Add chat-send first visible assistant output telemetry in the Control UI, plus Gateway diagnostics correlation attributes for chat.send dispatch spans. Verified with focused UI/Gateway tests, tsgo, oxlint, autoreview, PR checks, and Testbox-through-Crabbox check:changed.
Reduce Control UI draft-update work by guarding chat composer controls while keeping locale, session, model, settings, and busy-state invalidation. Verification: focused UI tests, format/lint/typecheck, autoreview clean, and changed gate tbx_01kt12rgjs8c077p2s0wmcsbyf.
Reduce Control UI draft-update work by guarding transcript group rendering while preserving assistant attachment availability invalidation. Verification: focused UI tests, format/lint/typecheck, autoreview clean, and changed gate tbx_01kt11qyc20ejbsbt8kd79bamx.
Revert release-time extension lane isolation for Telegram and memory, and make Telegram timer-flush tests wait for async side effects after manually firing timers.
Verification:
- pnpm test:serial extensions/telegram/src/bot.create-telegram-bot.channel-post-media.test.ts extensions/telegram/src/bot.create-telegram-bot.media-group-skip-warning.test.ts extensions/telegram/src/bot.media.stickers-and-fragments.e2e.test.ts extensions/telegram/src/bot.media.downloads-media-file-path-no-file-download.e2e.test.ts test/vitest-scoped-config.test.ts
- pnpm exec oxfmt --check on touched files
- git diff --check on touched files
Reduce Control UI typing work by avoiding slash-menu rerenders for ordinary non-command drafts. Verification: focused UI tests, format/lint/typecheck, autoreview clean, and changed gate tbx_01kt1086xrbxfzm85vynsf25hq.
Debounce draft-only Control UI chat composer persistence while snapshotting pending drafts so session changes and teardown still flush the correct state. Verified with focused UI lifecycle/composer tests, format, oxlint, tsgo core/UI test, clean autoreview, and PR checks.
* fix(diagnostics): clear embedded-run activity when recovery declares lane idle
Stuck-session recovery transitions a lane to idle via the recovery
coordinator, but only mutated the session-state store. When an aborted
embedded run was removed without markDiagnosticEmbeddedRunEnded, the
activity store kept hasActiveEmbeddedRun set, so the liveness sweep
reported idle/embedded_run and isIdleQueuedRecoverableSessionStall
re-triggered recovery indefinitely.
Reconcile the activity store from the authoritative idle declaration by
clearing the session's embedded-run owners. The existing generation
guard already excludes any newer run that re-armed activity, so a live
requeued run is preserved.
* fix(diagnostics): reconcile tool/model activity on authoritative idle cleanup
clearDiagnosticEmbeddedRunActivityForSession (renamed from
clearDiagnosticEmbeddedRunsForSession) now clears the aborted run's tool and
model markers alongside the embedded-run owners, matching the default
markDiagnosticEmbeddedRunEnded teardown. Clearing only the owner set left the
lane as idle + orphaned tool/model activity, which
isIdleQueuedRecoverableSessionStall still treats as recoverable while work is
queued, so the liveness sweep kept re-triggering recovery instead of converging.
Adds regression cases with stale tool and model markers plus queued work.
* test(phone-control): align service mocks with keyed store API
* fix(diagnostics): preserve rearmed recovery activity
* fix(diagnostics): clear recovered owner markers
* fix(diagnostics): clear recovered embedded work keys
* fix(diagnostics): ignore stale same-key recovery owners
* fix(diagnostics): preserve same-session recovery rearm
* fix(diagnostics): ignore stale queued activity starts
* fix(diagnostics): record recovery cutoffs for empty activity
* fix(diagnostics): preserve fresh recovery markers
* fix(diagnostics): prune stale activity before fresh recovery block
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* fix(agents): clear legacy auto fallback pins
* fix(agents): repair legacy auto-fallback test mock and tighten review feedback
Add hasLegacyAutoFallbackWithoutOrigin to the live-model-switch agent-scope mock so the agents-core lane runs, simplify the redundant hasSessionModelOverride guard, use a single source of truth for the legacy-pin staleness check with a comment on the load-bearing modelKey guard, and add preservation/edge-case/guard regression coverage. Rename the misleading primary-probe agent test.
* style(agents): format rebased fallback fix
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Make first Control UI chat sends visibly queue during pending model saves, preserve early streaming deltas that arrive before chat.send ACK, and keep model-wait queued prompts scoped/retryable across session switches.
Make Workboard cards compact by moving expanded task/run metadata, proof, diagnostics, worker logs, automation, protocol state, events, and operator notes into a detail drawer.
Keep execution state simple and safe: active, linked, and archived cards avoid duplicate start paths; stale task cache is ignored when session lifecycle is authoritative; recent proof/events stay visible; dispatcher capacity distinguishes unclaimed review cards from claimed cards.
* fix(cron): include job name in single-job run history
The cron.runs gateway handler enriches log entries with jobName in the all-jobs scope, but the single-job scope did not pass any job-name lookup into the SQLite run-log reader. Entries returned for one job could therefore reach Control UI without jobName, making the run-history title fall back to the raw job id.
