrappers before command-authorization probing so mention-prefixed commands (for example `@Bot/model` and `@Bot /reset`) are recognized as gateway commands instead of being forwarded to the agent. (#35994) Thanks @liuxiaopai-ai.
 - Agents/context pruning: guard assistant thinking/text char estimation against malformed blocks (missing `thinking`/`text` strings or null entries) so pruning no longer crashes with malformed provider content. (openclaw#35146) thanks @Sid-Qin.
+- Agents/transcript policy: set `preserveSignatures` to Anthropic-only handling in `resolveTranscriptPolicy` so Anthropic thinking signatures are preserved while non-Anthropic providers remain unchanged. (#32813) thanks @Sid-Qin.
 - Agents/schema cleaning: detect Venice + Grok model IDs as xAI-proxied targets so unsupported JSON Schema keywords are stripped before requests, preventing Venice/Grok `Invalid arguments` failures. (openclaw#35355) thanks @Sid-Qin.
 - Skills/native command deduplication: centralize skill command dedupe by canonical `skillName` in `listSkillCommandsForAgents` so duplicate suffixed variants (for example `_2`) are no longer surfaced across interfaces outside Discord. (#27521) thanks @shivama205.
 - Agents/xAI tool-call argument decoding: decode HTML-entity encoded xAI/Grok tool-call argument values (`&amp;`, `&quot;`, `&lt;`, `&gt;`, numeric entities) before tool execution so commands with shell operators and quotes no longer fail with parse errors. (#35276) Thanks @Sid-Qin.
 - Agents/thinking-tag promotion hardening: guard `promoteThinkingTagsToBlocks` against malformed assistant content entries (`null`/`undefined`) before `block.type` reads so malformed provider payloads no longer crash session processing while preserving pass-through behavior. (#35143) thanks @Sid-Qin.
 - Gateway/Control UI version reporting: align runtime and browser client version metadata to avoid `dev` placeholders, wait for bootstrap version before first UI websocket connect, and only forward bootstrap `serverVersion` to same-origin gateway targets to prevent cross-target version leakage. (from #35230, #30928, #33928) Thanks @Sid-Qin, @joelnishanth, and @MoerAI.
+- Control UI/markdown parser crash fallback: catch `marked.parse()` failures and fall back to escaped plain-text `<pre>` rendering so malformed recursive markdown no longer crashes Control UI session rendering on load. (#36445) Thanks @BinHPdev.
+- Control UI/markdown fallback regression coverage: add explicit regression assertions for parser-error fallback behavior so malformed markdown no longer risks reintroducing hard-crash rendering paths in future markdown/parser upgrades. (#36445) Thanks @BinHPdev.
 - Web UI/config form: treat `additionalProperties: true` object schemas as editable map entries instead of unsupported fields so Accounts-style maps stay editable in form mode. (#35380, supersedes #32072) Thanks @stakeswky and @liuxiaopai-ai.
 - Feishu/streaming card delivery synthesis: unify snapshot and delta streaming merge semantics, apply overlap-aware final merge, suppress duplicate final text delivery (including text+media final packets), prefer topic-thread `message.reply` routing when a reply target exists, and tune card print cadence to avoid duplicate incremental rendering. (from #33245, #32896, #33840) Thanks @rexl2018, @kcinzgg, and @aerelune.
+- Feishu/group mention detection: carry startup-probed bot display names through monitor dispatch so `requireMention` checks compare against current bot identity instead of stale config names, fixing missed `@bot` handling in groups while preserving multi-bot false-positive guards. (#36317, #34271) Thanks @liuxiaopai-ai.
 - Security/dependency audit: patch transitive Hono vulnerabilities by pinning `hono` to `4.12.5` and `@hono/node-server` to `1.19.10` in production resolution paths. Thanks @shakkernerd.
 - Security/dependency audit: bump `tar` to `7.5.10` (from `7.5.9`) to address the high-severity hardlink path traversal advisory (`GHSA-qffp-2rhf-9h96`). Thanks @shakkernerd.
 - Cron/announce delivery robustness: bypass pending-descendant announce guards for cron completion sends, ensure named-agent announce routes have outbound session entries, and fall back to direct delivery only when an announce send was actually attempted and failed. (from #35185, #32443, #34987) Thanks @Sid-Qin, @scoootscooob, and @bmendonca3.
+- Cron/announce best-effort fallback: run direct outbound fallback after attempted announce failures even when delivery is configured as best-effort, so Telegram cron sends are not left as attempted-but-undelivered after `cron announce delivery failed` warnings.
 - Auto-reply/system events: restore runtime system events to the message timeline (`System:` lines), preserve think-hint parsing with prepended events, and carry events into deferred followup/collect/steer-backlog prompts to keep cache behavior stable without dropping queued metadata. (#34794) Thanks @anisoptera.
 - Security/audit account handling: avoid prototype-chain account IDs in audit validation by using own-property checks for `accounts`. (#34982) Thanks @HOYALIM.
 - Cron/restart catch-up semantics: replay interrupted recurring jobs and missed immediate cron slots on startup without replaying interrupted one-shot jobs, with guarded missed-slot probing to avoid malformed-schedule startup aborts and duplicate-trigger drift after restart. (from #34466, #34896, #34625, #33206) Thanks @dunamismax, @dsantoreis, @Octane0411, and @Sid-Qin.
 - Agents/session usage tracking: preserve accumulated usage metadata on embedded Pi runner error exits so failed turns still update session `totalTokens` from real usage instead of stale prior values. (#34275) thanks @RealKai42.
+- Slack/reaction thread context routing: carry Slack native DM channel IDs through inbound context and threading tool resolution so reaction targets resolve consistently for DM `To=user:*` sessions (including `toolContext.currentChannelId` fallback behavior). (from #34831; overlaps #34440, #34502, #34483, #32754) Thanks @dunamismax.
+- Subagents/announce completion scoping: scope nested direct-child completion aggregation to the current requester run window, harden frozen completion capture for deterministic descendant synthesis, and route completion announce delivery through parent-agent announce turns with provenance-aware internal events. (#35080) Thanks @tyler6204.
 - Nodes/system.run approval hardening: use explicit argv-mutation signaling when regenerating prepared `rawCommand`, and cover the `system.run.prepare -> system.run` handoff so direct PATH-based `nodes.run` commands no longer fail with `rawCommand does not match command`. (#33137) thanks @Sid-Qin.
 - Models/custom provider headers: propagate `models.providers.<name>.headers` across inline, fallback, and registry-found model resolution so header-authenticated proxies consistently receive configured request headers. (#27490) thanks @Sid-Qin.
+- Ollama/remote provider auth fallback: synthesize a local runtime auth key for explicitly configured `models.providers.ollama` entries that omit `apiKey`, so remote Ollama endpoints run without requiring manual dummy-key setup while preserving env/profile/config key precedence and missing-config failures. (#11283) Thanks @cpreecs.
 - Ollama/custom provider headers: forward resolved model headers into native Ollama stream requests so header-authenticated Ollama proxies receive configured request headers. (#24337) thanks @echoVic.
 - Daemon/systemd install robustness: treat `systemctl --user is-enabled` exit-code-4 `not-found` responses as not-enabled by combining stderr/stdout detail parsing, so Ubuntu fresh installs no longer fail with `systemctl is-enabled unavailable`. (#33634) Thanks @Yuandiaodiaodiao.
 - Slack/system-event session routing: resolve reaction/member/pin/interaction system-event session keys through channel/account bindings (with sender-aware DM routing) so inbound Slack events target the correct agent session in multi-account setups instead of defaulting to `agent:main`. (#34045) Thanks @paulomcg, @daht-mad and @vincentkoc.
+- Slack/native streaming markdown conversion: stop pre-normalizing text passed to Slack native `markdown_text` in streaming start/append/stop paths to prevent Markdown style corruption from double conversion. (#34931)
 - Gateway/HTTP tools invoke media compatibility: preserve raw media payload access for direct `/tools/invoke` clients by allowing media `nodes` invoke commands only in HTTP tool context, while keeping agent-context media invoke blocking to prevent base64 prompt bloat. (#34365) Thanks @obviyus.
 - Agents/Nodes media outputs: add dedicated `photos_latest` action handling, block media-returning `nodes invoke` commands, keep metadata-only `camera.list` invoke allowed, and normalize empty `photos_latest` results to a consistent response shape to prevent base64 context bloat. (#34332) Thanks @obviyus.
 - TUI/session-key canonicalization: normalize `openclaw tui --session` values to lowercase so uppercase session names no longer drop real-time streaming updates due to gateway/TUI key mismatches. (#33866, #34013) thanks @lynnzc.
@@ -65,6 +114,7 @@ Docs: https://docs.openclaw.ai
 - Security/audit denyCommands guidance: suggest likely exact node command IDs for unknown `gateway.nodes.denyCommands` entries so ineffective denylist entries are easier to correct. (#29713) thanks @liquidhorizon88-bot.
 - Docs/security hardening guidance: document Docker `DOCKER-USER` + UFW policy and add cross-linking from Docker install docs for VPS/public-host setups. (#27613) thanks @dorukardahan.
 - Docs/security threat-model links: replace relative `.md` links with Mintlify-compatible root-relative routes in security docs to prevent broken internal navigation. (#27698) thanks @clawdoo.
+- Plugins/Update integrity drift: avoid false integrity drift prompts when updating npm-installed plugins from unpinned specs, while keeping drift checks for exact pinned versions. (#37179) Thanks @vincentkoc.
 - iOS/Voice timing safety: guard system speech start/finish callbacks to the active utterance to avoid misattributed start events during rapid stop/restart cycles. (#33304) thanks @mbelinky; original implementation direction by @ngutman.
 - iOS/Talk incremental speech pacing: allow long punctuation-free assistant chunks to start speaking at safe whitespace boundaries so voice responses begin sooner instead of waiting for terminal punctuation. (#33305) thanks @mbelinky; original implementation by @ngutman.
 - iOS/Watch reply reliability: make watch session activation waiters robust under concurrent requests so status/send calls no longer hang intermittently, and align delegate callbacks with Swift 6 actor safety. (#33306) thanks @mbelinky; original implementation by @Rocuts.
@@ -100,6 +150,7 @@ Docs: https://docs.openclaw.ai
 - Telegram/multi-account default routing clarity: warn only for ambiguous (2+) account setups without an explicit default, add `openclaw doctor` warnings for missing/invalid multi-account defaults across channels, and document explicit-default guidance for channel routing and Telegram config. (#32544) thanks @Sid-Qin.
 - Telegram/plugin outbound hook parity: run `message_sending` + `message_sent` in Telegram reply delivery, include reply-path hook metadata (`mediaUrls`, `threadId`), and report `message_sent.success=false` when hooks blank text and no outbound message is delivered. (#32649) Thanks @KimGLee.
 - CLI/Coding-agent reliability: switch default `claude-cli` non-interactive args to `--permission-mode bypassPermissions`, auto-normalize legacy `--dangerously-skip-permissions` backend overrides to the modern permission-mode form, align coding-agent + live-test docs with the non-PTY Claude path, and emit session system-event heartbeat notices when CLI watchdog no-output timeouts terminate runs. (#28610, #31149, #34055). Thanks @niceysam, @cryptomaltese and @vincentkoc.
+- Gateway/OpenAI chat completions: parse active-turn `image_url` content parts (including parameterized data URIs and guarded URL sources), forward them as multimodal `images`, accept image-only user turns, enforce per-request image-part/byte budgets, default URL-based image fetches to disabled unless explicitly enabled by config, and redact image base64 data in cache-trace/provider payload diagnostics. (#17685) Thanks @vincentkoc
 - ACP/ACPX session bootstrap: retry with `sessions new` when `sessions ensure` returns no session identifiers so ACP spawns avoid `NO_SESSION`/`ACP_TURN_FAILED` failures on affected agents. (#28786, #31338, #34055). Thanks @Sid-Qin and @vincentkoc.
 - ACP/sessions_spawn parent stream visibility: add `streamTo: "parent"` for `runtime: "acp"` to forward initial child-run progress/no-output/completion updates back into the requester session as system events (instead of direct child delivery), and emit a tail-able session-scoped relay log (`<sessionId>.acp-stream.jsonl`, returned as `streamLogPath` when available), improving orchestrator visibility for blocked or long-running harness turns. (#34310, #29909; reopened from #34055). Thanks @vincentkoc.
 - Agents/bootstrap truncation warning handling: unify bootstrap budget/truncation analysis across embedded + CLI runtime, `/context`, and `openclaw doctor`; add `agents.defaults.bootstrapPromptTruncationWarning` (`off|once|always`, default `once`) and persist warning-signature metadata so truncation warnings are consistent and deduped across turns. (#32769) Thanks @gumadeiras.
@@ -110,6 +161,8 @@ Docs: https://docs.openclaw.ai
 - Agents/Compaction safeguard structure hardening: require exact fallback summary headings, sanitize untrusted compaction instruction text before prompt embedding, and keep structured sections when preserving all turns. (#25555) thanks @rodrigouroz.
 - Gateway/status self version reporting: make Gateway self version in `openclaw status` prefer runtime `VERSION` (while preserving explicit `OPENCLAW_VERSION` override), preventing stale post-upgrade app version output. (#32655) thanks @liuxiaopai-ai.
 - Memory/QMD index isolation: set `QMD_CONFIG_DIR` alongside `XDG_CONFIG_HOME` so QMD config state stays per-agent despite upstream XDG handling bugs, preventing cross-agent collection indexing and excess disk/CPU usage. (#27028) thanks @HenryLoenwind.
+- Memory/QMD collection safety: stop destructive collection rebinds when QMD `collection list` only reports names without path metadata, preventing `memory search` from dropping existing collections if re-add fails. (#36870) Thanks @Adnannnnnnna.
+- Memory/QMD duplicate-document recovery: detect `UNIQUE constraint failed: documents.collection, documents.path` update failures, rebuild managed collections once, and retry update so periodic QMD syncs recover instead of failing every run; includes regression coverage to avoid over-matching unrelated unique constraints. (#27649) Thanks @MiscMich.
 - Memory/local embedding initialization hardening: add regression coverage for transient initialization retry and mixed `embedQuery` + `embedBatch` concurrent startup to lock single-flight initialization behavior. (#15639) thanks @SubtleSpark.
 - CLI/Coding-agent reliability: switch default `claude-cli` non-interactive args to `--permission-mode bypassPermissions`, auto-normalize legacy `--dangerously-skip-permissions` backend overrides to the modern permission-mode form, align coding-agent + live-test docs with the non-PTY Claude path, and emit session system-event heartbeat notices when CLI watchdog no-output timeouts terminate runs. Related to #28261. Landed from contributor PRs #28610 and #31149. Thanks @niceysam, @cryptomaltese and @vincentkoc.
 - ACP/ACPX session bootstrap: retry with `sessions new` when `sessions ensure` returns no session identifiers so ACP spawns avoid `NO_SESSION`/`ACP_TURN_FAILED` failures on affected agents. Related to #28786. Landed from contributor PR #31338. Thanks @Sid-Qin and @vincentkoc.
@@ -118,6 +171,21 @@ Docs: https://docs.openclaw.ai
 - LINE/context and routing synthesis: fix group/room peer routing and command-authorization context propagation, and keep processing later events in mixed-success webhook batches. (from #21955, #24475, #27035, #28286) Thanks @lailoo, @mcaxtr, @jervyclaw, @Glucksberg, and @Takhoffman.
 - LINE/status/config/webhook synthesis: fix status false positives from snapshot/config state and accept LINE webhook HEAD probes for compatibility. (from #10487, #25726, #27537, #27908, #31387) Thanks @BlueBirdBack, @stakeswky, @loiie45e, @puritysb, and @mcaxtr.
 - LINE cleanup/test follow-ups: fold cleanup/test learnings into the synthesis review path while keeping runtime changes focused on regression fixes. (from #17630, #17289) Thanks @Clawborn and @davidahmann.
+- Mattermost/interactive buttons: add interactive button send/callback support with directory-based channel/user target resolution, and harden callbacks via account-scoped HMAC verification plus sender-scoped DM routing. (#19957) thanks @tonydehnke.
+- Feishu/groupPolicy legacy alias compatibility: treat legacy `groupPolicy: "allowall"` as `open` in both schema parsing and runtime policy checks so intended open-group configs no longer silently drop group messages when `groupAllowFrom` is empty. (from #36358) Thanks @Sid-Qin.
+- Mattermost/plugin SDK import policy: replace remaining monolithic `openclaw/plugin-sdk` imports in Mattermost mention-gating paths/tests with scoped subpaths (`openclaw/plugin-sdk/compat` and `openclaw/plugin-sdk/mattermost`) so `pnpm check` passes `lint:plugins:no-monolithic-plugin-sdk-entry-imports` on baseline. (#36480) Thanks @Takhoffman.
+- Telegram/polls: add Telegram poll action support to channel action discovery and tool/CLI poll flows, with multi-account discoverability gated to accounts that can actually execute polls (`sendMessage` + `poll`). (#36547) thanks @gumadeiras.
+- Agents/failover cooldown classification: stop treating generic `cooling down` text as provider `rate_limit` so healthy models no longer show false global cooldown/rate-limit warnings while explicit `model_cooldown` markers still trigger failover. (#32972) thanks @stakeswky.
+- Agents/failover service-unavailable handling: stop treating bare proxy/CDN `service unavailable` errors as provider overload while keeping them retryable via the timeout/failover path, so transient outages no longer show false rate-limit warnings or block fallback. (#36646) thanks @jnMetaCode.
+- Plugins/HTTP route migration diagnostics: rewrite legacy `api.registerHttpHandler(...)` loader failures into actionable migration guidance so doctor/plugin diagnostics point operators to `api.registerHttpRoute(...)` or `registerPluginHttpRoute(...)`. (#36794) Thanks @vincentkoc
+- Doctor/Heartbeat upgrade diagnostics: warn when heartbeat delivery is configured with an implicit `directPolicy` so upgrades pin direct/DM behavior explicitly instead of relying on the current default. (#36789) Thanks @vincentkoc.
+- Agents/current-time UTC anchor: append a machine-readable UTC suffix alongside local `Current time:` lines in shared cron-style prompt contexts so agents can compare UTC-stamped workspace timestamps without doing timezone math. (#32423) thanks @jriff.
+- TUI/webchat command-owner scope alignment: treat internal-channel gateway sessions with `operator.admin` as owner-authorized in command auth, restoring cron/gateway/connector tool access for affected TUI/webchat sessions while keeping external channels on identity-based owner checks. (from #35666, #35673, #35704) Thanks @Naylenv, @Octane0411, and @Sid-Qin.
+- Discord/inbound timeout isolation: separate inbound worker timeout tracking from listener timeout budgets so queued Discord replies are no longer dropped when listener watchdog windows expire mid-run. (#36602) Thanks @dutifulbob.
+- Memory/doctor SecretRef handling: treat SecretRef-backed memory-search API keys as configured, and fail embedding setup with explicit unresolved-secret errors instead of crashing. (#36835) Thanks @joshavant.
+- Memory/flush default prompt: ban timestamped variant filenames during default memory flush runs so durable notes stay in the canonical daily `memory/YYYY-MM-DD.md` file. (#34951) thanks @zerone0x.
+- Agents/reply delivery timing: flush embedded Pi block replies before waiting on compaction retries so already-generated assistant replies reach channels before compaction wait completes. (#35489) thanks @Sid-Qin.
+- Agents/gateway config guidance: stop exposing `config.schema` through the agent `gateway` tool, remove prompt/docs guidance that told agents to call it, and keep agents on `config.get` plus `config.patch`/`config.apply` for config changes. (#7382) thanks @kakuteki.
 
 ## 2026.3.2
 
@@ -143,6 +211,7 @@ Docs: https://docs.openclaw.ai
 - Plugin runtime/system: expose `runtime.system.requestHeartbeatNow(...)` so extensions can wake targeted sessions immediately after enqueueing system events. (#19464) Thanks @AustinEral.
 - Plugin runtime/events: expose `runtime.events.onAgentEvent` and `runtime.events.onSessionTranscriptUpdate` for extension-side subscriptions, and isolate transcript-listener failures so one faulty listener cannot break the entire update fanout. (#16044) Thanks @scifantastic.
 - CLI/Banner taglines: add `cli.banner.taglineMode` (`random` | `default` | `off`) to control funny tagline behavior in startup output, with docs + FAQ guidance and regression tests for config override behavior.
+- Agents/compaction safeguard quality-audit rollout: keep summary quality audits disabled by default unless `agents.defaults.compaction.qualityGuard` is explicitly enabled, and add config plumbing for bounded retry control. (#25556) thanks @rodrigouroz.
 
 ### Breaking
 
@@ -229,6 +298,7 @@ Docs: https://docs.openclaw.ai
 - Synology Chat/reply delivery: resolve webhook usernames to Chat API `user_id` values for outbound chatbot replies, avoiding mismatches between webhook user IDs and `method=chatbot` recipient IDs in multi-account setups. (#23709) Thanks @druide67.
 - Slack/thread context payloads: only inject thread starter/history text on first thread turn for new sessions while preserving thread metadata, reducing repeated context-token bloat on long-lived thread sessions. (#32133) Thanks @sourman.
 - Slack/session routing: keep top-level channel messages in one shared session when `replyToMode=off`, while preserving thread-scoped keys for true thread replies and non-off modes. (#32193) Thanks @bmendonca3.
+- Slack/app_mention dedupe race handling: keep seen-message dedupe to prevent duplicate replies while allowing a one-time app_mention retry when the paired message event was dropped pre-dispatch, so requireMention channels do not lose mentions under Slack event reordering. (#34937) Thanks @littleben.
 - Voice-call/webhook routing: require exact webhook path matches (instead of prefix matches) so lookalike paths cannot reach provider verification/dispatch logic. (#31930) Thanks @afurm.
 - Zalo/Pairing auth tests: add webhook regression coverage asserting DM pairing-store reads/writes remain account-scoped, preventing cross-account authorization bleed in multi-account setups. (#26121) Thanks @bmendonca3.
 - Zalouser/Pairing auth tests: add account-scoped DM pairing-store regression coverage (`monitor.account-scope.test.ts`) to prevent cross-account allowlist bleed in multi-account setups. (#26672) Thanks @bmendonca3.
@@ -334,6 +404,7 @@ Docs: https://docs.openclaw.ai
 - Cron/store migration: normalize legacy cron jobs with string `schedule` and top-level `command`/`timeout` fields into canonical schedule/payload/session-target shape on load, preventing schedule-error loops on old persisted stores. (#31926) Thanks @bmendonca3.
 - Tests/Windows backup rotation: skip chmod-only backup permission assertions on Windows while retaining compose/rotation/prune coverage across platforms to avoid false CI failures from Windows non-POSIX mode semantics. (#32286) Thanks @jalehman.
 - Tests/Subagent announce: set `OPENCLAW_TEST_FAST=1` before importing `subagent-announce` format suites so module-level fast-mode constants are captured deterministically on Windows CI, preventing timeout flakes in nested completion announce coverage. (#31370) Thanks @zwffff.
+- Control UI/markdown recursion fallback: catch markdown parser failures and safely render escaped plain-text fallback instead of crashing the Control UI on pathological markdown history payloads. (#36445, fixes #36213) Thanks @BinHPdev.
 
 ## 2026.3.1
 
@@ -466,9 +537,11 @@ Docs: https://docs.openclaw.ai
 ### Changes
 
 - Docs/Contributing: require before/after screenshots for UI or visual PRs in the pre-PR checklist. (#32206) Thanks @hydro13.
+- Models/OpenAI forward compat: add support for `openai/gpt-5.4`, `openai/gpt-5.4-pro`, and `openai-codex/gpt-5.4`, including direct OpenAI Responses `serviceTier` passthrough safeguards for valid values. (#36590) Thanks @dorukardahan.
 
 ### Fixes
 
+- Models/provider config precedence: prefer exact `models.providers.<name>` matches before normalized provider aliases in embedded model resolution, preventing alias/canonical key collisions from applying the wrong provider `api`, `baseUrl`, or headers. (#35934) thanks @RealKai42.
 - Logging/Subsystem console timestamps: route subsystem console timestamp rendering through `formatConsoleTimestamp(...)` so `pretty` and timestamp-prefix output use local timezone formatting consistently instead of inline UTC `toISOString()` paths. (#25970) Thanks @openperf.
 - Feishu/Multi-account + reply reliability: add `channels.feishu.defaultAccount` outbound routing support with schema validation, prevent inbound preview text from leaking into prompt system events, keep quoted-message extraction text-first (post/interactive/file placeholders instead of raw JSON), route Feishu video sends as `msg_type: "file"`, and avoid websocket event blocking by using non-blocking event handling in monitor dispatch. Landed from contributor PRs #31209, #29610, #30432, #30331, and #29501. Thanks @stakeswky, @hclsys, @bmendonca3, @patrick-yingxi-pan, and @zwffff.
 - Feishu/Target routing + replies + dedupe: normalize provider-prefixed targets (`feishu:`/`lark:`), prefer configured `channels.feishu.defaultAccount` for tool execution, honor Feishu outbound `renderMode` in adapter text/caption sends, fall back to normal send when reply targets are withdrawn/deleted, and add synchronous in-memory dedupe guard for concurrent duplicate inbound events. Landed from contributor PRs #30428, #30438, #29958, #30444, and #29463. Thanks @bmendonca3 and @Yaxuan42.
@@ -715,6 +788,7 @@ Docs: https://docs.openclaw.ai
 - Channels/Multi-account config: when adding a non-default channel account to a single-account top-level channel setup, move existing account-scoped top-level single-account values into `channels.<channel>.accounts.default` before writing the new account so the original account keeps working without duplicated account values at channel root; `openclaw doctor --fix` now repairs previously mixed channel account shapes the same way. (#27334) thanks @gumadeiras.
 - iOS/Talk mode: stop injecting the voice directive hint into iOS Talk prompts and remove the Voice Directive Hint setting, reducing model bias toward tool-style TTS directives and keeping relay responses text-first by default. (#27543) thanks @ngutman.
 - CI/Windows: shard the Windows `checks-windows` test lane into two matrix jobs and honor explicit shard index overrides in `scripts/test-parallel.mjs` to reduce CI critical-path wall time. (#27234) Thanks @joshavant.
+- Mattermost/mention gating: honor `chatmode: "onmessage"` account override in inbound group/channel mention-gate resolution, while preserving explicit group `requireMention` config precedence and adding verbose drop diagnostics for skipped inbound posts. (#27160) thanks @turian.
 
 ## 2026.2.25
 

README.md

@@ -549,7 +549,7 @@ Thanks to all clawtributors:
   <a href="https://github.com/mattqdev"><img src="https://avatars.githubusercontent.com/u/115874885?v=4&s=48" width="48" height="48" alt="MattQ" title="MattQ"/></a> <a href="https://github.com/Milofax"><img src="https://avatars.githubusercontent.com/u/2537423?v=4&s=48" width="48" height="48" alt="Milofax" title="Milofax"/></a> <a href="https://github.com/stevebot-alive"><img src="https://avatars.githubusercontent.com/u/261149299?v=4&s=48" width="48" height="48" alt="Steve (OpenClaw)" title="Steve (OpenClaw)"/></a> <a href="https://github.com/ZetiMente"><img src="https://avatars.githubusercontent.com/u/76985631?v=4&s=48" width="48" height="48" alt="Matthew" title="Matthew"/></a> <a href="https://github.com/Cassius0924"><img src="https://avatars.githubusercontent.com/u/62874592?v=4&s=48" width="48" height="48" alt="Cassius0924" title="Cassius0924"/></a> <a href="https://github.com/0xbrak"><img src="https://avatars.githubusercontent.com/u/181251288?v=4&s=48" width="48" height="48" alt="0xbrak" title="0xbrak"/></a> <a href="https://github.com/8BlT"><img src="https://avatars.githubusercontent.com/u/162764392?v=4&s=48" width="48" height="48" alt="8BlT" title="8BlT"/></a> <a href="https://github.com/Abdul535"><img src="https://avatars.githubusercontent.com/u/54276938?v=4&s=48" width="48" height="48" alt="Abdul535" title="Abdul535"/></a> <a href="https://github.com/abhaymundhara"><img src="https://avatars.githubusercontent.com/u/62872231?v=4&s=48" width="48" height="48" alt="abhaymundhara" title="abhaymundhara"/></a> <a href="https://github.com/aduk059"><img src="https://avatars.githubusercontent.com/u/257603478?v=4&s=48" width="48" height="48" alt="aduk059" title="aduk059"/></a>
   <a href="https://github.com/afurm"><img src="https://avatars.githubusercontent.com/u/6375192?v=4&s=48" width="48" height="48" alt="afurm" title="afurm"/></a> <a href="https://github.com/aisling404"><img src="https://avatars.githubusercontent.com/u/211950534?v=4&s=48" width="48" height="48" alt="aisling404" title="aisling404"/></a> <a href="https://github.com/akari-musubi"><img src="https://avatars.githubusercontent.com/u/259925157?v=4&s=48" width="48" height="48" alt="akari-musubi" title="akari-musubi"/></a> <a href="https://github.com/albertlieyingadrian"><img src="https://avatars.githubusercontent.com/u/12984659?v=4&s=48" width="48" height="48" alt="albertlieyingadrian" title="albertlieyingadrian"/></a> <a href="https://github.com/Alex-Alaniz"><img src="https://avatars.githubusercontent.com/u/88956822?v=4&s=48" width="48" height="48" alt="Alex-Alaniz" title="Alex-Alaniz"/></a> <a href="https://github.com/ali-aljufairi"><img src="https://avatars.githubusercontent.com/u/85583841?v=4&s=48" width="48" height="48" alt="ali-aljufairi" title="ali-aljufairi"/></a> <a href="https://github.com/altaywtf"><img src="https://avatars.githubusercontent.com/u/9790196?v=4&s=48" width="48" height="48" alt="altaywtf" title="altaywtf"/></a> <a href="https://github.com/araa47"><img src="https://avatars.githubusercontent.com/u/22760261?v=4&s=48" width="48" height="48" alt="araa47" title="araa47"/></a> <a href="https://github.com/Asleep123"><img src="https://avatars.githubusercontent.com/u/122379135?v=4&s=48" width="48" height="48" alt="Asleep123" title="Asleep123"/></a> <a href="https://github.com/avacadobanana352"><img src="https://avatars.githubusercontent.com/u/263496834?v=4&s=48" width="48" height="48" alt="avacadobanana352" title="avacadobanana352"/></a>
   <a href="https://github.com/barronlroth"><img src="https://avatars.githubusercontent.com/u/5567884?v=4&s=48" width="48" height="48" alt="barronlroth" title="barronlroth"/></a> <a href="https://github.com/bennewton999"><img src="https://avatars.githubusercontent.com/u/458991?v=4&s=48" width="48" height="48" alt="bennewton999" title="bennewton999"/></a> <a href="https://github.com/bguidolim"><img src="https://avatars.githubusercontent.com/u/987360?v=4&s=48" width="48" height="48" alt="bguidolim" title="bguidolim"/></a> <a href="https://github.com/bigwest60"><img src="https://avatars.githubusercontent.com/u/12373979?v=4&s=48" width="48" height="48" alt="bigwest60" title="bigwest60"/></a> <a href="https://github.com/caelum0x"><img src="https://avatars.githubusercontent.com/u/130079063?v=4&s=48" width="48" height="48" alt="caelum0x" title="caelum0x"/></a> <a href="https://github.com/championswimmer"><img src="https://avatars.githubusercontent.com/u/1327050?v=4&s=48" width="48" height="48" alt="championswimmer" title="championswimmer"/></a> <a href="https://github.com/dutifulbob"><img src="https://avatars.githubusercontent.com/u/261991368?v=4&s=48" width="48" height="48" alt="dutifulbob" title="dutifulbob"/></a> <a href="https://github.com/eternauta1337"><img src="https://avatars.githubusercontent.com/u/550409?v=4&s=48" width="48" height="48" alt="eternauta1337" title="eternauta1337"/></a> <a href="https://github.com/foeken"><img src="https://avatars.githubusercontent.com/u/13864?v=4&s=48" width="48" height="48" alt="foeken" title="foeken"/></a> <a href="https://github.com/gittb"><img src="https://avatars.githubusercontent.com/u/8284364?v=4&s=48" width="48" height="48" alt="gittb" title="gittb"/></a>
-  <a href="https://github.com/HeimdallStrategy"><img src="https://avatars.githubusercontent.com/u/223014405?v=4&s=48" width="48" height="48" alt="HeimdallStrategy" title="HeimdallStrategy"/></a> <a href="https://github.com/junsuwhy"><img src="https://avatars.githubusercontent.com/u/4645498?v=4&s=48" width="48" height="48" alt="junsuwhy" title="junsuwhy"/></a> <a href="https://github.com/knocte"><img src="https://avatars.githubusercontent.com/u/331303?v=4&s=48" width="48" height="48" alt="knocte" title="knocte"/></a> <a href="https://github.com/MackDing"><img src="https://avatars.githubusercontent.com/u/19878893?v=4&s=48" width="48" height="48" alt="MackDing" title="MackDing"/></a> <a href="https://github.com/nobrainer-tech"><img src="https://avatars.githubusercontent.com/u/445466?v=4&s=48" width="48" height="48" alt="nobrainer-tech" title="nobrainer-tech"/></a> <a href="https://github.com/Noctivoro"><img src="https://avatars.githubusercontent.com/u/183974570?v=4&s=48" width="48" height="48" alt="Noctivoro" title="Noctivoro"/></a> <a href="https://github.com/Raikan10"><img src="https://avatars.githubusercontent.com/u/20675476?v=4&s=48" width="48" height="48" alt="Raikan10" title="Raikan10"/></a> <a href="https://github.com/Swader"><img src="https://avatars.githubusercontent.com/u/1430603?v=4&s=48" width="48" height="48" alt="Swader" title="Swader"/></a> <a href="https://github.com/alexstyl"><img src="https://avatars.githubusercontent.com/u/1665273?v=4&s=48" width="48" height="48" alt="alexstyl" title="alexstyl"/></a> <a href="https://github.com/ethanpalm"><img src="https://avatars.githubusercontent.com/u/56270045?v=4&s=48" width="48" height="48" alt="Ethan Palm" title="Ethan Palm"/></a>
+  <a href="https://github.com/HeimdallStrategy"><img src="https://avatars.githubusercontent.com/u/223014405?v=4&s=48" width="48" height="48" alt="HeimdallStrategy" title="HeimdallStrategy"/></a> <a href="https://github.com/junsuwhy"><img src="https://avatars.githubusercontent.com/u/4645498?v=4&s=48" width="48" height="48" alt="junsuwhy" title="junsuwhy"/></a> <a href="https://github.com/knocte"><img src="https://avatars.githubusercontent.com/u/331303?v=4&s=48" width="48" height="48" alt="knocte" title="knocte"/></a> <a href="https://github.com/MackDing"><img src="https://avatars.githubusercontent.com/u/19878893?v=4&s=48" width="48" height="48" alt="MackDing" title="MackDing"/></a> <a href="https://github.com/nobrainer-tech"><img src="https://avatars.githubusercontent.com/u/445466?v=4&s=48" width="48" height="48" alt="nobrainer-tech" title="nobrainer-tech"/></a> <a href="https://github.com/Noctivoro"><img src="https://avatars.githubusercontent.com/u/183974570?v=4&s=48" width="48" height="48" alt="Noctivoro" title="Noctivoro"/></a> <a href="https://github.com/Raikan10"><img src="https://avatars.githubusercontent.com/u/20675476?v=4&s=48" width="48" height="48" alt="Raikan10" title="Raikan10"/></a> <a href="https://github.com/Swader"><img src="https://avatars.githubusercontent.com/u/1430603?v=4&s=48" width="48" height="48" alt="Swader" title="Swader"/></a> <a href="https://github.com/algal"><img src="https://avatars.githubusercontent.com/u/264412?v=4&s=48" width="48" height="48" alt="Alexis Gallagher" title="Alexis Gallagher"/></a> <a href="https://github.com/alexstyl"><img src="https://avatars.githubusercontent.com/u/1665273?v=4&s=48" width="48" height="48" alt="alexstyl" title="alexstyl"/></a> <a href="https://github.com/ethanpalm"><img src="https://avatars.githubusercontent.com/u/56270045?v=4&s=48" width="48" height="48" alt="Ethan Palm" title="Ethan Palm"/></a>
   <a href="https://github.com/yingchunbai"><img src="https://avatars.githubusercontent.com/u/33477283?v=4&s=48" width="48" height="48" alt="yingchunbai" title="yingchunbai"/></a> <a href="https://github.com/joshrad-dev"><img src="https://avatars.githubusercontent.com/u/62785552?v=4&s=48" width="48" height="48" alt="joshrad-dev" title="joshrad-dev"/></a> <a href="https://github.com/danballance"><img src="https://avatars.githubusercontent.com/u/13839912?v=4&s=48" width="48" height="48" alt="Dan Ballance" title="Dan Ballance"/></a> <a href="https://github.com/GHesericsu"><img src="https://avatars.githubusercontent.com/u/60202455?v=4&s=48" width="48" height="48" alt="Eric Su" title="Eric Su"/></a> <a href="https://github.com/kimitaka"><img src="https://avatars.githubusercontent.com/u/167225?v=4&s=48" width="48" height="48" alt="Kimitaka Watanabe" title="Kimitaka Watanabe"/></a> <a href="https://github.com/itsjling"><img src="https://avatars.githubusercontent.com/u/2521993?v=4&s=48" width="48" height="48" alt="Justin Ling" title="Justin Ling"/></a> <a href="https://github.com/lutr0"><img src="https://avatars.githubusercontent.com/u/76906369?v=4&s=48" width="48" height="48" alt="lutr0" title="lutr0"/></a> <a href="https://github.com/RayBB"><img src="https://avatars.githubusercontent.com/u/921217?v=4&s=48" width="48" height="48" alt="Raymond Berger" title="Raymond Berger"/></a> <a href="https://github.com/atalovesyou"><img src="https://avatars.githubusercontent.com/u/3534502?v=4&s=48" width="48" height="48" alt="atalovesyou" title="atalovesyou"/></a> <a href="https://github.com/jayhickey"><img src="https://avatars.githubusercontent.com/u/1676460?v=4&s=48" width="48" height="48" alt="jayhickey" title="jayhickey"/></a>
   <a href="https://github.com/jonasjancarik"><img src="https://avatars.githubusercontent.com/u/2459191?v=4&s=48" width="48" height="48" alt="jonasjancarik" title="jonasjancarik"/></a> <a href="https://github.com/latitudeki5223"><img src="https://avatars.githubusercontent.com/u/119656367?v=4&s=48" width="48" height="48" alt="latitudeki5223" title="latitudeki5223"/></a> <a href="https://github.com/minghinmatthewlam"><img src="https://avatars.githubusercontent.com/u/14224566?v=4&s=48" width="48" height="48" alt="minghinmatthewlam" title="minghinmatthewlam"/></a> <a href="https://github.com/rafaelreis-r"><img src="https://avatars.githubusercontent.com/u/57492577?v=4&s=48" width="48" height="48" alt="rafaelreis-r" title="rafaelreis-r"/></a> <a href="https://github.com/ratulsarna"><img src="https://avatars.githubusercontent.com/u/105903728?v=4&s=48" width="48" height="48" alt="ratulsarna" title="ratulsarna"/></a> <a href="https://github.com/timkrase"><img src="https://avatars.githubusercontent.com/u/38947626?v=4&s=48" width="48" height="48" alt="timkrase" title="timkrase"/></a> <a href="https://github.com/efe-buken"><img src="https://avatars.githubusercontent.com/u/262546946?v=4&s=48" width="48" height="48" alt="efe-buken" title="efe-buken"/></a> <a href="https://github.com/manmal"><img src="https://avatars.githubusercontent.com/u/142797?v=4&s=48" width="48" height="48" alt="manmal" title="manmal"/></a> <a href="https://github.com/easternbloc"><img src="https://avatars.githubusercontent.com/u/92585?v=4&s=48" width="48" height="48" alt="easternbloc" title="easternbloc"/></a> <a href="https://github.com/ManuelHettich"><img src="https://avatars.githubusercontent.com/u/17690367?v=4&s=48" width="48" height="48" alt="manuelhettich" title="manuelhettich"/></a>
   <a href="https://github.com/sktbrd"><img src="https://avatars.githubusercontent.com/u/116202536?v=4&s=48" width="48" height="48" alt="sktbrd" title="sktbrd"/></a> <a href="https://github.com/larlyssa"><img src="https://avatars.githubusercontent.com/u/13128869?v=4&s=48" width="48" height="48" alt="larlyssa" title="larlyssa"/></a> <a href="https://github.com/Mind-Dragon"><img src="https://avatars.githubusercontent.com/u/262945885?v=4&s=48" width="48" height="48" alt="Mind-Dragon" title="Mind-Dragon"/></a> <a href="https://github.com/pcty-nextgen-service-account"><img src="https://avatars.githubusercontent.com/u/112553441?v=4&s=48" width="48" height="48" alt="pcty-nextgen-service-account" title="pcty-nextgen-service-account"/></a> <a href="https://github.com/tmchow"><img src="https://avatars.githubusercontent.com/u/517103?v=4&s=48" width="48" height="48" alt="tmchow" title="tmchow"/></a> <a href="https://github.com/uli-will-code"><img src="https://avatars.githubusercontent.com/u/49715419?v=4&s=48" width="48" height="48" alt="uli-will-code" title="uli-will-code"/></a> <a href="https://github.com/mgratch"><img src="https://avatars.githubusercontent.com/u/2238658?v=4&s=48" width="48" height="48" alt="Marc Gratch" title="Marc Gratch"/></a> <a href="https://github.com/JackyWay"><img src="https://avatars.githubusercontent.com/u/53031570?v=4&s=48" width="48" height="48" alt="JackyWay" title="JackyWay"/></a> <a href="https://github.com/aaronveklabs"><img src="https://avatars.githubusercontent.com/u/225997828?v=4&s=48" width="48" height="48" alt="aaronveklabs" title="aaronveklabs"/></a> <a href="https://github.com/CJWTRUST"><img src="https://avatars.githubusercontent.com/u/235565898?v=4&s=48" width="48" height="48" alt="CJWTRUST" title="CJWTRUST"/></a>

changelog/fragments/pr-feishu-reply-mechanism.md

@@ -1 +0,0 @@
-- Feishu reply routing now uses one canonical reply-target path across inbound and outbound flows: normal groups reply to the triggering message while topic-mode groups stay on topic roots, outbound sends preserve `replyToId`/`threadId`, withdrawn reply targets fall back to direct sends, and cron duplicate suppression normalizes Feishu/Lark target IDs consistently (#32980, #32958, #33572, #33526; #33789, #33575, #33515, #33161). Thanks @guoqunabc, @bmendonca3, @MunemHashmi, and @Jimmy-xuzimo.

docs/automation/cron-jobs.md

@@ -176,6 +176,7 @@ Common `agentTurn` fields:
 - `message`: required text prompt.
 - `model` / `thinking`: optional overrides (see below).
 - `timeoutSeconds`: optional timeout override.
+- `lightContext`: optional lightweight bootstrap mode for jobs that do not need workspace bootstrap file injection.
 