Build a one-entry jobNameById map for the current job and pass it through the same reader enrichment path used by all-jobs history. If the job no longer exists, the map stays undefined and existing fallback behavior is unchanged.
* test(cron): cover single-job run history job name enrichment
Asserts that readCronRunLogEntriesPage stamps a supplied jobNameById map onto single-job page entries, matching the gateway data shape used for both all-jobs and single-job cron.runs responses.
Addresses review feedback on #88294.
* test(cron): preserve nullable tool schema validation
* test(cron): assert runtime nullable tool schema
* test(cron): refresh prompt snapshots
---------
Co-authored-by: Kip Claw <kip@kipclaw.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Routes Mattermost send attachments through the upload path so local file paths and structured attachment media are uploaded instead of being posted as plain text. Preserves scoped media access for local uploads, rejects unsupported or ambiguous attachment payloads, and keeps HTTP media fallback behavior.
Fixes#87930.
Proof:
- autoreview clean
- node scripts/run-vitest.mjs extensions/mattermost/src/channel.test.ts extensions/mattermost/src/channel.message-adapter.test.ts extensions/mattermost/src/mattermost/send.test.ts src/infra/outbound/message-action-params.test.ts src/infra/outbound/outbound-send-service.test.ts src/infra/outbound/message-action-runner.media.test.ts src/media/load-options.test.ts
- pnpm prompt:snapshots:check
- GitHub Actions completed with no pending/failing checks for head 2a65cbb1ee
Fail closed when bundled trusted tool policy registry, registration, owner id, evaluation, or decision reads fail, so malformed trusted-policy state cannot crash diagnostics or accidentally allow a tool call.
Route before-tool-call diagnostics through guarded trusted-policy readers and keep healthy no-op policy behavior unchanged.
Add focused host-hook contract and before-tool-call e2e coverage for the new fail-closed paths.
PR: #88394
HTTP auth challenges (basic, digest, negotiate) only fire the browser's
native credentials dialog when the response comes straight from the
network. Service worker responses bypass the WWW-Authenticate flow, so
reverse-proxy deployments with HTTP auth in front of the gateway show
a bare 401 after the browser's HTTP-auth memory cache expires (e.g. on
full browser restart) — forcing users to clear site data to recover.
Skip event.request.mode === "navigate" so the browser handles those
requests natively. Offline navigation of the app shell is lost, but
the SPA cannot function without network (all API calls go to the
network), so the trade-off is acceptable.
Refs: #85939, #71669, #53274
Adds broad inline comments and JSDoc for CLI, cron, outbound/channel, plugin SDK, ACP, shared helpers, net policy, and related utility contracts. Proof: git diff --check on latest exact head plus focused cron tests passed; CI had no failing checks observed before merge attempt.
Fixes#88521.
Expose finalized inbound reply metadata on plugin-visible hook payloads so before_dispatch and message hooks can implement reply-aware behavior without channel-specific workarounds.
Return unknown config.schema.lookup paths as an in-band agent gateway tool result instead of throwing into channel warning surfaces.
The direct gateway RPC still reports INVALID_REQUEST, preserving the existing protocol contract, while the agent-facing gateway tool returns schema_path_not_found for exploratory misses.
Fixes#88813.
Thanks @ksj3421.
Reported by @cjalden.
* test(agents): include Ollama in small live model matrix
* test: avoid Ollama cloud key in local live runs
* test: recognize Ollama env secret refs
* test: type Ollama live key fixtures
* test: prevent Ollama cloud auth in local live probes
* test: preserve equivalent Ollama live credentials
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Make the iOS app a universal iPhone+iPad app by targeting device family 1,2 in the XcodeGen source of truth.
Update iOS docs and App Store metadata so user-facing copy no longer describes the app as iPhone-only.
Verification:
- git diff --check
- cd apps/ios && xcodegen generate
- xcodebuild -project apps/ios/OpenClaw.xcodeproj -scheme OpenClaw -configuration Debug -destination 'platform=iOS Simulator,id=410B81D3-784E-4A01-B69C-490B79EAFCEA' CODE_SIGNING_ALLOWED=NO build
- GitHub CI: Real behavior proof, macos-swift, macos-node, check-docs, preflight, security-fast, actionlint, no-tabs, dependency-guard, OpenGrep
Thanks @EmpX2025.
Restore TUI switch-back adoption for backgrounded visible chat-send runs by surfacing a bounded `chat.history.inFlightRun` snapshot.
The snapshot keeps the run id even when buffered text is empty or over budget, filters live text through the same projection path as streaming chat, scopes bare global history to the default agent, and excludes hidden internal agent runs.
Proof:
- node scripts/run-vitest.mjs run src/gateway/chat-abort.test.ts src/tui/tui-session-actions.test.ts
- node scripts/run-tsgo.mjs -p tsconfig.core.json
- pnpm --silent exec oxfmt --check src/gateway/chat-abort.ts src/gateway/chat-abort.test.ts src/gateway/server-methods/chat.ts src/tui/tui-session-actions.ts src/tui/tui-session-actions.test.ts
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
- CI: Real behavior proof, TUI PTY, dependency guard, OpenGrep precise diff, workflow sanity passed on PR head 2b8bf5f214.