 Delivery config:
 
@@ -235,6 +236,14 @@ Resolution priority:
 2. Hook-specific defaults (e.g., `hooks.gmail.model`)
 3. Agent config default
 
+### Lightweight bootstrap context
+
+Isolated jobs (`agentTurn`) can set `lightContext: true` to run with lightweight bootstrap context.
+
+- Use this for scheduled chores that do not need workspace bootstrap file injection.
+- In practice, the embedded runtime runs with `bootstrapContextMode: "lightweight"`, which keeps cron bootstrap context empty on purpose.
+- CLI equivalents: `openclaw cron add --light-context ...` and `openclaw cron edit --light-context`.
+
 ### Delivery (channel + target)
 
 Isolated jobs can deliver output to a channel via the top-level `delivery` config:
@@ -298,7 +307,8 @@ Recurring, isolated job with delivery:
   "wakeMode": "next-heartbeat",
   "payload": {
     "kind": "agentTurn",
-    "message": "Summarize overnight updates."
+    "message": "Summarize overnight updates.",
+    "lightContext": true
   },
   "delivery": {
     "mode": "announce",

docs/automation/hooks.md

@@ -243,6 +243,14 @@ Triggered when agent commands are issued:
 - **`command:reset`**: When `/reset` command is issued
 - **`command:stop`**: When `/stop` command is issued
 
+### Session Events
+
+- **`session:compact:before`**: Right before compaction summarizes history
+- **`session:compact:after`**: After compaction completes with summary metadata
+
+Internal hook payloads emit these as `type: "session"` with `action: "compact:before"` / `action: "compact:after"`; listeners subscribe with the combined keys above.
+Specific handler registration uses the literal key format `${type}:${action}`. For these events, register `session:compact:before` and `session:compact:after`.
+
 ### Agent Events
 
 - **`agent:bootstrap`**: Before workspace bootstrap files are injected (hooks may mutate `context.bootstrapFiles`)
@@ -351,6 +359,13 @@ These hooks are not event-stream listeners; they let plugins synchronously adjus
 
 - **`tool_result_persist`**: transform tool results before they are written to the session transcript. Must be synchronous; return the updated tool result payload or `undefined` to keep it as-is. See [Agent Loop](/concepts/agent-loop).
 
+### Plugin Hook Events
+
+Compaction lifecycle hooks exposed through the plugin hook runner:
+
+- **`before_compaction`**: Runs before compaction with count/token metadata
+- **`after_compaction`**: Runs after compaction with compaction summary metadata
+
 ### Future Events
 
 Planned event types:

docs/automation/poll.md

@@ -10,6 +10,7 @@ title: "Polls"
 
 ## Supported channels
 
+- Telegram
 - WhatsApp (web channel)
 - Discord
 - MS Teams (Adaptive Cards)
@@ -17,6 +18,13 @@ title: "Polls"
 ## CLI
 
 ```bash
+# Telegram
+openclaw message poll --channel telegram --target 123456789 \
+  --poll-question "Ship it?" --poll-option "Yes" --poll-option "No"
+openclaw message poll --channel telegram --target -1001234567890:topic:42 \
+  --poll-question "Pick a time" --poll-option "10am" --poll-option "2pm" \
+  --poll-duration-seconds 300
+
 # WhatsApp
 openclaw message poll --target +15555550123 \
   --poll-question "Lunch today?" --poll-option "Yes" --poll-option "No" --poll-option "Maybe"
@@ -36,9 +44,11 @@ openclaw message poll --channel msteams --target conversation:19:abc@thread.tacv
 
 Options:
 
-- `--channel`: `whatsapp` (default), `discord`, or `msteams`
+- `--channel`: `whatsapp` (default), `telegram`, `discord`, or `msteams`
 - `--poll-multi`: allow selecting multiple options
 - `--poll-duration-hours`: Discord-only (defaults to 24 when omitted)
+- `--poll-duration-seconds`: Telegram-only (5-600 seconds)
+- `--poll-anonymous` / `--poll-public`: Telegram-only poll visibility
 
 ## Gateway RPC
 
@@ -51,11 +61,14 @@ Params:
 - `options` (string[], required)
 - `maxSelections` (number, optional)
 - `durationHours` (number, optional)
+- `durationSeconds` (number, optional, Telegram-only)
+- `isAnonymous` (boolean, optional, Telegram-only)
 - `channel` (string, optional, default: `whatsapp`)
 - `idempotencyKey` (string, required)
 
 ## Channel differences
 
+- Telegram: 2-10 options. Supports forum topics via `threadId` or `:topic:` targets. Uses `durationSeconds` instead of `durationHours`, limited to 5-600 seconds. Supports anonymous and public polls.
 - WhatsApp: 2-12 options, `maxSelections` must be within option count, ignores `durationHours`.
 - Discord: 2-10 options, `durationHours` clamped to 1-768 hours (default 24). `maxSelections > 1` enables multi-select; Discord does not support a strict selection count.
 - MS Teams: Adaptive Card polls (OpenClaw-managed). No native poll API; `durationHours` is ignored.
@@ -64,6 +77,10 @@ Params:
 
 Use the `message` tool with `poll` action (`to`, `pollQuestion`, `pollOption`, optional `pollMulti`, `pollDurationHours`, `channel`).
 
+For Telegram, the tool also accepts `pollDurationSeconds`, `pollAnonymous`, and `pollPublic`.
+
+Use `action: "poll"` for poll creation. Poll fields passed with `action: "send"` are rejected.
+
 Note: Discord has no “pick exactly N” mode; `pollMulti` maps to multi-select.
 Teams polls are rendered as Adaptive Cards and require the gateway to stay online
 to record votes in `~/.openclaw/msteams-polls.json`.

docs/channels/discord.md

@@ -1102,12 +1102,19 @@ openclaw logs --follow
 
     - `Listener DiscordMessageListener timed out after 30000ms for event MESSAGE_CREATE`
     - `Slow listener detected ...`
+    - `discord inbound worker timed out after ...`
 
-    Canonical knob:
+    Listener budget knob:
 
     - single-account: `channels.discord.eventQueue.listenerTimeout`
     - multi-account: `channels.discord.accounts.<accountId>.eventQueue.listenerTimeout`
 
+    Worker run timeout knob:
+
+    - single-account: `channels.discord.inboundWorker.runTimeoutMs`
+    - multi-account: `channels.discord.accounts.<accountId>.inboundWorker.runTimeoutMs`
+    - default: `1800000` (30 minutes); set `0` to disable
+
     Recommended baseline:
 
 ```json5
@@ -1119,6 +1126,9 @@ openclaw logs --follow
           eventQueue: {
             listenerTimeout: 120000,
           },
+          inboundWorker: {
+            runTimeoutMs: 1800000,
+          },
         },
       },
     },
@@ -1126,7 +1136,8 @@ openclaw logs --follow
 }
 ```
 
-    Tune this first before adding alternate timeout controls elsewhere.
+    Use `eventQueue.listenerTimeout` for slow listener setup and `inboundWorker.runTimeoutMs`
+    only if you want a separate safety valve for queued agent turns.
 
   </Accordion>
 
@@ -1177,7 +1188,8 @@ High-signal Discord fields:
 - startup/auth: `enabled`, `token`, `accounts.*`, `allowBots`
 - policy: `groupPolicy`, `dm.*`, `guilds.*`, `guilds.*.channels.*`
 - command: `commands.native`, `commands.useAccessGroups`, `configWrites`, `slashCommand.*`
-- event queue: `eventQueue.listenerTimeout` (canonical), `eventQueue.maxQueueSize`, `eventQueue.maxConcurrency`
+- event queue: `eventQueue.listenerTimeout` (listener budget), `eventQueue.maxQueueSize`, `eventQueue.maxConcurrency`
+- inbound worker: `inboundWorker.runTimeoutMs`
 - reply/history: `replyToMode`, `historyLimit`, `dmHistoryLimit`, `dms.*.historyLimit`
 - delivery: `textChunkLimit`, `chunkMode`, `maxLinesPerMessage`
 - streaming: `streaming` (legacy alias: `streamMode`), `draftChunk`, `blockStreaming`, `blockStreamingCoalesce`

docs/channels/mattermost.md

@@ -175,6 +175,151 @@ Config:
 - `channels.mattermost.actions.reactions`: enable/disable reaction actions (default true).
 - Per-account override: `channels.mattermost.accounts.<id>.actions.reactions`.
 
+## Interactive buttons (message tool)
+
+Send messages with clickable buttons. When a user clicks a button, the agent receives the
+selection and can respond.
+
+Enable buttons by adding `inlineButtons` to the channel capabilities:
+
+```json5
+{
+  channels: {
+    mattermost: {
+      capabilities: ["inlineButtons"],
+    },
+  },
+}
+```
+
+Use `message action=send` with a `buttons` parameter. Buttons are a 2D array (rows of buttons):
+
+```
+message action=send channel=mattermost target=channel:<channelId> buttons=[[{"text":"Yes","callback_data":"yes"},{"text":"No","callback_data":"no"}]]
+```
+
+Button fields:
+
+- `text` (required): display label.
+- `callback_data` (required): value sent back on click (used as the action ID).
+- `style` (optional): `"default"`, `"primary"`, or `"danger"`.
+
+When a user clicks a button:
+
+1. All buttons are replaced with a confirmation line (e.g., "✓ **Yes** selected by @user").
+2. The agent receives the selection as an inbound message and responds.
+
+Notes:
+
+- Button callbacks use HMAC-SHA256 verification (automatic, no config needed).
+- Mattermost strips callback data from its API responses (security feature), so all buttons
+  are removed on click — partial removal is not possible.
+- Action IDs containing hyphens or underscores are sanitized automatically
+  (Mattermost routing limitation).
+
+Config:
+
+- `channels.mattermost.capabilities`: array of capability strings. Add `"inlineButtons"` to
+  enable the buttons tool description in the agent system prompt.
+
+### Direct API integration (external scripts)
+
+External scripts and webhooks can post buttons directly via the Mattermost REST API
+instead of going through the agent's `message` tool. Use `buildButtonAttachments()` from
+the extension when possible; if posting raw JSON, follow these rules:
+
+**Payload structure:**
+
+```json5
+{
+  channel_id: "<channelId>",
+  message: "Choose an option:",
+  props: {
+    attachments: [
+      {
+        actions: [
+          {
+            id: "mybutton01", // alphanumeric only — see below
+            type: "button", // required, or clicks are silently ignored
+            name: "Approve", // display label
+            style: "primary", // optional: "default", "primary", "danger"
+            integration: {
+              url: "http://localhost:18789/mattermost/interactions/default",
+              context: {
+                action_id: "mybutton01", // must match button id (for name lookup)
+                action: "approve",
+                // ... any custom fields ...
+                _token: "<hmac>", // see HMAC section below
+              },
+            },
+          },
+        ],
+      },
+    ],
+  },
+}
+```
+
+**Critical rules:**
+
+1. Attachments go in `props.attachments`, not top-level `attachments` (silently ignored).
+2. Every action needs `type: "button"` — without it, clicks are swallowed silently.
+3. Every action needs an `id` field — Mattermost ignores actions without IDs.
+4. Action `id` must be **alphanumeric only** (`[a-zA-Z0-9]`). Hyphens and underscores break
+   Mattermost's server-side action routing (returns 404). Strip them before use.
+5. `context.action_id` must match the button's `id` so the confirmation message shows the
+   button name (e.g., "Approve") instead of a raw ID.
+6. `context.action_id` is required — the interaction handler returns 400 without it.
+
+**HMAC token generation:**
+
+The gateway verifies button clicks with HMAC-SHA256. External scripts must generate tokens
+that match the gateway's verification logic:
+
+1. Derive the secret from the bot token:
+   `HMAC-SHA256(key="openclaw-mattermost-interactions", data=botToken)`
+2. Build the context object with all fields **except** `_token`.
+3. Serialize with **sorted keys** and **no spaces** (the gateway uses `JSON.stringify`
+   with sorted keys, which produces compact output).
+4. Sign: `HMAC-SHA256(key=secret, data=serializedContext)`
+5. Add the resulting hex digest as `_token` in the context.
+
+Python example:
+
+```python
+import hmac, hashlib, json
+
+secret = hmac.new(
+    b"openclaw-mattermost-interactions",
+    bot_token.encode(), hashlib.sha256
+).hexdigest()
+
+ctx = {"action_id": "mybutton01", "action": "approve"}
+payload = json.dumps(ctx, sort_keys=True, separators=(",", ":"))
+token = hmac.new(secret.encode(), payload.encode(), hashlib.sha256).hexdigest()
+
+context = {**ctx, "_token": token}
+```
+
+Common HMAC pitfalls:
+
+- Python's `json.dumps` adds spaces by default (`{"key": "val"}`). Use
+  `separators=(",", ":")` to match JavaScript's compact output (`{"key":"val"}`).
+- Always sign **all** context fields (minus `_token`). The gateway strips `_token` then
+  signs everything remaining. Signing a subset causes silent verification failure.
+- Use `sort_keys=True` — the gateway sorts keys before signing, and Mattermost may
+  reorder context fields when storing the payload.
+- Derive the secret from the bot token (deterministic), not random bytes. The secret
+  must be the same across the process that creates buttons and the gateway that verifies.
+
+## Directory adapter
+
+The Mattermost plugin includes a directory adapter that resolves channel and user names
+via the Mattermost API. This enables `#channel-name` and `@username` targets in
+`openclaw message send` and cron/webhook deliveries.
+
+No configuration is needed — the adapter uses the bot token from the account config.
+
 ## Multi-account
 
 Mattermost supports multiple accounts under `channels.mattermost.accounts`:
@@ -197,3 +342,10 @@ Mattermost supports multiple accounts under `channels.mattermost.accounts`:
 - No replies in channels: ensure the bot is in the channel and mention it (oncall), use a trigger prefix (onchar), or set `chatmode: "onmessage"`.
 - Auth errors: check the bot token, base URL, and whether the account is enabled.
 - Multi-account issues: env vars only apply to the `default` account.
+- Buttons appear as white boxes: the agent may be sending malformed button data. Check that each button has both `text` and `callback_data` fields.
+- Buttons render but clicks do nothing: verify `AllowedUntrustedInternalConnections` in Mattermost server config includes `127.0.0.1 localhost`, and that `EnablePostActionIntegration` is `true` in ServiceSettings.
+- Buttons return 404 on click: the button `id` likely contains hyphens or underscores. Mattermost's action router breaks on non-alphanumeric IDs. Use `[a-zA-Z0-9]` only.
+- Gateway logs `invalid _token`: HMAC mismatch. Check that you sign all context fields (not a subset), use sorted keys, and use compact JSON (no spaces). See the HMAC section above.
+- Gateway logs `missing _token in context`: the `_token` field is not in the button's context. Ensure it is included when building the integration payload.
+- Confirmation shows raw ID instead of button name: `context.action_id` does not match the button's `id`. Set both to the same sanitized value.
+- Agent doesn't know about buttons: add `capabilities: ["inlineButtons"]` to the Mattermost channel config.

docs/channels/slack.md

@@ -321,7 +321,21 @@ Resolution order:
 Notes:
 
 - Slack expects shortcodes (for example `"eyes"`).
-- Use `""` to disable the reaction for a channel or account.
+- Use `""` to disable the reaction for the Slack account or globally.
+
+## Typing reaction fallback
+
+`typingReaction` adds a temporary reaction to the inbound Slack message while OpenClaw is processing a reply, then removes it when the run finishes. This is a useful fallback when Slack native assistant typing is unavailable, especially in DMs.
+
+Resolution order:
+
+- `channels.slack.accounts.<accountId>.typingReaction`
+- `channels.slack.typingReaction`
+
+Notes:
+
+- Slack expects shortcodes (for example `"hourglass_flowing_sand"`).
+- The reaction is best-effort and cleanup is attempted automatically after the reply or failure path completes.
 
 ## Manifest and scope checklist
 

docs/channels/telegram.md

@@ -524,6 +524,13 @@ curl "https://api.telegram.org/bot<bot_token>/getUpdates"
 
     This is currently scoped to forum topics in groups and supergroups.
 
+    **Thread-bound ACP spawn from chat**:
+
+    - `/acp spawn <agent> --thread here|auto` can bind the current Telegram topic to a new ACP session.
+    - Follow-up topic messages route to the bound ACP session directly (no `/acp steer` required).
+    - OpenClaw pins the spawn confirmation message in-topic after a successful bind.
+    - Requires `channels.telegram.threadBindings.spawnAcpSessions=true`.
+
     Template context includes:
 
     - `MessageThreadId`
@@ -732,6 +739,28 @@ openclaw message send --channel telegram --target 123456789 --message "hi"
 openclaw message send --channel telegram --target @name --message "hi"
 ```
 
+    Telegram polls use `openclaw message poll` and support forum topics:
+
+```bash
+openclaw message poll --channel telegram --target 123456789 \
+  --poll-question "Ship it?" --poll-option "Yes" --poll-option "No"
+openclaw message poll --channel telegram --target -1001234567890:topic:42 \
+  --poll-question "Pick a time" --poll-option "10am" --poll-option "2pm" \
+  --poll-duration-seconds 300 --poll-public
+```
+
+    Telegram-only poll flags:
+
+    - `--poll-duration-seconds` (5-600)
+    - `--poll-anonymous`
+    - `--poll-public`
+    - `--thread-id` for forum topics (or use a `:topic:` target)
+
+    Action gating:
+
+    - `channels.telegram.actions.sendMessage=false` disables outbound Telegram messages, including polls
+    - `channels.telegram.actions.poll=false` disables Telegram poll creation while leaving regular sends enabled
+
   </Accordion>
 </AccordionGroup>
 
@@ -813,6 +842,7 @@ Primary reference:
 - `channels.telegram.tokenFile`: read token from file path.
 - `channels.telegram.dmPolicy`: `pairing | allowlist | open | disabled` (default: pairing).
 - `channels.telegram.allowFrom`: DM allowlist (numeric Telegram user IDs). `allowlist` requires at least one sender ID. `open` requires `"*"`. `openclaw doctor --fix` can resolve legacy `@username` entries to IDs and can recover allowlist entries from pairing-store files in allowlist migration flows.
+- `channels.telegram.actions.poll`: enable or disable Telegram poll creation (default: enabled; still requires `sendMessage`).
 - `channels.telegram.defaultTo`: default Telegram target used by CLI `--deliver` when no explicit `--reply-to` is provided.
 - `channels.telegram.groupPolicy`: `open | allowlist | disabled` (default: allowlist).
 - `channels.telegram.groupAllowFrom`: group sender allowlist (numeric Telegram user IDs). `openclaw doctor --fix` can resolve legacy `@username` entries to IDs. Non-numeric entries are ignored at auth time. Group auth does not use DM pairing-store fallback (`2026.2.25+`).

docs/cli/channels.md

@@ -67,6 +67,7 @@ openclaw channels logout --channel whatsapp
 - Run `openclaw status --deep` for a broad probe.
 - Use `openclaw doctor` for guided fixes.
 - `openclaw channels list` prints `Claude: HTTP 403 ... user:profile` → usage snapshot needs the `user:profile` scope. Use `--no-usage`, or provide a claude.ai session key (`CLAUDE_WEB_SESSION_KEY` / `CLAUDE_WEB_COOKIE`), or re-auth via Claude Code CLI.
+- `openclaw channels status` falls back to config-only summaries when the gateway is unreachable. If a supported channel credential is configured via SecretRef but unavailable in the current command path, it reports that account as configured with degraded notes instead of showing it as not configured.
 
 ## Capabilities probe
 
@@ -97,3 +98,4 @@ Notes:
 
 - Use `--kind user|group|auto` to force the target type.
 - Resolution prefers active matches when multiple entries share the same name.
+- `channels resolve` is read-only. If a selected account is configured via SecretRef but that credential is unavailable in the current command path, the command returns degraded unresolved results with notes instead of aborting the entire run.

docs/cli/configure.md

@@ -24,6 +24,9 @@ Notes:
 
 - Choosing where the Gateway runs always updates `gateway.mode`. You can select "Continue" without other sections if that is all you need.
 - Channel-oriented services (Slack/Discord/Matrix/Microsoft Teams) prompt for channel/room allowlists during setup. You can enter names or IDs; the wizard resolves names to IDs when possible.
+- If you run the daemon install step, token auth requires a token, and `gateway.auth.token` is SecretRef-managed, configure validates the SecretRef but does not persist resolved plaintext token values into supervisor service environment metadata.
+- If token auth requires a token and the configured token SecretRef is unresolved, configure blocks daemon install with actionable remediation guidance.
+- If both `gateway.auth.token` and `gateway.auth.password` are configured and `gateway.auth.mode` is unset, configure blocks daemon install until mode is set explicitly.
 
 ## Examples
 

docs/cli/cron.md

@@ -42,8 +42,28 @@ Disable delivery for an isolated job:
 openclaw cron edit <job-id> --no-deliver
 ```
 
+Enable lightweight bootstrap context for an isolated job:
+
+```bash
+openclaw cron edit <job-id> --light-context
+```
+
 Announce to a specific channel:
 
 ```bash
 openclaw cron edit <job-id> --announce --channel slack --to "channel:C1234567890"
 ```
+
+Create an isolated job with lightweight bootstrap context:
+
+```bash
+openclaw cron add \
+  --name "Lightweight morning brief" \
+  --cron "0 7 * * *" \
+  --session isolated \
+  --message "Summarize overnight updates." \
+  --light-context \
+  --no-deliver
+```
+
+`--light-context` applies to isolated agent-turn jobs only. For cron runs, lightweight mode keeps bootstrap context empty instead of injecting the full workspace bootstrap set.

docs/cli/daemon.md

@@ -38,6 +38,13 @@ openclaw daemon uninstall
 - `install`: `--port`, `--runtime <node|bun>`, `--token`, `--force`, `--json`
 - lifecycle (`uninstall|start|stop|restart`): `--json`
 
+Notes:
+
+- `status` resolves configured auth SecretRefs for probe auth when possible.
+- When token auth requires a token and `gateway.auth.token` is SecretRef-managed, `install` validates that the SecretRef is resolvable but does not persist the resolved token into service environment metadata.
+- If token auth requires a token and the configured token SecretRef is unresolved, install fails closed.
+- If both `gateway.auth.token` and `gateway.auth.password` are configured and `gateway.auth.mode` is unset, install is blocked until mode is set explicitly.
+
 ## Prefer
 
 Use [`openclaw gateway`](/cli/gateway) for current docs and examples.

docs/cli/dashboard.md

@@ -14,3 +14,9 @@ Open the Control UI using your current auth.
 openclaw dashboard
 openclaw dashboard --no-open
 ```
+
+Notes:
+
+- `dashboard` resolves configured `gateway.auth.token` SecretRefs when possible.
+- For SecretRef-managed tokens (resolved or unresolved), `dashboard` prints/copies/opens a non-tokenized URL to avoid exposing external secrets in terminal output, clipboard history, or browser-launch arguments.
+- If `gateway.auth.token` is SecretRef-managed but unresolved in this command path, the command prints a non-tokenized URL and explicit remediation guidance instead of embedding an invalid token placeholder.

docs/cli/gateway.md

@@ -105,6 +105,11 @@ Options:
 - `--no-probe`: skip the RPC probe (service-only view).
 - `--deep`: scan system-level services too.
 
+Notes:
+
+- `gateway status` resolves configured auth SecretRefs for probe auth when possible.
+- If a required auth SecretRef is unresolved in this command path, probe auth can fail; pass `--token`/`--password` explicitly or resolve the secret source first.
+
 ### `gateway probe`
 
 `gateway probe` is the “debug everything” command. It always probes:
@@ -162,6 +167,10 @@ openclaw gateway uninstall
 Notes:
 
 - `gateway install` supports `--port`, `--runtime`, `--token`, `--force`, `--json`.
+- When token auth requires a token and `gateway.auth.token` is SecretRef-managed, `gateway install` validates that the SecretRef is resolvable but does not persist the resolved token into service environment metadata.
+- If token auth requires a token and the configured token SecretRef is unresolved, install fails closed instead of persisting fallback plaintext.
+- In inferred auth mode, shell-only `OPENCLAW_GATEWAY_PASSWORD`/`CLAWDBOT_GATEWAY_PASSWORD` does not relax install token requirements; use durable config (`gateway.auth.password` or config `env`) when installing a managed service.
+- If both `gateway.auth.token` and `gateway.auth.password` are configured and `gateway.auth.mode` is unset, install is blocked until mode is set explicitly.
 - Lifecycle commands accept `--json` for scripting.
 
 ## Discover gateways (Bonjour)

docs/cli/index.md

@@ -359,6 +359,7 @@ Options:
 - `--gateway-bind <loopback|lan|tailnet|auto|custom>`
 - `--gateway-auth <token|password>`
 - `--gateway-token <token>`
+- `--gateway-token-ref-env <name>` (non-interactive; store `gateway.auth.token` as an env SecretRef; requires that env var to be set; cannot be combined with `--gateway-token`)
 - `--gateway-password <password>`
 - `--remote-url <url>`
 - `--remote-token <token>`

docs/cli/onboard.md

@@ -61,6 +61,28 @@ Non-interactive `ref` mode contract:
 - Do not pass inline key flags (for example `--openai-api-key`) unless that env var is also set.
 - If an inline key flag is passed without the required env var, onboarding fails fast with guidance.
 
+Gateway token options in non-interactive mode:
+
+- `--gateway-auth token --gateway-token <token>` stores a plaintext token.
+- `--gateway-auth token --gateway-token-ref-env <name>` stores `gateway.auth.token` as an env SecretRef.
+- `--gateway-token` and `--gateway-token-ref-env` are mutually exclusive.
+- `--gateway-token-ref-env` requires a non-empty env var in the onboarding process environment.
+- With `--install-daemon`, when token auth requires a token, SecretRef-managed gateway tokens are validated but not persisted as resolved plaintext in supervisor service environment metadata.
+- With `--install-daemon`, if token mode requires a token and the configured token SecretRef is unresolved, onboarding fails closed with remediation guidance.
+- With `--install-daemon`, if both `gateway.auth.token` and `gateway.auth.password` are configured and `gateway.auth.mode` is unset, onboarding blocks install until mode is set explicitly.
+
+Example:
+
+```bash
+export OPENCLAW_GATEWAY_TOKEN="your-token"
+openclaw onboard --non-interactive \
+  --mode local \
+  --auth-choice skip \
+  --gateway-auth token \
+  --gateway-token-ref-env OPENCLAW_GATEWAY_TOKEN \
+  --accept-risk
+```
+
 Interactive onboarding behavior with reference mode:
 
 - Choose **Use secret reference** when prompted.

docs/cli/qr.md

@@ -35,7 +35,10 @@ openclaw qr --url wss://gateway.example/ws --token '<token>'
 
 - `--token` and `--password` are mutually exclusive.
 - With `--remote`, if effectively active remote credentials are configured as SecretRefs and you do not pass `--token` or `--password`, the command resolves them from the active gateway snapshot. If gateway is unavailable, the command fails fast.
-- Without `--remote`, local `gateway.auth.password` SecretRefs are resolved when password auth can win (explicit `gateway.auth.mode="password"` or inferred password mode with no winning token from auth/env), and no CLI auth override is passed.
+- Without `--remote`, local gateway auth SecretRefs are resolved when no CLI auth override is passed:
+  - `gateway.auth.token` resolves when token auth can win (explicit `gateway.auth.mode="token"` or inferred mode where no password source wins).
+  - `gateway.auth.password` resolves when password auth can win (explicit `gateway.auth.mode="password"` or inferred mode with no winning token from auth/env).
+- If both `gateway.auth.token` and `gateway.auth.password` are configured (including SecretRefs) and `gateway.auth.mode` is unset, setup-code resolution fails until mode is set explicitly.
 - Gateway version skew note: this command path requires a gateway that supports `secrets.resolve`; older gateways return an unknown-method error.
 - After scanning, approve device pairing with:
   - `openclaw devices list`

docs/cli/status.md

@@ -24,3 +24,5 @@ Notes:
 - Overview includes Gateway + node host service install/runtime status when available.
 - Overview includes update channel + git SHA (for source checkouts).
 - Update info surfaces in the Overview; if an update is available, status prints a hint to run `openclaw update` (see [Updating](/install/updating)).
+- Read-only status surfaces (`status`, `status --json`, `status --all`) resolve supported SecretRefs for their targeted config paths when possible.
+- If a supported channel SecretRef is configured but unavailable in the current command path, status stays read-only and reports degraded output instead of crashing. Human output shows warnings such as “configured token unavailable in this command path”, and JSON output includes `secretDiagnostics`.

docs/cli/tui.md

@@ -14,6 +14,10 @@ Related:
 
 - TUI guide: [TUI](/web/tui)
 
+Notes:
+
+- `tui` resolves configured gateway auth SecretRefs for token/password auth when possible (`env`/`file`/`exec` providers).
+
 ## Examples
 
 ```bash

docs/concepts/agent-loop.md

@@ -82,7 +82,7 @@ See [Hooks](/automation/hooks) for setup and examples.
 These run inside the agent loop or gateway pipeline:
 
 - **`before_model_resolve`**: runs pre-session (no `messages`) to deterministically override provider/model before model resolution.
-- **`before_prompt_build`**: runs after session load (with `messages`) to inject `prependContext`/`systemPrompt` before prompt submission.
+- **`before_prompt_build`**: runs after session load (with `messages`) to inject `prependContext`, `systemPrompt`, `prependSystemContext`, or `appendSystemContext` before prompt submission. Use `prependContext` for per-turn dynamic text and system-context fields for stable guidance that should sit in system prompt space.
 - **`before_agent_start`**: legacy compatibility hook that may run in either phase; prefer the explicit hooks above.
 - **`agent_end`**: inspect the final message list and run metadata after completion.
 - **`before_compaction` / `after_compaction`**: observe or annotate compaction cycles.

docs/concepts/model-providers.md

@@ -41,15 +41,16 @@ OpenClaw ships with the pi‑ai catalog. These providers require **no**
 - Provider: `openai`
 - Auth: `OPENAI_API_KEY`
 - Optional rotation: `OPENAI_API_KEYS`, `OPENAI_API_KEY_1`, `OPENAI_API_KEY_2`, plus `OPENCLAW_LIVE_OPENAI_KEY` (single override)
-- Example model: `openai/gpt-5.1-codex`
+- Example models: `openai/gpt-5.4`, `openai/gpt-5.4-pro`
 - CLI: `openclaw onboard --auth-choice openai-api-key`
 - Default transport is `auto` (WebSocket-first, SSE fallback)
 - Override per model via `agents.defaults.models["openai/<model>"].params.transport` (`"sse"`, `"websocket"`, or `"auto"`)
 - OpenAI Responses WebSocket warm-up defaults to enabled via `params.openaiWsWarmup` (`true`/`false`)
+- OpenAI priority processing can be enabled via `agents.defaults.models["openai/<model>"].params.serviceTier`
 
 ```json5
 {
-  agents: { defaults: { model: { primary: "openai/gpt-5.1-codex" } } },
+  agents: { defaults: { model: { primary: "openai/gpt-5.4" } } },
 }
 ```
 
@@ -73,7 +74,7 @@ OpenClaw ships with the pi‑ai catalog. These providers require **no**
 
 - Provider: `openai-codex`
 - Auth: OAuth (ChatGPT)
-- Example model: `openai-codex/gpt-5.3-codex`
+- Example model: `openai-codex/gpt-5.4`
 - CLI: `openclaw onboard --auth-choice openai-codex` or `openclaw models auth login --provider openai-codex`
 - Default transport is `auto` (WebSocket-first, SSE fallback)
 - Override per model via `agents.defaults.models["openai-codex/<model>"].params.transport` (`"sse"`, `"websocket"`, or `"auto"`)
@@ -81,7 +82,7 @@ OpenClaw ships with the pi‑ai catalog. These providers require **no**
 
 ```json5
 {
-  agents: { defaults: { model: { primary: "openai-codex/gpt-5.3-codex" } } },
+  agents: { defaults: { model: { primary: "openai-codex/gpt-5.4" } } },
 }
 ```
 

docs/experiments/plans/discord-async-inbound-worker.md

@@ -0,0 +1,337 @@
+---
+summary: "Status and next steps for decoupling Discord gateway listeners from long-running agent turns with a Discord-specific inbound worker"
+owner: "openclaw"
+status: "in_progress"
+last_updated: "2026-03-05"
+title: "Discord Async Inbound Worker Plan"
+---
+
+# Discord Async Inbound Worker Plan
+
+## Objective
+
+Remove Discord listener timeout as a user-facing failure mode by making inbound Discord turns asynchronous:
+
+1. Gateway listener accepts and normalizes inbound events quickly.
+2. A Discord run queue stores serialized jobs keyed by the same ordering boundary we use today.
+3. A worker executes the actual agent turn outside the Carbon listener lifetime.
+4. Replies are delivered back to the originating channel or thread after the run completes.
+
+This is the long-term fix for queued Discord runs timing out at `channels.discord.eventQueue.listenerTimeout` while the agent run itself is still making progress.
+
+## Current status
+
+This plan is partially implemented.
+
+Already done:
+
+- Discord listener timeout and Discord run timeout are now separate settings.
+- Accepted inbound Discord turns are enqueued into `src/discord/monitor/inbound-worker.ts`.
+- The worker now owns the long-running turn instead of the Carbon listener.
+- Existing per-route ordering is preserved by queue key.
+- Timeout regression coverage exists for the Discord worker path.
+
+What this means in plain language:
+
+- the production timeout bug is fixed
+- the long-running turn no longer dies just because the Discord listener budget expires
+- the worker architecture is not finished yet
+
+What is still missing:
+
+- `DiscordInboundJob` is still only partially normalized and still carries live runtime references
+- command semantics (`stop`, `new`, `reset`, future session controls) are not yet fully worker-native
+- worker observability and operator status are still minimal
+- there is still no restart durability
+
+## Why this exists
+
+Current behavior ties the full agent turn to the listener lifetime:
+
+- `src/discord/monitor/listeners.ts` applies the timeout and abort boundary.
+- `src/discord/monitor/message-handler.ts` keeps the queued run inside that boundary.
+- `src/discord/monitor/message-handler.process.ts` performs media loading, routing, dispatch, typing, draft streaming, and final reply delivery inline.
+
+That architecture has two bad properties:
+
+- long but healthy turns can be aborted by the listener watchdog
+- users can see no reply even when the downstream runtime would have produced one
+
+Raising the timeout helps but does not change the failure mode.
+
+## Non-goals
+
+- Do not redesign non-Discord channels in this pass.
+- Do not broaden this into a generic all-channel worker framework in the first implementation.
+- Do not extract a shared cross-channel inbound worker abstraction yet; only share low-level primitives when duplication is obvious.
+- Do not add durable crash recovery in the first pass unless needed to land safely.
+- Do not change route selection, binding semantics, or ACP policy in this plan.
+
+## Current constraints
+
+The current Discord processing path still depends on some live runtime objects that should not stay inside the long-term job payload:
+
+- Carbon `Client`
+- raw Discord event shapes
+- in-memory guild history map
+- thread binding manager callbacks
+- live typing and draft stream state
+
+We already moved execution onto a worker queue, but the normalization boundary is still incomplete. Right now the worker is "run later in the same process with some of the same live objects," not a fully data-only job boundary.
+
+## Target architecture
+
+### 1. Listener stage
+
+`DiscordMessageListener` remains the ingress point, but its job becomes:
+
+- run preflight and policy checks
+- normalize accepted input into a serializable `DiscordInboundJob`
+- enqueue the job into a per-session or per-channel async queue
+- return immediately to Carbon once the enqueue succeeds
+
+The listener should no longer own the end-to-end LLM turn lifetime.
+
+### 2. Normalized job payload
+
+Introduce a serializable job descriptor that contains only the data needed to run the turn later.
+
+Minimum shape:
+
+- route identity
+  - `agentId`
+  - `sessionKey`
+  - `accountId`
+  - `channel`
+- delivery identity
+  - destination channel id
+  - reply target message id
+  - thread id if present
+- sender identity
+  - sender id, label, username, tag
+- channel context
+  - guild id
+  - channel name or slug
+  - thread metadata
+  - resolved system prompt override
+- normalized message body
+  - base text
+  - effective message text
+  - attachment descriptors or resolved media references
+- gating decisions
+  - mention requirement outcome
+  - command authorization outcome
+  - bound session or agent metadata if applicable
+
+The job payload must not contain live Carbon objects or mutable closures.
+
+Current implementation status:
+
+- partially done
+- `src/discord/monitor/inbound-job.ts` exists and defines the worker handoff
+- the payload still contains live Discord runtime context and should be reduced further
+
+### 3. Worker stage
+
+Add a Discord-specific worker runner responsible for:
+
+- reconstructing the turn context from `DiscordInboundJob`
+- loading media and any additional channel metadata needed for the run
+- dispatching the agent turn
+- delivering final reply payloads
+- updating status and diagnostics
+
+Recommended location:
+
+- `src/discord/monitor/inbound-worker.ts`
+- `src/discord/monitor/inbound-job.ts`
+
+### 4. Ordering model
+
+Ordering must remain equivalent to today for a given route boundary.
+
+Recommended key:
+
+- use the same queue key logic as `resolveDiscordRunQueueKey(...)`
+
+This preserves existing behavior:
+
+- one bound agent conversation does not interleave with itself
+- different Discord channels can still progress independently
+
+### 5. Timeout model
+
+After cutover, there are two separate timeout classes:
+
+- listener timeout
+  - only covers normalization and enqueue
+  - should be short
+- run timeout
+  - optional, worker-owned, explicit, and user-visible
+  - should not be inherited accidentally from Carbon listener settings
+
+This removes the current accidental coupling between "Discord gateway listener stayed alive" and "agent run is healthy."
+
+## Recommended implementation phases
+
+### Phase 1: normalization boundary
+
+- Status: partially implemented
+- Done:
+  - extracted `buildDiscordInboundJob(...)`
+  - added worker handoff tests
+- Remaining:
+  - make `DiscordInboundJob` plain data only
+  - move live runtime dependencies to worker-owned services instead of per-job payload
+  - stop rebuilding process context by stitching live listener refs back into the job
+
+### Phase 2: in-memory worker queue
+
+- Status: implemented
+- Done:
+  - added `DiscordInboundWorkerQueue` keyed by resolved run queue key
+  - listener enqueues jobs instead of directly awaiting `processDiscordMessage(...)`
+  - worker executes jobs in-process, in memory only
+
+This is the first functional cutover.
+
+### Phase 3: process split
+
+- Status: not started
+- Move delivery, typing, and draft streaming ownership behind worker-facing adapters.
+- Replace direct use of live preflight context with worker context reconstruction.
+- Keep `processDiscordMessage(...)` temporarily as a facade if needed, then split it.
+
+### Phase 4: command semantics
+
+- Status: not started
+  Make sure native Discord commands still behave correctly when work is queued:
+
+- `stop`
+- `new`
+- `reset`
+- any future session-control commands
+
+The worker queue must expose enough run state for commands to target the active or queued turn.
+
+### Phase 5: observability and operator UX
+
+- Status: not started
+- emit queue depth and active worker counts into monitor status
+- record enqueue time, start time, finish time, and timeout or cancellation reason
+- surface worker-owned timeout or delivery failures clearly in logs
+
+### Phase 6: optional durability follow-up
+
+- Status: not started
+  Only after the in-memory version is stable:
+
+- decide whether queued Discord jobs should survive gateway restart
+- if yes, persist job descriptors and delivery checkpoints
+- if no, document the explicit in-memory boundary
+
+This should be a separate follow-up unless restart recovery is required to land.
+
+## File impact
+
+Current primary files:
+
+- `src/discord/monitor/listeners.ts`
+- `src/discord/monitor/message-handler.ts`
+- `src/discord/monitor/message-handler.preflight.ts`
+- `src/discord/monitor/message-handler.process.ts`
+- `src/discord/monitor/status.ts`
+
+Current worker files:
+
+- `src/discord/monitor/inbound-job.ts`
+- `src/discord/monitor/inbound-worker.ts`
+- `src/discord/monitor/inbound-job.test.ts`
+- `src/discord/monitor/message-handler.queue.test.ts`
+
+Likely next touch points:
+
+- `src/auto-reply/dispatch.ts`
+- `src/discord/monitor/reply-delivery.ts`
+- `src/discord/monitor/thread-bindings.ts`
+- `src/discord/monitor/native-command.ts`
+
+## Next step now
+
+The next step is to make the worker boundary real instead of partial.
+
+Do this next:
+
+1. Move live runtime dependencies out of `DiscordInboundJob`
+2. Keep those dependencies on the Discord worker instance instead
+3. Reduce queued jobs to plain Discord-specific data:
+   - route identity
+   - delivery target
+   - sender info
+   - normalized message snapshot
+   - gating and binding decisions
+4. Reconstruct worker execution context from that plain data inside the worker
+
+In practice, that means:
+
+- `client`
+- `threadBindings`
+- `guildHistories`
+- `discordRestFetch`
+- other mutable runtime-only handles
+
+should stop living on each queued job and instead live on the worker itself or behind worker-owned adapters.
+
+After that lands, the next follow-up should be command-state cleanup for `stop`, `new`, and `reset`.
+
+## Testing plan
+
+Keep the existing timeout repro coverage in:
+
+- `src/discord/monitor/message-handler.queue.test.ts`
+
+Add new tests for:
+
+1. listener returns after enqueue without awaiting full turn
+2. per-route ordering is preserved
+3. different channels still run concurrently
+4. replies are delivered to the original message destination
+5. `stop` cancels the active worker-owned run
+6. worker failure produces visible diagnostics without blocking later jobs
+7. ACP-bound Discord channels still route correctly under worker execution
+
+## Risks and mitigations
+
+- Risk: command semantics drift from current synchronous behavior
+  Mitigation: land command-state plumbing in the same cutover, not later
+
+- Risk: reply delivery loses thread or reply-to context
+  Mitigation: make delivery identity first-class in `DiscordInboundJob`
+
+- Risk: duplicate sends during retries or queue restarts
+  Mitigation: keep first pass in-memory only, or add explicit delivery idempotency before persistence
+
+- Risk: `message-handler.process.ts` becomes harder to reason about during migration
+  Mitigation: split into normalization, execution, and delivery helpers before or during worker cutover
+
+## Acceptance criteria
+
+The plan is complete when:
+
+1. Discord listener timeout no longer aborts healthy long-running turns.
+2. Listener lifetime and agent-turn lifetime are separate concepts in code.
+3. Existing per-session ordering is preserved.
+4. ACP-bound Discord channels work through the same worker path.
+5. `stop` targets the worker-owned run instead of the old listener-owned call stack.
+6. Timeout and delivery failures become explicit worker outcomes, not silent listener drops.
+
+## Remaining landing strategy
+
+Finish this in follow-up PRs:
+
+1. make `DiscordInboundJob` plain-data only and move live runtime refs onto the worker
+2. clean up command-state ownership for `stop`, `new`, and `reset`
+3. add worker observability and operator status
+4. decide whether durability is needed or explicitly document the in-memory boundary
+
+This is still a bounded follow-up if kept Discord-only and if we continue to avoid a premature cross-channel worker abstraction.

docs/gateway/cli-backends.md

@@ -31,7 +31,7 @@ openclaw agent --message "hi" --model claude-cli/opus-4.6
 Codex CLI also works out of the box:
 
 ```bash
-openclaw agent --message "hi" --model codex-cli/gpt-5.3-codex
+openclaw agent --message "hi" --model codex-cli/gpt-5.4
 ```
 
 If your gateway runs under launchd/systemd and PATH is minimal, add just the

docs/gateway/configuration-reference.md

@@ -406,6 +406,7 @@ WhatsApp runs through the gateway's web channel (Baileys Web). It starts automat
         sessionPrefix: "slack:slash",
         ephemeral: true,
       },
+      typingReaction: "hourglass_flowing_sand",
       textChunkLimit: 4000,
       chunkMode: "length",
       streaming: "partial", // off | partial | block | progress (preview mode)
@@ -427,6 +428,8 @@ WhatsApp runs through the gateway's web channel (Baileys Web). It starts automat
 
 **Thread session isolation:** `thread.historyScope` is per-thread (default) or shared across channel. `thread.inheritParent` copies parent channel transcript to new threads.
 
+- `typingReaction` adds a temporary reaction to the inbound Slack message while a reply is running, then removes it on completion. Use a Slack emoji shortcode such as `"hourglass_flowing_sand"`.
+
 | Action group | Default | Notes                  |
 | ------------ | ------- | ---------------------- |
 | reactions    | enabled | React + list reactions |
@@ -968,6 +971,7 @@ Periodic heartbeat runs.
         every: "30m", // 0m disables
         model: "openai/gpt-5.2-mini",
         includeReasoning: false,
+        lightContext: false, // default: false; true keeps only HEARTBEAT.md from workspace bootstrap files
         session: "main",
         to: "+15555550123",
         directPolicy: "allow", // allow (default) | block
@@ -984,6 +988,7 @@ Periodic heartbeat runs.
 - `every`: duration string (ms/s/m/h). Default: `30m`.
 - `suppressToolErrorWarnings`: when true, suppresses tool error warning payloads during heartbeat runs.
 - `directPolicy`: direct/DM delivery policy. `allow` (default) permits direct-target delivery. `block` suppresses direct-target delivery and emits `reason=dm-blocked`.
+- `lightContext`: when true, heartbeat runs use lightweight bootstrap context and keep only `HEARTBEAT.md` from workspace bootstrap files.
 - Per-agent: set `agents.list[].heartbeat`. When any agent defines `heartbeat`, **only those agents** run heartbeats.
 - Heartbeats run full agent turns — shorter intervals burn more tokens.
 
@@ -1618,6 +1623,7 @@ Batches rapid text-only messages from the same sender into a single agent turn.
       },
       openai: {
         apiKey: "openai_api_key",
+        baseUrl: "https://api.openai.com/v1",
         model: "gpt-4o-mini-tts",
         voice: "alloy",
       },
@@ -1630,6 +1636,8 @@ Batches rapid text-only messages from the same sender into a single agent turn.
 - `summaryModel` overrides `agents.defaults.model.primary` for auto-summary.
 - `modelOverrides` is enabled by default; `modelOverrides.allowProvider` defaults to `false` (opt-in).
 - API keys fall back to `ELEVENLABS_API_KEY`/`XI_API_KEY` and `OPENAI_API_KEY`.
+- `openai.baseUrl` overrides the OpenAI TTS endpoint. Resolution order is config, then `OPENAI_TTS_BASE_URL`, then `https://api.openai.com/v1`.
+- When `openai.baseUrl` points to a non-OpenAI endpoint, OpenClaw treats it as an OpenAI-compatible TTS server and relaxes model/voice validation.
 
 ---
 
@@ -2287,6 +2295,9 @@ See [Local Models](/gateway/local-models). TL;DR: run MiniMax M2.5 via LM Studio
     entries: {
       "voice-call": {
         enabled: true,
+        hooks: {
+          allowPromptInjection: false,
+        },
         config: { provider: "twilio" },
       },
     },
@@ -2299,6 +2310,7 @@ See [Local Models](/gateway/local-models). TL;DR: run MiniMax M2.5 via LM Studio
 - `allow`: optional allowlist (only listed plugins load). `deny` wins.
 - `plugins.entries.<id>.apiKey`: plugin-level API key convenience field (when supported by the plugin).
 - `plugins.entries.<id>.env`: plugin-scoped env var map.
+- `plugins.entries.<id>.hooks.allowPromptInjection`: when `false`, core blocks `before_prompt_build` and ignores prompt-mutating fields from legacy `before_agent_start`, while preserving legacy `modelOverride` and `providerOverride`.
 - `plugins.entries.<id>.config`: plugin-defined config object (validated by plugin schema).
 - `plugins.slots.memory`: pick the active memory plugin id, or `"none"` to disable memory plugins.
 - `plugins.installs`: CLI-managed install metadata used by `openclaw plugins update`.
@@ -2431,6 +2443,7 @@ See [Plugins](/tools/plugin).
 - **Legacy bind aliases**: use bind mode values in `gateway.bind` (`auto`, `loopback`, `lan`, `tailnet`, `custom`), not host aliases (`0.0.0.0`, `127.0.0.1`, `localhost`, `::`, `::1`).
 - **Docker note**: the default `loopback` bind listens on `127.0.0.1` inside the container. With Docker bridge networking (`-p 18789:18789`), traffic arrives on `eth0`, so the gateway is unreachable. Use `--network host`, or set `bind: "lan"` (or `bind: "custom"` with `customBindHost: "0.0.0.0"`) to listen on all interfaces.
 - **Auth**: required by default. Non-loopback binds require a shared token/password. Onboarding wizard generates a token by default.
+- If both `gateway.auth.token` and `gateway.auth.password` are configured (including SecretRefs), set `gateway.auth.mode` explicitly to `token` or `password`. Startup and service install/repair flows fail when both are configured and mode is unset.
 - `gateway.auth.mode: "none"`: explicit no-auth mode. Use only for trusted local loopback setups; this is intentionally not offered by onboarding prompts.
 - `gateway.auth.mode: "trusted-proxy"`: delegate auth to an identity-aware reverse proxy and trust identity headers from `gateway.trustedProxies` (see [Trusted Proxy Auth](/gateway/trusted-proxy-auth)).
 - `gateway.auth.allowTailscale`: when `true`, Tailscale Serve identity headers can satisfy Control UI/WebSocket auth (verified via `tailscale whois`); HTTP API endpoints still require token/password auth. This tokenless flow assumes the gateway host is trusted. Defaults to `true` when `tailscale.mode = "serve"`.

docs/gateway/doctor.md

@@ -77,7 +77,7 @@ cat ~/.openclaw/openclaw.json
 - Gateway runtime best-practice checks (Node vs Bun, version-manager paths).
 - Gateway port collision diagnostics (default `18789`).
 - Security warnings for open DM policies.
-- Gateway auth warnings when no `gateway.auth.token` is set (local mode; offers token generation).
+- Gateway auth checks for local token mode (offers token generation when no token source exists; does not overwrite token SecretRef configs).
 - systemd linger check on Linux.
 - Source install checks (pnpm workspace mismatch, missing UI assets, missing tsx binary).
 - Writes updated config + wizard metadata.
@@ -238,9 +238,19 @@ workspace.
 
 ### 12) Gateway auth checks (local token)
 
-Doctor warns when `gateway.auth` is missing on a local gateway and offers to
-generate a token. Use `openclaw doctor --generate-gateway-token` to force token
-creation in automation.
+Doctor checks local gateway token auth readiness.
+
+- If token mode needs a token and no token source exists, doctor offers to generate one.
+- If `gateway.auth.token` is SecretRef-managed but unavailable, doctor warns and does not overwrite it with plaintext.
+- `openclaw doctor --generate-gateway-token` forces generation only when no token SecretRef is configured.
+
+### 12b) Read-only SecretRef-aware repairs
+
+Some repair flows need to inspect configured credentials without weakening runtime fail-fast behavior.
+
+- `openclaw doctor --fix` now uses the same read-only SecretRef summary model as status-family commands for targeted config repairs.
+- Example: Telegram `allowFrom` / `groupAllowFrom` `@username` repair tries to use configured bot credentials when available.
+- If the Telegram bot token is configured via SecretRef but unavailable in the current command path, doctor reports that the credential is configured-but-unavailable and skips auto-resolution instead of crashing or misreporting the token as missing.
 
 ### 13) Gateway health check + restart
 
@@ -265,6 +275,9 @@ Notes:
 - `openclaw doctor --yes` accepts the default repair prompts.
 - `openclaw doctor --repair` applies recommended fixes without prompts.
 - `openclaw doctor --repair --force` overwrites custom supervisor configs.
+- If token auth requires a token and `gateway.auth.token` is SecretRef-managed, doctor service install/repair validates the SecretRef but does not persist resolved plaintext token values into supervisor service environment metadata.
+- If token auth requires a token and the configured token SecretRef is unresolved, doctor blocks the install/repair path with actionable guidance.
+- If both `gateway.auth.token` and `gateway.auth.password` are configured and `gateway.auth.mode` is unset, doctor blocks install/repair until mode is set explicitly.
 - You can always force a full rewrite via `openclaw gateway install --force`.
 
 ### 16) Gateway runtime + port diagnostics

docs/gateway/heartbeat.md

@@ -21,7 +21,8 @@ Troubleshooting: [/automation/troubleshooting](/automation/troubleshooting)
 2. Create a tiny `HEARTBEAT.md` checklist in the agent workspace (optional but recommended).
 3. Decide where heartbeat messages should go (`target: "none"` is the default; set `target: "last"` to route to the last contact).
 4. Optional: enable heartbeat reasoning delivery for transparency.
-5. Optional: restrict heartbeats to active hours (local time).
+5. Optional: use lightweight bootstrap context if heartbeat runs only need `HEARTBEAT.md`.
+6. Optional: restrict heartbeats to active hours (local time).
 
 Example config:
 
@@ -33,6 +34,7 @@ Example config:
         every: "30m",
         target: "last", // explicit delivery to last contact (default is "none")
         directPolicy: "allow", // default: allow direct/DM targets; set "block" to suppress
+        lightContext: true, // optional: only inject HEARTBEAT.md from bootstrap files
         // activeHours: { start: "08:00", end: "24:00" },
         // includeReasoning: true, // optional: send separate `Reasoning:` message too
       },
@@ -88,6 +90,7 @@ and logged; a message that is only `HEARTBEAT_OK` is dropped.
         every: "30m", // default: 30m (0m disables)
         model: "anthropic/claude-opus-4-6",
         includeReasoning: false, // default: false (deliver separate Reasoning: message when available)
+        lightContext: false, // default: false; true keeps only HEARTBEAT.md from workspace bootstrap files
         target: "last", // default: none | options: last | none | <channel id> (core or plugin, e.g. "bluebubbles")
         to: "+15551234567", // optional channel-specific override
         accountId: "ops-bot", // optional multi-account channel id
@@ -208,6 +211,7 @@ Use `accountId` to target a specific account on multi-account channels like Tele
 - `every`: heartbeat interval (duration string; default unit = minutes).
 - `model`: optional model override for heartbeat runs (`provider/model`).
 - `includeReasoning`: when enabled, also deliver the separate `Reasoning:` message when available (same shape as `/reasoning on`).
+- `lightContext`: when true, heartbeat runs use lightweight bootstrap context and keep only `HEARTBEAT.md` from workspace bootstrap files.
 - `session`: optional session key for heartbeat runs.
   - `main` (default): agent main session.
   - Explicit session key (copy from `openclaw sessions --json` or the [sessions CLI](/cli/sessions)).

docs/gateway/secrets.md

@@ -46,11 +46,13 @@ Examples of inactive surfaces:
     In local mode without those remote surfaces:
   - `gateway.remote.token` is active when token auth can win and no env/auth token is configured.
   - `gateway.remote.password` is active only when password auth can win and no env/auth password is configured.
+- `gateway.auth.token` SecretRef is inactive for startup auth resolution when `OPENCLAW_GATEWAY_TOKEN` (or `CLAWDBOT_GATEWAY_TOKEN`) is set, because env token input wins for that runtime.
 
 ## Gateway auth surface diagnostics
 
-When a SecretRef is configured on `gateway.auth.password`, `gateway.remote.token`, or
-`gateway.remote.password`, gateway startup/reload logs the surface state explicitly:
+When a SecretRef is configured on `gateway.auth.token`, `gateway.auth.password`,
+`gateway.remote.token`, or `gateway.remote.password`, gateway startup/reload logs the
+surface state explicitly:
 
 - `active`: the SecretRef is part of the effective auth surface and must resolve.
 - `inactive`: the SecretRef is ignored for this runtime because another auth surface wins, or
@@ -65,6 +67,7 @@ When onboarding runs in interactive mode and you choose SecretRef storage, OpenC
 
 - Env refs: validates env var name and confirms a non-empty value is visible during onboarding.
 - Provider refs (`file` or `exec`): validates provider selection, resolves `id`, and checks resolved value type.
+- Quickstart reuse path: when `gateway.auth.token` is already a SecretRef, onboarding resolves it before probe/dashboard bootstrap (for `env`, `file`, and `exec` refs) using the same fail-fast gate.
 
 If validation fails, onboarding shows the error and lets you retry.
 
@@ -336,10 +339,22 @@ Behavior:
 
 ## Command-path resolution
 
-Credential-sensitive command paths that opt in (for example `openclaw memory` remote-memory paths and `openclaw qr --remote`) can resolve supported SecretRefs via gateway snapshot RPC.
+Command paths can opt into supported SecretRef resolution via gateway snapshot RPC.
+
+There are two broad behaviors:
+
+- Strict command paths (for example `openclaw memory` remote-memory paths and `openclaw qr --remote`) read from the active snapshot and fail fast when a required SecretRef is unavailable.
+- Read-only command paths (for example `openclaw status`, `openclaw status --all`, `openclaw channels status`, `openclaw channels resolve`, and read-only doctor/config repair flows) also prefer the active snapshot, but degrade instead of aborting when a targeted SecretRef is unavailable in that command path.
+
+Read-only behavior:
+
+- When the gateway is running, these commands read from the active snapshot first.
+- If gateway resolution is incomplete or the gateway is unavailable, they attempt targeted local fallback for the specific command surface.
+- If a targeted SecretRef is still unavailable, the command continues with degraded read-only output and explicit diagnostics such as “configured but unavailable in this command path”.
+- This degraded behavior is command-local only. It does not weaken runtime startup, reload, or send/auth paths.
+
+Other notes:
 
-- When gateway is running, those command paths read from the active snapshot.
-- If a configured SecretRef is required and gateway is unavailable, command resolution fails fast with actionable diagnostics.
 - Snapshot refresh after backend secret rotation is handled by `openclaw secrets reload`.
 - Gateway RPC method used by these command paths: `secrets.resolve`.
 

docs/help/faq.md

@@ -767,7 +767,7 @@ Yes - via pi-ai's **Amazon Bedrock (Converse)** provider with **manual config**.
 
 ### How does Codex auth work
 
-OpenClaw supports **OpenAI Code (Codex)** via OAuth (ChatGPT sign-in). The wizard can run the OAuth flow and will set the default model to `openai-codex/gpt-5.3-codex` when appropriate. See [Model providers](/concepts/model-providers) and [Wizard](/start/wizard).
+OpenClaw supports **OpenAI Code (Codex)** via OAuth (ChatGPT sign-in). The wizard can run the OAuth flow and will set the default model to `openai-codex/gpt-5.4` when appropriate. See [Model providers](/concepts/model-providers) and [Wizard](/start/wizard).
 
 ### Do you support OpenAI subscription auth Codex OAuth
 
@@ -2156,8 +2156,8 @@ Use `/model status` to confirm which auth profile is active.
 
 Yes. Set one as default and switch as needed:
 
-- **Quick switch (per session):** `/model gpt-5.2` for daily tasks, `/model gpt-5.3-codex` for coding.
-- **Default + switch:** set `agents.defaults.model.primary` to `openai/gpt-5.2`, then switch to `openai-codex/gpt-5.3-codex` when coding (or the other way around).
+- **Quick switch (per session):** `/model gpt-5.2` for daily tasks, `/model openai-codex/gpt-5.4` for coding with Codex OAuth.
+- **Default + switch:** set `agents.defaults.model.primary` to `openai/gpt-5.2`, then switch to `openai-codex/gpt-5.4` when coding (or the other way around).
 - **Sub-agents:** route coding tasks to sub-agents with a different default model.
 
 See [Models](/concepts/models) and [Slash commands](/tools/slash-commands).

docs/help/testing.md

@@ -222,7 +222,7 @@ OPENCLAW_LIVE_SETUP_TOKEN=1 OPENCLAW_LIVE_SETUP_TOKEN_PROFILE=anthropic:setup-to
   - Args: `["-p","--output-format","json","--permission-mode","bypassPermissions"]`
 - Overrides (optional):
   - `OPENCLAW_LIVE_CLI_BACKEND_MODEL="claude-cli/claude-opus-4-6"`
-  - `OPENCLAW_LIVE_CLI_BACKEND_MODEL="codex-cli/gpt-5.3-codex"`
+  - `OPENCLAW_LIVE_CLI_BACKEND_MODEL="codex-cli/gpt-5.4"`
   - `OPENCLAW_LIVE_CLI_BACKEND_COMMAND="/full/path/to/claude"`
   - `OPENCLAW_LIVE_CLI_BACKEND_ARGS='["-p","--output-format","json","--permission-mode","bypassPermissions"]'`
   - `OPENCLAW_LIVE_CLI_BACKEND_CLEAR_ENV='["ANTHROPIC_API_KEY","ANTHROPIC_API_KEY_OLD"]'`
@@ -275,7 +275,7 @@ There is no fixed “CI model list” (live is opt-in), but these are the **reco
 This is the “common models” run we expect to keep working:
 
 - OpenAI (non-Codex): `openai/gpt-5.2` (optional: `openai/gpt-5.1`)
-- OpenAI Codex: `openai-codex/gpt-5.3-codex` (optional: `openai-codex/gpt-5.3-codex-codex`)
+- OpenAI Codex: `openai-codex/gpt-5.4`
 - Anthropic: `anthropic/claude-opus-4-6` (or `anthropic/claude-sonnet-4-5`)
 - Google (Gemini API): `google/gemini-3-pro-preview` and `google/gemini-3-flash-preview` (avoid older Gemini 2.x models)
 - Google (Antigravity): `google-antigravity/claude-opus-4-6-thinking` and `google-antigravity/gemini-3-flash`
@@ -283,7 +283,7 @@ This is the “common models” run we expect to keep working:
 - MiniMax: `minimax/minimax-m2.5`
 
 Run gateway smoke with tools + image:
-`OPENCLAW_LIVE_GATEWAY_MODELS="openai/gpt-5.2,openai-codex/gpt-5.3-codex,anthropic/claude-opus-4-6,google/gemini-3-pro-preview,google/gemini-3-flash-preview,google-antigravity/claude-opus-4-6-thinking,google-antigravity/gemini-3-flash,zai/glm-4.7,minimax/minimax-m2.5" pnpm test:live src/gateway/gateway-models.profiles.live.test.ts`
+`OPENCLAW_LIVE_GATEWAY_MODELS="openai/gpt-5.2,openai-codex/gpt-5.4,anthropic/claude-opus-4-6,google/gemini-3-pro-preview,google/gemini-3-flash-preview,google-antigravity/claude-opus-4-6-thinking,google-antigravity/gemini-3-flash,zai/glm-4.7,minimax/minimax-m2.5" pnpm test:live src/gateway/gateway-models.profiles.live.test.ts`
 
 ### Baseline: tool calling (Read + optional Exec)
 

docs/providers/openai.md

@@ -30,10 +30,13 @@ openclaw onboard --openai-api-key "$OPENAI_API_KEY"
 ```json5
 {
   env: { OPENAI_API_KEY: "sk-..." },
-  agents: { defaults: { model: { primary: "openai/gpt-5.2" } } },
+  agents: { defaults: { model: { primary: "openai/gpt-5.4" } } },
 }
 ```
 
+OpenAI's current API model docs list `gpt-5.4` and `gpt-5.4-pro` for direct
+OpenAI API usage. OpenClaw forwards both through the `openai/*` Responses path.
+
 ## Option B: OpenAI Code (Codex) subscription
 
 **Best for:** using ChatGPT/Codex subscription access instead of an API key.
@@ -53,10 +56,13 @@ openclaw models auth login --provider openai-codex
 
 ```json5
 {
-  agents: { defaults: { model: { primary: "openai-codex/gpt-5.3-codex" } } },
+  agents: { defaults: { model: { primary: "openai-codex/gpt-5.4" } } },
 }
 ```
 
+OpenAI's current Codex docs list `gpt-5.4` as the current Codex model. OpenClaw
+maps that to `openai-codex/gpt-5.4` for ChatGPT/Codex OAuth usage.
+
 ### Transport default
 
 OpenClaw uses `pi-ai` for model streaming. For both `openai/*` and
@@ -81,9 +87,9 @@ Related OpenAI docs:
 {
   agents: {
     defaults: {
-      model: { primary: "openai-codex/gpt-5.3-codex" },
+      model: { primary: "openai-codex/gpt-5.4" },
       models: {
-        "openai-codex/gpt-5.3-codex": {
+        "openai-codex/gpt-5.4": {
           params: {
             transport: "auto",
           },
@@ -106,7 +112,7 @@ OpenAI docs describe warm-up as optional. OpenClaw enables it by default for
   agents: {
     defaults: {
       models: {
-        "openai/gpt-5.2": {
+        "openai/gpt-5.4": {
           params: {
             openaiWsWarmup: false,
           },
@@ -124,7 +130,7 @@ OpenAI docs describe warm-up as optional. OpenClaw enables it by default for
   agents: {
     defaults: {
       models: {
-        "openai/gpt-5.2": {
+        "openai/gpt-5.4": {
           params: {
             openaiWsWarmup: true,
           },
@@ -135,6 +141,30 @@ OpenAI docs describe warm-up as optional. OpenClaw enables it by default for
 }
 ```
 
+### OpenAI priority processing
+
+OpenAI's API exposes priority processing via `service_tier=priority`. In
+OpenClaw, set `agents.defaults.models["openai/<model>"].params.serviceTier` to
+pass that field through on direct `openai/*` Responses requests.
+
+```json5
+{
+  agents: {
+    defaults: {
+      models: {
+        "openai/gpt-5.4": {
+          params: {
+            serviceTier: "priority",
+          },
+        },
+      },
+    },
+  },
+}
+```
+
+Supported values are `auto`, `default`, `flex`, and `priority`.
+
 ### OpenAI Responses server-side compaction
 
 For direct OpenAI Responses models (`openai/*` using `api: "openai-responses"` with
@@ -157,7 +187,7 @@ Responses models (for example Azure OpenAI Responses):
   agents: {
     defaults: {
       models: {
-        "azure-openai-responses/gpt-5.2": {
+        "azure-openai-responses/gpt-5.4": {
           params: {
             responsesServerCompaction: true,
           },
@@ -175,7 +205,7 @@ Responses models (for example Azure OpenAI Responses):
   agents: {
     defaults: {
       models: {
-        "openai/gpt-5.2": {
+        "openai/gpt-5.4": {
           params: {
             responsesServerCompaction: true,
             responsesCompactThreshold: 120000,
@@ -194,7 +224,7 @@ Responses models (for example Azure OpenAI Responses):
   agents: {
     defaults: {
       models: {
-        "openai/gpt-5.2": {
+        "openai/gpt-5.4": {
           params: {
             responsesServerCompaction: false,
           },

docs/reference/secretref-credential-surface.md

@@ -36,6 +36,7 @@ Scope intent:
 - `tools.web.search.kimi.apiKey`
 - `tools.web.search.perplexity.apiKey`
 - `gateway.auth.password`
+- `gateway.auth.token`
 - `gateway.remote.token`
 - `gateway.remote.password`
 - `cron.webhookToken`
@@ -107,7 +108,6 @@ Out-of-scope credentials include:
 
 [//]: # "secretref-unsupported-list-start"
 
-- `gateway.auth.token`
 - `commands.ownerDisplaySecret`
 - `channels.matrix.accessToken`
 - `channels.matrix.accounts.*.accessToken`

docs/reference/secretref-user-supplied-credentials-matrix.json

@@ -7,7 +7,6 @@
     "commands.ownerDisplaySecret",
     "channels.matrix.accessToken",
     "channels.matrix.accounts.*.accessToken",
-    "gateway.auth.token",
     "hooks.token",
     "hooks.gmail.pushToken",
     "hooks.mappings[].sessionKey",
@@ -385,6 +384,13 @@
       "secretShape": "secret_input",
       "optIn": true
     },
+    {
+      "id": "gateway.auth.token",
+      "configFile": "openclaw.json",
+      "path": "gateway.auth.token",
+      "secretShape": "secret_input",
+      "optIn": true
+    },
     {
       "id": "gateway.remote.password",
       "configFile": "openclaw.json",

docs/reference/wizard.md

@@ -71,6 +71,15 @@ For a high-level overview, see [Onboarding Wizard](/start/wizard).
   <Step title="Gateway">
     - Port, bind, auth mode, tailscale exposure.
     - Auth recommendation: keep **Token** even for loopback so local WS clients must authenticate.
+    - In token mode, interactive onboarding offers:
+      - **Generate/store plaintext token** (default)
+      - **Use SecretRef** (opt-in)
+      - Quickstart reuses existing `gateway.auth.token` SecretRefs across `env`, `file`, and `exec` providers for onboarding probe/dashboard bootstrap.
+      - If that SecretRef is configured but cannot be resolved, onboarding fails early with a clear fix message instead of silently degrading runtime auth.
+    - In password mode, interactive onboarding also supports plaintext or SecretRef storage.
+    - Non-interactive token SecretRef path: `--gateway-token-ref-env <ENV_VAR>`.
+      - Requires a non-empty env var in the onboarding process environment.
+      - Cannot be combined with `--gateway-token`.
     - Disable auth only if you fully trust every local process.
     - Non‑loopback binds still require auth.
   </Step>
@@ -92,6 +101,9 @@ For a high-level overview, see [Onboarding Wizard](/start/wizard).
       - Wizard attempts to enable lingering via `loginctl enable-linger <user>` so the Gateway stays up after logout.
       - May prompt for sudo (writes `/var/lib/systemd/linger`); it tries without sudo first.
     - **Runtime selection:** Node (recommended; required for WhatsApp/Telegram). Bun is **not recommended**.
+    - If token auth requires a token and `gateway.auth.token` is SecretRef-managed, daemon install validates it but does not persist resolved plaintext token values into supervisor service environment metadata.
+    - If token auth requires a token and the configured token SecretRef is unresolved, daemon install is blocked with actionable guidance.
+    - If both `gateway.auth.token` and `gateway.auth.password` are configured and `gateway.auth.mode` is unset, daemon install is blocked until mode is set explicitly.
   </Step>
   <Step title="Health check">
     - Starts the Gateway (if needed) and runs `openclaw health`.
@@ -130,6 +142,19 @@ openclaw onboard --non-interactive \
 
 Add `--json` for a machine‑readable summary.
 
+Gateway token SecretRef in non-interactive mode:
+
+```bash
+export OPENCLAW_GATEWAY_TOKEN="your-token"
+openclaw onboard --non-interactive \
+  --mode local \
+  --auth-choice skip \
+  --gateway-auth token \
+  --gateway-token-ref-env OPENCLAW_GATEWAY_TOKEN
+```
+
+`--gateway-token` and `--gateway-token-ref-env` are mutually exclusive.
+
 <Note>
 `--json` does **not** imply non-interactive mode. Use `--non-interactive` (and `--workspace`) for scripts.
 </Note>

docs/start/wizard-cli-reference.md

@@ -51,6 +51,13 @@ It does not install or modify anything on the remote host.
   <Step title="Gateway">
     - Prompts for port, bind, auth mode, and tailscale exposure.
     - Recommended: keep token auth enabled even for loopback so local WS clients must authenticate.
+    - In token mode, interactive onboarding offers:
+      - **Generate/store plaintext token** (default)
+      - **Use SecretRef** (opt-in)
+    - In password mode, interactive onboarding also supports plaintext or SecretRef storage.
+    - Non-interactive token SecretRef path: `--gateway-token-ref-env <ENV_VAR>`.
+      - Requires a non-empty env var in the onboarding process environment.
+      - Cannot be combined with `--gateway-token`.
     - Disable auth only if you fully trust every local process.
     - Non-loopback binds still require auth.
   </Step>
@@ -136,7 +143,7 @@ What you set:
   <Accordion title="OpenAI Code subscription (OAuth)">
     Browser flow; paste `code#state`.
 
-    Sets `agents.defaults.model` to `openai-codex/gpt-5.3-codex` when model is unset or `openai/*`.
+    Sets `agents.defaults.model` to `openai-codex/gpt-5.4` when model is unset or `openai/*`.
 
   </Accordion>
   <Accordion title="OpenAI API key">
@@ -206,7 +213,7 @@ Credential and profile paths:
 - OAuth credentials: `~/.openclaw/credentials/oauth.json`
 - Auth profiles (API keys + OAuth): `~/.openclaw/agents/<agentId>/agent/auth-profiles.json`
 
-API key storage mode:
+Credential storage mode:
 
 - Default onboarding behavior persists API keys as plaintext values in auth profiles.
 - `--secret-input-mode ref` enables reference mode instead of plaintext key storage.
@@ -222,6 +229,10 @@ API key storage mode:
   - Inline key flags (for example `--openai-api-key`) require that env var to be set; otherwise onboarding fails fast.
   - For custom providers, non-interactive `ref` mode stores `models.providers.<id>.apiKey` as `{ source: "env", provider: "default", id: "CUSTOM_API_KEY" }`.
   - In that custom-provider case, `--custom-api-key` requires `CUSTOM_API_KEY` to be set; otherwise onboarding fails fast.
+- Gateway auth credentials support plaintext and SecretRef choices in interactive onboarding:
+  - Token mode: **Generate/store plaintext token** (default) or **Use SecretRef**.
+  - Password mode: plaintext or SecretRef.
+- Non-interactive token SecretRef path: `--gateway-token-ref-env <ENV_VAR>`.
 - Existing plaintext setups continue to work unchanged.
 