Co-authored-by: William Liu <william@williamliu.ai>
Respect explicit PI/OpenClaw runtime policy when deciding whether Codex plugin diagnostics are actionable.
Diagnostics now use the resolved OpenAI route: intentional PI and custom OpenAI-compatible routes suppress only the missing `plugins.entries.codex` noise, while enabled/stale Codex policy still warns.
Proof: focused doctor/config/agent routing Vitest coverage, full lint, test types, dependency checks, isolated live doctor configs, autoreview clean, and GitHub CI green at c5a84de4ca.
Fixes#88706.
Co-authored-by: Elfka Toruviel <aeb31988340aa87b@toruviel.online>
Fixes#88333
Preserves contributor workspace contents when an attested workspace disappears or is partially regenerated, and clears OpenClaw-owned attestation state on delete/reset/uninstall.
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
Resolve gateway auth SecretRef targets in status deep audit.
The static secret target coverage now includes gateway auth and remote token/password keys for both status and security audit scans. Focused status/secret-target tests passed, Auto Review reported no actionable findings, and CI is running on rebased head 41b052a181.
Fixes#87815
* fix(config): skip state-dir dotenv values that are unresolved shell references
readStateDirDotEnvVarsFromStateDir accepted any non-empty value from the
state-dir .env file and passed it into the managed service env. When a value
contains an unresolved shell variable reference such as "${SUPERMEMORY_KEY}"
or "$MY_VAR", dotenv preserves the literal string. The value then reaches
the LaunchAgent/systemd wrapper as a single-quoted literal, so the credential
is never resolved.
Add containsUnresolvedShellReference() and skip any value matching
$IDENTIFIER, ${...}, or $(...) in parseStateDirDotEnvContent(). Real credential
values (e.g. "sm_abc123") are unaffected.
Fixes#88274
* fix(config): narrow shell-reference detector to whole-value patterns only
The previous /$[\w{(]/ regex matched any value containing $ followed by
a word character, which would incorrectly drop real credentials that merely
contain a dollar sign (e.g. a password like abc$2!xyz).
Replace with isUnresolvedShellReference() that only matches values whose
ENTIRE content is a recognised reference form:
- $VAR_NAME (simple reference)
- ${VAR_NAME} (brace-form reference)
- $(command) (command substitution)
Add a regression test that verifies dollar-bearing real secrets are kept.
* fix(config): use letter/underscore-anchored pattern to avoid matching dollar-numbers
$100, $2, etc. are NOT shell variable references — shell variable names must
begin with a letter or underscore. The previous /^$[\w_]/ would match them.
Change to /^$[A-Za-z_]\w*$/ so only genuine named-variable references like
$MY_VAR are rejected. Dollar-number sequences are now preserved.
* fix(daemon): drop stale systemd env-file refs for skipped state-dir dotenv keys
When a state-dir .env value is an unresolved shell reference ($VAR/${VAR}/$(cmd))
the parser skips it from the managed environment. A prior install could have
written that literal reference into gateway.systemd.env; because the skipped key
no longer appeared in the incoming env or the managed-key removal sets, the stale
literal survived re-stage and could override fresh inline Environment= values.
Surface the skipped shell-reference keys from the state-dir dotenv parser and add
them to the systemd env-file managed-key removal set so re-staging strips the
obsolete literal while preserving operator-only secrets that were never managed
via state-dir .env. launchd regenerates its env file wholesale, so it is
unaffected.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(config): skip quoted shell parameter dotenv refs
* fix(config): preserve lowercase dollar-prefixed dotenv literals
* fix(daemon): clear stale unresolved systemd env refs
* fix(daemon): avoid re-staging unresolved file env refs
* fix(daemon): drop unresolved file env refs inline
* fix(daemon): drop inline-and-file unresolved env refs
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Preserve the active per-plugin managed npm project when npm-backed install validation blocks a candidate after npm has already mutated local state.
This snapshots package.json, package-lock.json, and node_modules before managed npm installs, restores that exact project state on failed validation, and rolls back staged npm-pack archives so blocked pack installs do not leave candidate debris.
Validation:
- OPENCLAW_VITEST_MAX_WORKERS=1 node scripts/run-vitest.mjs src/plugins/install.npm-spec.test.ts
- pnpm tsgo:core && pnpm tsgo:core:test
- node scripts/run-oxlint.mjs src/plugins/install.ts src/plugins/install.npm-spec.test.ts
- .agents/skills/autoreview/scripts/autoreview --mode local
- GitHub CI 26729255950
- Crabbox run_26e9f9f7591c
Thanks @zhuisDEV.
Co-authored-by: Brian <95547369+zhuisDEV@users.noreply.github.com>
Adds regression coverage for Google Vertex API-key model config planning when the credential comes from an env-backed auth profile. This keeps the planner-level guard around the Vertex static catalog rows that fixed#88816 on main.