 <Note>

docs/start/wizard.md

@@ -72,8 +72,13 @@ The wizard starts with **QuickStart** (defaults) vs **Advanced** (full control).
    In interactive runs, choosing secret reference mode lets you point at either an environment variable or a configured provider ref (`file` or `exec`), with a fast preflight validation before saving.
 2. **Workspace** — Location for agent files (default `~/.openclaw/workspace`). Seeds bootstrap files.
 3. **Gateway** — Port, bind address, auth mode, Tailscale exposure.
+   In interactive token mode, choose default plaintext token storage or opt into SecretRef.
+   Non-interactive token SecretRef path: `--gateway-token-ref-env <ENV_VAR>`.
 4. **Channels** — WhatsApp, Telegram, Discord, Google Chat, Mattermost, Signal, BlueBubbles, or iMessage.
 5. **Daemon** — Installs a LaunchAgent (macOS) or systemd user unit (Linux/WSL2).
+   If token auth requires a token and `gateway.auth.token` is SecretRef-managed, daemon install validates it but does not persist the resolved token into supervisor service environment metadata.
+   If token auth requires a token and the configured token SecretRef is unresolved, daemon install is blocked with actionable guidance.
+   If both `gateway.auth.token` and `gateway.auth.password` are configured and `gateway.auth.mode` is unset, daemon install is blocked until mode is set explicitly.
 6. **Health check** — Starts the Gateway and verifies it's running.
 7. **Skills** — Installs recommended skills and optional dependencies.
 

docs/tools/acp-agents.md

@@ -79,11 +79,14 @@ Required feature flags for thread-bound ACP:
 - `acp.dispatch.enabled` is on by default (set `false` to pause ACP dispatch)
 - Channel-adapter ACP thread-spawn flag enabled (adapter-specific)
   - Discord: `channels.discord.threadBindings.spawnAcpSessions=true`
+  - Telegram: `channels.telegram.threadBindings.spawnAcpSessions=true`
 
 ### Thread supporting channels
 
 - Any channel adapter that exposes session/thread binding capability.
-- Current built-in support: Discord.
+- Current built-in support:
+  - Discord threads/channels
+  - Telegram topics (forum topics in groups/supergroups and DM topics)
 - Plugin channels can add support through the same binding interface.
 
 ## Channel specific settings
@@ -303,7 +306,9 @@ If no target resolves, OpenClaw returns a clear error (`Unable to resolve sessio
 Notes:
 
 - On non-thread binding surfaces, default behavior is effectively `off`.
-- Thread-bound spawn requires channel policy support (for Discord: `channels.discord.threadBindings.spawnAcpSessions=true`).
+- Thread-bound spawn requires channel policy support:
+  - Discord: `channels.discord.threadBindings.spawnAcpSessions=true`
+  - Telegram: `channels.telegram.threadBindings.spawnAcpSessions=true`
 
 ## ACP controls
 

docs/tools/diffs.md

@@ -10,7 +10,7 @@ read_when:
 
 # Diffs
 
-`diffs` is an optional plugin tool and companion skill that turns change content into a read-only diff artifact for agents.
+`diffs` is an optional plugin tool with short built-in system guidance and a companion skill that turns change content into a read-only diff artifact for agents.
 
 It accepts either:
 
@@ -23,6 +23,8 @@ It can return:
 - a rendered file path (PNG or PDF) for message delivery
 - both outputs in one call
 
+When enabled, the plugin prepends concise usage guidance into system-prompt space and also exposes a detailed skill for cases where the agent needs fuller instructions.
+
 ## Quick start
 