Verification:
- `node scripts/run-vitest.mjs src/agents/models-config.applies-config-env-vars.test.ts extensions/google/provider-catalog.test.ts extensions/google/provider-models.test.ts`
- `./node_modules/.bin/oxfmt --check --threads=1 src/agents/models-config.applies-config-env-vars.test.ts extensions/ollama/src/stream.ts extensions/qa-lab/src/mantis/slack-desktop-smoke.runtime.ts extensions/qa-lab/src/mantis/telegram-desktop-builder.runtime.ts extensions/qa-lab/src/mantis/visual-task.runtime.ts`
- `git diff --check`
- `pnpm deadcode:dependencies`
CI note: PR CI had an unrelated `check-dependencies` failure for `ui/package.json: three`; the PR diff is one `src/agents` test file.
Refs #88816
Routes MiniMax OAuth device-code and token polling directly to account-hosted OAuth2 endpoints for global and CN regions, avoiding guarded-fetch cross-origin redirect body stripping. Keeps provider API base URLs unchanged and adds regression coverage for both endpoint pairs.
Proof: local minimax OAuth tests, oxfmt check, lint, autoreview clean, official MiniMax CLI/source check, live MiniMax endpoint probes, and CI run 26729242892 on 6bfe20eb06.
Co-authored-by: Matt Schleder <schledermatthew@gmail.com>
Fixes#88520.
Adds focused regression coverage for the embedded attempt trajectory recorder cleanup boundary so a stalled trajectory flush resolves after the cleanup timeout and logs pending write details instead of rejecting attempt cleanup.
Verification:
- node scripts/run-vitest.mjs src/agents/run-cleanup-timeout.test.ts
- git diff --check origin/main...origin/pr/88802
- PR CI green: https://github.com/openclaw/openclaw/actions/runs/26727232564
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
Retire isolated cron session MCP runtimes on timeout and dispose so orphaned MCP servers do not accumulate after cron cleanup. Bound MCP session disposal to 5 seconds and force-close hung transports, including streamable-HTTP DELETE hangs, to prefer gateway availability over unbounded teardown.
Fixes#87821.
PR: #87981.
Proof: latest Real behavior proof check passed after body fix; local autoreview clean with focused cron/gateway/MCP tests covering 108 tests.
Co-authored-by: 忻役 <xinyi@mininglamp.com>
Co-authored-by: Jerry-Xin <jerryxin0@gmail.com>
* refactor: move imessage monitor state to sqlite
* test: use OpenClaw temp root in iMessage state helper
* test: avoid pending promise lint in chat tests
* test: harden gateway ci flakes
* test: align session list merge expectation
Fixes#57376.
Hide placeholder agent store keys from sessions.list while preserving real agent-scoped sessions.
Co-authored-by: Alix-007 <li.long15@xydigit.com>
Preserve task and TaskFlow durability by persisting before in-memory registry mutation and surfacing explicit persistence failures instead of reporting fake success.
Adds non-throwing try-create runtime helpers while keeping existing throwing public create APIs compatible. Maintainer follow-up keeps task/TaskFlow sync repair bounded, prevents split task/delivery-state writes, and keeps CI green on the current base.
Thanks @Feelw00.
Roll both subagent token usage formatters over to the million unit when rounded thousands reach the next unit.
The original fix covers `formatTokenShort`, which feeds the subagent list usage line. The maintainer follow-up applies the same unit-boundary rule to compact subagent announcement stats, preserving that formatter's one-decimal style while preventing `1000.0k` output.
Verification:
- focused runtime probe for list and compact announce stats at 999,999 tokens
- `oxfmt --check` on touched formatter/test files
- `git diff --check origin/main..HEAD`
- `node scripts/run-tsgo.mjs -p test/tsconfig/tsconfig.core.test.json --incremental --tsBuildInfoFile .artifacts/tsgo-cache/core-test-pr88209.tsbuildinfo`
- autoreview local closeout clean
- exact-head CI passed for Real behavior proof, check-test-types, check-prod-types, check-guards, security-fast, and preflight
Known unrelated current-main reds at merge: `check-lint`, `checks-node-agentic-gateway-methods`, and `checks-node-agentic-control-plane-agent-chat`.
Co-authored-by: coder999999999 <coder999999999@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Skip the generic DeepSeek V4 OpenAI-compatible `thinking` payload wrapper for Microsoft Foundry fallback models. Foundry's OpenAI-compatible gateway rejects the non-standard top-level `thinking` argument, while the rest of the DeepSeek proxy path still keeps the wrapper.
Proof:
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main --parallel-tests "node scripts/run-vitest.mjs src/agents/embedded-agent-runner-extraparams.test.ts"
- node scripts/run-vitest.mjs src/agents/embedded-agent-runner-extraparams.test.ts passed, 130/130
- CI run 26681069909 passed for c950ac112e
Thanks @silvesterxm.
Stop memory-core dream diary fallback paths from persisting raw memory staging snippets or promotions into DREAMS.md when narrative generation times out, returns empty output, or fails in request-scoped runtime. Successful generated narratives are unchanged.
Maintainer fixup: align current gateway session-list tests with the full loadSessionEntry mock shape and model-derived context token behavior on main.