 1. Enable the plugin.
@@ -44,6 +46,29 @@ It can return:
 }
 ```
 
+## Disable built-in system guidance
+
+If you want to keep the `diffs` tool enabled but disable its built-in system-prompt guidance, set `plugins.entries.diffs.hooks.allowPromptInjection` to `false`:
+
+```json5
+{
+  plugins: {
+    entries: {
+      diffs: {
+        enabled: true,
+        hooks: {
+          allowPromptInjection: false,
+        },
+      },
+    },
+  },
+}
+```
+
+This blocks the diffs plugin's `before_prompt_build` hook while keeping the plugin, tool, and companion skill available.
+
+If you want to disable both the guidance and the tool, disable the plugin instead.
+
 ## Typical agent workflow
 
 1. Agent calls `diffs`.

docs/tools/index.md

@@ -453,7 +453,7 @@ Restart or apply updates to the running Gateway process (in-place).
 Core actions:
 
 - `restart` (authorizes + sends `SIGUSR1` for in-process restart; `openclaw gateway` restart in-place)
-- `config.get` / `config.schema`
+- `config.get`
 - `config.apply` (validate + write config + restart + wake)
 - `config.patch` (merge partial update + restart + wake)
 - `update.run` (run update + restart + wake)
@@ -461,6 +461,7 @@ Core actions:
 Notes:
 
 - Use `delayMs` (defaults to 2000) to avoid interrupting an in-flight reply.
+- `config.schema` remains available to internal Control UI flows and is not exposed through the agent `gateway` tool.
 - `restart` is enabled by default; set `commands.restart: false` to disable it.
 
 ### `sessions_list` / `sessions_history` / `sessions_send` / `sessions_spawn` / `session_status`

docs/tools/llm-task.md

@@ -53,9 +53,9 @@ without writing custom OpenClaw code for each workflow.
         "enabled": true,
         "config": {
           "defaultProvider": "openai-codex",
-          "defaultModel": "gpt-5.2",
+          "defaultModel": "gpt-5.4",
           "defaultAuthProfileId": "main",
-          "allowedModels": ["openai-codex/gpt-5.3-codex"],
+          "allowedModels": ["openai-codex/gpt-5.4"],
           "maxTokens": 800,
           "timeoutMs": 30000
         }

docs/tools/plugin.md

@@ -62,7 +62,7 @@ Schema instead. See [Plugin manifest](/plugins/manifest).
 Plugins can register:
 
 - Gateway RPC methods
-- Gateway HTTP handlers
+- Gateway HTTP routes
 - Agent tools
 - CLI commands
 - Background services
@@ -106,6 +106,37 @@ Notes:
 - Uses core media-understanding audio configuration (`tools.media.audio`) and provider fallback order.
 - Returns `{ text: undefined }` when no transcription output is produced (for example skipped/unsupported input).
 
+## Gateway HTTP routes
+
+Plugins can expose HTTP endpoints with `api.registerHttpRoute(...)`.
+
+```ts
+api.registerHttpRoute({
+  path: "/acme/webhook",
+  auth: "plugin",
+  match: "exact",
+  handler: async (_req, res) => {
+    res.statusCode = 200;
+    res.end("ok");
+    return true;
+  },
+});
+```
+
+Route fields:
+
+- `path`: route path under the gateway HTTP server.
+- `auth`: required. Use `"gateway"` to require normal gateway auth, or `"plugin"` for plugin-managed auth/webhook verification.
+- `match`: optional. `"exact"` (default) or `"prefix"`.
+- `replaceExisting`: optional. Allows the same plugin to replace its own existing route registration.
+- `handler`: return `true` when the route handled the request.
+
+Notes:
+
+- `api.registerHttpHandler(...)` is obsolete. Use `api.registerHttpRoute(...)`.
+- Plugin routes must declare `auth` explicitly.
+- Exact `path + match` conflicts are rejected unless `replaceExisting: true`, and one plugin cannot replace another plugin's route.
+
 ## Plugin SDK import paths
 
 Use SDK subpaths instead of the monolithic `openclaw/plugin-sdk` import when
@@ -147,6 +178,38 @@ Compatibility note:
   subpaths; use `core` for generic surfaces and `compat` only when broader
   shared helpers are required.
 
+## Read-only channel inspection
+
+If your plugin registers a channel, prefer implementing
+`plugin.config.inspectAccount(cfg, accountId)` alongside `resolveAccount(...)`.
+
+Why:
+
+- `resolveAccount(...)` is the runtime path. It is allowed to assume credentials
+  are fully materialized and can fail fast when required secrets are missing.
+- Read-only command paths such as `openclaw status`, `openclaw status --all`,
+  `openclaw channels status`, `openclaw channels resolve`, and doctor/config
+  repair flows should not need to materialize runtime credentials just to
+  describe configuration.
+
+Recommended `inspectAccount(...)` behavior:
+
+- Return descriptive account state only.
+- Preserve `enabled` and `configured`.
+- Include credential source/status fields when relevant, such as:
+  - `tokenSource`, `tokenStatus`
+  - `botTokenSource`, `botTokenStatus`
+  - `appTokenSource`, `appTokenStatus`
+  - `signingSecretSource`, `signingSecretStatus`
+- You do not need to return raw token values just to report read-only
+  availability. Returning `tokenStatus: "available"` (and the matching source
+  field) is enough for status-style commands.
+- Use `configured_unavailable` when a credential is configured via SecretRef but
+  unavailable in the current command path.
+
+This lets read-only commands report “configured but unavailable in this command
+path” instead of crashing or misreporting the account as not configured.
+
 Performance note:
 
 - Plugin discovery and manifest metadata use short in-process caches to reduce
@@ -431,6 +494,59 @@ Notes:
 - Plugin-managed hooks show up in `openclaw hooks list` with `plugin:<id>`.
 - You cannot enable/disable plugin-managed hooks via `openclaw hooks`; enable/disable the plugin instead.
 
+### Agent lifecycle hooks (`api.on`)
+
+For typed runtime lifecycle hooks, use `api.on(...)`:
+
+```ts
+export default function register(api) {
+  api.on(
+    "before_prompt_build",
+    (event, ctx) => {
+      return {
+        prependSystemContext: "Follow company style guide.",
+      };
+    },
+    { priority: 10 },
+  );
+}
+```
+
+Important hooks for prompt construction:
+
+- `before_model_resolve`: runs before session load (`messages` are not available). Use this to deterministically override `modelOverride` or `providerOverride`.
+- `before_prompt_build`: runs after session load (`messages` are available). Use this to shape prompt input.
+- `before_agent_start`: legacy compatibility hook. Prefer the two explicit hooks above.
+
+Core-enforced hook policy:
+
+- Operators can disable prompt mutation hooks per plugin via `plugins.entries.<id>.hooks.allowPromptInjection: false`.
+- When disabled, OpenClaw blocks `before_prompt_build` and ignores prompt-mutating fields returned from legacy `before_agent_start` while preserving legacy `modelOverride` and `providerOverride`.
+
+`before_prompt_build` result fields:
+
+- `prependContext`: prepends text to the user prompt for this run. Best for turn-specific or dynamic content.
+- `systemPrompt`: full system prompt override.
+- `prependSystemContext`: prepends text to the current system prompt.
+- `appendSystemContext`: appends text to the current system prompt.
+
+Prompt build order in embedded runtime:
+
+1. Apply `prependContext` to the user prompt.
+2. Apply `systemPrompt` override when provided.
+3. Apply `prependSystemContext + current system prompt + appendSystemContext`.
+
+Merge and precedence notes:
+
+- Hook handlers run by priority (higher first).
+- For merged context fields, values are concatenated in execution order.
+- `before_prompt_build` values are applied before legacy `before_agent_start` fallback values.
+
+Migration guidance:
+
+- Move static guidance from `prependContext` to `prependSystemContext` (or `appendSystemContext`) so providers can cache stable system-prefix content.
+- Keep `prependContext` for per-turn dynamic context that should stay tied to the user message.
+
 ## Provider plugins (model auth)
 
 Plugins can register **model provider auth** flows so users can run OAuth or

docs/tools/subagents.md

@@ -214,7 +214,11 @@ Sub-agents report back via an announce step:
 
 - The announce step runs inside the sub-agent session (not the requester session).
 - If the sub-agent replies exactly `ANNOUNCE_SKIP`, nothing is posted.
-- Otherwise the announce reply is posted to the requester chat channel via a follow-up `agent` call (`deliver=true`).
+- Otherwise delivery depends on requester depth:
+  - top-level requester sessions use a follow-up `agent` call with external delivery (`deliver=true`)
+  - nested requester subagent sessions receive an internal follow-up injection (`deliver=false`) so the orchestrator can synthesize child results in-session
+  - if a nested requester subagent session is gone, OpenClaw falls back to that session's requester when available
+- Child completion aggregation is scoped to the current requester run when building nested completion findings, preventing stale prior-run child outputs from leaking into the current announce.
 - Announce replies preserve thread/topic routing when available on channel adapters.
 - Announce context is normalized to a stable internal event block:
   - source (`subagent` or `cron`)

docs/tts.md

@@ -93,6 +93,7 @@ Full schema is in [Gateway configuration](/gateway/configuration).
       },
       openai: {
         apiKey: "openai_api_key",
+        baseUrl: "https://api.openai.com/v1",
         model: "gpt-4o-mini-tts",
         voice: "alloy",
       },
@@ -216,6 +217,9 @@ Then run:
 - `prefsPath`: override the local prefs JSON path (provider/limit/summary).
 - `apiKey` values fall back to env vars (`ELEVENLABS_API_KEY`/`XI_API_KEY`, `OPENAI_API_KEY`).
 - `elevenlabs.baseUrl`: override ElevenLabs API base URL.
+- `openai.baseUrl`: override the OpenAI TTS endpoint.
+  - Resolution order: `messages.tts.openai.baseUrl` -> `OPENAI_TTS_BASE_URL` -> `https://api.openai.com/v1`
+  - Non-default values are treated as OpenAI-compatible TTS endpoints, so custom model and voice names are accepted.
 - `elevenlabs.voiceSettings`:
   - `stability`, `similarityBoost`, `style`: `0..1`
   - `useSpeakerBoost`: `true|false`

docs/web/control-ui.md

@@ -60,6 +60,15 @@ you revoke it with `openclaw devices revoke --device <id> --role <role>`. See
 - Each browser profile generates a unique device ID, so switching browsers or
   clearing browser data will require re-pairing.
 
+## Language support
+
+The Control UI can localize itself on first load based on your browser locale, and you can override it later from the language picker in the Access card.
+
+- Supported locales: `en`, `zh-CN`, `zh-TW`, `pt-BR`, `de`, `es`
+- Non-English translations are lazy-loaded in the browser.
+- The selected locale is saved in browser storage and reused on future visits.
+- Missing translation keys fall back to English.
+
 ## What it can do (today)
 
 - Chat with the model via Gateway WS (`chat.history`, `chat.send`, `chat.abort`, `chat.inject`)

docs/web/dashboard.md

@@ -37,10 +37,15 @@ Prefer localhost, Tailscale Serve, or an SSH tunnel.
 
 - **Localhost**: open `http://127.0.0.1:18789/`.
 - **Token source**: `gateway.auth.token` (or `OPENCLAW_GATEWAY_TOKEN`); the UI stores a copy in localStorage after you connect.
+- If `gateway.auth.token` is SecretRef-managed, `openclaw dashboard` prints/copies/opens a non-tokenized URL by design. This avoids exposing externally managed tokens in shell logs, clipboard history, or browser-launch arguments.
+- If `gateway.auth.token` is configured as a SecretRef and is unresolved in your current shell, `openclaw dashboard` still prints a non-tokenized URL plus actionable auth setup guidance.
 - **Not localhost**: use Tailscale Serve (tokenless for Control UI/WebSocket if `gateway.auth.allowTailscale: true`, assumes trusted gateway host; HTTP APIs still need token/password), tailnet bind with a token, or an SSH tunnel. See [Web surfaces](/web).
 
 ## If you see “unauthorized” / 1008
 
 - Ensure the gateway is reachable (local: `openclaw status`; remote: SSH tunnel `ssh -N -L 18789:127.0.0.1:18789 user@host` then open `http://127.0.0.1:18789/`).
-- Retrieve the token from the gateway host: `openclaw config get gateway.auth.token` (or generate one: `openclaw doctor --generate-gateway-token`).
+- Retrieve or supply the token from the gateway host:
+  - Plaintext config: `openclaw config get gateway.auth.token`
+  - SecretRef-managed config: resolve the external secret provider or export `OPENCLAW_GATEWAY_TOKEN` in this shell, then rerun `openclaw dashboard`
+  - No token configured: `openclaw doctor --generate-gateway-token`
 - In the dashboard settings, paste the token into the auth field, then connect.

extensions/acpx/src/runtime-internals/test-fixtures.ts

@@ -223,6 +223,10 @@ if (command === "prompt") {
     process.exit(1);
   }
 
+  if (stdinText.includes("permission-denied")) {
+    process.exit(5);
+  }
+
   if (stdinText.includes("split-spacing")) {
     emitUpdate(sessionFromOption, {
       sessionUpdate: "agent_message_chunk",

extensions/acpx/src/runtime.test.ts

@@ -224,6 +224,42 @@ describe("AcpxRuntime", () => {
     });
   });
 
+  it("maps acpx permission-denied exits to actionable guidance", async () => {
+    const runtime = sharedFixture?.runtime;
+    expect(runtime).toBeDefined();
+    if (!runtime) {
+      throw new Error("shared runtime fixture missing");
+    }
+    const handle = await runtime.ensureSession({
+      sessionKey: "agent:codex:acp:permission-denied",
+      agent: "codex",
+      mode: "persistent",
+    });
+
+    const events = [];
+    for await (const event of runtime.runTurn({
+      handle,
+      text: "permission-denied",
+      mode: "prompt",
+      requestId: "req-perm",
+    })) {
+      events.push(event);
+    }
+
+    expect(events).toContainEqual(
+      expect.objectContaining({
+        type: "error",
+        message: expect.stringContaining("Permission denied by ACP runtime (acpx)."),
+      }),
+    );
+    expect(events).toContainEqual(
+      expect.objectContaining({
+        type: "error",
+        message: expect.stringContaining("approve-reads, approve-all, deny-all"),
+      }),
+    );
+  });
+
   it("supports cancel and close using encoded runtime handle state", async () => {
     const { runtime, logPath, config } = await createMockRuntimeFixture();
     const handle = await runtime.ensureSession({

extensions/acpx/src/runtime.ts

@@ -42,10 +42,30 @@ export const ACPX_BACKEND_ID = "acpx";
 
 const ACPX_RUNTIME_HANDLE_PREFIX = "acpx:v1:";
 const DEFAULT_AGENT_FALLBACK = "codex";
+const ACPX_EXIT_CODE_PERMISSION_DENIED = 5;
 const ACPX_CAPABILITIES: AcpRuntimeCapabilities = {
   controls: ["session/set_mode", "session/set_config_option", "session/status"],
 };
 
+function formatPermissionModeGuidance(): string {
+  return "Configure plugins.entries.acpx.config.permissionMode to one of: approve-reads, approve-all, deny-all.";
+}
+
+function formatAcpxExitMessage(params: {
+  stderr: string;
+  exitCode: number | null | undefined;
+}): string {
+  const stderr = params.stderr.trim();
+  if (params.exitCode === ACPX_EXIT_CODE_PERMISSION_DENIED) {
+    return [
+      stderr || "Permission denied by ACP runtime (acpx).",
+      "ACPX blocked a write/exec permission request in a non-interactive session.",
+      formatPermissionModeGuidance(),
+    ].join(" ");
+  }
+  return stderr || `acpx exited with code ${params.exitCode ?? "unknown"}`;
+}
+
 export function encodeAcpxRuntimeHandleState(state: AcpxHandleState): string {
   const payload = Buffer.from(JSON.stringify(state), "utf8").toString("base64url");
   return `${ACPX_RUNTIME_HANDLE_PREFIX}${payload}`;
@@ -333,7 +353,10 @@ export class AcpxRuntime implements AcpRuntime {
       if ((exit.code ?? 0) !== 0 && !sawError) {
         yield {
           type: "error",
-          message: stderr.trim() || `acpx exited with code ${exit.code ?? "unknown"}`,
+          message: formatAcpxExitMessage({
+            stderr,
+            exitCode: exit.code,
+          }),
         };
         return;
       }
@@ -639,7 +662,10 @@ export class AcpxRuntime implements AcpRuntime {
     if ((result.code ?? 0) !== 0) {
       throw new AcpRuntimeError(
         params.fallbackCode,
-        result.stderr.trim() || `acpx exited with code ${result.code ?? "unknown"}`,
+        formatAcpxExitMessage({
+          stderr: result.stderr,
+          exitCode: result.code,
+        }),
       );
     }
     return events;

extensions/diffs/README.md

@@ -16,7 +16,7 @@ The tool can return:
 - `details.filePath`: a local rendered artifact path when file rendering is requested
 - `details.fileFormat`: the rendered file format (`png` or `pdf`)
 
-When the plugin is enabled, it also ships a companion skill from `skills/` that guides when to use `diffs`. This guidance is delivered through normal skill loading, not unconditional prompt-hook injection on every turn.
+When the plugin is enabled, it also ships a companion skill from `skills/` and prepends stable tool-usage guidance into system-prompt space via `before_prompt_build`. The hook uses `prependSystemContext`, so the guidance stays out of user-prompt space while still being available every turn.
 
 This means an agent can:
 

extensions/diffs/index.test.ts

@@ -4,7 +4,7 @@ import { createMockServerResponse } from "../../src/test-utils/mock-http-respons
 import plugin from "./index.js";
 
 describe("diffs plugin registration", () => {
-  it("registers the tool and http route", () => {
+  it("registers the tool, http route, and system-prompt guidance hook", async () => {
     const registerTool = vi.fn();
     const registerHttpRoute = vi.fn();
     const on = vi.fn();
@@ -43,7 +43,14 @@ describe("diffs plugin registration", () => {
       auth: "plugin",
       match: "prefix",
     });
-    expect(on).not.toHaveBeenCalled();
+    expect(on).toHaveBeenCalledTimes(1);
+    expect(on.mock.calls[0]?.[0]).toBe("before_prompt_build");
+    const beforePromptBuild = on.mock.calls[0]?.[1];
+    const result = await beforePromptBuild?.({}, {});
+    expect(result).toMatchObject({
+      prependSystemContext: expect.stringContaining("prefer the `diffs` tool"),
+    });
+    expect(result?.prependContext).toBeUndefined();
   });
 
   it("applies plugin-config defaults through registered tool and viewer handler", async () => {

extensions/diffs/index.ts

@@ -7,6 +7,7 @@ import {
   resolveDiffsPluginSecurity,
 } from "./src/config.js";
 import { createDiffsHttpHandler } from "./src/http.js";
+import { DIFFS_AGENT_GUIDANCE } from "./src/prompt-guidance.js";
 import { DiffArtifactStore } from "./src/store.js";
 import { createDiffsTool } from "./src/tool.js";
 
@@ -34,6 +35,9 @@ const plugin = {
         allowRemoteViewer: security.allowRemoteViewer,
       }),
     });
+    api.on("before_prompt_build", async () => ({
+      prependSystemContext: DIFFS_AGENT_GUIDANCE,
+    }));
   },
 };
 

extensions/diffs/src/prompt-guidance.ts

@@ -0,0 +1,7 @@
+export const DIFFS_AGENT_GUIDANCE = [
+  "When you need to show edits as a real diff, prefer the `diffs` tool instead of writing a manual summary.",
+  "It accepts either `before` + `after` text or a unified `patch`.",
+  "`mode=view` returns `details.viewerUrl` for canvas use; `mode=file` returns `details.filePath`; `mode=both` returns both.",
+  "If you need to send the rendered file, use the `message` tool with `path` or `filePath`.",
+  "Include `path` when you know the filename, and omit presentation overrides unless needed.",
+].join("\n");

extensions/discord/src/channel.ts

@@ -10,6 +10,7 @@ import {
   DiscordConfigSchema,
   formatPairingApproveHint,
   getChatChannelMeta,
+  inspectDiscordAccount,
   listDiscordAccountIds,
   listDiscordDirectoryGroupsFromConfig,
   listDiscordDirectoryPeersFromConfig,
@@ -19,6 +20,8 @@ import {
   normalizeDiscordMessagingTarget,
   normalizeDiscordOutboundTarget,
   PAIRING_APPROVED_MESSAGE,
+  projectCredentialSnapshotFields,
+  resolveConfiguredFromCredentialStatuses,
   resolveDiscordAccount,
   resolveDefaultDiscordAccountId,
   resolveDiscordGroupRequireMention,
@@ -80,6 +83,7 @@ export const discordPlugin: ChannelPlugin<ResolvedDiscordAccount> = {
   config: {
     listAccountIds: (cfg) => listDiscordAccountIds(cfg),
     resolveAccount: (cfg, accountId) => resolveDiscordAccount({ cfg, accountId }),
+    inspectAccount: (cfg, accountId) => inspectDiscordAccount({ cfg, accountId }),
     defaultAccountId: (cfg) => resolveDefaultDiscordAccountId(cfg),
     setAccountEnabled: ({ cfg, accountId, enabled }) =>
       setAccountEnabledInConfigSection({
@@ -390,7 +394,8 @@ export const discordPlugin: ChannelPlugin<ResolvedDiscordAccount> = {
       return { ...audit, unresolvedChannels };
     },
     buildAccountSnapshot: ({ account, runtime, probe, audit }) => {
-      const configured = Boolean(account.token?.trim());
+      const configured =
+        resolveConfiguredFromCredentialStatuses(account) ?? Boolean(account.token?.trim());
       const app = runtime?.application ?? (probe as { application?: unknown })?.application;
       const bot = runtime?.bot ?? (probe as { bot?: unknown })?.bot;
       return {
@@ -398,7 +403,7 @@ export const discordPlugin: ChannelPlugin<ResolvedDiscordAccount> = {
         name: account.name,
         enabled: account.enabled,
         configured,
-        tokenSource: account.tokenSource,
+        ...projectCredentialSnapshotFields(account),
         running: runtime?.running ?? false,
         lastStartAt: runtime?.lastStartAt ?? null,
         lastStopAt: runtime?.lastStopAt ?? null,

extensions/feishu/src/bot.checkBotMentioned.test.ts

@@ -76,6 +76,14 @@ describe("parseFeishuMessageEvent – mentionedBot", () => {
     expect(ctx.mentionedBot).toBe(true);
   });
 
+  it("returns mentionedBot=true when bot mention name differs from configured botName", () => {
+    const event = makeEvent("group", [
+      { key: "@_user_1", name: "OpenClaw Bot (Alias)", id: { open_id: BOT_OPEN_ID } },
+    ]);
+    const ctx = parseFeishuMessageEvent(event as any, BOT_OPEN_ID, "OpenClaw Bot");
+    expect(ctx.mentionedBot).toBe(true);
+  });
+
   it("returns mentionedBot=false when only other users are mentioned", () => {
     const event = makeEvent("group", [
       { key: "@_user_1", name: "Alice", id: { open_id: "ou_alice" } },

extensions/feishu/src/bot.stripBotMention.test.ts

@@ -37,7 +37,7 @@ describe("normalizeMentions (via parseFeishuMessageEvent)", () => {
     expect(ctx.content).toBe("hello");
   });
 
-  it("normalizes bot mention to <at> tag in group (semantic content)", () => {
+  it("strips bot mention in group so slash commands work (#35994)", () => {
     const ctx = parseFeishuMessageEvent(
       makeEvent(
         "@_bot_1 hello",
@@ -46,7 +46,19 @@ describe("normalizeMentions (via parseFeishuMessageEvent)", () => {
       ) as any,
       BOT_OPEN_ID,
     );
-    expect(ctx.content).toBe('<at user_id="ou_bot">Bot</at> hello');
+    expect(ctx.content).toBe("hello");
+  });
+
+  it("strips bot mention in group preserving slash command prefix (#35994)", () => {
+    const ctx = parseFeishuMessageEvent(
+      makeEvent(
+        "@_bot_1 /model",
+        [{ key: "@_bot_1", name: "Bot", id: { open_id: "ou_bot" } }],
+        "group",
+      ) as any,
+      BOT_OPEN_ID,
+    );
+    expect(ctx.content).toBe("/model");
   });
 
   it("strips bot mention but normalizes other mentions in p2p (mention-forward)", () => {

extensions/feishu/src/bot.test.ts

@@ -521,6 +521,42 @@ describe("handleFeishuMessage command authorization", () => {
     );
   });
 
+  it("normalizes group mention-prefixed slash commands before command-auth probing", async () => {
+    mockShouldComputeCommandAuthorized.mockReturnValue(true);
+
+    const cfg: ClawdbotConfig = {
+      channels: {
+        feishu: {
+          groups: {
+            "oc-group": {
+              requireMention: false,
+            },
+          },
+        },
+      },
+    } as ClawdbotConfig;
+
+    const event: FeishuMessageEvent = {
+      sender: {
+        sender_id: {
+          open_id: "ou-attacker",
+        },
+      },
+      message: {
+        message_id: "msg-group-mention-command-probe",
+        chat_id: "oc-group",
+        chat_type: "group",
+        message_type: "text",
+        content: JSON.stringify({ text: "@_user_1/model" }),
+        mentions: [{ key: "@_user_1", id: { open_id: "ou-bot" }, name: "Bot", tenant_key: "" }],
+      },
+    };
+
+    await dispatchMessage({ cfg, event });
+
+    expect(mockShouldComputeCommandAuthorized).toHaveBeenCalledWith("/model", cfg);
+  });
+
   it("falls back to top-level allowFrom for group command authorization", async () => {
     mockShouldComputeCommandAuthorized.mockReturnValue(true);
     mockResolveCommandAuthorizedFromAuthorizers.mockReturnValue(true);

extensions/feishu/src/bot.ts

@@ -450,24 +450,15 @@ function formatSubMessageContent(content: string, contentType: string): string {
   }
 }
 
-function checkBotMentioned(
-  event: FeishuMessageEvent,
-  botOpenId?: string,
-  botName?: string,
-): boolean {
+function checkBotMentioned(event: FeishuMessageEvent, botOpenId?: string): boolean {
   if (!botOpenId) return false;
   // Check for @all (@_all in Feishu) — treat as mentioning every bot
   const rawContent = event.message.content ?? "";
   if (rawContent.includes("@_all")) return true;
   const mentions = event.message.mentions ?? [];
   if (mentions.length > 0) {
-    return mentions.some((m) => {
-      if (m.id.open_id !== botOpenId) return false;
-      // Guard against Feishu WS open_id remapping in multi-app groups:
-      // if botName is known and mention name differs, this is a false positive.
-      if (botName && m.name && m.name !== botName) return false;
-      return true;
-    });
+    // Rely on Feishu mention IDs; display names can vary by alias/context.
+    return mentions.some((m) => m.id.open_id === botOpenId);
   }
   // Post (rich text) messages may have empty message.mentions when they contain docs/paste
   if (event.message.message_type === "post") {
@@ -503,6 +494,17 @@ function normalizeMentions(
   return result;
 }
 
+function normalizeFeishuCommandProbeBody(text: string): string {
+  if (!text) {
+    return "";
+  }
+  return text
+    .replace(/<at\b[^>]*>[^<]*<\/at>/giu, " ")
+    .replace(/(^|\s)@[^/\s]+(?=\s|$|\/)/gu, "$1")
+    .replace(/\s+/g, " ")
+    .trim();
+}
+
 /**
  * Parse media keys from message content based on message type.
  */
@@ -768,19 +770,17 @@ export function buildBroadcastSessionKey(
 export function parseFeishuMessageEvent(
   event: FeishuMessageEvent,
   botOpenId?: string,
-  botName?: string,
+  _botName?: string,
 ): FeishuMessageContext {
   const rawContent = parseMessageContent(event.message.content, event.message.message_type);
-  const mentionedBot = checkBotMentioned(event, botOpenId, botName);
+  const mentionedBot = checkBotMentioned(event, botOpenId);
   const hasAnyMention = (event.message.mentions?.length ?? 0) > 0;
-  // In p2p, the bot mention is a pure addressing prefix with no semantic value;
-  // strip it so slash commands like @Bot /help still have a leading /.
+  // Strip the bot's own mention so slash commands like @Bot /help retain
+  // the leading /. This applies in both p2p *and* group contexts — the
+  // mentionedBot flag already captures whether the bot was addressed, so
+  // keeping the mention tag in content only breaks command detection (#35994).
   // Non-bot mentions (e.g. mention-forward targets) are still normalized to <at> tags.
-  const content = normalizeMentions(
-    rawContent,
-    event.message.mentions,
-    event.message.chat_type === "p2p" ? botOpenId : undefined,
-  );
+  const content = normalizeMentions(rawContent, event.message.mentions, botOpenId);
   const senderOpenId = event.sender.sender_id.open_id?.trim();
   const senderUserId = event.sender.sender_id.user_id?.trim();
   const senderFallbackId = senderOpenId || senderUserId || "";
@@ -1080,8 +1080,9 @@ export async function handleFeishuMessage(params: {
       channel: "feishu",
       accountId: account.accountId,
     });
+    const commandProbeBody = isGroup ? normalizeFeishuCommandProbeBody(ctx.content) : ctx.content;
     const shouldComputeCommandAuthorized = core.channel.commands.shouldComputeCommandAuthorized(
-      ctx.content,
+      commandProbeBody,
       cfg,
     );
     const storeAllowFrom =

extensions/feishu/src/client.test.ts

@@ -12,6 +12,17 @@ const httpsProxyAgentCtorMock = vi.hoisted(() =>
   }),
 );
 
+const mockBaseHttpInstance = vi.hoisted(() => ({
+  request: vi.fn().mockResolvedValue({}),
+  get: vi.fn().mockResolvedValue({}),
+  post: vi.fn().mockResolvedValue({}),
+  put: vi.fn().mockResolvedValue({}),
+  patch: vi.fn().mockResolvedValue({}),
+  delete: vi.fn().mockResolvedValue({}),
+  head: vi.fn().mockResolvedValue({}),
+  options: vi.fn().mockResolvedValue({}),
+}));
+
 vi.mock("@larksuiteoapi/node-sdk", () => ({
   AppType: { SelfBuild: "self" },
   Domain: { Feishu: "https://open.feishu.cn", Lark: "https://open.larksuite.com" },
@@ -19,18 +30,28 @@ vi.mock("@larksuiteoapi/node-sdk", () => ({
   Client: vi.fn(),
   WSClient: wsClientCtorMock,
   EventDispatcher: vi.fn(),
+  defaultHttpInstance: mockBaseHttpInstance,
 }));
 
 vi.mock("https-proxy-agent", () => ({
   HttpsProxyAgent: httpsProxyAgentCtorMock,
 }));
 
-import { createFeishuWSClient } from "./client.js";
+import { Client as LarkClient } from "@larksuiteoapi/node-sdk";
+import {
+  createFeishuClient,
+  createFeishuWSClient,
+  clearClientCache,
+  FEISHU_HTTP_TIMEOUT_MS,
+  FEISHU_HTTP_TIMEOUT_MAX_MS,
+  FEISHU_HTTP_TIMEOUT_ENV_VAR,
+} from "./client.js";
 
 const proxyEnvKeys = ["https_proxy", "HTTPS_PROXY", "http_proxy", "HTTP_PROXY"] as const;
 type ProxyEnvKey = (typeof proxyEnvKeys)[number];
 
 let priorProxyEnv: Partial<Record<ProxyEnvKey, string | undefined>> = {};
+let priorFeishuTimeoutEnv: string | undefined;
 
 const baseAccount: ResolvedFeishuAccount = {
   accountId: "main",
@@ -50,6 +71,8 @@ function firstWsClientOptions(): { agent?: unknown } {
 
 beforeEach(() => {
   priorProxyEnv = {};
+  priorFeishuTimeoutEnv = process.env[FEISHU_HTTP_TIMEOUT_ENV_VAR];
+  delete process.env[FEISHU_HTTP_TIMEOUT_ENV_VAR];
   for (const key of proxyEnvKeys) {
     priorProxyEnv[key] = process.env[key];
     delete process.env[key];
@@ -66,6 +89,179 @@ afterEach(() => {
       process.env[key] = value;
     }
   }
+  if (priorFeishuTimeoutEnv === undefined) {
+    delete process.env[FEISHU_HTTP_TIMEOUT_ENV_VAR];
+  } else {
+    process.env[FEISHU_HTTP_TIMEOUT_ENV_VAR] = priorFeishuTimeoutEnv;
+  }
+});
+
+describe("createFeishuClient HTTP timeout", () => {
+  beforeEach(() => {
+    clearClientCache();
+  });
+
+  it("passes a custom httpInstance with default timeout to Lark.Client", () => {
+    createFeishuClient({ appId: "app_1", appSecret: "secret_1", accountId: "timeout-test" });
+
+    const calls = (LarkClient as unknown as ReturnType<typeof vi.fn>).mock.calls;
+    const lastCall = calls[calls.length - 1][0] as { httpInstance?: unknown };
+    expect(lastCall.httpInstance).toBeDefined();
+  });
+
+  it("injects default timeout into HTTP request options", async () => {
+    createFeishuClient({ appId: "app_2", appSecret: "secret_2", accountId: "timeout-inject" });
+
+    const calls = (LarkClient as unknown as ReturnType<typeof vi.fn>).mock.calls;
+    const lastCall = calls[calls.length - 1][0] as {
+      httpInstance: { post: (...args: unknown[]) => Promise<unknown> };
+    };
+    const httpInstance = lastCall.httpInstance;
+
+    await httpInstance.post(
+      "https://example.com/api",
+      { data: 1 },
+      { headers: { "X-Custom": "yes" } },
+    );
+
+    expect(mockBaseHttpInstance.post).toHaveBeenCalledWith(
+      "https://example.com/api",
+      { data: 1 },
+      expect.objectContaining({ timeout: FEISHU_HTTP_TIMEOUT_MS, headers: { "X-Custom": "yes" } }),
+    );
+  });
+
+  it("allows explicit timeout override per-request", async () => {
+    createFeishuClient({ appId: "app_3", appSecret: "secret_3", accountId: "timeout-override" });
+
+    const calls = (LarkClient as unknown as ReturnType<typeof vi.fn>).mock.calls;
+    const lastCall = calls[calls.length - 1][0] as {
+      httpInstance: { get: (...args: unknown[]) => Promise<unknown> };
+    };
+    const httpInstance = lastCall.httpInstance;
+
+    await httpInstance.get("https://example.com/api", { timeout: 5_000 });
+
+    expect(mockBaseHttpInstance.get).toHaveBeenCalledWith(
+      "https://example.com/api",
+      expect.objectContaining({ timeout: 5_000 }),
+    );
+  });
+
+  it("uses config-configured default timeout when provided", async () => {
+    createFeishuClient({
+      appId: "app_4",
+      appSecret: "secret_4",
+      accountId: "timeout-config",
+      config: { httpTimeoutMs: 45_000 },
+    });
+
+    const calls = (LarkClient as unknown as ReturnType<typeof vi.fn>).mock.calls;
+    const lastCall = calls[calls.length - 1][0] as {
+      httpInstance: { get: (...args: unknown[]) => Promise<unknown> };
+    };
+    const httpInstance = lastCall.httpInstance;
+
+    await httpInstance.get("https://example.com/api");
+
+    expect(mockBaseHttpInstance.get).toHaveBeenCalledWith(
+      "https://example.com/api",
+      expect.objectContaining({ timeout: 45_000 }),
+    );
+  });
+
+  it("falls back to default timeout when configured timeout is invalid", async () => {
+    createFeishuClient({
+      appId: "app_5",
+      appSecret: "secret_5",
+      accountId: "timeout-config-invalid",
+      config: { httpTimeoutMs: -1 },
+    });
+
+    const calls = (LarkClient as unknown as ReturnType<typeof vi.fn>).mock.calls;
+    const lastCall = calls[calls.length - 1][0] as {
+      httpInstance: { get: (...args: unknown[]) => Promise<unknown> };
+    };
+    const httpInstance = lastCall.httpInstance;
+
+    await httpInstance.get("https://example.com/api");
+
+    expect(mockBaseHttpInstance.get).toHaveBeenCalledWith(
+      "https://example.com/api",
+      expect.objectContaining({ timeout: FEISHU_HTTP_TIMEOUT_MS }),
+    );
+  });
+
+  it("uses env timeout override when provided", async () => {
+    process.env[FEISHU_HTTP_TIMEOUT_ENV_VAR] = "60000";
+
+    createFeishuClient({
+      appId: "app_8",
+      appSecret: "secret_8",
+      accountId: "timeout-env-override",
+      config: { httpTimeoutMs: 45_000 },
+    });
+
+    const calls = (LarkClient as unknown as ReturnType<typeof vi.fn>).mock.calls;
+    const lastCall = calls[calls.length - 1][0] as {
+      httpInstance: { get: (...args: unknown[]) => Promise<unknown> };
+    };
+    await lastCall.httpInstance.get("https://example.com/api");
+
+    expect(mockBaseHttpInstance.get).toHaveBeenCalledWith(
+      "https://example.com/api",
+      expect.objectContaining({ timeout: 60_000 }),
+    );
+  });
+
+  it("clamps env timeout override to max bound", async () => {
+    process.env[FEISHU_HTTP_TIMEOUT_ENV_VAR] = String(FEISHU_HTTP_TIMEOUT_MAX_MS + 123_456);
+
+    createFeishuClient({
+      appId: "app_9",
+      appSecret: "secret_9",
+      accountId: "timeout-env-clamp",
+    });
+
+    const calls = (LarkClient as unknown as ReturnType<typeof vi.fn>).mock.calls;
+    const lastCall = calls[calls.length - 1][0] as {
+      httpInstance: { get: (...args: unknown[]) => Promise<unknown> };
+    };
+    await lastCall.httpInstance.get("https://example.com/api");
+
+    expect(mockBaseHttpInstance.get).toHaveBeenCalledWith(
+      "https://example.com/api",
+      expect.objectContaining({ timeout: FEISHU_HTTP_TIMEOUT_MAX_MS }),
+    );
+  });
+
+  it("recreates cached client when configured timeout changes", async () => {
+    createFeishuClient({
+      appId: "app_6",
+      appSecret: "secret_6",
+      accountId: "timeout-cache-change",
+      config: { httpTimeoutMs: 30_000 },
+    });
+    createFeishuClient({
+      appId: "app_6",
+      appSecret: "secret_6",
+      accountId: "timeout-cache-change",
+      config: { httpTimeoutMs: 45_000 },
+    });
+
+    const calls = (LarkClient as unknown as ReturnType<typeof vi.fn>).mock.calls;
+    expect(calls.length).toBe(2);
+
+    const lastCall = calls[calls.length - 1][0] as {
+      httpInstance: { get: (...args: unknown[]) => Promise<unknown> };
+    };
+    await lastCall.httpInstance.get("https://example.com/api");
+
+    expect(mockBaseHttpInstance.get).toHaveBeenCalledWith(
+      "https://example.com/api",
+      expect.objectContaining({ timeout: 45_000 }),
+    );
+  });
 });
 
 describe("createFeishuWSClient proxy handling", () => {

extensions/feishu/src/client.ts

@@ -1,6 +1,11 @@
 import * as Lark from "@larksuiteoapi/node-sdk";
 import { HttpsProxyAgent } from "https-proxy-agent";
-import type { FeishuDomain, ResolvedFeishuAccount } from "./types.js";
+import type { FeishuConfig, FeishuDomain, ResolvedFeishuAccount } from "./types.js";
+
+/** Default HTTP timeout for Feishu API requests (30 seconds). */
+export const FEISHU_HTTP_TIMEOUT_MS = 30_000;
+export const FEISHU_HTTP_TIMEOUT_MAX_MS = 300_000;
+export const FEISHU_HTTP_TIMEOUT_ENV_VAR = "OPENCLAW_FEISHU_HTTP_TIMEOUT_MS";
 
 function getWsProxyAgent(): HttpsProxyAgent<string> | undefined {
   const proxyUrl =
@@ -17,7 +22,7 @@ const clientCache = new Map<
   string,
   {
     client: Lark.Client;
-    config: { appId: string; appSecret: string; domain?: FeishuDomain };
+    config: { appId: string; appSecret: string; domain?: FeishuDomain; httpTimeoutMs: number };
   }
 >();
 
@@ -31,6 +36,30 @@ function resolveDomain(domain: FeishuDomain | undefined): Lark.Domain | string {
   return domain.replace(/\/+$/, ""); // Custom URL for private deployment
 }
 
+/**
+ * Create an HTTP instance that delegates to the Lark SDK's default instance
+ * but injects a default request timeout to prevent indefinite hangs
+ * (e.g. when the Feishu API is slow, causing per-chat queue deadlocks).
+ */
+function createTimeoutHttpInstance(defaultTimeoutMs: number): Lark.HttpInstance {
+  const base: Lark.HttpInstance = Lark.defaultHttpInstance as unknown as Lark.HttpInstance;
+
+  function injectTimeout<D>(opts?: Lark.HttpRequestOptions<D>): Lark.HttpRequestOptions<D> {
+    return { timeout: defaultTimeoutMs, ...opts } as Lark.HttpRequestOptions<D>;
+  }
+
+  return {
+    request: (opts) => base.request(injectTimeout(opts)),
+    get: (url, opts) => base.get(url, injectTimeout(opts)),
+    post: (url, data, opts) => base.post(url, data, injectTimeout(opts)),
+    put: (url, data, opts) => base.put(url, data, injectTimeout(opts)),
+    patch: (url, data, opts) => base.patch(url, data, injectTimeout(opts)),
+    delete: (url, opts) => base.delete(url, injectTimeout(opts)),
+    head: (url, opts) => base.head(url, injectTimeout(opts)),
+    options: (url, opts) => base.options(url, injectTimeout(opts)),
+  };
+}
+
 /**
  * Credentials needed to create a Feishu client.
  * Both FeishuConfig and ResolvedFeishuAccount satisfy this interface.
@@ -40,14 +69,40 @@ export type FeishuClientCredentials = {
   appId?: string;
   appSecret?: string;
   domain?: FeishuDomain;
+  httpTimeoutMs?: number;
+  config?: Pick<FeishuConfig, "httpTimeoutMs">;
 };
 
+function resolveConfiguredHttpTimeoutMs(creds: FeishuClientCredentials): number {
+  const clampTimeout = (value: number): number => {
+    const rounded = Math.floor(value);
+    return Math.min(Math.max(rounded, 1), FEISHU_HTTP_TIMEOUT_MAX_MS);
+  };
+
+  const envRaw = process.env[FEISHU_HTTP_TIMEOUT_ENV_VAR];
+  if (envRaw) {
+    const envValue = Number(envRaw);
+    if (Number.isFinite(envValue) && envValue > 0) {
+      return clampTimeout(envValue);
+    }
+  }
+
+  const fromConfig = creds.config?.httpTimeoutMs;
+  const fromDirectField = creds.httpTimeoutMs;
+  const timeout = fromDirectField ?? fromConfig;
+  if (typeof timeout !== "number" || !Number.isFinite(timeout) || timeout <= 0) {
+    return FEISHU_HTTP_TIMEOUT_MS;
+  }
+  return clampTimeout(timeout);
+}
+
 /**
  * Create or get a cached Feishu client for an account.
  * Accepts any object with appId, appSecret, and optional domain/accountId.
  */
 export function createFeishuClient(creds: FeishuClientCredentials): Lark.Client {
   const { accountId = "default", appId, appSecret, domain } = creds;
+  const defaultHttpTimeoutMs = resolveConfiguredHttpTimeoutMs(creds);
 
   if (!appId || !appSecret) {
     throw new Error(`Feishu credentials not configured for account "${accountId}"`);
@@ -59,23 +114,25 @@ export function createFeishuClient(creds: FeishuClientCredentials): Lark.Client
     cached &&
     cached.config.appId === appId &&
     cached.config.appSecret === appSecret &&
-    cached.config.domain === domain
+    cached.config.domain === domain &&
+    cached.config.httpTimeoutMs === defaultHttpTimeoutMs
   ) {
     return cached.client;
   }
 
-  // Create new client
+  // Create new client with timeout-aware HTTP instance
   const client = new Lark.Client({
     appId,
     appSecret,
     appType: Lark.AppType.SelfBuild,
     domain: resolveDomain(domain),
+    httpInstance: createTimeoutHttpInstance(defaultHttpTimeoutMs),
   });
 
   // Cache it
   clientCache.set(accountId, {
     client,
-    config: { appId, appSecret, domain },
+    config: { appId, appSecret, domain, httpTimeoutMs: defaultHttpTimeoutMs },
   });
 
   return client;

extensions/feishu/src/config-schema.test.ts

@@ -24,6 +24,14 @@ describe("FeishuConfigSchema webhook validation", () => {
     expect(result.accounts?.main?.requireMention).toBeUndefined();
   });
 
+  it("normalizes legacy groupPolicy allowall to open", () => {
+    const result = FeishuConfigSchema.parse({
+      groupPolicy: "allowall",
+    });
+
+    expect(result.groupPolicy).toBe("open");
+  });
+
   it("rejects top-level webhook mode without verificationToken", () => {
     const result = FeishuConfigSchema.safeParse({
       connectionMode: "webhook",

extensions/feishu/src/config-schema.ts

@@ -4,7 +4,10 @@ export { z };
 import { buildSecretInputSchema, hasConfiguredSecretInput } from "./secret-input.js";
 
 const DmPolicySchema = z.enum(["open", "pairing", "allowlist"]);
-const GroupPolicySchema = z.enum(["open", "allowlist", "disabled"]);
+const GroupPolicySchema = z.union([
+  z.enum(["open", "allowlist", "disabled"]),
+  z.literal("allowall").transform(() => "open" as const),
+]);
 const FeishuDomainSchema = z.union([
   z.enum(["feishu", "lark"]),
   z.string().url().startsWith("https://"),
@@ -162,6 +165,7 @@ const FeishuSharedConfigShape = {
   chunkMode: z.enum(["length", "newline"]).optional(),
   blockStreamingCoalesce: BlockStreamingCoalesceSchema,
   mediaMaxMb: z.number().positive().optional(),
+  httpTimeoutMs: z.number().int().positive().max(300_000).optional(),
   heartbeat: ChannelHeartbeatVisibilitySchema,
   renderMode: RenderModeSchema,
   streaming: StreamingModeSchema,

extensions/feishu/src/media.test.ts

@@ -10,6 +10,7 @@ const resolveReceiveIdTypeMock = vi.hoisted(() => vi.fn());
 const loadWebMediaMock = vi.hoisted(() => vi.fn());
 
 const fileCreateMock = vi.hoisted(() => vi.fn());
+const imageCreateMock = vi.hoisted(() => vi.fn());
 const imageGetMock = vi.hoisted(() => vi.fn());
 const messageCreateMock = vi.hoisted(() => vi.fn());
 const messageResourceGetMock = vi.hoisted(() => vi.fn());
@@ -75,6 +76,7 @@ describe("sendMediaFeishu msg_type routing", () => {
           create: fileCreateMock,
         },
         image: {
+          create: imageCreateMock,
           get: imageGetMock,
         },
         message: {
@@ -91,6 +93,10 @@ describe("sendMediaFeishu msg_type routing", () => {
       code: 0,
       data: { file_key: "file_key_1" },
     });
+    imageCreateMock.mockResolvedValue({
+      code: 0,
+      data: { image_key: "image_key_1" },
+    });
 
     messageCreateMock.mockResolvedValue({
       code: 0,
@@ -176,6 +182,26 @@ describe("sendMediaFeishu msg_type routing", () => {
     );
   });
 
+  it("uses image upload timeout override for image media", async () => {
+    await sendMediaFeishu({
+      cfg: {} as any,
+      to: "user:ou_target",
+      mediaBuffer: Buffer.from("image"),
+      fileName: "photo.png",
+    });
+
+    expect(imageCreateMock).toHaveBeenCalledWith(
+      expect.objectContaining({
+        timeout: 120_000,
+      }),
+    );
+    expect(messageCreateMock).toHaveBeenCalledWith(
+      expect.objectContaining({
+        data: expect.objectContaining({ msg_type: "image" }),
+      }),
+    );
+  });
+
   it("uses msg_type=media when replying with mp4", async () => {
     await sendMediaFeishu({
       cfg: {} as any,
@@ -291,6 +317,12 @@ describe("sendMediaFeishu msg_type routing", () => {
       imageKey,
     });
 
+    expect(imageGetMock).toHaveBeenCalledWith(
+      expect.objectContaining({
+        path: { image_key: imageKey },
+        timeout: 120_000,
+      }),
+    );
     expect(result.buffer).toEqual(Buffer.from("image-data"));
     expect(capturedPath).toBeDefined();
     expectPathIsolatedToTmpRoot(capturedPath as string, imageKey);
@@ -476,10 +508,13 @@ describe("downloadMessageResourceFeishu", () => {
       type: "file",
     });
 
-    expect(messageResourceGetMock).toHaveBeenCalledWith({
-      path: { message_id: "om_audio_msg", file_key: "file_key_audio" },