Fixes#88391
Co-authored-by: Alix-007 <li.long15@xydigit.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Cap the in-memory workspace bootstrap snapshot cache to 64 session keys so long-lived gateway processes do not retain one loaded bundle per distinct session key indefinitely. Older entries are evicted while active keys continue refreshing against the guarded workspace loader.
Verification:
- node scripts/run-vitest.mjs src/agents/bootstrap-cache.test.ts
PR: #88149
sanitizeTransportPayloadText() called text.replace() directly, so runtime-undefined content from malformed replay/error handling could crash embedded agent transport serialization with "Cannot read properties of undefined (reading 'replace')".
Return an empty string for non-string runtime payloads at the shared sanitizer boundary, preserving existing unpaired-surrogate cleanup for strings. Empty values still degrade through sanitizeNonEmptyTransportPayloadText() to "(no output)" where that non-empty fallback is required.
Proof:
- pnpm test src/agents/transport-stream-shared.test.ts
- pnpm exec oxfmt --check --threads=1 src/agents/transport-stream-shared.ts src/agents/transport-stream-shared.test.ts
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main --parallel-tests "pnpm test src/agents/transport-stream-shared.test.ts"
Fixes#60113
Co-authored-by: Pluviobyte <Pluviobyte@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Fix Nostr allowFrom npub normalization by returning the decoded hex string from nostr-tools instead of iterating the hex string as bytes.
Proof:
- node scripts/run-vitest.mjs extensions/nostr/src/nostr-bus.test.ts
- PR CI green at head 7c3433435b
Co-authored-by: DocNR <danieljwyler@gmail.com>
Use chat.history metadata to hydrate TUI and web startup state without the extra sessions.list refresh, with guards for aliases, stale active rows, blank-session defaults, and lightweight TUI usage metadata.
When a configured Google provider/model row had no explicit
but had a baseUrl set, the fallback defaulted to openai-completions,
causing Gemini requests to route through the OpenAI Responses
transport instead of the native @google/genai transport.
Made resolveConfiguredProviderDefaultApi provider-aware: for the
google provider, the default API is now google-generative-ai.
Root cause: the generic fallback assumed any provider with a baseUrl
should use openai-completions, which is incorrect for Google's native
Gemini API.
Co-authored-by: xin <1052326311+xin@users.noreply.github.com>
Preserve long Feishu streaming replies by falling oversized finals back to chunked message/static-card delivery instead of closing through an over-limit streaming CardKit payload.
Keeps late-final suppression after a streaming card closes, and uses markdown-aware chunking for static card fallback replies.
Fixes#88631.
Co-authored-by: Ted Li <tl2493@columbia.edu>
Keep native subagent spawns with `lightContext=true` and resolved isolated context out of context-engine pre-spawn preparation so they remain lightweight.
The normal isolated and forked context-engine lifecycle stays intact, and docs now call out the lightweight isolated exception.
Fixes#81214
Fix JSONL file-log hostnames getting pinned to `unknown` when the first hostname read returns an empty value. The logger now retries empty hostname reads and caches the first non-empty value, keeping the top-level `hostname` and `_meta.hostname` fields aligned.
Fixes#87258.
Thanks @lonexreb for the fix.
Verification:
- `node scripts/run-vitest.mjs src/logging/logger-redaction-behavior.test.ts src/logger.test.ts`
- `node_modules/.bin/oxfmt --check --threads=1 src/logging/logger.ts src/logging/logger-redaction-behavior.test.ts`
- `.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main`
- `gh pr checks 88131 --watch=false`
Co-authored-by: lonexreb <reach2shubhankar@gmail.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Expose session status route context so agents can distinguish session origin, active live route, and persisted delivery route.
Add maintainer fixup to keep active route metadata on the real live run key when policy and run keys differ.
Thanks @nxmxbbd.
Closes#84544
Preserve the current container-related service opt-in environment when regenerating daemon service files, while continuing to drop stale or arbitrary `OPENCLAW_*` variables.
Verification:
- `git diff --check`
- `node scripts/run-vitest.mjs src/commands/daemon-install-helpers.test.ts -t "operator opt-in allowlist"`
- `.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main --prompt "Review PR #82828 fixup for daemon service env preservation. Focus on whether the allowlist should include only current container opt-in env keys and whether tests cover stale/arbitrary OPENCLAW_* filtering."`
- GitHub CI on `2e4b7f7fccbc46541c9c0ac271b1c97f1a6aa071`
Co-authored-by: wAngByg <281221101+wAngByg@users.noreply.github.com>
Carry the canonical session UUID from the session store into interactive dispatch diagnostic lifecycle events, matching the cron path so downstream diagnostic consumers can join events back to the JSONL transcript id.
Guard native command redirects by only attaching the UUID when the lifecycle session key matches the session-store lookup key, avoiding a target UUID under a source conversation key.
Verification:
- `pnpm test src/auto-reply/reply/dispatch-from-config.test.ts -t "carries the session store UUID|does not stamp a command target"`
- `.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main --prompt ...`
- synthetic merge-tree against current `origin/main`
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Address Codex review (P2 x3): replace the duplicate fs.access-based entry
checks in runPostUpgradeProbes with a call to
validatePackageExtensionEntriesForInstall so the doctor probe enforces the
same contract as plugin install/discovery:
- runtimeExtensions shape and length-mismatch validation
- plugin-root boundary enforcement (rejects absolute paths and ../ escapes)
- inferred dist/*.js peer for TypeScript entries; TS source-only entries
without compiled output are now flagged
Adds 4 regression tests covering the boundary-escape, dist-peer accept,
TS-source-only reject, and runtimeExtensions length-mismatch cases.
Refs: https://github.com/openclaw/openclaw/pull/79260#issuecomment-4403594002
Add a Doctor health contribution that checks free space on the partition containing the active OpenClaw state directory. Doctor now warns below 500 MB and reports critical below 100 MB so disk pressure is visible before config writes, session transcripts, or log rotation start failing.
The contribution reuses the shared `src/infra/disk-space.ts` probe, runs before state integrity, and is registered in the Doctor health conversion plan with focused coverage for thresholds, formatting, and note behavior.
PR: #59196
Proof: `pnpm test src/commands/doctor-disk-space.test.ts src/flows/doctor-health-conversion-plan.test.ts`; `git diff --check origin/main...HEAD`; `git merge-tree --write-tree origin/main refs/remotes/pr/59196`; GitHub CI run `26720861380`; Real behavior proof run `26720996848`.
Co-authored-by: alkor2000 <200923177@qq.com>
Forward prompt-submission owned session write publication into the embedded session lock controller so same-process announcement/completion writes can advance the requester fence while external edits still trigger takeover protection.
Adds regression coverage for a second controller publishing an owned announcement write and for preserving rejection of a later unowned edit.
Closes#88703.
Thanks @TurboTheTurtle.
Show existing Workboard card comments in the edit modal and allow operators to append a new comment through the existing `workboard.cards.comment` gateway method.
Refs #88592.
Verification:
- node scripts/run-vitest.mjs ui/src/ui/views/workboard.test.ts
- pnpm tsgo:test:ui
- git diff --check origin/main...HEAD
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
Co-authored-by: Ted Li <tl2493@columbia.edu>
Keep cron media generation detached while making cron runs wait for image/music/video completion before final closeout. Records async task IDs, falls back to the task registry for active run-scoped media work, handles timeout races, and scopes no-target generated-media delivery. Fixes#88001.
Guard the remaining Windows Testbox workflow ref logging against GitHub Actions template injection by moving `target_ref` through step env before PowerShell reads it.
Extend the local workflow check wrapper to run pinned `zizmor` across every workflow file, and keep Workflow Sanity's CI audit explicit with trusted-base pre-commit and zizmor configs for pull-request runs.
Thanks @WT-WSL for the original report and patch.
Co-authored-by: dev111-actor <captaintobb@outlook.com>
Split ACP manager session-flow ownership into focused helpers for initialization, status reads, cancellation, and startup identity reconciliation.
Verification:
- `node scripts/run-oxlint.mjs src/acp/control-plane/manager.core.ts src/acp/control-plane/manager.initialize-session.ts src/acp/control-plane/manager.status.ts src/acp/control-plane/manager.cancel-session.ts src/acp/control-plane/manager.startup-identity-reconcile.ts src/acp/control-plane/manager.close-session.ts src/acp/control-plane/manager.turn-runner.ts src/acp/control-plane/manager.runtime-options-commands.ts src/acp/control-plane/manager.types.ts src/acp/control-plane/manager.test.ts src/acp/control-plane/manager.initialize-session.test.ts src/acp/control-plane/manager.cancel-session.test.ts src/acp/control-plane/manager.startup-identity-reconcile.test.ts src/acp/control-plane/manager.runtime-config.test.ts`
- `pnpm tsgo:prod`
- `pnpm test src/acp/control-plane/manager.test.ts src/acp/control-plane/manager.initialize-session.test.ts src/acp/control-plane/manager.cancel-session.test.ts src/acp/control-plane/manager.startup-identity-reconcile.test.ts src/acp/control-plane/manager.runtime-config.test.ts src/acp/control-plane/manager.runtime-handles.test.ts`
- `pnpm format:check src/acp/control-plane/manager.core.ts src/acp/control-plane/manager.initialize-session.ts src/acp/control-plane/manager.status.ts src/acp/control-plane/manager.cancel-session.ts src/acp/control-plane/manager.startup-identity-reconcile.ts src/acp/control-plane/manager.close-session.ts src/acp/control-plane/manager.turn-runner.ts src/acp/control-plane/manager.runtime-options-commands.ts src/acp/control-plane/manager.types.ts src/acp/control-plane/manager.test.ts src/acp/control-plane/manager.initialize-session.test.ts src/acp/control-plane/manager.cancel-session.test.ts src/acp/control-plane/manager.startup-identity-reconcile.test.ts src/acp/control-plane/manager.runtime-config.test.ts`
- `git diff --check`
- `pnpm check:test-types`
- `.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main`
- GitHub PR checks for #88752 passed
Real behavior proof:
Behavior addressed: ACP manager session-flow ownership is split out of `AcpSessionManager` without changing initialization, status, cancel, startup identity reconciliation, close, turn, or runtime-option behavior.