-      params: { type: "file" },
-    });
+    expect(messageResourceGetMock).toHaveBeenCalledWith(
+      expect.objectContaining({
+        path: { message_id: "om_audio_msg", file_key: "file_key_audio" },
+        params: { type: "file" },
+        timeout: 120_000,
+      }),
+    );
     expect(result.buffer).toBeInstanceOf(Buffer);
   });
 
@@ -493,10 +528,13 @@ describe("downloadMessageResourceFeishu", () => {
       type: "image",
     });
 
-    expect(messageResourceGetMock).toHaveBeenCalledWith({
-      path: { message_id: "om_img_msg", file_key: "img_key_1" },
-      params: { type: "image" },
-    });
+    expect(messageResourceGetMock).toHaveBeenCalledWith(
+      expect.objectContaining({
+        path: { message_id: "om_img_msg", file_key: "img_key_1" },
+        params: { type: "image" },
+        timeout: 120_000,
+      }),
+    );
     expect(result.buffer).toBeInstanceOf(Buffer);
   });
 });

extensions/feishu/src/media.ts

@@ -9,6 +9,8 @@ import { getFeishuRuntime } from "./runtime.js";
 import { assertFeishuMessageApiSuccess, toFeishuSendResult } from "./send-result.js";
 import { resolveFeishuSendTarget } from "./send-target.js";
 
+const FEISHU_MEDIA_HTTP_TIMEOUT_MS = 120_000;
+
 export type DownloadImageResult = {
   buffer: Buffer;
   contentType?: string;
@@ -97,7 +99,10 @@ export async function downloadImageFeishu(params: {
     throw new Error(`Feishu account "${account.accountId}" not configured`);
   }
 
-  const client = createFeishuClient(account);
+  const client = createFeishuClient({
+    ...account,
+    httpTimeoutMs: FEISHU_MEDIA_HTTP_TIMEOUT_MS,
+  });
 
   const response = await client.im.image.get({
     path: { image_key: normalizedImageKey },
@@ -132,7 +137,10 @@ export async function downloadMessageResourceFeishu(params: {
     throw new Error(`Feishu account "${account.accountId}" not configured`);
   }
 
-  const client = createFeishuClient(account);
+  const client = createFeishuClient({
+    ...account,
+    httpTimeoutMs: FEISHU_MEDIA_HTTP_TIMEOUT_MS,
+  });
 
   const response = await client.im.messageResource.get({
     path: { message_id: messageId, file_key: normalizedFileKey },
@@ -176,7 +184,10 @@ export async function uploadImageFeishu(params: {
     throw new Error(`Feishu account "${account.accountId}" not configured`);
   }
 
-  const client = createFeishuClient(account);
+  const client = createFeishuClient({
+    ...account,
+    httpTimeoutMs: FEISHU_MEDIA_HTTP_TIMEOUT_MS,
+  });
 
   // SDK accepts Buffer directly or fs.ReadStream for file paths
   // Using Readable.from(buffer) causes issues with form-data library
@@ -243,7 +254,10 @@ export async function uploadFileFeishu(params: {
     throw new Error(`Feishu account "${account.accountId}" not configured`);
   }
 
-  const client = createFeishuClient(account);
+  const client = createFeishuClient({
+    ...account,
+    httpTimeoutMs: FEISHU_MEDIA_HTTP_TIMEOUT_MS,
+  });
 
   // SDK accepts Buffer directly or fs.ReadStream for file paths
   // Using Readable.from(buffer) causes issues with form-data library

extensions/feishu/src/monitor.account.ts

@@ -19,8 +19,8 @@ import {
   warmupDedupFromDisk,
 } from "./dedup.js";
 import { isMentionForwardRequest } from "./mention.js";
-import { fetchBotOpenIdForMonitor } from "./monitor.startup.js";
-import { botOpenIds } from "./monitor.state.js";
+import { fetchBotIdentityForMonitor } from "./monitor.startup.js";
+import { botNames, botOpenIds } from "./monitor.state.js";
 import { monitorWebhook, monitorWebSocket } from "./monitor.transport.js";
 import { getFeishuRuntime } from "./runtime.js";
 import { getMessageFeishu } from "./send.js";
@@ -247,6 +247,7 @@ function registerEventHandlers(
         cfg,
         event,
         botOpenId: botOpenIds.get(accountId),
+        botName: botNames.get(accountId),
         runtime,
         chatHistories,
         accountId,
@@ -260,7 +261,7 @@ function registerEventHandlers(
   };
   const resolveDebounceText = (event: FeishuMessageEvent): string => {
     const botOpenId = botOpenIds.get(accountId);
-    const parsed = parseFeishuMessageEvent(event, botOpenId);
+    const parsed = parseFeishuMessageEvent(event, botOpenId, botNames.get(accountId));
     return parsed.content.trim();
   };
   const recordSuppressedMessageIds = async (
@@ -430,6 +431,7 @@ function registerEventHandlers(
           cfg,
           event: syntheticEvent,
           botOpenId: myBotId,
+          botName: botNames.get(accountId),
           runtime,
           chatHistories,
           accountId,
@@ -483,7 +485,9 @@ function registerEventHandlers(
   });
 }
 
-export type BotOpenIdSource = { kind: "prefetched"; botOpenId?: string } | { kind: "fetch" };
+export type BotOpenIdSource =
+  | { kind: "prefetched"; botOpenId?: string; botName?: string }
+  | { kind: "fetch" };
 
 export type MonitorSingleAccountParams = {
   cfg: ClawdbotConfig;
@@ -499,11 +503,18 @@ export async function monitorSingleAccount(params: MonitorSingleAccountParams):
   const log = runtime?.log ?? console.log;
 
   const botOpenIdSource = params.botOpenIdSource ?? { kind: "fetch" };
-  const botOpenId =
+  const botIdentity =
     botOpenIdSource.kind === "prefetched"
-      ? botOpenIdSource.botOpenId
-      : await fetchBotOpenIdForMonitor(account, { runtime, abortSignal });
+      ? { botOpenId: botOpenIdSource.botOpenId, botName: botOpenIdSource.botName }
+      : await fetchBotIdentityForMonitor(account, { runtime, abortSignal });
+  const botOpenId = botIdentity.botOpenId;
+  const botName = botIdentity.botName?.trim();
   botOpenIds.set(accountId, botOpenId ?? "");
+  if (botName) {
+    botNames.set(accountId, botName);
+  } else {
+    botNames.delete(accountId);
+  }
   log(`feishu[${accountId}]: bot open_id resolved: ${botOpenId ?? "unknown"}`);
 
   const connectionMode = account.config.connectionMode ?? "websocket";

extensions/feishu/src/monitor.reaction.test.ts

@@ -109,7 +109,10 @@ function createTextEvent(params: {
   };
 }
 
-async function setupDebounceMonitor(): Promise<(data: unknown) => Promise<void>> {
+async function setupDebounceMonitor(params?: {
+  botOpenId?: string;
+  botName?: string;
+}): Promise<(data: unknown) => Promise<void>> {
   const register = vi.fn((registered: Record<string, (data: unknown) => Promise<void>>) => {
     handlers = registered;
   });
@@ -123,7 +126,11 @@ async function setupDebounceMonitor(): Promise<(data: unknown) => Promise<void>>
       error: vi.fn(),
       exit: vi.fn(),
     } as RuntimeEnv,
-    botOpenIdSource: { kind: "prefetched", botOpenId: "ou_bot" },
+    botOpenIdSource: {
+      kind: "prefetched",
+      botOpenId: params?.botOpenId ?? "ou_bot",
+      botName: params?.botName,
+    },
   });
 
   const onMessage = handlers["im.message.receive_v1"];
@@ -434,6 +441,37 @@ describe("Feishu inbound debounce regressions", () => {
     expect(mergedMentions.some((mention) => mention.id.open_id === "ou_user_a")).toBe(false);
   });
 
+  it("passes prefetched botName through to handleFeishuMessage", async () => {
+    vi.spyOn(dedup, "tryRecordMessage").mockReturnValue(true);
+    vi.spyOn(dedup, "tryRecordMessagePersistent").mockResolvedValue(true);
+    vi.spyOn(dedup, "hasRecordedMessage").mockReturnValue(false);
+    vi.spyOn(dedup, "hasRecordedMessagePersistent").mockResolvedValue(false);
+    const onMessage = await setupDebounceMonitor({ botName: "OpenClaw Bot" });
+
+    await onMessage(
+      createTextEvent({
+        messageId: "om_name_passthrough",
+        text: "@bot hello",
+        mentions: [
+          {
+            key: "@_user_1",
+            id: { open_id: "ou_bot" },
+            name: "OpenClaw Bot",
+          },
+        ],
+      }),
+    );
+    await Promise.resolve();
+    await Promise.resolve();
+    await vi.advanceTimersByTimeAsync(25);
+
+    expect(handleFeishuMessageMock).toHaveBeenCalledTimes(1);
+    const firstParams = handleFeishuMessageMock.mock.calls[0]?.[0] as
+      | { botName?: string }
+      | undefined;
+    expect(firstParams?.botName).toBe("OpenClaw Bot");
+  });
+
   it("does not synthesize mention-forward intent across separate messages", async () => {
     vi.spyOn(dedup, "tryRecordMessage").mockReturnValue(true);
     vi.spyOn(dedup, "tryRecordMessagePersistent").mockResolvedValue(true);

extensions/feishu/src/monitor.startup.ts

@@ -10,6 +10,11 @@ type FetchBotOpenIdOptions = {
   timeoutMs?: number;
 };
 
+export type FeishuMonitorBotIdentity = {
+  botOpenId?: string;
+  botName?: string;
+};
+
 function isTimeoutErrorMessage(message: string | undefined): boolean {
   return message?.toLowerCase().includes("timeout") || message?.toLowerCase().includes("timed out")
     ? true
@@ -20,12 +25,12 @@ function isAbortErrorMessage(message: string | undefined): boolean {
   return message?.toLowerCase().includes("aborted") ?? false;
 }
 
-export async function fetchBotOpenIdForMonitor(
+export async function fetchBotIdentityForMonitor(
   account: ResolvedFeishuAccount,
   options: FetchBotOpenIdOptions = {},
-): Promise<string | undefined> {
+): Promise<FeishuMonitorBotIdentity> {
   if (options.abortSignal?.aborted) {
-    return undefined;
+    return {};
   }
 
   const timeoutMs = options.timeoutMs ?? FEISHU_STARTUP_BOT_INFO_TIMEOUT_MS;
@@ -34,11 +39,11 @@ export async function fetchBotOpenIdForMonitor(
     abortSignal: options.abortSignal,
   });
   if (result.ok) {
-    return result.botOpenId;
+    return { botOpenId: result.botOpenId, botName: result.botName };
   }
 
   if (options.abortSignal?.aborted || isAbortErrorMessage(result.error)) {
-    return undefined;
+    return {};
   }
 
   if (isTimeoutErrorMessage(result.error)) {
@@ -47,5 +52,13 @@ export async function fetchBotOpenIdForMonitor(
       `feishu[${account.accountId}]: bot info probe timed out after ${timeoutMs}ms; continuing startup`,
     );
   }
-  return undefined;
+  return {};
+}
+
+export async function fetchBotOpenIdForMonitor(
+  account: ResolvedFeishuAccount,
+  options: FetchBotOpenIdOptions = {},
+): Promise<string | undefined> {
+  const identity = await fetchBotIdentityForMonitor(account, options);
+  return identity.botOpenId;
 }

extensions/feishu/src/monitor.state.ts

@@ -11,6 +11,7 @@ import {
 export const wsClients = new Map<string, Lark.WSClient>();
 export const httpServers = new Map<string, http.Server>();
 export const botOpenIds = new Map<string, string>();
+export const botNames = new Map<string, string>();
 
 export const FEISHU_WEBHOOK_MAX_BODY_BYTES = 1024 * 1024;
 export const FEISHU_WEBHOOK_BODY_TIMEOUT_MS = 30_000;
@@ -140,6 +141,7 @@ export function stopFeishuMonitorState(accountId?: string): void {
       httpServers.delete(accountId);
     }
     botOpenIds.delete(accountId);
+    botNames.delete(accountId);
     return;
   }
 
@@ -149,4 +151,5 @@ export function stopFeishuMonitorState(accountId?: string): void {
   }
   httpServers.clear();
   botOpenIds.clear();
+  botNames.clear();
 }

extensions/feishu/src/monitor.transport.ts

@@ -7,6 +7,7 @@ import {
 } from "openclaw/plugin-sdk/feishu";
 import { createFeishuWSClient } from "./client.js";
 import {
+  botNames,
   botOpenIds,
   FEISHU_WEBHOOK_BODY_TIMEOUT_MS,
   FEISHU_WEBHOOK_MAX_BODY_BYTES,
@@ -42,6 +43,7 @@ export async function monitorWebSocket({
     const cleanup = () => {
       wsClients.delete(accountId);
       botOpenIds.delete(accountId);
+      botNames.delete(accountId);
     };
 
     const handleAbort = () => {
@@ -134,6 +136,7 @@ export async function monitorWebhook({
       server.close();
       httpServers.delete(accountId);
       botOpenIds.delete(accountId);
+      botNames.delete(accountId);
     };
 
     const handleAbort = () => {

extensions/feishu/src/monitor.ts

@@ -5,7 +5,7 @@ import {
   resolveReactionSyntheticEvent,
   type FeishuReactionCreatedEvent,
 } from "./monitor.account.js";
-import { fetchBotOpenIdForMonitor } from "./monitor.startup.js";
+import { fetchBotIdentityForMonitor } from "./monitor.startup.js";
 import {
   clearFeishuWebhookRateLimitStateForTest,
   getFeishuWebhookRateLimitStateSizeForTest,
@@ -66,7 +66,7 @@ export async function monitorFeishuProvider(opts: MonitorFeishuOpts = {}): Promi
     }
 
     // Probe sequentially so large multi-account startups do not burst Feishu's bot-info endpoint.
-    const botOpenId = await fetchBotOpenIdForMonitor(account, {
+    const { botOpenId, botName } = await fetchBotIdentityForMonitor(account, {
       runtime: opts.runtime,
       abortSignal: opts.abortSignal,
     });
@@ -82,7 +82,7 @@ export async function monitorFeishuProvider(opts: MonitorFeishuOpts = {}): Promi
         account,
         runtime: opts.runtime,
         abortSignal: opts.abortSignal,
-        botOpenIdSource: { kind: "prefetched", botOpenId },
+        botOpenIdSource: { kind: "prefetched", botOpenId, botName },
       }),
     );
   }

extensions/feishu/src/policy.test.ts

@@ -110,5 +110,45 @@ describe("feishu policy", () => {
         }),
       ).toBe(true);
     });
+
+    it("allows group when groupPolicy is 'open'", () => {
+      expect(
+        isFeishuGroupAllowed({
+          groupPolicy: "open",
+          allowFrom: [],
+          senderId: "oc_group_999",
+        }),
+      ).toBe(true);
+    });
+
+    it("treats 'allowall' as equivalent to 'open'", () => {
+      expect(
+        isFeishuGroupAllowed({
+          groupPolicy: "allowall",
+          allowFrom: [],
+          senderId: "oc_group_999",
+        }),
+      ).toBe(true);
+    });
+
+    it("rejects group when groupPolicy is 'disabled'", () => {
+      expect(
+        isFeishuGroupAllowed({
+          groupPolicy: "disabled",
+          allowFrom: ["oc_group_999"],
+          senderId: "oc_group_999",
+        }),
+      ).toBe(false);
+    });
+
+    it("rejects group when groupPolicy is 'allowlist' and allowFrom is empty", () => {
+      expect(
+        isFeishuGroupAllowed({
+          groupPolicy: "allowlist",
+          allowFrom: [],
+          senderId: "oc_group_999",
+        }),
+      ).toBe(false);
+    });
   });
 });

extensions/feishu/src/policy.ts

@@ -92,7 +92,7 @@ export function resolveFeishuGroupToolPolicy(
 }
 
 export function isFeishuGroupAllowed(params: {
-  groupPolicy: "open" | "allowlist" | "disabled";
+  groupPolicy: "open" | "allowlist" | "disabled" | "allowall";
   allowFrom: Array<string | number>;
   senderId: string;
   senderIds?: Array<string | null | undefined>;
@@ -102,7 +102,7 @@ export function isFeishuGroupAllowed(params: {
   if (groupPolicy === "disabled") {
     return false;
   }
-  if (groupPolicy === "open") {
+  if (groupPolicy === "open" || groupPolicy === "allowall") {
     return true;
   }
   return resolveFeishuAllowlistMatch(params).allowed;

extensions/llm-task/src/llm-task-tool.ts

@@ -25,11 +25,15 @@ async function loadRunEmbeddedPiAgent(): Promise<RunEmbeddedPiAgentFn> {
   }
 
   // Bundled install (built)
-  const mod = await import("../../../src/agents/pi-embedded-runner.js");
-  if (typeof mod.runEmbeddedPiAgent !== "function") {
+  // NOTE: there is no src/ tree in a packaged install. Prefer a stable internal entrypoint.
+  const distExtensionApi = "../../../dist/extensionAPI.js";
+  const mod = (await import(distExtensionApi)) as { runEmbeddedPiAgent?: unknown };
+  // oxlint-disable-next-line typescript/no-explicit-any
+  const fn = (mod as any).runEmbeddedPiAgent;
+  if (typeof fn !== "function") {
     throw new Error("Internal error: runEmbeddedPiAgent not available");
   }
-  return mod.runEmbeddedPiAgent as RunEmbeddedPiAgentFn;
+  return fn as RunEmbeddedPiAgentFn;
 }
 
 function stripCodeFences(s: string): string {

extensions/mattermost/src/channel.test.ts

@@ -102,8 +102,9 @@ describe("mattermostPlugin", () => {
 
       const actions = mattermostPlugin.actions?.listActions?.({ cfg }) ?? [];
       expect(actions).toContain("react");
-      expect(actions).not.toContain("send");
+      expect(actions).toContain("send");
       expect(mattermostPlugin.actions?.supportsAction?.({ action: "react" })).toBe(true);
+      expect(mattermostPlugin.actions?.supportsAction?.({ action: "send" })).toBe(true);
     });
 
     it("hides react when mattermost is not configured", () => {
@@ -133,7 +134,7 @@ describe("mattermostPlugin", () => {
 
       const actions = mattermostPlugin.actions?.listActions?.({ cfg }) ?? [];
       expect(actions).not.toContain("react");
-      expect(actions).not.toContain("send");
+      expect(actions).toContain("send");
     });
 
     it("respects per-account actions.reactions in listActions", () => {

extensions/mattermost/src/channel.ts

@@ -22,6 +22,15 @@ import {
   type ResolvedMattermostAccount,
 } from "./mattermost/accounts.js";
 import { normalizeMattermostBaseUrl } from "./mattermost/client.js";
+import {
+  listMattermostDirectoryGroups,
+  listMattermostDirectoryPeers,
+} from "./mattermost/directory.js";
+import {
+  buildButtonAttachments,
+  resolveInteractionCallbackUrl,
+  setInteractionSecret,
+} from "./mattermost/interactions.js";
 import { monitorMattermostProvider } from "./mattermost/monitor.js";
 import { probeMattermost } from "./mattermost/probe.js";
 import { addMattermostReaction, removeMattermostReaction } from "./mattermost/reactions.js";
@@ -32,62 +41,91 @@ import { getMattermostRuntime } from "./runtime.js";
 
 const mattermostMessageActions: ChannelMessageActionAdapter = {
   listActions: ({ cfg }) => {
-    const actionsConfig = cfg.channels?.mattermost?.actions as { reactions?: boolean } | undefined;
-    const baseReactions = actionsConfig?.reactions;
-    const hasReactionCapableAccount = listMattermostAccountIds(cfg)
+    const enabledAccounts = listMattermostAccountIds(cfg)
       .map((accountId) => resolveMattermostAccount({ cfg, accountId }))
       .filter((account) => account.enabled)
-      .filter((account) => Boolean(account.botToken?.trim() && account.baseUrl?.trim()))
-      .some((account) => {
-        const accountActions = account.config.actions as { reactions?: boolean } | undefined;
-        return (accountActions?.reactions ?? baseReactions ?? true) !== false;
-      });
+      .filter((account) => Boolean(account.botToken?.trim() && account.baseUrl?.trim()));
 
-    if (!hasReactionCapableAccount) {
-      return [];
+    const actions: ChannelMessageActionName[] = [];
+
+    // Send (buttons) is available whenever there's at least one enabled account
+    if (enabledAccounts.length > 0) {
+      actions.push("send");
     }
 
-    return ["react"];
+    // React requires per-account reactions config check
+    const actionsConfig = cfg.channels?.mattermost?.actions as { reactions?: boolean } | undefined;
+    const baseReactions = actionsConfig?.reactions;
+    const hasReactionCapableAccount = enabledAccounts.some((account) => {
+      const accountActions = account.config.actions as { reactions?: boolean } | undefined;
+      return (accountActions?.reactions ?? baseReactions ?? true) !== false;
+    });
+    if (hasReactionCapableAccount) {
+      actions.push("react");
+    }
+
+    return actions;
   },
   supportsAction: ({ action }) => {
-    return action === "react";
+    return action === "send" || action === "react";
+  },
+  supportsButtons: ({ cfg }) => {
+    const accounts = listMattermostAccountIds(cfg)
+      .map((id) => resolveMattermostAccount({ cfg, accountId: id }))
+      .filter((a) => a.enabled && a.botToken?.trim() && a.baseUrl?.trim());
+    return accounts.length > 0;
   },
   handleAction: async ({ action, params, cfg, accountId }) => {
-    if (action !== "react") {
-      throw new Error(`Mattermost action ${action} not supported`);
-    }
-    // Check reactions gate: per-account config takes precedence over base config
-    const mmBase = cfg?.channels?.mattermost as Record<string, unknown> | undefined;
-    const accounts = mmBase?.accounts as Record<string, Record<string, unknown>> | undefined;
-    const resolvedAccountId = accountId ?? resolveDefaultMattermostAccountId(cfg);
-    const acctConfig = accounts?.[resolvedAccountId];
-    const acctActions = acctConfig?.actions as { reactions?: boolean } | undefined;
-    const baseActions = mmBase?.actions as { reactions?: boolean } | undefined;
-    const reactionsEnabled = acctActions?.reactions ?? baseActions?.reactions ?? true;
-    if (!reactionsEnabled) {
-      throw new Error("Mattermost reactions are disabled in config");
-    }
+    if (action === "react") {
+      // Check reactions gate: per-account config takes precedence over base config
+      const mmBase = cfg?.channels?.mattermost as Record<string, unknown> | undefined;
+      const accounts = mmBase?.accounts as Record<string, Record<string, unknown>> | undefined;
+      const resolvedAccountId = accountId ?? resolveDefaultMattermostAccountId(cfg);
+      const acctConfig = accounts?.[resolvedAccountId];
+      const acctActions = acctConfig?.actions as { reactions?: boolean } | undefined;
+      const baseActions = mmBase?.actions as { reactions?: boolean } | undefined;
+      const reactionsEnabled = acctActions?.reactions ?? baseActions?.reactions ?? true;
+      if (!reactionsEnabled) {
+        throw new Error("Mattermost reactions are disabled in config");
+      }
 
-    const postIdRaw =
-      typeof (params as any)?.messageId === "string"
-        ? (params as any).messageId
-        : typeof (params as any)?.postId === "string"
-          ? (params as any).postId
-          : "";
-    const postId = postIdRaw.trim();
-    if (!postId) {
-      throw new Error("Mattermost react requires messageId (post id)");
-    }
+      const postIdRaw =
+        typeof (params as any)?.messageId === "string"
+          ? (params as any).messageId
+          : typeof (params as any)?.postId === "string"
+            ? (params as any).postId
+            : "";
+      const postId = postIdRaw.trim();
+      if (!postId) {
+        throw new Error("Mattermost react requires messageId (post id)");
+      }
 
-    const emojiRaw = typeof (params as any)?.emoji === "string" ? (params as any).emoji : "";
-    const emojiName = emojiRaw.trim().replace(/^:+|:+$/g, "");
-    if (!emojiName) {
-      throw new Error("Mattermost react requires emoji");
-    }
+      const emojiRaw = typeof (params as any)?.emoji === "string" ? (params as any).emoji : "";
+      const emojiName = emojiRaw.trim().replace(/^:+|:+$/g, "");
+      if (!emojiName) {
+        throw new Error("Mattermost react requires emoji");
+      }
 
-    const remove = (params as any)?.remove === true;
-    if (remove) {
-      const result = await removeMattermostReaction({
+      const remove = (params as any)?.remove === true;
+      if (remove) {
+        const result = await removeMattermostReaction({
+          cfg,
+          postId,
+          emojiName,
+          accountId: resolvedAccountId,
+        });
+        if (!result.ok) {
+          throw new Error(result.error);
+        }
+        return {
+          content: [
+            { type: "text" as const, text: `Removed reaction :${emojiName}: from ${postId}` },
+          ],
+          details: {},
+        };
+      }
+
+      const result = await addMattermostReaction({
         cfg,
         postId,
         emojiName,
@@ -96,26 +134,92 @@ const mattermostMessageActions: ChannelMessageActionAdapter = {
       if (!result.ok) {
         throw new Error(result.error);
       }
+
       return {
-        content: [
-          { type: "text" as const, text: `Removed reaction :${emojiName}: from ${postId}` },
-        ],
+        content: [{ type: "text" as const, text: `Reacted with :${emojiName}: on ${postId}` }],
         details: {},
       };
     }
 
-    const result = await addMattermostReaction({
-      cfg,
-      postId,
-      emojiName,
-      accountId: resolvedAccountId,
-    });
-    if (!result.ok) {
-      throw new Error(result.error);
+    if (action !== "send") {
+      throw new Error(`Unsupported Mattermost action: ${action}`);
     }
 
+    // Send action with optional interactive buttons
+    const to =
+      typeof params.to === "string"
+        ? params.to.trim()
+        : typeof params.target === "string"
+          ? params.target.trim()
+          : "";
+    if (!to) {
+      throw new Error("Mattermost send requires a target (to).");
+    }
+
+    const message = typeof params.message === "string" ? params.message : "";
+    const replyToId = typeof params.replyToId === "string" ? params.replyToId : undefined;
+    const resolvedAccountId = accountId || undefined;
+
+    // Build props with button attachments if buttons are provided
+    let props: Record<string, unknown> | undefined;
+    if (params.buttons && Array.isArray(params.buttons)) {
+      const account = resolveMattermostAccount({ cfg, accountId: resolvedAccountId });
+      if (account.botToken) setInteractionSecret(account.accountId, account.botToken);
+      const callbackUrl = resolveInteractionCallbackUrl(account.accountId, cfg);
+
+      // Flatten 2D array (rows of buttons) to 1D — core schema sends Array<Array<Button>>
+      // but Mattermost doesn't have row layout, so we flatten all rows into a single list.
+      // Also supports 1D arrays for backward compatibility.
+      const rawButtons = (params.buttons as Array<unknown>).flatMap((item) =>
+        Array.isArray(item) ? item : [item],
+      ) as Array<Record<string, unknown>>;
+
+      const buttons = rawButtons
+        .map((btn) => ({
+          id: String(btn.id ?? btn.callback_data ?? ""),
+          name: String(btn.text ?? btn.name ?? btn.label ?? ""),
+          style: (btn.style as "default" | "primary" | "danger") ?? "default",
+          context:
+            typeof btn.context === "object" && btn.context !== null
+              ? (btn.context as Record<string, unknown>)
+              : undefined,
+        }))
+        .filter((btn) => btn.id && btn.name);
+
+      const attachmentText =
+        typeof params.attachmentText === "string" ? params.attachmentText : undefined;
+      props = {
+        attachments: buildButtonAttachments({
+          callbackUrl,
+          accountId: account.accountId,
+          buttons,
+          text: attachmentText,
+        }),
+      };
+    }
+
+    const mediaUrl =
+      typeof params.media === "string" ? params.media.trim() || undefined : undefined;
+
+    const result = await sendMessageMattermost(to, message, {
+      accountId: resolvedAccountId,
+      replyToId,
+      props,
+      mediaUrl,
+    });
+
     return {
-      content: [{ type: "text" as const, text: `Reacted with :${emojiName}: on ${postId}` }],
+      content: [
+        {
+          type: "text" as const,
+          text: JSON.stringify({
+            ok: true,
+            channel: "mattermost",
+            messageId: result.messageId,
+            channelId: result.channelId,
+          }),
+        },
+      ],
       details: {},
     };
   },
@@ -249,6 +353,12 @@ export const mattermostPlugin: ChannelPlugin<ResolvedMattermostAccount> = {
     resolveRequireMention: resolveMattermostGroupRequireMention,
   },
   actions: mattermostMessageActions,
+  directory: {
+    listGroups: async (params) => listMattermostDirectoryGroups(params),
+    listGroupsLive: async (params) => listMattermostDirectoryGroups(params),
+    listPeers: async (params) => listMattermostDirectoryPeers(params),
+    listPeersLive: async (params) => listMattermostDirectoryPeers(params),
+  },
   messaging: {
     normalizeTarget: normalizeMattermostMessagingTarget,
     targetResolver: {

extensions/mattermost/src/config-schema.ts

@@ -50,6 +50,11 @@ const MattermostAccountSchemaBase = z
       })
       .optional(),
     commands: MattermostSlashCommandsSchema,
+    interactions: z
+      .object({
+        callbackBaseUrl: z.string().optional(),
+      })
+      .optional(),
   })
   .strict();
 

extensions/mattermost/src/group-mentions.test.ts

@@ -0,0 +1,46 @@
+import type { OpenClawConfig } from "openclaw/plugin-sdk/mattermost";
+import { describe, expect, it } from "vitest";
+import { resolveMattermostGroupRequireMention } from "./group-mentions.js";
+
+describe("resolveMattermostGroupRequireMention", () => {
+  it("defaults to requiring mention when no override is configured", () => {
+    const cfg: OpenClawConfig = {
+      channels: {
+        mattermost: {},
+      },
+    };
+
+    const requireMention = resolveMattermostGroupRequireMention({ cfg, accountId: "default" });
+    expect(requireMention).toBe(true);
+  });
+
+  it("respects chatmode-derived account override", () => {
+    const cfg: OpenClawConfig = {
+      channels: {
+        mattermost: {
+          chatmode: "onmessage",
+        },
+      },
+    };
+
+    const requireMention = resolveMattermostGroupRequireMention({ cfg, accountId: "default" });
+    expect(requireMention).toBe(false);
+  });
+
+  it("prefers an explicit runtime override when provided", () => {
+    const cfg: OpenClawConfig = {
+      channels: {
+        mattermost: {
+          chatmode: "oncall",
+        },
+      },
+    };
+
+    const requireMention = resolveMattermostGroupRequireMention({
+      cfg,
+      accountId: "default",
+      requireMentionOverride: false,
+    });
+    expect(requireMention).toBe(false);
+  });
+});

extensions/mattermost/src/group-mentions.ts

@@ -1,15 +1,23 @@
+import { resolveChannelGroupRequireMention } from "openclaw/plugin-sdk/compat";
 import type { ChannelGroupContext } from "openclaw/plugin-sdk/mattermost";
 import { resolveMattermostAccount } from "./mattermost/accounts.js";
 
 export function resolveMattermostGroupRequireMention(
-  params: ChannelGroupContext,
+  params: ChannelGroupContext & { requireMentionOverride?: boolean },
 ): boolean | undefined {
   const account = resolveMattermostAccount({
     cfg: params.cfg,
     accountId: params.accountId,
   });
-  if (typeof account.requireMention === "boolean") {
-    return account.requireMention;
-  }
-  return true;
+  const requireMentionOverride =
+    typeof params.requireMentionOverride === "boolean"
+      ? params.requireMentionOverride
+      : account.requireMention;
+  return resolveChannelGroupRequireMention({
+    cfg: params.cfg,
+    channel: "mattermost",
+    groupId: params.groupId,
+    accountId: params.accountId,
+    requireMentionOverride,
+  });
 }

extensions/mattermost/src/mattermost/client.test.ts

@@ -1,19 +1,298 @@
 import { describe, expect, it, vi } from "vitest";
-import { createMattermostClient } from "./client.js";
+import {
+  createMattermostClient,
+  createMattermostPost,
+  normalizeMattermostBaseUrl,
+  updateMattermostPost,
+} from "./client.js";
 
-describe("mattermost client", () => {
-  it("request returns undefined on 204 responses", async () => {
+// ── Helper: mock fetch that captures requests ────────────────────────
+
+function createMockFetch(response?: { status?: number; body?: unknown; contentType?: string }) {
+  const status = response?.status ?? 200;
+  const body = response?.body ?? {};
+  const contentType = response?.contentType ?? "application/json";
+
+  const calls: Array<{ url: string; init?: RequestInit }> = [];
+
+  const mockFetch = vi.fn(async (url: string | URL | Request, init?: RequestInit) => {
+    const urlStr = typeof url === "string" ? url : url.toString();
+    calls.push({ url: urlStr, init });
+    return new Response(JSON.stringify(body), {
+      status,
+      headers: { "content-type": contentType },
+    });
+  });
+
+  return { mockFetch: mockFetch as unknown as typeof fetch, calls };
+}
+
+// ── normalizeMattermostBaseUrl ────────────────────────────────────────
+
+describe("normalizeMattermostBaseUrl", () => {
+  it("strips trailing slashes", () => {
+    expect(normalizeMattermostBaseUrl("http://localhost:8065/")).toBe("http://localhost:8065");
+  });
+
+  it("strips /api/v4 suffix", () => {
+    expect(normalizeMattermostBaseUrl("http://localhost:8065/api/v4")).toBe(
+      "http://localhost:8065",
+    );
+  });
+
+  it("returns undefined for empty input", () => {
+    expect(normalizeMattermostBaseUrl("")).toBeUndefined();
+    expect(normalizeMattermostBaseUrl(null)).toBeUndefined();
+    expect(normalizeMattermostBaseUrl(undefined)).toBeUndefined();
+  });
+
+  it("preserves valid base URL", () => {
+    expect(normalizeMattermostBaseUrl("http://mm.example.com")).toBe("http://mm.example.com");
+  });
+});
+
+// ── createMattermostClient ───────────────────────────────────────────
+
+describe("createMattermostClient", () => {
+  it("creates a client with normalized baseUrl", () => {
+    const { mockFetch } = createMockFetch();
+    const client = createMattermostClient({
+      baseUrl: "http://localhost:8065/",
+      botToken: "tok",
+      fetchImpl: mockFetch,
+    });
+    expect(client.baseUrl).toBe("http://localhost:8065");
+    expect(client.apiBaseUrl).toBe("http://localhost:8065/api/v4");
+  });
+
+  it("throws on empty baseUrl", () => {
+    expect(() => createMattermostClient({ baseUrl: "", botToken: "tok" })).toThrow(
+      "baseUrl is required",
+    );
+  });
+
+  it("sends Authorization header with Bearer token", async () => {
+    const { mockFetch, calls } = createMockFetch({ body: { id: "u1" } });
+    const client = createMattermostClient({
+      baseUrl: "http://localhost:8065",
+      botToken: "my-secret-token",
+      fetchImpl: mockFetch,
+    });
+    await client.request("/users/me");
+    const headers = new Headers(calls[0].init?.headers);
+    expect(headers.get("Authorization")).toBe("Bearer my-secret-token");
+  });
+
+  it("sets Content-Type for string bodies", async () => {
+    const { mockFetch, calls } = createMockFetch({ body: { id: "p1" } });
+    const client = createMattermostClient({
+      baseUrl: "http://localhost:8065",
+      botToken: "tok",
+      fetchImpl: mockFetch,
+    });
+    await client.request("/posts", { method: "POST", body: JSON.stringify({ message: "hi" }) });
+    const headers = new Headers(calls[0].init?.headers);
+    expect(headers.get("Content-Type")).toBe("application/json");
+  });
+
+  it("throws on non-ok responses", async () => {
+    const { mockFetch } = createMockFetch({
+      status: 404,
+      body: { message: "Not Found" },
+    });
+    const client = createMattermostClient({
+      baseUrl: "http://localhost:8065",
+      botToken: "tok",
+      fetchImpl: mockFetch,
+    });
+    await expect(client.request("/missing")).rejects.toThrow("Mattermost API 404");
+  });
+
+  it("returns undefined on 204 responses", async () => {
     const fetchImpl = vi.fn(async () => {
       return new Response(null, { status: 204 });
     });
-
     const client = createMattermostClient({
       baseUrl: "https://chat.example.com",
       botToken: "test-token",
       fetchImpl: fetchImpl as any,
     });
-
     const result = await client.request<unknown>("/anything", { method: "DELETE" });
     expect(result).toBeUndefined();
   });
 });
+
+// ── createMattermostPost ─────────────────────────────────────────────
+
+describe("createMattermostPost", () => {
+  it("sends channel_id and message", async () => {
+    const { mockFetch, calls } = createMockFetch({ body: { id: "post1" } });
+    const client = createMattermostClient({
+      baseUrl: "http://localhost:8065",
+      botToken: "tok",
+      fetchImpl: mockFetch,
+    });
+
+    await createMattermostPost(client, {
+      channelId: "ch123",
+      message: "Hello world",
+    });
+
+    const body = JSON.parse(calls[0].init?.body as string);
+    expect(body.channel_id).toBe("ch123");
+    expect(body.message).toBe("Hello world");
+  });
+
+  it("includes rootId when provided", async () => {
+    const { mockFetch, calls } = createMockFetch({ body: { id: "post2" } });
+    const client = createMattermostClient({
+      baseUrl: "http://localhost:8065",
+      botToken: "tok",
+      fetchImpl: mockFetch,
+    });
+
+    await createMattermostPost(client, {
+      channelId: "ch123",
+      message: "Reply",
+      rootId: "root456",
+    });
+
+    const body = JSON.parse(calls[0].init?.body as string);
+    expect(body.root_id).toBe("root456");
+  });
+
+  it("includes fileIds when provided", async () => {
+    const { mockFetch, calls } = createMockFetch({ body: { id: "post3" } });
+    const client = createMattermostClient({
+      baseUrl: "http://localhost:8065",
+      botToken: "tok",
+      fetchImpl: mockFetch,
+    });
+
+    await createMattermostPost(client, {
+      channelId: "ch123",
+      message: "With file",
+      fileIds: ["file1", "file2"],
+    });
+
+    const body = JSON.parse(calls[0].init?.body as string);
+    expect(body.file_ids).toEqual(["file1", "file2"]);
+  });
+
+  it("includes props when provided (for interactive buttons)", async () => {
+    const { mockFetch, calls } = createMockFetch({ body: { id: "post4" } });
+    const client = createMattermostClient({
+      baseUrl: "http://localhost:8065",
+      botToken: "tok",
+      fetchImpl: mockFetch,
+    });
+
+    const props = {
+      attachments: [
+        {
+          text: "Choose:",
+          actions: [{ id: "btn1", type: "button", name: "Click" }],
+        },
+      ],
+    };
+
+    await createMattermostPost(client, {
+      channelId: "ch123",
+      message: "Pick an option",
+      props,
+    });
+
+    const body = JSON.parse(calls[0].init?.body as string);
+    expect(body.props).toEqual(props);
+    expect(body.props.attachments[0].actions[0].type).toBe("button");
+  });
+
+  it("omits props when not provided", async () => {
+    const { mockFetch, calls } = createMockFetch({ body: { id: "post5" } });
+    const client = createMattermostClient({
+      baseUrl: "http://localhost:8065",
+      botToken: "tok",
+      fetchImpl: mockFetch,
+    });
+
+    await createMattermostPost(client, {
+      channelId: "ch123",
+      message: "No props",
+    });
+
+    const body = JSON.parse(calls[0].init?.body as string);
+    expect(body.props).toBeUndefined();
+  });
+});
+
+// ── updateMattermostPost ─────────────────────────────────────────────
+
+describe("updateMattermostPost", () => {
+  it("sends PUT to /posts/{id}", async () => {
+    const { mockFetch, calls } = createMockFetch({ body: { id: "post1" } });
+    const client = createMattermostClient({
+      baseUrl: "http://localhost:8065",
+      botToken: "tok",
+      fetchImpl: mockFetch,
+    });
+
+    await updateMattermostPost(client, "post1", { message: "Updated" });
+
+    expect(calls[0].url).toContain("/posts/post1");
+    expect(calls[0].init?.method).toBe("PUT");
+  });
+
+  it("includes post id in the body", async () => {
+    const { mockFetch, calls } = createMockFetch({ body: { id: "post1" } });
+    const client = createMattermostClient({
+      baseUrl: "http://localhost:8065",
+      botToken: "tok",
+      fetchImpl: mockFetch,
+    });
+
+    await updateMattermostPost(client, "post1", { message: "Updated" });
+
+    const body = JSON.parse(calls[0].init?.body as string);
+    expect(body.id).toBe("post1");
+    expect(body.message).toBe("Updated");
+  });
+
+  it("includes props for button completion updates", async () => {
+    const { mockFetch, calls } = createMockFetch({ body: { id: "post1" } });
+    const client = createMattermostClient({
+      baseUrl: "http://localhost:8065",
+      botToken: "tok",
+      fetchImpl: mockFetch,
+    });
+
+    await updateMattermostPost(client, "post1", {
+      message: "Original message",
+      props: {
+        attachments: [{ text: "✓ **do_now** selected by @tony" }],
+      },
+    });
+
+    const body = JSON.parse(calls[0].init?.body as string);
+    expect(body.message).toBe("Original message");
+    expect(body.props.attachments[0].text).toContain("✓");
+    expect(body.props.attachments[0].text).toContain("do_now");
+  });
+
+  it("omits message when not provided", async () => {
+    const { mockFetch, calls } = createMockFetch({ body: { id: "post1" } });
+    const client = createMattermostClient({
+      baseUrl: "http://localhost:8065",
+      botToken: "tok",
+      fetchImpl: mockFetch,
+    });
+
+    await updateMattermostPost(client, "post1", {
+      props: { attachments: [] },
+    });
+
+    const body = JSON.parse(calls[0].init?.body as string);
+    expect(body.id).toBe("post1");
+    expect(body.message).toBeUndefined();
+    expect(body.props).toEqual({ attachments: [] });
+  });
+});

extensions/mattermost/src/mattermost/client.ts

@@ -138,6 +138,16 @@ export async function fetchMattermostChannel(
   return await client.request<MattermostChannel>(`/channels/${channelId}`);
 }
 
+export async function fetchMattermostChannelByName(
+  client: MattermostClient,
+  teamId: string,
+  channelName: string,
+): Promise<MattermostChannel> {
+  return await client.request<MattermostChannel>(
+    `/teams/${teamId}/channels/name/${encodeURIComponent(channelName)}`,
+  );
+}
+
 export async function sendMattermostTyping(
   client: MattermostClient,
   params: { channelId: string; parentId?: string },
@@ -172,9 +182,10 @@ export async function createMattermostPost(
     message: string;
     rootId?: string;
     fileIds?: string[];
+    props?: Record<string, unknown>;
   },
 ): Promise<MattermostPost> {
-  const payload: Record<string, string> = {
+  const payload: Record<string, unknown> = {
     channel_id: params.channelId,
     message: params.message,
   };
@@ -182,7 +193,10 @@ export async function createMattermostPost(
     payload.root_id = params.rootId;
   }
   if (params.fileIds?.length) {
-    (payload as Record<string, unknown>).file_ids = params.fileIds;
+    payload.file_ids = params.fileIds;
+  }
+  if (params.props) {
+    payload.props = params.props;
   }
   return await client.request<MattermostPost>("/posts", {
     method: "POST",
@@ -203,6 +217,27 @@ export async function fetchMattermostUserTeams(
   return await client.request<MattermostTeam[]>(`/users/${userId}/teams`);
 }
 
+export async function updateMattermostPost(
+  client: MattermostClient,
+  postId: string,
+  params: {
+    message?: string;
+    props?: Record<string, unknown>;
+  },
+): Promise<MattermostPost> {
+  const payload: Record<string, unknown> = { id: postId };
+  if (params.message !== undefined) {
+    payload.message = params.message;
+  }
+  if (params.props !== undefined) {
+    payload.props = params.props;
+  }
+  return await client.request<MattermostPost>(`/posts/${postId}`, {
+    method: "PUT",
+    body: JSON.stringify(payload),
+  });
+}
+
 export async function uploadMattermostFile(
   client: MattermostClient,
   params: {

extensions/mattermost/src/mattermost/directory.ts

@@ -0,0 +1,172 @@
+import type {
+  ChannelDirectoryEntry,
+  OpenClawConfig,
+  RuntimeEnv,
+} from "openclaw/plugin-sdk/mattermost";
+import { listMattermostAccountIds, resolveMattermostAccount } from "./accounts.js";
+import {
+  createMattermostClient,
+  fetchMattermostMe,
+  type MattermostChannel,
+  type MattermostClient,
+  type MattermostUser,
+} from "./client.js";
+
+export type MattermostDirectoryParams = {
+  cfg: OpenClawConfig;
+  accountId?: string | null;
+  query?: string | null;
+  limit?: number | null;
+  runtime: RuntimeEnv;
+};
+
+function buildClient(params: {
+  cfg: OpenClawConfig;
+  accountId?: string | null;
+}): MattermostClient | null {
+  const account = resolveMattermostAccount({ cfg: params.cfg, accountId: params.accountId });
+  if (!account.enabled || !account.botToken || !account.baseUrl) {
+    return null;
+  }
+  return createMattermostClient({ baseUrl: account.baseUrl, botToken: account.botToken });
+}
+
+/**
+ * Build clients from ALL enabled accounts (deduplicated by token).
+ *
+ * We always scan every account because:
+ * - Private channels are only visible to bots that are members
+ * - The requesting agent's account may have an expired/invalid token
+ *
+ * This means a single healthy bot token is enough for directory discovery.
+ */
+function buildClients(params: MattermostDirectoryParams): MattermostClient[] {
+  const accountIds = listMattermostAccountIds(params.cfg);
+  const seen = new Set<string>();
+  const clients: MattermostClient[] = [];
+  for (const id of accountIds) {
+    const client = buildClient({ cfg: params.cfg, accountId: id });
+    if (client && !seen.has(client.token)) {
+      seen.add(client.token);
+      clients.push(client);
+    }
+  }
+  return clients;
+}
+
+/**
+ * List channels (public + private) visible to any configured bot account.
+ *
+ * NOTE: Uses per_page=200 which covers most instances. Mattermost does not
+ * return a "has more" indicator, so very large instances (200+ channels per bot)
+ * may see incomplete results. Pagination can be added if needed.
+ */
+export async function listMattermostDirectoryGroups(
+  params: MattermostDirectoryParams,
+): Promise<ChannelDirectoryEntry[]> {
+  const clients = buildClients(params);
+  if (!clients.length) {
+    return [];
+  }
+  const q = params.query?.trim().toLowerCase() || "";
+  const seenIds = new Set<string>();
+  const entries: ChannelDirectoryEntry[] = [];
+
+  for (const client of clients) {
+    try {
+      const me = await fetchMattermostMe(client);
+      const channels = await client.request<MattermostChannel[]>(
+        `/users/${me.id}/channels?per_page=200`,
+      );
+      for (const ch of channels) {
+        if (ch.type !== "O" && ch.type !== "P") continue;
+        if (seenIds.has(ch.id)) continue;
+        if (q) {
+          const name = (ch.name ?? "").toLowerCase();
+          const display = (ch.display_name ?? "").toLowerCase();
+          if (!name.includes(q) && !display.includes(q)) continue;
+        }
+        seenIds.add(ch.id);
+        entries.push({
+          kind: "group" as const,
+          id: `channel:${ch.id}`,
+          name: ch.name ?? undefined,
+          handle: ch.display_name ?? undefined,
+        });
+      }
+    } catch (err) {
+      // Token may be expired/revoked — skip this account and try others
+      console.debug?.(
+        "[mattermost-directory] listGroups: skipping account:",
+        (err as Error)?.message,
+      );
+      continue;
+    }
+  }
+  return params.limit && params.limit > 0 ? entries.slice(0, params.limit) : entries;
+}
+
+/**
+ * List team members as peer directory entries.
+ *
+ * Uses only the first available client since all bots in a team see the same
+ * user list (unlike channels where membership varies). Uses the first team
+ * returned — multi-team setups will only see members from that team.
+ *
+ * NOTE: per_page=200 for member listing; same pagination caveat as groups.
+ */
+export async function listMattermostDirectoryPeers(
+  params: MattermostDirectoryParams,
+): Promise<ChannelDirectoryEntry[]> {
+  const clients = buildClients(params);
+  if (!clients.length) {
+    return [];
+  }
+  // All bots see the same user list, so one client suffices (unlike channels
+  // where private channel membership varies per bot).
+  const client = clients[0];
+  try {
+    const me = await fetchMattermostMe(client);
+    const teams = await client.request<{ id: string }[]>("/users/me/teams");
+    if (!teams.length) {
+      return [];
+    }
+    // Uses first team — multi-team setups may need iteration in the future
+    const teamId = teams[0].id;
+    const q = params.query?.trim().toLowerCase() || "";
+
+    let users: MattermostUser[];
+    if (q) {
+      users = await client.request<MattermostUser[]>("/users/search", {
+        method: "POST",
+        body: JSON.stringify({ term: q, team_id: teamId }),
+      });
+    } else {
+      const members = await client.request<{ user_id: string }[]>(
+        `/teams/${teamId}/members?per_page=200`,
+      );
+      const userIds = members.map((m) => m.user_id).filter((id) => id !== me.id);
+      if (!userIds.length) {
+        return [];
+      }
+      users = await client.request<MattermostUser[]>("/users/ids", {
+        method: "POST",
+        body: JSON.stringify(userIds),
+      });
+    }
+
+    const entries = users
+      .filter((u) => u.id !== me.id)
+      .map((u) => ({
+        kind: "user" as const,
+        id: `user:${u.id}`,
+        name: u.username ?? undefined,
+        handle:
+          [u.first_name, u.last_name].filter(Boolean).join(" ").trim() || u.nickname || undefined,
+      }));
+    return params.limit && params.limit > 0 ? entries.slice(0, params.limit) : entries;
+  } catch (err) {
+    console.debug?.("[mattermost-directory] listPeers failed:", (err as Error)?.message);
+    return [];
+  }
+}

extensions/mattermost/src/mattermost/interactions.test.ts

@@ -0,0 +1,335 @@
+import { type IncomingMessage } from "node:http";
+import { describe, expect, it, beforeEach, afterEach } from "vitest";
+import {
+  buildButtonAttachments,
+  generateInteractionToken,
+  getInteractionCallbackUrl,
+  getInteractionSecret,
+  isLocalhostRequest,
+  resolveInteractionCallbackUrl,
+  setInteractionCallbackUrl,
+  setInteractionSecret,
+  verifyInteractionToken,
+} from "./interactions.js";
+
+// ── HMAC token management ────────────────────────────────────────────
+
+describe("setInteractionSecret / getInteractionSecret", () => {
+  beforeEach(() => {
+    setInteractionSecret("test-bot-token");
+  });
+
+  it("derives a deterministic secret from the bot token", () => {
+    setInteractionSecret("token-a");
+    const secretA = getInteractionSecret();
+    setInteractionSecret("token-a");
+    const secretA2 = getInteractionSecret();
+    expect(secretA).toBe(secretA2);
+  });
+
+  it("produces different secrets for different tokens", () => {
+    setInteractionSecret("token-a");
+    const secretA = getInteractionSecret();
+    setInteractionSecret("token-b");
+    const secretB = getInteractionSecret();
+    expect(secretA).not.toBe(secretB);
+  });
+
+  it("returns a hex string", () => {
+    expect(getInteractionSecret()).toMatch(/^[0-9a-f]+$/);
+  });
+});
+
+// ── Token generation / verification ──────────────────────────────────
+
+describe("generateInteractionToken / verifyInteractionToken", () => {
+  beforeEach(() => {
+    setInteractionSecret("test-bot-token");
+  });
+
+  it("generates a hex token", () => {
+    const token = generateInteractionToken({ action_id: "click" });
+    expect(token).toMatch(/^[0-9a-f]{64}$/);
+  });
+
+  it("verifies a valid token", () => {
+    const context = { action_id: "do_now", item_id: "123" };
+    const token = generateInteractionToken(context);
+    expect(verifyInteractionToken(context, token)).toBe(true);
+  });
+
+  it("rejects a tampered token", () => {
+    const context = { action_id: "do_now" };
+    const token = generateInteractionToken(context);
+    const tampered = token.replace(/.$/, token.endsWith("0") ? "1" : "0");
+    expect(verifyInteractionToken(context, tampered)).toBe(false);
+  });
+
+  it("rejects a token generated with different context", () => {
+    const token = generateInteractionToken({ action_id: "a" });
+    expect(verifyInteractionToken({ action_id: "b" }, token)).toBe(false);
+  });
+
+  it("rejects tokens with wrong length", () => {
+    const context = { action_id: "test" };
+    expect(verifyInteractionToken(context, "short")).toBe(false);
+  });
+
+  it("is deterministic for the same context", () => {
+    const context = { action_id: "test", x: 1 };
+    const t1 = generateInteractionToken(context);
+    const t2 = generateInteractionToken(context);
+    expect(t1).toBe(t2);
+  });
+
+  it("produces the same token regardless of key order", () => {
+    const contextA = { action_id: "do_now", tweet_id: "123", action: "do" };
+    const contextB = { action: "do", action_id: "do_now", tweet_id: "123" };
+    const contextC = { tweet_id: "123", action: "do", action_id: "do_now" };
+    const tokenA = generateInteractionToken(contextA);
+    const tokenB = generateInteractionToken(contextB);
+    const tokenC = generateInteractionToken(contextC);
+    expect(tokenA).toBe(tokenB);
+    expect(tokenB).toBe(tokenC);
+  });
+
+  it("verifies a token when Mattermost reorders context keys", () => {
+    // Simulate: token generated with keys in one order, verified with keys in another
+    // (Mattermost reorders context keys when storing/returning interactive message payloads)
+    const originalContext = { action_id: "bm_do", tweet_id: "999", action: "do" };
+    const token = generateInteractionToken(originalContext);
+
+    // Mattermost returns keys in alphabetical order (or any arbitrary order)
+    const reorderedContext = { action: "do", action_id: "bm_do", tweet_id: "999" };
+    expect(verifyInteractionToken(reorderedContext, token)).toBe(true);
+  });
+
+  it("scopes tokens per account when account secrets differ", () => {
+    setInteractionSecret("acct-a", "bot-token-a");
+    setInteractionSecret("acct-b", "bot-token-b");
+    const context = { action_id: "do_now", item_id: "123" };
+    const tokenA = generateInteractionToken(context, "acct-a");
+
+    expect(verifyInteractionToken(context, tokenA, "acct-a")).toBe(true);
+    expect(verifyInteractionToken(context, tokenA, "acct-b")).toBe(false);
+  });
+});
+
+// ── Callback URL registry ────────────────────────────────────────────
+
+describe("callback URL registry", () => {
+  it("stores and retrieves callback URLs", () => {
+    setInteractionCallbackUrl("acct1", "http://localhost:18789/mattermost/interactions/acct1");
+    expect(getInteractionCallbackUrl("acct1")).toBe(
+      "http://localhost:18789/mattermost/interactions/acct1",
+    );
+  });
+
+  it("returns undefined for unknown account", () => {
+    expect(getInteractionCallbackUrl("nonexistent-account-id")).toBeUndefined();
+  });
+});
+
+describe("resolveInteractionCallbackUrl", () => {
+  afterEach(() => {
+    setInteractionCallbackUrl("resolve-test", "");
+  });
+
+  it("prefers cached URL from registry", () => {
+    setInteractionCallbackUrl("cached", "http://cached:1234/path");
+    expect(resolveInteractionCallbackUrl("cached")).toBe("http://cached:1234/path");
+  });
+
+  it("falls back to computed URL from gateway port config", () => {
+    const url = resolveInteractionCallbackUrl("default", { gateway: { port: 9999 } });
+    expect(url).toBe("http://localhost:9999/mattermost/interactions/default");
+  });
+
+  it("uses default port 18789 when no config provided", () => {
+    const url = resolveInteractionCallbackUrl("myaccount");
+    expect(url).toBe("http://localhost:18789/mattermost/interactions/myaccount");
+  });
+
+  it("uses default port when gateway config has no port", () => {
+    const url = resolveInteractionCallbackUrl("acct", { gateway: {} });
+    expect(url).toBe("http://localhost:18789/mattermost/interactions/acct");
+  });
+});
+
+// ── buildButtonAttachments ───────────────────────────────────────────
+
+describe("buildButtonAttachments", () => {
+  beforeEach(() => {
+    setInteractionSecret("test-bot-token");
+  });
+
+  it("returns an array with one attachment containing all buttons", () => {
+    const result = buildButtonAttachments({
+      callbackUrl: "http://localhost:18789/mattermost/interactions/default",
+      buttons: [
+        { id: "btn1", name: "Click Me" },
+        { id: "btn2", name: "Skip", style: "danger" },
+      ],
+    });
+
+    expect(result).toHaveLength(1);
+    expect(result[0].actions).toHaveLength(2);
+  });
+
+  it("sets type to 'button' on every action", () => {
+    const result = buildButtonAttachments({
+      callbackUrl: "http://localhost:18789/cb",
+      buttons: [{ id: "a", name: "A" }],
+    });
+
+    expect(result[0].actions![0].type).toBe("button");
+  });
+
+  it("includes HMAC _token in integration context", () => {
+    const result = buildButtonAttachments({
+      callbackUrl: "http://localhost:18789/cb",
+      buttons: [{ id: "test", name: "Test" }],
+    });
+
+    const action = result[0].actions![0];
+    expect(action.integration.context._token).toMatch(/^[0-9a-f]{64}$/);
+  });
+
+  it("includes sanitized action_id in integration context", () => {
+    const result = buildButtonAttachments({
+      callbackUrl: "http://localhost:18789/cb",
+      buttons: [{ id: "my_action", name: "Do It" }],
+    });
+
+    const action = result[0].actions![0];
+    // sanitizeActionId strips hyphens and underscores (Mattermost routing bug #25747)
+    expect(action.integration.context.action_id).toBe("myaction");
+    expect(action.id).toBe("myaction");
+  });
+
+  it("merges custom context into integration context", () => {
+    const result = buildButtonAttachments({
+      callbackUrl: "http://localhost:18789/cb",
+      buttons: [{ id: "btn", name: "Go", context: { tweet_id: "123", batch: true } }],
+    });
+
+    const ctx = result[0].actions![0].integration.context;
+    expect(ctx.tweet_id).toBe("123");
+    expect(ctx.batch).toBe(true);
+    expect(ctx.action_id).toBe("btn");
+    expect(ctx._token).toBeDefined();
+  });
+
+  it("passes callback URL to each button integration", () => {
+    const url = "http://localhost:18789/mattermost/interactions/default";
+    const result = buildButtonAttachments({
+      callbackUrl: url,
+      buttons: [
+        { id: "a", name: "A" },
+        { id: "b", name: "B" },
+      ],
+    });
+
+    for (const action of result[0].actions!) {
+      expect(action.integration.url).toBe(url);
+    }
+  });
+
+  it("preserves button style", () => {
+    const result = buildButtonAttachments({
+      callbackUrl: "http://localhost/cb",
+      buttons: [
+        { id: "ok", name: "OK", style: "primary" },
+        { id: "no", name: "No", style: "danger" },
+      ],
+    });
+
+    expect(result[0].actions![0].style).toBe("primary");
+    expect(result[0].actions![1].style).toBe("danger");
+  });
+
+  it("uses provided text for the attachment", () => {
+    const result = buildButtonAttachments({
+      callbackUrl: "http://localhost/cb",
+      buttons: [{ id: "x", name: "X" }],
+      text: "Choose an action:",
+    });
+
+    expect(result[0].text).toBe("Choose an action:");
+  });
+
+  it("defaults to empty string text when not provided", () => {
+    const result = buildButtonAttachments({
+      callbackUrl: "http://localhost/cb",
+      buttons: [{ id: "x", name: "X" }],
+    });
+
+    expect(result[0].text).toBe("");
+  });
+
+  it("generates verifiable tokens", () => {
+    const result = buildButtonAttachments({
+      callbackUrl: "http://localhost/cb",
+      buttons: [{ id: "verify_me", name: "V", context: { extra: "data" } }],
+    });
+
+    const ctx = result[0].actions![0].integration.context;
+    const token = ctx._token as string;
+    const { _token, ...contextWithoutToken } = ctx;
+    expect(verifyInteractionToken(contextWithoutToken, token)).toBe(true);
+  });
+
+  it("generates tokens that verify even when Mattermost reorders context keys", () => {
+    const result = buildButtonAttachments({
+      callbackUrl: "http://localhost/cb",
+      buttons: [{ id: "do_action", name: "Do", context: { tweet_id: "42", category: "ai" } }],
+    });
+
+    const ctx = result[0].actions![0].integration.context;
+    const token = ctx._token as string;
+
+    // Simulate Mattermost returning context with keys in a different order
+    const reordered: Record<string, unknown> = {};
+    const keys = Object.keys(ctx).filter((k) => k !== "_token");
+    // Reverse the key order to simulate reordering
+    for (const key of keys.reverse()) {
+      reordered[key] = ctx[key];
+    }
+    expect(verifyInteractionToken(reordered, token)).toBe(true);
+  });
+});
+
+// ── isLocalhostRequest ───────────────────────────────────────────────
+
+describe("isLocalhostRequest", () => {
+  function fakeReq(remoteAddress?: string): IncomingMessage {
+    return {
+      socket: { remoteAddress },
+    } as unknown as IncomingMessage;
+  }
+
+  it("accepts 127.0.0.1", () => {
+    expect(isLocalhostRequest(fakeReq("127.0.0.1"))).toBe(true);
+  });
+
+  it("accepts ::1", () => {
+    expect(isLocalhostRequest(fakeReq("::1"))).toBe(true);
+  });
+
+  it("accepts ::ffff:127.0.0.1", () => {
+    expect(isLocalhostRequest(fakeReq("::ffff:127.0.0.1"))).toBe(true);
+  });
+
+  it("rejects external addresses", () => {
+    expect(isLocalhostRequest(fakeReq("10.0.0.1"))).toBe(false);
+    expect(isLocalhostRequest(fakeReq("192.168.1.1"))).toBe(false);
+  });
+
+  it("rejects when socket has no remote address", () => {
+    expect(isLocalhostRequest(fakeReq(undefined))).toBe(false);
+  });
+
+  it("rejects when socket is missing", () => {
+    expect(isLocalhostRequest({} as IncomingMessage)).toBe(false);
+  });
+});

extensions/mattermost/src/mattermost/interactions.ts

@@ -0,0 +1,429 @@
+import { createHmac, timingSafeEqual } from "node:crypto";
+import type { IncomingMessage, ServerResponse } from "node:http";
+import { getMattermostRuntime } from "../runtime.js";
+import { updateMattermostPost, type MattermostClient } from "./client.js";
+
+const INTERACTION_MAX_BODY_BYTES = 64 * 1024;
+const INTERACTION_BODY_TIMEOUT_MS = 10_000;
+
+/**
+ * Mattermost interactive message callback payload.
+ * Sent by Mattermost when a user clicks an action button.
+ * See: https://developers.mattermost.com/integrate/plugins/interactive-messages/
+ */
+export type MattermostInteractionPayload = {
+  user_id: string;
+  user_name?: string;
+  channel_id: string;
+  team_id?: string;
+  post_id: string;
+  trigger_id?: string;
+  type?: string;
+  data_source?: string;
+  context?: Record<string, unknown>;
+};
+
+export type MattermostInteractionResponse = {
+  update?: {
+    message: string;
+    props?: Record<string, unknown>;
+  };
+  ephemeral_text?: string;
+};
+
+// ── Callback URL registry ──────────────────────────────────────────────
+
+const callbackUrls = new Map<string, string>();
+
+export function setInteractionCallbackUrl(accountId: string, url: string): void {
+  callbackUrls.set(accountId, url);
+}
+
+export function getInteractionCallbackUrl(accountId: string): string | undefined {
+  return callbackUrls.get(accountId);
+}
+
+/**
+ * Resolve the interaction callback URL for an account.
+ * Prefers the in-memory registered URL (set by the gateway monitor).
+ * Falls back to computing it from the gateway port in config (for CLI callers).
+ */
+export function resolveInteractionCallbackUrl(
+  accountId: string,
+  cfg?: { gateway?: { port?: number } },
+): string {
+  const cached = callbackUrls.get(accountId);
+  if (cached) {
+    return cached;
+  }
+  const port = typeof cfg?.gateway?.port === "number" ? cfg.gateway.port : 18789;
+  return `http://localhost:${port}/mattermost/interactions/${accountId}`;
+}
+
+// ── HMAC token management ──────────────────────────────────────────────
+// Secret is derived from the bot token so it's stable across CLI and gateway processes.
+
+const interactionSecrets = new Map<string, string>();
+let defaultInteractionSecret: string | undefined;
+
+function deriveInteractionSecret(botToken: string): string {
+  return createHmac("sha256", "openclaw-mattermost-interactions").update(botToken).digest("hex");
+}
+
+export function setInteractionSecret(accountIdOrBotToken: string, botToken?: string): void {
+  if (typeof botToken === "string") {
+    interactionSecrets.set(accountIdOrBotToken, deriveInteractionSecret(botToken));
+    return;
+  }
+  // Backward-compatible fallback for call sites/tests that only pass botToken.
+  defaultInteractionSecret = deriveInteractionSecret(accountIdOrBotToken);
+}
+
+export function getInteractionSecret(accountId?: string): string {
+  const scoped = accountId ? interactionSecrets.get(accountId) : undefined;
+  if (scoped) {
+    return scoped;
+  }
+  if (defaultInteractionSecret) {
+    return defaultInteractionSecret;
+  }
+  // Fallback for single-account runtimes that only registered scoped secrets.
+  if (interactionSecrets.size === 1) {
+    const first = interactionSecrets.values().next().value;
+    if (typeof first === "string") {
+      return first;
+    }
+  }
+  throw new Error(
+    "Interaction secret not initialized — call setInteractionSecret(accountId, botToken) first",
+  );
+}
+
+export function generateInteractionToken(
+  context: Record<string, unknown>,
+  accountId?: string,
+): string {
+  const secret = getInteractionSecret(accountId);
+  // Sort keys for stable serialization — Mattermost may reorder context keys
+  const payload = JSON.stringify(context, Object.keys(context).sort());
+  return createHmac("sha256", secret).update(payload).digest("hex");
+}
+
+export function verifyInteractionToken(
+  context: Record<string, unknown>,
+  token: string,
+  accountId?: string,
+): boolean {
+  const expected = generateInteractionToken(context, accountId);
+  if (expected.length !== token.length) {
+    return false;
+  }
+  return timingSafeEqual(Buffer.from(expected), Buffer.from(token));
+}
+
+// ── Button builder helpers ─────────────────────────────────────────────
+
+export type MattermostButton = {
+  id: string;
+  type: "button" | "select";
+  name: string;
+  style?: "default" | "primary" | "danger";
+  integration: {
+    url: string;
+    context: Record<string, unknown>;
+  };
+};
+
+export type MattermostAttachment = {
+  text?: string;
+  actions?: MattermostButton[];
+  [key: string]: unknown;
+};
+
+/**
+ * Build Mattermost `props.attachments` with interactive buttons.
+ *
+ * Each button includes an HMAC token in its integration context so the
+ * callback handler can verify the request originated from a legitimate
+ * button click (Mattermost's recommended security pattern).
+ */
+/**
+ * Sanitize a button ID so Mattermost's action router can match it.
+ * Mattermost uses the action ID in the URL path `/api/v4/posts/{id}/actions/{actionId}`
+ * and IDs containing hyphens or underscores break the server-side routing.
+ * See: https://github.com/mattermost/mattermost/issues/25747
+ */
+function sanitizeActionId(id: string): string {
+  return id.replace(/[-_]/g, "");
+}
+
+export function buildButtonAttachments(params: {
+  callbackUrl: string;
+  accountId?: string;
+  buttons: Array<{
+    id: string;
+    name: string;
+    style?: "default" | "primary" | "danger";
+    context?: Record<string, unknown>;
+  }>;
+  text?: string;
+}): MattermostAttachment[] {
+  const actions: MattermostButton[] = params.buttons.map((btn) => {
+    const safeId = sanitizeActionId(btn.id);
+    const context: Record<string, unknown> = {
+      action_id: safeId,
+      ...btn.context,
+    };
+    const token = generateInteractionToken(context, params.accountId);
+    return {
+      id: safeId,
+      type: "button" as const,
+      name: btn.name,
+      style: btn.style,
+      integration: {
+        url: params.callbackUrl,
+        context: {
+          ...context,
+          _token: token,
+        },
+      },
+    };
+  });
+
+  return [
+    {
+      text: params.text ?? "",
+      actions,
+    },
+  ];
+}
+
+// ── Localhost validation ───────────────────────────────────────────────
+
+const LOCALHOST_ADDRESSES = new Set(["127.0.0.1", "::1", "::ffff:127.0.0.1"]);
+
+export function isLocalhostRequest(req: IncomingMessage): boolean {
+  const addr = req.socket?.remoteAddress;
+  if (!addr) {
+    return false;
+  }
+  return LOCALHOST_ADDRESSES.has(addr);
+}
+
+// ── Request body reader ────────────────────────────────────────────────
+
+function readInteractionBody(req: IncomingMessage): Promise<string> {
+  return new Promise((resolve, reject) => {
+    const chunks: Buffer[] = [];
+    let totalBytes = 0;
+
+    const timer = setTimeout(() => {
+      req.destroy();
+      reject(new Error("Request body read timeout"));
+    }, INTERACTION_BODY_TIMEOUT_MS);
+
+    req.on("data", (chunk: Buffer) => {
+      totalBytes += chunk.length;
+      if (totalBytes > INTERACTION_MAX_BODY_BYTES) {
+        req.destroy();
+        clearTimeout(timer);
+        reject(new Error("Request body too large"));
+        return;
+      }
+      chunks.push(chunk);
+    });
+
+    req.on("end", () => {
+      clearTimeout(timer);
+      resolve(Buffer.concat(chunks).toString("utf8"));
+    });
+
+    req.on("error", (err) => {
+      clearTimeout(timer);
+      reject(err);
+    });
+  });
+}
+
+// ── HTTP handler ───────────────────────────────────────────────────────
+
+export function createMattermostInteractionHandler(params: {
+  client: MattermostClient;
+  botUserId: string;
+  accountId: string;
+  callbackUrl: string;
+  resolveSessionKey?: (channelId: string, userId: string) => Promise<string>;
+  dispatchButtonClick?: (opts: {
+    channelId: string;
+    userId: string;
+    userName: string;
+    actionId: string;
+    actionName: string;
+    postId: string;
+  }) => Promise<void>;
+  log?: (message: string) => void;
+}): (req: IncomingMessage, res: ServerResponse) => Promise<void> {
+  const { client, accountId, log } = params;
+  const core = getMattermostRuntime();
+
+  return async (req: IncomingMessage, res: ServerResponse) => {
+    // Only accept POST
+    if (req.method !== "POST") {
+      res.statusCode = 405;
+      res.setHeader("Allow", "POST");
+      res.setHeader("Content-Type", "application/json");
+      res.end(JSON.stringify({ error: "Method Not Allowed" }));
+      return;
+    }
+
+    // Verify request is from localhost
+    if (!isLocalhostRequest(req)) {
+      log?.(
+        `mattermost interaction: rejected non-localhost request from ${req.socket?.remoteAddress}`,
+      );
+      res.statusCode = 403;
+      res.setHeader("Content-Type", "application/json");
+      res.end(JSON.stringify({ error: "Forbidden" }));
+      return;
+    }
+
+    let payload: MattermostInteractionPayload;
+    try {
+      const raw = await readInteractionBody(req);
+      payload = JSON.parse(raw) as MattermostInteractionPayload;
+    } catch (err) {
+      log?.(`mattermost interaction: failed to parse body: ${String(err)}`);
+      res.statusCode = 400;
+      res.setHeader("Content-Type", "application/json");
+      res.end(JSON.stringify({ error: "Invalid request body" }));
+      return;
+    }
+
+    const context = payload.context;
+    if (!context) {
+      res.statusCode = 400;
+      res.setHeader("Content-Type", "application/json");
+      res.end(JSON.stringify({ error: "Missing context" }));
+      return;
+    }
+
+    // Verify HMAC token
+    const token = context._token;
+    if (typeof token !== "string") {
+      log?.("mattermost interaction: missing _token in context");
+      res.statusCode = 403;
+      res.setHeader("Content-Type", "application/json");
+      res.end(JSON.stringify({ error: "Missing token" }));
+      return;
+    }
+
+    // Strip _token before verification (it wasn't in the original context)
+    const { _token, ...contextWithoutToken } = context;
+    if (!verifyInteractionToken(contextWithoutToken, token, accountId)) {
+      log?.("mattermost interaction: invalid _token");
+      res.statusCode = 403;
+      res.setHeader("Content-Type", "application/json");
+      res.end(JSON.stringify({ error: "Invalid token" }));
+      return;
+    }
+
+    const actionId = context.action_id;
+    if (typeof actionId !== "string") {
+      res.statusCode = 400;
+      res.setHeader("Content-Type", "application/json");
+      res.end(JSON.stringify({ error: "Missing action_id in context" }));
+      return;
+    }
+
+    log?.(
+      `mattermost interaction: action=${actionId} user=${payload.user_name ?? payload.user_id} ` +
+        `post=${payload.post_id} channel=${payload.channel_id}`,
+    );
+
+    // Dispatch as system event so the agent can handle it.
+    // Wrapped in try/catch — the post update below must still run even if
+    // system event dispatch fails (e.g. missing sessionKey or channel lookup).
+    try {
+      const eventLabel =
+        `Mattermost button click: action="${actionId}" ` +
+        `by ${payload.user_name ?? payload.user_id} ` +
+        `in channel ${payload.channel_id}`;
+
+      const sessionKey = params.resolveSessionKey
+        ? await params.resolveSessionKey(payload.channel_id, payload.user_id)
+        : `agent:main:mattermost:${accountId}:${payload.channel_id}`;
+
+      core.system.enqueueSystemEvent(eventLabel, {
+        sessionKey,
+        contextKey: `mattermost:interaction:${payload.post_id}:${actionId}`,
+      });
+    } catch (err) {
+      log?.(`mattermost interaction: system event dispatch failed: ${String(err)}`);
+    }
+
+    // Fetch the original post to preserve its message and find the clicked button name.
+    const userName = payload.user_name ?? payload.user_id;
+    let originalMessage = "";
+    let clickedButtonName = actionId; // fallback to action ID if we can't find the name
+    try {
+      const originalPost = await client.request<{
+        message?: string;
+        props?: Record<string, unknown>;
+      }>(`/posts/${payload.post_id}`);
+      originalMessage = originalPost?.message ?? "";
+
+      // Find the clicked button's display name from the original attachments
+      const postAttachments = Array.isArray(originalPost?.props?.attachments)
+        ? (originalPost.props.attachments as Array<{
+            actions?: Array<{ id?: string; name?: string }>;
+          }>)
+        : [];
+      for (const att of postAttachments) {
+        const match = att.actions?.find((a) => a.id === actionId);
+        if (match?.name) {
+          clickedButtonName = match.name;
+          break;
+        }
+      }
+    } catch (err) {
+      log?.(`mattermost interaction: failed to fetch post ${payload.post_id}: ${String(err)}`);
+    }
+
+    // Update the post via API to replace buttons with a completion indicator.
+    try {
+      await updateMattermostPost(client, payload.post_id, {
+        message: originalMessage,
+        props: {
+          attachments: [
+            {
+              text: `✓ **${clickedButtonName}** selected by @${userName}`,
+            },
+          ],
+        },
+      });
+    } catch (err) {
+      log?.(`mattermost interaction: failed to update post ${payload.post_id}: ${String(err)}`);
+    }
+
+    // Respond with empty JSON — the post update is handled above
+    res.statusCode = 200;
+    res.setHeader("Content-Type", "application/json");
+    res.end("{}");
+
+    // Dispatch a synthetic inbound message so the agent responds to the button click.
+    if (params.dispatchButtonClick) {
+      try {
+        await params.dispatchButtonClick({
+          channelId: payload.channel_id,
+          userId: payload.user_id,
+          userName,
+          actionId,
+          actionName: clickedButtonName,
+          postId: payload.post_id,
+        });
+      } catch (err) {
+        log?.(`mattermost interaction: dispatchButtonClick failed: ${String(err)}`);
+      }
+    }
+  };
+}

extensions/mattermost/src/mattermost/monitor.test.ts

@@ -0,0 +1,109 @@
+import type { OpenClawConfig } from "openclaw/plugin-sdk/mattermost";
+import { describe, expect, it, vi } from "vitest";
+import { resolveMattermostAccount } from "./accounts.js";
+import {
+  evaluateMattermostMentionGate,
+  type MattermostMentionGateInput,
+  type MattermostRequireMentionResolverInput,
+} from "./monitor.js";
+
+function resolveRequireMentionForTest(params: MattermostRequireMentionResolverInput): boolean {
+  const root = params.cfg.channels?.mattermost;
+  const accountGroups = root?.accounts?.[params.accountId]?.groups;
+  const groups = accountGroups ?? root?.groups;
+  const groupConfig = params.groupId ? groups?.[params.groupId] : undefined;
+  const defaultGroupConfig = groups?.["*"];
+  const configMention =
+    typeof groupConfig?.requireMention === "boolean"
+      ? groupConfig.requireMention
+      : typeof defaultGroupConfig?.requireMention === "boolean"
+        ? defaultGroupConfig.requireMention
+        : undefined;
+  if (typeof configMention === "boolean") {
+    return configMention;
+  }
+  if (typeof params.requireMentionOverride === "boolean") {
+    return params.requireMentionOverride;
+  }
+  return true;
+}
+
+function evaluateMentionGateForMessage(params: { cfg: OpenClawConfig; threadRootId?: string }) {
+  const account = resolveMattermostAccount({ cfg: params.cfg, accountId: "default" });
+  const resolver = vi.fn(resolveRequireMentionForTest);
+  const input: MattermostMentionGateInput = {
+    kind: "channel",
+    cfg: params.cfg,
+    accountId: account.accountId,
+    channelId: "chan-1",
+    threadRootId: params.threadRootId,
+    requireMentionOverride: account.requireMention,
+    resolveRequireMention: resolver,
+    wasMentioned: false,
+    isControlCommand: false,
+    commandAuthorized: false,
+    oncharEnabled: false,
+    oncharTriggered: false,
+    canDetectMention: true,
+  };
+  const decision = evaluateMattermostMentionGate(input);
+  return { account, resolver, decision };
+}
+
+describe("mattermost mention gating", () => {
+  it("accepts unmentioned root channel posts in onmessage mode", () => {
+    const cfg: OpenClawConfig = {
+      channels: {
+        mattermost: {
+          chatmode: "onmessage",
+          groupPolicy: "open",
+        },
+      },
+    };
+    const { resolver, decision } = evaluateMentionGateForMessage({ cfg });
+    expect(decision.dropReason).toBeNull();
+    expect(decision.shouldRequireMention).toBe(false);
+    expect(resolver).toHaveBeenCalledWith(
+      expect.objectContaining({
+        accountId: "default",
+        groupId: "chan-1",
+        requireMentionOverride: false,
+      }),
+    );
+  });
+
+  it("accepts unmentioned thread replies in onmessage mode", () => {
+    const cfg: OpenClawConfig = {
+      channels: {
+        mattermost: {
+          chatmode: "onmessage",
+          groupPolicy: "open",
+        },
+      },
+    };
+    const { resolver, decision } = evaluateMentionGateForMessage({
+      cfg,
+      threadRootId: "thread-root-1",
+    });
+    expect(decision.dropReason).toBeNull();
+    expect(decision.shouldRequireMention).toBe(false);
+    const resolverCall = resolver.mock.calls.at(-1)?.[0];
+    expect(resolverCall?.groupId).toBe("chan-1");
+    expect(resolverCall?.groupId).not.toBe("thread-root-1");
+  });
+
+  it("rejects unmentioned channel posts in oncall mode", () => {
+    const cfg: OpenClawConfig = {
+      channels: {
+        mattermost: {
+          chatmode: "oncall",
+          groupPolicy: "open",
+        },
+      },
+    };
+    const { decision, account } = evaluateMentionGateForMessage({ cfg });
+    expect(account.requireMention).toBe(true);
+    expect(decision.shouldRequireMention).toBe(true);
+    expect(decision.dropReason).toBe("missing-mention");
+  });
+});

extensions/mattermost/src/mattermost/monitor.ts

@@ -18,6 +18,7 @@ import {
   DEFAULT_GROUP_HISTORY_LIMIT,
   recordPendingHistoryEntryIfEnabled,
   isDangerousNameMatchingEnabled,
+  registerPluginHttpRoute,
   resolveControlCommandGate,
   readStoreAllowFromForDmPolicy,
   resolveDmGroupAccessWithLists,
@@ -42,6 +43,11 @@ import {
   type MattermostPost,
   type MattermostUser,
 } from "./client.js";
+import {
+  createMattermostInteractionHandler,
+  setInteractionCallbackUrl,
+  setInteractionSecret,
+} from "./interactions.js";
 import { isMattermostSenderAllowed, normalizeMattermostAllowList } from "./monitor-auth.js";
 import {
   createDedupeCache,
@@ -156,6 +162,89 @@ function channelChatType(kind: ChatType): "direct" | "group" | "channel" {
   return "channel";
 }
 
+export type MattermostRequireMentionResolverInput = {
+  cfg: OpenClawConfig;
+  channel: "mattermost";
+  accountId: string;
+  groupId: string;
+  requireMentionOverride?: boolean;
+};
+
+export type MattermostMentionGateInput = {
+  kind: ChatType;
+  cfg: OpenClawConfig;
+  accountId: string;
+  channelId: string;
+  threadRootId?: string;
+  requireMentionOverride?: boolean;
+  resolveRequireMention: (params: MattermostRequireMentionResolverInput) => boolean;
+  wasMentioned: boolean;
+  isControlCommand: boolean;
+  commandAuthorized: boolean;
+  oncharEnabled: boolean;
+  oncharTriggered: boolean;
+  canDetectMention: boolean;
+};
+
+type MattermostMentionGateDecision = {
+  shouldRequireMention: boolean;
+  shouldBypassMention: boolean;
+  effectiveWasMentioned: boolean;
+  dropReason: "onchar-not-triggered" | "missing-mention" | null;
+};
+
+export function evaluateMattermostMentionGate(
+  params: MattermostMentionGateInput,
+): MattermostMentionGateDecision {
+  const shouldRequireMention =
+    params.kind !== "direct" &&
+    params.resolveRequireMention({
+      cfg: params.cfg,
+      channel: "mattermost",
+      accountId: params.accountId,
+      groupId: params.channelId,
+      requireMentionOverride: params.requireMentionOverride,
+    });
+  const shouldBypassMention =
+    params.isControlCommand &&
+    shouldRequireMention &&
+    !params.wasMentioned &&
+    params.commandAuthorized;
+  const effectiveWasMentioned =
+    params.wasMentioned || shouldBypassMention || params.oncharTriggered;
+  if (
+    params.oncharEnabled &&
+    !params.oncharTriggered &&
+    !params.wasMentioned &&
+    !params.isControlCommand
+  ) {
+    return {
+      shouldRequireMention,
+      shouldBypassMention,
+      effectiveWasMentioned,
+      dropReason: "onchar-not-triggered",
+    };
+  }
+  if (
+    params.kind !== "direct" &&
+    shouldRequireMention &&
+    params.canDetectMention &&
+    !effectiveWasMentioned
+  ) {
+    return {
+      shouldRequireMention,
+      shouldBypassMention,
+      effectiveWasMentioned,
+      dropReason: "missing-mention",
+    };
+  }
+  return {
+    shouldRequireMention,
+    shouldBypassMention,
+    effectiveWasMentioned,
+    dropReason: null,
+  };
+}
 type MattermostMediaInfo = {
   path: string;
   contentType?: string;
@@ -235,12 +324,12 @@ export async function monitorMattermostProvider(opts: MonitorMattermostOpts = {}
       // a different port.
       const envPortRaw = process.env.OPENCLAW_GATEWAY_PORT?.trim();
       const envPort = envPortRaw ? Number.parseInt(envPortRaw, 10) : NaN;
-      const gatewayPort =
+      const slashGatewayPort =
         Number.isFinite(envPort) && envPort > 0 ? envPort : (cfg.gateway?.port ?? 18789);
 
-      const callbackUrl = resolveCallbackUrl({
+      const slashCallbackUrl = resolveCallbackUrl({
         config: slashConfig,
-        gatewayPort,
+        gatewayPort: slashGatewayPort,
         gatewayHost: cfg.gateway?.customBindHost ?? undefined,
       });
 
@@ -249,7 +338,7 @@ export async function monitorMattermostProvider(opts: MonitorMattermostOpts = {}
 
       try {
         const mmHost = new URL(baseUrl).hostname;
-        const callbackHost = new URL(callbackUrl).hostname;
+        const callbackHost = new URL(slashCallbackUrl).hostname;
 
         // NOTE: We cannot infer network reachability from hostnames alone.
         // Mattermost might be accessed via a public domain while still running on the same
@@ -257,7 +346,7 @@ export async function monitorMattermostProvider(opts: MonitorMattermostOpts = {}
         // So treat loopback callback URLs as an advisory warning only.
         if (isLoopbackHost(callbackHost) && !isLoopbackHost(mmHost)) {
           runtime.error?.(
-            `mattermost: slash commands callbackUrl resolved to ${callbackUrl} (loopback) while baseUrl is ${baseUrl}. This MAY be unreachable depending on your deployment. If native slash commands don't work, set channels.mattermost.commands.callbackUrl to a URL reachable from the Mattermost server (e.g. your public reverse proxy URL).`,
+            `mattermost: slash commands callbackUrl resolved to ${slashCallbackUrl} (loopback) while baseUrl is ${baseUrl}. This MAY be unreachable depending on your deployment. If native slash commands don't work, set channels.mattermost.commands.callbackUrl to a URL reachable from the Mattermost server (e.g. your public reverse proxy URL).`,
           );
         }
       } catch {
@@ -307,7 +396,7 @@ export async function monitorMattermostProvider(opts: MonitorMattermostOpts = {}
             client,
             teamId: team.id,
             creatorUserId: botUserId,
-            callbackUrl,
+            callbackUrl: slashCallbackUrl,
             commands: dedupedCommands,
             log: (msg) => runtime.log?.(msg),
           });
@@ -349,7 +438,7 @@ export async function monitorMattermostProvider(opts: MonitorMattermostOpts = {}
         });
 
         runtime.log?.(
-          `mattermost: slash commands registered (${allRegistered.length} commands across ${teams.length} teams, callback=${callbackUrl})`,
+          `mattermost: slash commands registered (${allRegistered.length} commands across ${teams.length} teams, callback=${slashCallbackUrl})`,
         );
       }
     } catch (err) {
@@ -357,6 +446,182 @@ export async function monitorMattermostProvider(opts: MonitorMattermostOpts = {}
     }
   }
 
+  // ─── Interactive buttons registration ──────────────────────────────────────
+  // Derive a stable HMAC secret from the bot token so CLI and gateway share it.
+  setInteractionSecret(account.accountId, botToken);
+
+  // Register HTTP callback endpoint for interactive button clicks.
+  // Mattermost POSTs to this URL when a user clicks a button action.
+  const gatewayPort = typeof cfg.gateway?.port === "number" ? cfg.gateway.port : 18789;
+  const interactionPath = `/mattermost/interactions/${account.accountId}`;
+  const callbackUrl = `http://localhost:${gatewayPort}${interactionPath}`;
+  setInteractionCallbackUrl(account.accountId, callbackUrl);
+  const unregisterInteractions = registerPluginHttpRoute({
+    path: interactionPath,
+    fallbackPath: "/mattermost/interactions/default",
+    auth: "plugin",
+    handler: createMattermostInteractionHandler({
+      client,
+      botUserId,
+      accountId: account.accountId,
+      callbackUrl,
+      resolveSessionKey: async (channelId: string, userId: string) => {
+        const channelInfo = await resolveChannelInfo(channelId);
+        const kind = mapMattermostChannelTypeToChatType(channelInfo?.type);
+        const teamId = channelInfo?.team_id ?? undefined;
+        const route = core.channel.routing.resolveAgentRoute({
+          cfg,
+          channel: "mattermost",
+          accountId: account.accountId,
+          teamId,
+          peer: {
+            kind,
+            id: kind === "direct" ? userId : channelId,
+          },
+        });
+        return route.sessionKey;
+      },
+      dispatchButtonClick: async (opts) => {
+        const channelInfo = await resolveChannelInfo(opts.channelId);
+        const kind = mapMattermostChannelTypeToChatType(channelInfo?.type);
+        const chatType = channelChatType(kind);
+        const teamId = channelInfo?.team_id ?? undefined;
+        const channelName = channelInfo?.name ?? undefined;
+        const channelDisplay = channelInfo?.display_name ?? channelName ?? opts.channelId;
+        const route = core.channel.routing.resolveAgentRoute({
+          cfg,
+          channel: "mattermost",
+          accountId: account.accountId,
+          teamId,
+          peer: {
+            kind,
+            id: kind === "direct" ? opts.userId : opts.channelId,
+          },
+        });
+        const to = kind === "direct" ? `user:${opts.userId}` : `channel:${opts.channelId}`;
+        const bodyText = `[Button click: user @${opts.userName} selected "${opts.actionName}"]`;
+        const ctxPayload = core.channel.reply.finalizeInboundContext({
+          Body: bodyText,
+          BodyForAgent: bodyText,
+          RawBody: bodyText,
+          CommandBody: bodyText,
+          From:
+            kind === "direct"
+              ? `mattermost:${opts.userId}`
+              : kind === "group"
+                ? `mattermost:group:${opts.channelId}`
+                : `mattermost:channel:${opts.channelId}`,
+          To: to,
+          SessionKey: route.sessionKey,
+          AccountId: route.accountId,
+          ChatType: chatType,
+          ConversationLabel: `mattermost:${opts.userName}`,
+          GroupSubject: kind !== "direct" ? channelDisplay : undefined,
+          GroupChannel: channelName ? `#${channelName}` : undefined,
+          GroupSpace: teamId,
+          SenderName: opts.userName,
+          SenderId: opts.userId,
+          Provider: "mattermost" as const,
+          Surface: "mattermost" as const,
+          MessageSid: `interaction:${opts.postId}:${opts.actionId}`,
+          WasMentioned: true,
+          CommandAuthorized: true,
+          OriginatingChannel: "mattermost" as const,
+          OriginatingTo: to,
+        });
+
+        const textLimit = core.channel.text.resolveTextChunkLimit(
+          cfg,
+          "mattermost",
+          account.accountId,
+          { fallbackLimit: account.textChunkLimit ?? 4000 },
+        );
+        const tableMode = core.channel.text.resolveMarkdownTableMode({
+          cfg,
+          channel: "mattermost",
+          accountId: account.accountId,
+        });
+        const { onModelSelected, ...prefixOptions } = createReplyPrefixOptions({
+          cfg,
+          agentId: route.agentId,
+          channel: "mattermost",
+          accountId: account.accountId,
+        });
+        const typingCallbacks = createTypingCallbacks({
+          start: () => sendTypingIndicator(opts.channelId),
+          onStartError: (err) => {
+            logTypingFailure({
+              log: (message) => logger.debug?.(message),
+              channel: "mattermost",
+              target: opts.channelId,
+              error: err,
+            });
+          },
+        });
+        const { dispatcher, replyOptions, markDispatchIdle } =
+          core.channel.reply.createReplyDispatcherWithTyping({
+            ...prefixOptions,
+            humanDelay: core.channel.reply.resolveHumanDelayConfig(cfg, route.agentId),
+            deliver: async (payload: ReplyPayload) => {
+              const mediaUrls = payload.mediaUrls ?? (payload.mediaUrl ? [payload.mediaUrl] : []);
+              const text = core.channel.text.convertMarkdownTables(payload.text ?? "", tableMode);
+              if (mediaUrls.length === 0) {
+                const chunkMode = core.channel.text.resolveChunkMode(
+                  cfg,
+                  "mattermost",
+                  account.accountId,
+                );