Real environment tested: Local OpenClaw checkout, Node/pnpm repo toolchain, GitHub Actions PR CI.
Exact steps or command run after this patch: Focused ACP manager/runtime config/runtime handle tests plus prod/test type checks, lint, format check, diff check, autoreview, and PR CI.
Evidence after fix: All listed local commands passed, autoreview reported no accepted/actionable findings, and GitHub PR checks passed.
Observed result after fix: `manager.core.ts` is down to 612 LOC, with init/status/cancel/startup identity flows in focused modules and matching focused tests.
What was not tested: Live ACP backend session initialization/cancel/status against a real external ACP provider.
Adds optional `gateway.tailscale.serviceName` support for Tailscale Serve so the Gateway Control UI can be exposed through a named Tailscale Service while existing hostname-based Serve and Funnel behavior stays unchanged.
The implementation validates `svc:<dns-label>`, passes the Service name to `tailscale serve`, clears named Service config with `tailscale serve clear <service>` when resetOnExit runs, and uses the derived Service hostname in startup logs, status output, and pairing URLs.
Verification:
- node scripts/run-vitest.mjs src/infra/tailscale.test.ts src/gateway/server-tailscale.test.ts src/config/config.gateway-tailscale-bind.test.ts src/gateway/startup-auth.test.ts src/commands/status.scan.shared.test.ts src/pairing/setup-code.test.ts
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main --parallel-tests "node scripts/run-vitest.mjs src/infra/tailscale.test.ts src/gateway/server-tailscale.test.ts src/config/config.gateway-tailscale-bind.test.ts src/gateway/startup-auth.test.ts src/commands/status.scan.shared.test.ts src/pairing/setup-code.test.ts"
- git diff --check
- git merge-tree --write-tree origin/main origin/pr/88691
Closes#88629.
Co-authored-by: Charles OpenClaw <charles-openclaw@9bcfae.inboxapi.ai>
Expose the existing virtual Communication > Notifications settings tab for Web Push controls, while keeping it out of the unscoped root settings view. Adds browser regression coverage for the scoped virtual tab.
Thanks @VladyslavLevchuk.
Co-authored-by: Vladyslav Levchuk <32742736+VladyslavLevchuk@users.noreply.github.com>
Extract ACP runtime-option command flows from `AcpSessionManager` into `manager.runtime-options-commands.ts`.
Verification:
- `pnpm format:fix src/acp/control-plane/manager.core.ts src/acp/control-plane/manager.runtime-options-commands.ts`
- `node scripts/run-oxlint.mjs src/acp/control-plane/manager.core.ts src/acp/control-plane/manager.runtime-options-commands.ts`
- `pnpm tsgo:prod`
- `pnpm test src/acp/control-plane/manager.runtime-config.test.ts src/acp/control-plane/manager.runtime-handles.test.ts src/acp/control-plane/manager.test.ts`
- `pnpm format:check src/acp/control-plane/manager.core.ts src/acp/control-plane/manager.runtime-options-commands.ts`
- `git diff --check`
- `pnpm check:test-types`
- `.agents/skills/autoreview/scripts/autoreview --mode local`
- GitHub PR checks for #88747 passed
Real behavior proof:
Behavior addressed: ACP runtime-option mutation ownership moved out of `AcpSessionManager` without changing set-mode, set-config-option, raw update, reset, persistence, or runtime-cache invalidation semantics.
Real environment tested: Local OpenClaw checkout, Node/pnpm repo toolchain, GitHub Actions PR CI.
Exact steps or command run after this patch: Focused ACP runtime config/handle/manager tests plus prod/test type checks, lint, format, diff check, autoreview, and PR CI.
Evidence after fix: All listed local commands passed, autoreview reported no accepted/actionable findings, and GitHub PR checks passed.
Observed result after fix: `manager.core.ts` is down to 885 LOC, with runtime-option command logic isolated in `manager.runtime-options-commands.ts`.
What was not tested: Live ACP backend mode/config option mutation against a real external ACP provider.
Prefer the clean channel command body when ACP decides whether an inbound message should bypass the agent loop for local OpenClaw commands.
This keeps envelope-wrapped channel text, such as WhatsApp display bodies, from hiding commands like /status when the channel already provided a normalized command body. The ACP runtime prefilter now uses the same command-text resolution as dispatch, and dispatch still requires registry-backed local commands before bypassing.
Co-authored-by: RoeeJ <RoeeJ@users.noreply.github.com>
Force required preflight context compaction before oversized turns can enter the agent runtime. Treat required preflight compaction as a hard gate: compact, skip only explicit harmless no-op reasons, or surface a visible recovery message when compaction cannot recover.
Fixes#87234.
Co-authored-by: ArthurNie <264332276+ArthurNie@users.noreply.github.com>
Refactor ACP close-session ownership by extracting the runtime close/recovery lifecycle into `manager.close-session.ts`.