+                const chunks = core.channel.text.chunkMarkdownTextWithMode(
+                  text,
+                  textLimit,
+                  chunkMode,
+                );
+                for (const chunk of chunks.length > 0 ? chunks : [text]) {
+                  if (!chunk) continue;
+                  await sendMessageMattermost(to, chunk, {
+                    accountId: account.accountId,
+                  });
+                }
+              } else {
+                let first = true;
+                for (const mediaUrl of mediaUrls) {
+                  const caption = first ? text : "";
+                  first = false;
+                  await sendMessageMattermost(to, caption, {
+                    accountId: account.accountId,
+                    mediaUrl,
+                  });
+                }
+              }
+              runtime.log?.(`delivered button-click reply to ${to}`);
+            },
+            onError: (err, info) => {
+              runtime.error?.(`mattermost button-click ${info.kind} reply failed: ${String(err)}`);
+            },
+            onReplyStart: typingCallbacks.onReplyStart,
+          });
+
+        await core.channel.reply.dispatchReplyFromConfig({
+          ctx: ctxPayload,
+          cfg,
+          dispatcher,
+          replyOptions: {
+            ...replyOptions,
+            disableBlockStreaming:
+              typeof account.blockStreaming === "boolean" ? !account.blockStreaming : undefined,
+            onModelSelected,
+          },
+        });
+        markDispatchIdle();
+      },
+      log: (msg) => runtime.log?.(msg),
+    }),
+    pluginId: "mattermost",
+    source: "mattermost-interactions",
+    accountId: account.accountId,
+    log: (msg: string) => runtime.log?.(msg),
+  });
+
   const channelCache = new Map<string, { value: MattermostChannel | null; expiresAt: number }>();
   const userCache = new Map<string, { value: MattermostUser | null; expiresAt: number }>();
   const logger = core.logging.getChildLogger({ module: "mattermost" });
@@ -410,6 +675,10 @@ export async function monitorMattermostProvider(opts: MonitorMattermostOpts = {}
           },
           filePathHint: fileId,
           maxBytes: mediaMaxBytes,
+          // Allow fetching from the Mattermost server host (may be localhost or
+          // a private IP). Without this, SSRF guards block media downloads.
+          // Credit: #22594 (@webclerk)
+          ssrfPolicy: { allowedHostnames: [new URL(client.baseUrl).hostname] },
         });
         const saved = await core.channel.media.saveMediaBuffer(
           fetched.buffer,
@@ -485,28 +754,36 @@ export async function monitorMattermostProvider(opts: MonitorMattermostOpts = {}
   ) => {
     const channelId = post.channel_id ?? payload.data?.channel_id ?? payload.broadcast?.channel_id;
     if (!channelId) {
+      logVerboseMessage("mattermost: drop post (missing channel id)");
       return;
     }
 
     const allMessageIds = messageIds?.length ? messageIds : post.id ? [post.id] : [];
     if (allMessageIds.length === 0) {
+      logVerboseMessage("mattermost: drop post (missing message id)");
       return;
     }
     const dedupeEntries = allMessageIds.map((id) =>
       recentInboundMessages.check(`${account.accountId}:${id}`),
     );
     if (dedupeEntries.length > 0 && dedupeEntries.every(Boolean)) {
+      logVerboseMessage(
+        `mattermost: drop post (dedupe account=${account.accountId} ids=${allMessageIds.length})`,
+      );
       return;
     }
 
     const senderId = post.user_id ?? payload.broadcast?.user_id;
     if (!senderId) {
+      logVerboseMessage("mattermost: drop post (missing sender id)");
       return;
     }
     if (senderId === botUserId) {
+      logVerboseMessage(`mattermost: drop post (self sender=${senderId})`);
       return;
     }
     if (isSystemPost(post)) {
+      logVerboseMessage(`mattermost: drop post (system post type=${post.type ?? "unknown"})`);
       return;
     }
 
@@ -707,30 +984,38 @@ export async function monitorMattermostProvider(opts: MonitorMattermostOpts = {}
       ? stripOncharPrefix(rawText, oncharPrefixes)
       : { triggered: false, stripped: rawText };
     const oncharTriggered = oncharResult.triggered;
-
-    const shouldRequireMention =
-      kind !== "direct" &&
-      core.channel.groups.resolveRequireMention({
-        cfg,
-        channel: "mattermost",
-        accountId: account.accountId,
-        groupId: channelId,
-      });
-    const shouldBypassMention =
-      isControlCommand && shouldRequireMention && !wasMentioned && commandAuthorized;
-    const effectiveWasMentioned = wasMentioned || shouldBypassMention || oncharTriggered;
     const canDetectMention = Boolean(botUsername) || mentionRegexes.length > 0;
+    const mentionDecision = evaluateMattermostMentionGate({
+      kind,
+      cfg,
+      accountId: account.accountId,
+      channelId,
+      threadRootId,
+      requireMentionOverride: account.requireMention,
+      resolveRequireMention: core.channel.groups.resolveRequireMention,
+      wasMentioned,
+      isControlCommand,
+      commandAuthorized,
+      oncharEnabled,
+      oncharTriggered,
+      canDetectMention,
+    });
+    const { shouldRequireMention, shouldBypassMention } = mentionDecision;
 
-    if (oncharEnabled && !oncharTriggered && !wasMentioned && !isControlCommand) {
+    if (mentionDecision.dropReason === "onchar-not-triggered") {
+      logVerboseMessage(
+        `mattermost: drop group message (onchar not triggered channel=${channelId} sender=${senderId})`,
+      );
       recordPendingHistory();
       return;
     }
 
-    if (kind !== "direct" && shouldRequireMention && canDetectMention) {
-      if (!effectiveWasMentioned) {
-        recordPendingHistory();
-        return;
-      }
+    if (mentionDecision.dropReason === "missing-mention") {
+      logVerboseMessage(
+        `mattermost: drop group message (missing mention channel=${channelId} sender=${senderId} requireMention=${shouldRequireMention} bypass=${shouldBypassMention} canDetectMention=${canDetectMention})`,
+      );
+      recordPendingHistory();
+      return;
     }
     const mediaList = await resolveMattermostMedia(post.file_ids);
     const mediaPlaceholder = buildMattermostAttachmentPlaceholder(mediaList);
@@ -738,6 +1023,9 @@ export async function monitorMattermostProvider(opts: MonitorMattermostOpts = {}
     const baseText = [bodySource, mediaPlaceholder].filter(Boolean).join("\n").trim();
     const bodyText = normalizeMention(baseText, botUsername);
     if (!bodyText) {
+      logVerboseMessage(
+        `mattermost: drop group message (empty body after normalization channel=${channelId} sender=${senderId})`,
+      );
       return;
     }
 
@@ -841,7 +1129,7 @@ export async function monitorMattermostProvider(opts: MonitorMattermostOpts = {}
       ReplyToId: threadRootId,
       MessageThreadId: threadRootId,
       Timestamp: typeof post.create_at === "number" ? post.create_at : undefined,
-      WasMentioned: kind !== "direct" ? effectiveWasMentioned : undefined,
+      WasMentioned: kind !== "direct" ? mentionDecision.effectiveWasMentioned : undefined,
       CommandAuthorized: commandAuthorized,
       OriginatingChannel: "mattermost" as const,
       OriginatingTo: to,
@@ -1194,17 +1482,21 @@ export async function monitorMattermostProvider(opts: MonitorMattermostOpts = {}
     }
   }
 
-  await runWithReconnect(connectOnce, {
-    abortSignal: opts.abortSignal,
-    jitterRatio: 0.2,
-    onError: (err) => {
-      runtime.error?.(`mattermost connection failed: ${String(err)}`);
-      opts.statusSink?.({ lastError: String(err), connected: false });
-    },
-    onReconnect: (delayMs) => {
-      runtime.log?.(`mattermost reconnecting in ${Math.round(delayMs / 1000)}s`);
-    },
-  });
+  try {
+    await runWithReconnect(connectOnce, {
+      abortSignal: opts.abortSignal,
+      jitterRatio: 0.2,
+      onError: (err) => {
+        runtime.error?.(`mattermost connection failed: ${String(err)}`);
+        opts.statusSink?.({ lastError: String(err), connected: false });
+      },
+      onReconnect: (delayMs) => {
+        runtime.log?.(`mattermost reconnecting in ${Math.round(delayMs / 1000)}s`);
+      },
+    });
+  } finally {
+    unregisterInteractions?.();
+  }
 
   if (slashShutdownCleanup) {
     await slashShutdownCleanup;

extensions/mattermost/src/mattermost/send.test.ts

@@ -1,5 +1,5 @@
 import { beforeEach, describe, expect, it, vi } from "vitest";
-import { sendMessageMattermost } from "./send.js";
+import { parseMattermostTarget, sendMessageMattermost } from "./send.js";
 
 const mockState = vi.hoisted(() => ({
   loadConfig: vi.fn(() => ({})),
@@ -12,7 +12,9 @@ const mockState = vi.hoisted(() => ({
   createMattermostClient: vi.fn(),
   createMattermostDirectChannel: vi.fn(),
   createMattermostPost: vi.fn(),
+  fetchMattermostChannelByName: vi.fn(),
   fetchMattermostMe: vi.fn(),
+  fetchMattermostUserTeams: vi.fn(),
   fetchMattermostUserByUsername: vi.fn(),
   normalizeMattermostBaseUrl: vi.fn((input: string | undefined) => input?.trim() ?? ""),
   uploadMattermostFile: vi.fn(),
@@ -30,7 +32,9 @@ vi.mock("./client.js", () => ({
   createMattermostClient: mockState.createMattermostClient,
   createMattermostDirectChannel: mockState.createMattermostDirectChannel,
   createMattermostPost: mockState.createMattermostPost,
+  fetchMattermostChannelByName: mockState.fetchMattermostChannelByName,
   fetchMattermostMe: mockState.fetchMattermostMe,
+  fetchMattermostUserTeams: mockState.fetchMattermostUserTeams,
   fetchMattermostUserByUsername: mockState.fetchMattermostUserByUsername,
   normalizeMattermostBaseUrl: mockState.normalizeMattermostBaseUrl,
   uploadMattermostFile: mockState.uploadMattermostFile,
@@ -71,11 +75,16 @@ describe("sendMessageMattermost", () => {
     mockState.createMattermostClient.mockReset();
     mockState.createMattermostDirectChannel.mockReset();
     mockState.createMattermostPost.mockReset();
+    mockState.fetchMattermostChannelByName.mockReset();
     mockState.fetchMattermostMe.mockReset();
+    mockState.fetchMattermostUserTeams.mockReset();
     mockState.fetchMattermostUserByUsername.mockReset();
     mockState.uploadMattermostFile.mockReset();
     mockState.createMattermostClient.mockReturnValue({});
     mockState.createMattermostPost.mockResolvedValue({ id: "post-1" });
+    mockState.fetchMattermostMe.mockResolvedValue({ id: "bot-user" });
+    mockState.fetchMattermostUserTeams.mockResolvedValue([{ id: "team-1" }]);
+    mockState.fetchMattermostChannelByName.mockResolvedValue({ id: "town-square" });
     mockState.uploadMattermostFile.mockResolvedValue({ id: "file-1" });
   });
 
@@ -148,3 +157,86 @@ describe("sendMessageMattermost", () => {
     );
   });
 });
+
+describe("parseMattermostTarget", () => {
+  it("parses channel: prefix with valid ID as channel id", () => {
+    const target = parseMattermostTarget("channel:dthcxgoxhifn3pwh65cut3ud3w");
+    expect(target).toEqual({ kind: "channel", id: "dthcxgoxhifn3pwh65cut3ud3w" });
+  });
+
+  it("parses channel: prefix with non-ID as channel name", () => {
+    const target = parseMattermostTarget("channel:abc123");
+    expect(target).toEqual({ kind: "channel-name", name: "abc123" });
+  });
+
+  it("parses user: prefix as user id", () => {
+    const target = parseMattermostTarget("user:usr456");
+    expect(target).toEqual({ kind: "user", id: "usr456" });
+  });
+
+  it("parses mattermost: prefix as user id", () => {
+    const target = parseMattermostTarget("mattermost:usr789");
+    expect(target).toEqual({ kind: "user", id: "usr789" });
+  });
+
+  it("parses @ prefix as username", () => {
+    const target = parseMattermostTarget("@alice");
+    expect(target).toEqual({ kind: "user", username: "alice" });
+  });
+
+  it("parses # prefix as channel name", () => {
+    const target = parseMattermostTarget("#off-topic");
+    expect(target).toEqual({ kind: "channel-name", name: "off-topic" });
+  });
+
+  it("parses # prefix with spaces", () => {
+    const target = parseMattermostTarget("  #general  ");
+    expect(target).toEqual({ kind: "channel-name", name: "general" });
+  });
+
+  it("treats 26-char alphanumeric bare string as channel id", () => {
+    const target = parseMattermostTarget("dthcxgoxhifn3pwh65cut3ud3w");
+    expect(target).toEqual({ kind: "channel", id: "dthcxgoxhifn3pwh65cut3ud3w" });
+  });
+
+  it("treats non-ID bare string as channel name", () => {
+    const target = parseMattermostTarget("off-topic");
+    expect(target).toEqual({ kind: "channel-name", name: "off-topic" });
+  });
+
+  it("treats channel: with non-ID value as channel name", () => {
+    const target = parseMattermostTarget("channel:off-topic");
+    expect(target).toEqual({ kind: "channel-name", name: "off-topic" });
+  });
+
+  it("throws on empty string", () => {
+    expect(() => parseMattermostTarget("")).toThrow("Recipient is required");
+  });
+
+  it("throws on empty # prefix", () => {
+    expect(() => parseMattermostTarget("#")).toThrow("Channel name is required");
+  });
+
+  it("throws on empty @ prefix", () => {
+    expect(() => parseMattermostTarget("@")).toThrow("Username is required");
+  });
+
+  it("parses channel:#name as channel name", () => {
+    const target = parseMattermostTarget("channel:#off-topic");
+    expect(target).toEqual({ kind: "channel-name", name: "off-topic" });
+  });
+
+  it("parses channel:#name with spaces", () => {
+    const target = parseMattermostTarget("  channel: #general  ");
+    expect(target).toEqual({ kind: "channel-name", name: "general" });
+  });
+
+  it("is case-insensitive for prefixes", () => {
+    expect(parseMattermostTarget("CHANNEL:dthcxgoxhifn3pwh65cut3ud3w")).toEqual({
+      kind: "channel",
+      id: "dthcxgoxhifn3pwh65cut3ud3w",
+    });
+    expect(parseMattermostTarget("User:XYZ")).toEqual({ kind: "user", id: "XYZ" });
+    expect(parseMattermostTarget("Mattermost:QRS")).toEqual({ kind: "user", id: "QRS" });
+  });
+});

extensions/mattermost/src/mattermost/send.ts

@@ -5,8 +5,10 @@ import {
   createMattermostClient,
   createMattermostDirectChannel,
   createMattermostPost,
+  fetchMattermostChannelByName,
   fetchMattermostMe,
   fetchMattermostUserByUsername,
+  fetchMattermostUserTeams,
   normalizeMattermostBaseUrl,
   uploadMattermostFile,
   type MattermostUser,
@@ -20,6 +22,7 @@ export type MattermostSendOpts = {
   mediaUrl?: string;
   mediaLocalRoots?: readonly string[];
   replyToId?: string;
+  props?: Record<string, unknown>;
 };
 
 export type MattermostSendResult = {
@@ -29,10 +32,12 @@ export type MattermostSendResult = {
 
 type MattermostTarget =
   | { kind: "channel"; id: string }
+  | { kind: "channel-name"; name: string }
   | { kind: "user"; id?: string; username?: string };
 
 const botUserCache = new Map<string, MattermostUser>();
 const userByNameCache = new Map<string, MattermostUser>();
+const channelByNameCache = new Map<string, string>();
 
 const getCore = () => getMattermostRuntime();
 
@@ -50,7 +55,12 @@ function isHttpUrl(value: string): boolean {
   return /^https?:\/\//i.test(value);
 }
 
-function parseMattermostTarget(raw: string): MattermostTarget {
+/** Mattermost IDs are 26-character lowercase alphanumeric strings. */
+function isMattermostId(value: string): boolean {
+  return /^[a-z0-9]{26}$/.test(value);
+}
+
+export function parseMattermostTarget(raw: string): MattermostTarget {
   const trimmed = raw.trim();
   if (!trimmed) {
     throw new Error("Recipient is required for Mattermost sends");
@@ -61,6 +71,16 @@ function parseMattermostTarget(raw: string): MattermostTarget {
     if (!id) {
       throw new Error("Channel id is required for Mattermost sends");
     }
+    if (id.startsWith("#")) {
+      const name = id.slice(1).trim();
+      if (!name) {
+        throw new Error("Channel name is required for Mattermost sends");
+      }
+      return { kind: "channel-name", name };
+    }
+    if (!isMattermostId(id)) {
+      return { kind: "channel-name", name: id };
+    }
     return { kind: "channel", id };
   }
   if (lower.startsWith("user:")) {
@@ -84,6 +104,16 @@ function parseMattermostTarget(raw: string): MattermostTarget {
     }
     return { kind: "user", username };
   }
+  if (trimmed.startsWith("#")) {
+    const name = trimmed.slice(1).trim();
+    if (!name) {
+      throw new Error("Channel name is required for Mattermost sends");
+    }
+    return { kind: "channel-name", name };
+  }
+  if (!isMattermostId(trimmed)) {
+    return { kind: "channel-name", name: trimmed };
+  }
   return { kind: "channel", id: trimmed };
 }
 
@@ -116,6 +146,34 @@ async function resolveUserIdByUsername(params: {
   return user.id;
 }
 
+async function resolveChannelIdByName(params: {
+  baseUrl: string;
+  token: string;
+  name: string;
+}): Promise<string> {
+  const { baseUrl, token, name } = params;
+  const key = `${cacheKey(baseUrl, token)}::channel::${name.toLowerCase()}`;
+  const cached = channelByNameCache.get(key);
+  if (cached) {
+    return cached;
+  }
+  const client = createMattermostClient({ baseUrl, botToken: token });
+  const me = await fetchMattermostMe(client);
+  const teams = await fetchMattermostUserTeams(client, me.id);
+  for (const team of teams) {
+    try {
+      const channel = await fetchMattermostChannelByName(client, team.id, name);
+      if (channel?.id) {
+        channelByNameCache.set(key, channel.id);
+        return channel.id;
+      }
+    } catch {
+      // Channel not found in this team, try next
+    }
+  }
+  throw new Error(`Mattermost channel "#${name}" not found in any team the bot belongs to`);
+}
+
 async function resolveTargetChannelId(params: {
   target: MattermostTarget;
   baseUrl: string;
@@ -124,6 +182,13 @@ async function resolveTargetChannelId(params: {
   if (params.target.kind === "channel") {
     return params.target.id;
   }
+  if (params.target.kind === "channel-name") {
+    return await resolveChannelIdByName({
+      baseUrl: params.baseUrl,
+      token: params.token,
+      name: params.target.name,
+    });
+  }
   const userId = params.target.id
     ? params.target.id
     : await resolveUserIdByUsername({
@@ -221,6 +286,7 @@ export async function sendMessageMattermost(
     message,
     rootId: opts.replyToId,
     fileIds,
+    props: opts.props,
   });
 
   core.channel.activity.record({

extensions/mattermost/src/normalize.test.ts

@@ -0,0 +1,96 @@
+import { describe, expect, it } from "vitest";
+import { looksLikeMattermostTargetId, normalizeMattermostMessagingTarget } from "./normalize.js";
+
+describe("normalizeMattermostMessagingTarget", () => {
+  it("returns undefined for empty input", () => {
+    expect(normalizeMattermostMessagingTarget("")).toBeUndefined();
+    expect(normalizeMattermostMessagingTarget("  ")).toBeUndefined();
+  });
+
+  it("normalizes channel: prefix", () => {
+    expect(normalizeMattermostMessagingTarget("channel:abc123")).toBe("channel:abc123");
+    expect(normalizeMattermostMessagingTarget("Channel:ABC")).toBe("channel:ABC");
+  });
+
+  it("normalizes group: prefix to channel:", () => {
+    expect(normalizeMattermostMessagingTarget("group:abc123")).toBe("channel:abc123");
+  });
+
+  it("normalizes user: prefix", () => {
+    expect(normalizeMattermostMessagingTarget("user:abc123")).toBe("user:abc123");
+  });
+
+  it("normalizes mattermost: prefix to user:", () => {
+    expect(normalizeMattermostMessagingTarget("mattermost:abc123")).toBe("user:abc123");
+  });
+
+  it("keeps @username targets", () => {
+    expect(normalizeMattermostMessagingTarget("@alice")).toBe("@alice");
+    expect(normalizeMattermostMessagingTarget("@Alice")).toBe("@Alice");
+  });
+
+  it("returns undefined for #channel (triggers directory lookup)", () => {
+    expect(normalizeMattermostMessagingTarget("#bookmarks")).toBeUndefined();
+    expect(normalizeMattermostMessagingTarget("#off-topic")).toBeUndefined();
+    expect(normalizeMattermostMessagingTarget("# ")).toBeUndefined();
+  });
+
+  it("returns undefined for bare names (triggers directory lookup)", () => {
+    expect(normalizeMattermostMessagingTarget("bookmarks")).toBeUndefined();
+    expect(normalizeMattermostMessagingTarget("off-topic")).toBeUndefined();
+  });
+
+  it("returns undefined for empty prefixed values", () => {
+    expect(normalizeMattermostMessagingTarget("channel:")).toBeUndefined();
+    expect(normalizeMattermostMessagingTarget("user:")).toBeUndefined();
+    expect(normalizeMattermostMessagingTarget("@")).toBeUndefined();
+    expect(normalizeMattermostMessagingTarget("#")).toBeUndefined();
+  });
+});
+
+describe("looksLikeMattermostTargetId", () => {
+  it("returns false for empty input", () => {
+    expect(looksLikeMattermostTargetId("")).toBe(false);
+    expect(looksLikeMattermostTargetId("  ")).toBe(false);
+  });
+
+  it("recognizes prefixed targets", () => {
+    expect(looksLikeMattermostTargetId("channel:abc")).toBe(true);
+    expect(looksLikeMattermostTargetId("Channel:abc")).toBe(true);
+    expect(looksLikeMattermostTargetId("user:abc")).toBe(true);
+    expect(looksLikeMattermostTargetId("group:abc")).toBe(true);
+    expect(looksLikeMattermostTargetId("mattermost:abc")).toBe(true);
+  });
+
+  it("recognizes @username", () => {
+    expect(looksLikeMattermostTargetId("@alice")).toBe(true);
+  });
+
+  it("does NOT recognize #channel (should go to directory)", () => {
+    expect(looksLikeMattermostTargetId("#bookmarks")).toBe(false);
+    expect(looksLikeMattermostTargetId("#off-topic")).toBe(false);
+  });
+
+  it("recognizes 26-char alphanumeric Mattermost IDs", () => {
+    expect(looksLikeMattermostTargetId("abcdefghijklmnopqrstuvwxyz")).toBe(true);
+    expect(looksLikeMattermostTargetId("12345678901234567890123456")).toBe(true);
+    expect(looksLikeMattermostTargetId("AbCdEf1234567890abcdef1234")).toBe(true);
+  });
+
+  it("recognizes DM channel format (26__26)", () => {
+    expect(
+      looksLikeMattermostTargetId("abcdefghijklmnopqrstuvwxyz__12345678901234567890123456"),
+    ).toBe(true);
+  });
+
+  it("rejects short strings that are not Mattermost IDs", () => {
+    expect(looksLikeMattermostTargetId("password")).toBe(false);
+    expect(looksLikeMattermostTargetId("hi")).toBe(false);
+    expect(looksLikeMattermostTargetId("bookmarks")).toBe(false);
+    expect(looksLikeMattermostTargetId("off-topic")).toBe(false);
+  });
+
+  it("rejects strings longer than 26 chars that are not DM format", () => {
+    expect(looksLikeMattermostTargetId("abcdefghijklmnopqrstuvwxyz1")).toBe(false);
+  });
+});

extensions/mattermost/src/normalize.ts

@@ -25,13 +25,16 @@ export function normalizeMattermostMessagingTarget(raw: string): string | undefi
     return id ? `@${id}` : undefined;
   }
   if (trimmed.startsWith("#")) {
-    const id = trimmed.slice(1).trim();
-    return id ? `channel:${id}` : undefined;
+    // Strip # prefix and fall through to directory lookup (same as bare names).
+    // The core's resolveMessagingTarget will use the directory adapter to
+    // resolve the channel name to its Mattermost ID.
+    return undefined;
   }
-  return `channel:${trimmed}`;
+  // Bare name without prefix — return undefined to allow directory lookup
+  return undefined;
 }
 
-export function looksLikeMattermostTargetId(raw: string): boolean {
+export function looksLikeMattermostTargetId(raw: string, normalized?: string): boolean {
   const trimmed = raw.trim();
   if (!trimmed) {
     return false;
@@ -39,8 +42,9 @@ export function looksLikeMattermostTargetId(raw: string): boolean {
   if (/^(user|channel|group|mattermost):/i.test(trimmed)) {
     return true;
   }
-  if (/^[@#]/.test(trimmed)) {
+  if (trimmed.startsWith("@")) {
     return true;
   }
-  return /^[a-z0-9]{8,}$/i.test(trimmed);
+  // Mattermost IDs: 26-char alnum, or DM channels like "abc123__xyz789" (53 chars)
+  return /^[a-z0-9]{26}$/i.test(trimmed) || /^[a-z0-9]{26}__[a-z0-9]{26}$/i.test(trimmed);
 }

extensions/mattermost/src/types.ts

@@ -70,6 +70,10 @@ export type MattermostAccountConfig = {
     /** Explicit callback URL (e.g. behind reverse proxy). */
     callbackUrl?: string;
   };
+  interactions?: {
+    /** External base URL used for Mattermost interaction callbacks. */
+    callbackBaseUrl?: string;
+  };
 };
 
 export type MattermostConfig = {

extensions/slack/src/channel.test.ts

@@ -182,4 +182,53 @@ describe("slackPlugin config", () => {
     expect(configured).toBe(false);
     expect(snapshot?.configured).toBe(false);
   });
+
+  it("does not mark partial configured-unavailable token status as configured", async () => {
+    const snapshot = await slackPlugin.status?.buildAccountSnapshot?.({
+      account: {
+        accountId: "default",
+        name: "Default",
+        enabled: true,
+        configured: false,
+        botTokenStatus: "configured_unavailable",
+        appTokenStatus: "missing",
+        botTokenSource: "config",
+        appTokenSource: "none",
+        config: {},
+      } as never,
+      cfg: {} as OpenClawConfig,
+      runtime: undefined,
+    });
+
+    expect(snapshot?.configured).toBe(false);
+    expect(snapshot?.botTokenStatus).toBe("configured_unavailable");
+    expect(snapshot?.appTokenStatus).toBe("missing");
+  });
+
+  it("keeps HTTP mode signing-secret unavailable accounts configured in snapshots", async () => {
+    const snapshot = await slackPlugin.status?.buildAccountSnapshot?.({
+      account: {
+        accountId: "default",
+        name: "Default",
+        enabled: true,
+        configured: true,
+        mode: "http",
+        botTokenStatus: "available",
+        signingSecretStatus: "configured_unavailable",
+        botTokenSource: "config",
+        signingSecretSource: "config",
+        config: {
+          mode: "http",
+          botToken: "xoxb-http",
+          signingSecret: { source: "env", provider: "default", id: "SLACK_SIGNING_SECRET" },
+        },
+      } as never,
+      cfg: {} as OpenClawConfig,
+      runtime: undefined,
+    });
+
+    expect(snapshot?.configured).toBe(true);
+    expect(snapshot?.botTokenStatus).toBe("available");
+    expect(snapshot?.signingSecretStatus).toBe("configured_unavailable");
+  });
 });

extensions/slack/src/channel.ts

@@ -7,6 +7,7 @@ import {
   formatPairingApproveHint,
   getChatChannelMeta,
   handleSlackMessageAction,
+  inspectSlackAccount,
   listSlackMessageActions,
   listSlackAccountIds,
   listSlackDirectoryGroupsFromConfig,
@@ -16,6 +17,8 @@ import {
   normalizeAccountId,
   normalizeSlackMessagingTarget,
   PAIRING_APPROVED_MESSAGE,
+  projectCredentialSnapshotFields,
+  resolveConfiguredFromRequiredCredentialStatuses,
   resolveDefaultSlackAccountId,
   resolveSlackAccount,
   resolveSlackReplyToMode,
@@ -131,6 +134,7 @@ export const slackPlugin: ChannelPlugin<ResolvedSlackAccount> = {
   config: {
     listAccountIds: (cfg) => listSlackAccountIds(cfg),
     resolveAccount: (cfg, accountId) => resolveSlackAccount({ cfg, accountId }),
+    inspectAccount: (cfg, accountId) => inspectSlackAccount({ cfg, accountId }),
     defaultAccountId: (cfg) => resolveDefaultSlackAccountId(cfg),
     setAccountEnabled: ({ cfg, accountId, enabled }) =>
       setAccountEnabledInConfigSection({
@@ -428,14 +432,23 @@ export const slackPlugin: ChannelPlugin<ResolvedSlackAccount> = {
       return await getSlackRuntime().channel.slack.probeSlack(token, timeoutMs);
     },
     buildAccountSnapshot: ({ account, runtime, probe }) => {
-      const configured = isSlackAccountConfigured(account);
+      const mode = account.config.mode ?? "socket";
+      const configured =
+        (mode === "http"
+          ? resolveConfiguredFromRequiredCredentialStatuses(account, [
+              "botTokenStatus",
+              "signingSecretStatus",
+            ])
+          : resolveConfiguredFromRequiredCredentialStatuses(account, [
+              "botTokenStatus",
+              "appTokenStatus",
+            ])) ?? isSlackAccountConfigured(account);
       return {
         accountId: account.accountId,
         name: account.name,
         enabled: account.enabled,
         configured,
-        botTokenSource: account.botTokenSource,
-        appTokenSource: account.appTokenSource,
+        ...projectCredentialSnapshotFields(account),
         running: runtime?.running ?? false,
         lastStartAt: runtime?.lastStartAt ?? null,
         lastStopAt: runtime?.lastStopAt ?? null,

extensions/telegram/src/channel.ts

@@ -7,6 +7,7 @@ import {
   deleteAccountFromConfigSection,
   formatPairingApproveHint,
   getChatChannelMeta,
+  inspectTelegramAccount,
   listTelegramAccountIds,
   listTelegramDirectoryGroupsFromConfig,
   listTelegramDirectoryPeersFromConfig,
@@ -17,6 +18,8 @@ import {
   PAIRING_APPROVED_MESSAGE,
   parseTelegramReplyToMessageId,
   parseTelegramThreadId,
+  projectCredentialSnapshotFields,
+  resolveConfiguredFromCredentialStatuses,
   resolveDefaultTelegramAccountId,
   resolveAllowlistProviderRuntimeGroupPolicy,
   resolveDefaultGroupPolicy,
@@ -43,7 +46,7 @@ function findTelegramTokenOwnerAccountId(params: {
   const normalizedAccountId = normalizeAccountId(params.accountId);
   const tokenOwners = new Map<string, string>();
   for (const id of listTelegramAccountIds(params.cfg)) {
-    const account = resolveTelegramAccount({ cfg: params.cfg, accountId: id });
+    const account = inspectTelegramAccount({ cfg: params.cfg, accountId: id });
     const token = (account.token ?? "").trim();
     if (!token) {
       continue;
@@ -122,6 +125,7 @@ export const telegramPlugin: ChannelPlugin<ResolvedTelegramAccount, TelegramProb
   config: {
     listAccountIds: (cfg) => listTelegramAccountIds(cfg),
     resolveAccount: (cfg, accountId) => resolveTelegramAccount({ cfg, accountId }),
+    inspectAccount: (cfg, accountId) => inspectTelegramAccount({ cfg, accountId }),
     defaultAccountId: (cfg) => resolveDefaultTelegramAccountId(cfg),
     setAccountEnabled: ({ cfg, accountId, enabled }) =>
       setAccountEnabledInConfigSection({
@@ -416,6 +420,7 @@ export const telegramPlugin: ChannelPlugin<ResolvedTelegramAccount, TelegramProb
       return { ...audit, unresolvedGroups, hasWildcardUnmentionedGroups };
     },
     buildAccountSnapshot: ({ account, cfg, runtime, probe, audit }) => {
+      const configuredFromStatus = resolveConfiguredFromCredentialStatuses(account);
       const ownerAccountId = findTelegramTokenOwnerAccountId({
         cfg,
         accountId: account.accountId,
@@ -426,7 +431,8 @@ export const telegramPlugin: ChannelPlugin<ResolvedTelegramAccount, TelegramProb
             ownerAccountId,
           })
         : null;
-      const configured = Boolean(account.token?.trim()) && !ownerAccountId;
+      const configured =
+        (configuredFromStatus ?? Boolean(account.token?.trim())) && !ownerAccountId;
       const groups =
         cfg.channels?.telegram?.accounts?.[account.accountId]?.groups ??
         cfg.channels?.telegram?.groups;
@@ -440,7 +446,7 @@ export const telegramPlugin: ChannelPlugin<ResolvedTelegramAccount, TelegramProb
         name: account.name,
         enabled: account.enabled,
         configured,
-        tokenSource: account.tokenSource,
+        ...projectCredentialSnapshotFields(account),
         running: runtime?.running ?? false,
         lastStartAt: runtime?.lastStartAt ?? null,
         lastStopAt: runtime?.lastStopAt ?? null,

pnpm-lock.yaml

@@ -553,8 +553,8 @@ importers:
         specifier: 3.0.0
         version: 3.0.0
       dompurify:
-        specifier: ^3.3.1
-        version: 3.3.1
+        specifier: ^3.3.2
+        version: 3.3.2
       lit:
         specifier: ^3.3.2
         version: 3.3.2
@@ -3820,8 +3820,9 @@ packages:
     resolution: {integrity: sha512-cgwlv/1iFQiFnU96XXgROh8xTeetsnJiDsTc7TYCLFd9+/WNkIqPTxiM/8pSd8VIrhXGTf1Ny1q1hquVqDJB5w==}
     engines: {node: '>= 4'}
 
-  dompurify@3.3.1:
-    resolution: {integrity: sha512-qkdCKzLNtrgPFP1Vo+98FRzJnBRGe4ffyCea9IwHB1fyxPOeNTHpLKYGd4Uk9xvNoH0ZoOjwZxNptyMwqrId1Q==}
+  dompurify@3.3.2:
+    resolution: {integrity: sha512-6obghkliLdmKa56xdbLOpUZ43pAR6xFy1uOrxBaIDjT+yaRuuybLjGS9eVBoSR/UPU5fq3OXClEHLJNGvbxKpQ==}
+    engines: {node: '>=20'}
 
   domutils@3.2.2:
     resolution: {integrity: sha512-6kZKyUajlDuqlHKVX1w7gyslj9MPIXzIFiz/rGu35uC1wMi+kMhQwGhl4lt9unC9Vb9INnY9Z3/ZA3+FhASLaw==}
@@ -9885,7 +9886,7 @@ snapshots:
     dependencies:
       domelementtype: 2.3.0
 
-  dompurify@3.3.1:
+  dompurify@3.3.2:
     optionalDependencies:
       '@types/trusted-types': 2.0.7
 

skills/nano-banana-pro/SKILL.md

@@ -50,9 +50,16 @@ API key
 - `GEMINI_API_KEY` env var
 - Or set `skills."nano-banana-pro".apiKey` / `skills."nano-banana-pro".env.GEMINI_API_KEY` in `~/.openclaw/openclaw.json`
 
+Specific aspect ratio (optional)
+
+```bash
+uv run {baseDir}/scripts/generate_image.py --prompt "portrait photo" --filename "output.png" --aspect-ratio 9:16
+```
+
 Notes
 
 - Resolutions: `1K` (default), `2K`, `4K`.
+- Aspect ratios: `1:1`, `2:3`, `3:2`, `3:4`, `4:3`, `4:5`, `5:4`, `9:16`, `16:9`, `21:9`. Without `--aspect-ratio` / `-a`, the model picks freely - use this flag for avatars, profile pics, or consistent batch generation.
 - Use timestamps in filenames: `yyyy-mm-dd-hh-mm-ss-name.png`.
 - The script prints a `MEDIA:` line for OpenClaw to auto-attach on supported chat providers.
 - Do not read the image back; report the saved path only.

skills/nano-banana-pro/scripts/generate_image.py

@@ -21,6 +21,19 @@ import os
 import sys
 from pathlib import Path
 
+SUPPORTED_ASPECT_RATIOS = [
+    "1:1",
+    "2:3",
+    "3:2",
+    "3:4",
+    "4:3",
+    "4:5",
+    "5:4",
+    "9:16",
+    "16:9",
+    "21:9",
+]
+
 
 def get_api_key(provided_key: str | None) -> str | None:
     """Get API key from argument first, then environment."""
@@ -56,6 +69,12 @@ def main():
         default="1K",
         help="Output resolution: 1K (default), 2K, or 4K"
     )
+    parser.add_argument(
+        "--aspect-ratio", "-a",
+        choices=SUPPORTED_ASPECT_RATIOS,
+        default=None,
+        help=f"Output aspect ratio (default: model decides). Options: {', '.join(SUPPORTED_ASPECT_RATIOS)}"
+    )
     parser.add_argument(
         "--api-key", "-k",
         help="Gemini API key (overrides GEMINI_API_KEY env var)"
@@ -127,14 +146,17 @@ def main():
         print(f"Generating image with resolution {output_resolution}...")
 
     try:
+        # Build image config with optional aspect ratio
+        image_cfg_kwargs = {"image_size": output_resolution}
+        if args.aspect_ratio:
+            image_cfg_kwargs["aspect_ratio"] = args.aspect_ratio
+
         response = client.models.generate_content(
             model="gemini-3-pro-image-preview",
             contents=contents,
             config=types.GenerateContentConfig(
                 response_modalities=["TEXT", "IMAGE"],
-                image_config=types.ImageConfig(
-                    image_size=output_resolution
-                )
+                image_config=types.ImageConfig(**image_cfg_kwargs)
             )
         )
 

src/agents/anthropic-payload-log.test.ts

@@ -0,0 +1,49 @@
+import crypto from "node:crypto";
+import type { StreamFn } from "@mariozechner/pi-agent-core";
+import { describe, expect, it } from "vitest";
+import { createAnthropicPayloadLogger } from "./anthropic-payload-log.js";
+
+describe("createAnthropicPayloadLogger", () => {
+  it("redacts image base64 payload data before writing logs", async () => {
+    const lines: string[] = [];
+    const logger = createAnthropicPayloadLogger({
+      env: { OPENCLAW_ANTHROPIC_PAYLOAD_LOG: "1" },
+      writer: {
+        filePath: "memory",
+        write: (line) => lines.push(line),
+      },
+    });
+    expect(logger).not.toBeNull();
+
+    const payload = {
+      messages: [
+        {
+          role: "user",
+          content: [
+            {
+              type: "image",
+              source: { type: "base64", media_type: "image/png", data: "QUJDRA==" },
+            },
+          ],
+        },
+      ],
+    };
+    const streamFn: StreamFn = ((_, __, options) => {
+      options?.onPayload?.(payload);
+      return {} as never;
+    }) as StreamFn;
+
+    const wrapped = logger?.wrapStreamFn(streamFn);
+    await wrapped?.({ api: "anthropic-messages" } as never, { messages: [] } as never, {});
+
+    const event = JSON.parse(lines[0]?.trim() ?? "{}") as Record<string, unknown>;
+    const message = ((event.payload as { messages?: unknown[] } | undefined)?.messages ??
+      []) as Array<Record<string, unknown>>;
+    const source = (((message[0]?.content as Array<Record<string, unknown>> | undefined) ?? [])[0]
+      ?.source ?? {}) as Record<string, unknown>;
+    expect(source.data).toBe("<redacted>");
+    expect(source.bytes).toBe(4);
+    expect(source.sha256).toBe(crypto.createHash("sha256").update("QUJDRA==").digest("hex"));
+    expect(event.payloadDigest).toBeDefined();
+  });
+});

src/agents/anthropic-payload-log.ts

@@ -7,6 +7,7 @@ import { createSubsystemLogger } from "../logging/subsystem.js";
 import { resolveUserPath } from "../utils.js";
 import { parseBooleanValue } from "../utils/boolean.js";
 import { safeJsonStringify } from "../utils/safe-json.js";
+import { redactImageDataForDiagnostics } from "./payload-redaction.js";
 import { getQueuedFileWriter, type QueuedFileWriter } from "./queued-file-writer.js";
 
 type PayloadLogStage = "request" | "usage";
@@ -103,6 +104,7 @@ export function createAnthropicPayloadLogger(params: {
   modelId?: string;
   modelApi?: string | null;
   workspaceDir?: string;
+  writer?: PayloadLogWriter;
 }): AnthropicPayloadLogger | null {
   const env = params.env ?? process.env;
   const cfg = resolvePayloadLogConfig(env);
@@ -110,7 +112,7 @@ export function createAnthropicPayloadLogger(params: {
     return null;
   }
 
-  const writer = getWriter(cfg.filePath);
+  const writer = params.writer ?? getWriter(cfg.filePath);
   const base: Omit<PayloadLogEvent, "ts" | "stage"> = {
     runId: params.runId,
     sessionId: params.sessionId,
@@ -135,12 +137,13 @@ export function createAnthropicPayloadLogger(params: {
         return streamFn(model, context, options);
       }
       const nextOnPayload = (payload: unknown) => {
+        const redactedPayload = redactImageDataForDiagnostics(payload);
         record({
           ...base,
           ts: new Date().toISOString(),
           stage: "request",
-          payload,
-          payloadDigest: digest(payload),
+          payload: redactedPayload,
+          payloadDigest: digest(redactedPayload),
         });
         options?.onPayload?.(payload);
       };

src/agents/auth-profiles/oauth.openai-codex-refresh-fallback.test.ts

@@ -0,0 +1,141 @@
+import fs from "node:fs/promises";
+import os from "node:os";
+import path from "node:path";
+import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
+import { captureEnv } from "../../test-utils/env.js";
+import { resolveApiKeyForProfile } from "./oauth.js";
+import {
+  clearRuntimeAuthProfileStoreSnapshots,
+  ensureAuthProfileStore,
+  saveAuthProfileStore,
+} from "./store.js";
+import type { AuthProfileStore } from "./types.js";
+
+const { getOAuthApiKeyMock } = vi.hoisted(() => ({
+  getOAuthApiKeyMock: vi.fn(async () => {
+    throw new Error("Failed to extract accountId from token");
+  }),
+}));
+
+vi.mock("@mariozechner/pi-ai", async () => {
+  const actual = await vi.importActual<typeof import("@mariozechner/pi-ai")>("@mariozechner/pi-ai");
+  return {
+    ...actual,
+    getOAuthApiKey: getOAuthApiKeyMock,
+    getOAuthProviders: () => [
+      { id: "openai-codex", envApiKey: "OPENAI_API_KEY", oauthTokenEnv: "OPENAI_OAUTH_TOKEN" },
+      { id: "anthropic", envApiKey: "ANTHROPIC_API_KEY", oauthTokenEnv: "ANTHROPIC_OAUTH_TOKEN" },
+    ],
+  };
+});
+
+function createExpiredOauthStore(params: {
+  profileId: string;
+  provider: string;
+  access?: string;
+}): AuthProfileStore {
+  return {
+    version: 1,
+    profiles: {
+      [params.profileId]: {
+        type: "oauth",
+        provider: params.provider,
+        access: params.access ?? "cached-access-token",
+        refresh: "refresh-token",
+        expires: Date.now() - 60_000,
+      },
+    },
+  };
+}
+
+describe("resolveApiKeyForProfile openai-codex refresh fallback", () => {
+  const envSnapshot = captureEnv([
+    "OPENCLAW_STATE_DIR",
+    "OPENCLAW_AGENT_DIR",
+    "PI_CODING_AGENT_DIR",
+  ]);
+  let tempRoot = "";
+  let agentDir = "";
+
+  beforeEach(async () => {
+    getOAuthApiKeyMock.mockClear();
+    clearRuntimeAuthProfileStoreSnapshots();
+    tempRoot = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-codex-refresh-fallback-"));
+    agentDir = path.join(tempRoot, "agents", "main", "agent");
+    await fs.mkdir(agentDir, { recursive: true });
+    process.env.OPENCLAW_STATE_DIR = tempRoot;
+    process.env.OPENCLAW_AGENT_DIR = agentDir;
+    process.env.PI_CODING_AGENT_DIR = agentDir;
+  });
+
+  afterEach(async () => {
+    clearRuntimeAuthProfileStoreSnapshots();
+    envSnapshot.restore();
+    await fs.rm(tempRoot, { recursive: true, force: true });
+  });
+
+  it("falls back to cached access token when openai-codex refresh fails on accountId extraction", async () => {
+    const profileId = "openai-codex:default";
+    saveAuthProfileStore(
+      createExpiredOauthStore({
+        profileId,
+        provider: "openai-codex",
+      }),
+      agentDir,
+    );
+
+    const result = await resolveApiKeyForProfile({
+      store: ensureAuthProfileStore(agentDir),
+      profileId,
+      agentDir,
+    });
+
+    expect(result).toEqual({
+      apiKey: "cached-access-token",
+      provider: "openai-codex",
+      email: undefined,
+    });
+    expect(getOAuthApiKeyMock).toHaveBeenCalledTimes(1);
+  });
+
+  it("keeps throwing for non-codex providers on the same refresh error", async () => {
+    const profileId = "anthropic:default";
+    saveAuthProfileStore(
+      createExpiredOauthStore({
+        profileId,
+        provider: "anthropic",
+      }),
+      agentDir,
+    );
+
+    await expect(
+      resolveApiKeyForProfile({
+        store: ensureAuthProfileStore(agentDir),
+        profileId,
+        agentDir,
+      }),
+    ).rejects.toThrow(/OAuth token refresh failed for anthropic/);
+  });
+
+  it("does not use fallback for unrelated openai-codex refresh errors", async () => {
+    const profileId = "openai-codex:default";
+    saveAuthProfileStore(
+      createExpiredOauthStore({
+        profileId,
+        provider: "openai-codex",
+      }),
+      agentDir,
+    );
+    getOAuthApiKeyMock.mockImplementationOnce(async () => {
+      throw new Error("invalid_grant");
+    });
+
+    await expect(
+      resolveApiKeyForProfile({
+        store: ensureAuthProfileStore(agentDir),
+        profileId,
+        agentDir,
+      }),
+    ).rejects.toThrow(/OAuth token refresh failed for openai-codex/);
+  });
+});

src/agents/auth-profiles/oauth.ts

@@ -10,6 +10,7 @@ import { withFileLock } from "../../infra/file-lock.js";
 import { refreshQwenPortalCredentials } from "../../providers/qwen-portal-oauth.js";
 import { resolveSecretRefString, type SecretRefResolveCache } from "../../secrets/resolve.js";
 import { refreshChutesTokens } from "../chutes-oauth.js";
+import { normalizeProviderId } from "../model-selection.js";
 import { AUTH_STORE_LOCK_OPTIONS, log } from "./constants.js";
 import { resolveTokenExpiryState } from "./credential-state.js";
 import { formatAuthDoctorHint } from "./doctor.js";
@@ -87,6 +88,27 @@ function buildOAuthProfileResult(params: {
   });
 }
 
+function extractErrorMessage(error: unknown): string {
+  return error instanceof Error ? error.message : String(error);
+}
+
+function shouldUseOpenaiCodexRefreshFallback(params: {
+  provider: string;
+  credentials: OAuthCredentials;
+  error: unknown;
+}): boolean {
+  if (normalizeProviderId(params.provider) !== "openai-codex") {
+    return false;
+  }
+  const message = extractErrorMessage(params.error);
+  if (!/extract\s+accountid\s+from\s+token/i.test(message)) {
+    return false;
+  }
+  return (
+    typeof params.credentials.access === "string" && params.credentials.access.trim().length > 0
+  );
+}
+
 type ResolveApiKeyForProfileParams = {
   cfg?: OpenClawConfig;
   store: AuthProfileStore;
@@ -434,7 +456,25 @@ export async function resolveApiKeyForProfile(
       }
     }
 
-    const message = error instanceof Error ? error.message : String(error);
+    if (
+      shouldUseOpenaiCodexRefreshFallback({
+        provider: cred.provider,
+        credentials: cred,
+        error,
+      })
+    ) {
+      log.warn("openai-codex oauth refresh failed; using cached access token fallback", {
+        profileId,
+        provider: cred.provider,
+      });
+      return buildApiKeyProfileResult({
+        apiKey: cred.access,
+        provider: cred.provider,
+        email: cred.email,
+      });
+    }
+
+    const message = extractErrorMessage(error);
     const hint = formatAuthDoctorHint({
       cfg,
       store: refreshedStore,