Verification:
- `pnpm test src/acp/control-plane/manager.test.ts src/acp/control-plane/manager.runtime-config.test.ts src/acp/control-plane/manager.runtime-handles.test.ts`
- `pnpm tsgo:prod`
- `pnpm check:test-types`
- `node scripts/run-oxlint.mjs src/acp/control-plane/manager.core.ts src/acp/control-plane/manager.close-session.ts`
- `pnpm format:check src/acp/control-plane/manager.core.ts src/acp/control-plane/manager.close-session.ts`
- `git diff --check`
- `.agents/skills/autoreview/scripts/autoreview --mode local`
- GitHub PR checks for #88744 passed
Real behavior proof:
Behavior addressed: ACP close-session ownership moved out of `AcpSessionManager` without changing close/recovery behavior.
Real environment tested: Local OpenClaw checkout, Node/pnpm repo toolchain, GitHub Actions PR CI.
Exact steps or command run after this patch: Focused ACP manager tests covering close-session behavior, runtime config, and runtime handles, plus prod/test type checks, lint, format, diff check, autoreview, and PR CI.
Evidence after fix: All listed local commands passed, autoreview reported no accepted/actionable findings, and GitHub PR checks passed.
Observed result after fix: `manager.core.ts` dropped from 1149 LOC to 1038 LOC while close-session runtime lifecycle handling lives in `manager.close-session.ts`.
What was not tested: Live ACP backend close/recovery against a real external ACP provider.
Bounds skills watcher subscriptions and workspace snapshot-version state to active workspaces on the current `src/skills/runtime` implementation.
The fix keeps shared path watchers as the owner boundary, evicts idle workspace subscriptions after 1 hour without closing watchers still used by other workspaces, and clears per-workspace version keys only after preserving/advancing invalidation so cached skill snapshots cannot miss changes across teardown or re-enable.
Thanks @fede-kamel.
Fixes#77997.
Co-authored-by: Federico Kamelhar <federico.kamelhar@oracle.com>
Refactor ACP turn execution ownership by extracting the backend attempt and cleanup loop into `manager.turn-runner.ts`.
Verification:
- `pnpm test src/acp/control-plane/manager.test.ts src/acp/control-plane/manager.turn-results.test.ts src/acp/control-plane/manager.failover.test.ts src/acp/control-plane/manager.runtime-handles.test.ts src/acp/control-plane/manager.runtime-config.test.ts`
- `pnpm tsgo:prod`
- `pnpm check:test-types`
- `node scripts/run-oxlint.mjs src/acp/control-plane/manager.core.ts src/acp/control-plane/manager.turn-runner.ts`
- `pnpm format:check src/acp/control-plane/manager.core.ts src/acp/control-plane/manager.turn-runner.ts`
- `git diff --check`
- `.agents/skills/autoreview/scripts/autoreview --mode local`
- GitHub PR checks for #88739 passed
Real behavior proof:
Behavior addressed: ACP turn execution ownership moved out of `AcpSessionManager` without changing runtime behavior.
Real environment tested: Local OpenClaw checkout, Node/pnpm repo toolchain, GitHub Actions PR CI.
Exact steps or command run after this patch: Focused ACP manager tests covering turn results, failover, runtime handles, runtime config, plus prod/test type checks, lint, format, diff check, autoreview, and PR CI.
Evidence after fix: All listed local commands passed, autoreview reported no accepted/actionable findings, and GitHub PR checks passed.
Observed result after fix: `manager.core.ts` dropped from 1495 LOC to 1149 LOC while turn execution lives in `manager.turn-runner.ts`.
What was not tested: Live ACP backend process recovery against a real external ACP provider.
Sanitize credential-shaped provider HTTP 401 failures in embedded-agent replies so chat users see a re-authentication hint instead of raw provider text such as `HTTP 401: "Invalid token"`.
The classifier now requires auth classification plus positive 401 evidence, and it stays narrow to credential-shaped failures so billing, scope, replay-invalid, schema, message-only auth, and plain 403 paths keep their existing behavior.
Fixes#56197. Thanks @lokamir.
Co-authored-by: jeffrey701 <jeffreyconradtucker@gmail.com>
Phase-signal store reads now recover only missing files and corrupt JSON. Nonrecoverable filesystem read failures propagate so dreaming aborts before overwriting existing phase-signal history with an empty replacement.
Fixes#77881.
Thanks @bennewell35.
Co-authored-by: bennewell35 <newelljben@gmail.com>
Extract ACP runtime resume/discard recovery helpers from `AcpSessionManager` into `manager.runtime-resume-state.ts`, and share the manager session-meta writer callback type from `manager.types.ts`. Keeps close-time fresh-session recovery, early-turn retry, persisted resume identifier clearing, and discard-persistent-state behavior intact while reducing `manager.core.ts` from 1655 LOC to 1495 LOC.
Proof: focused ACP manager runtime-handle/runtime-config/turn-result tests, prod + test type checks, narrow oxlint, format check, diff check, autoreview clean, PR CI green.
Bound DiscordEntityCache entries with a write-time expired-entry sweep and a default 5,000-entry cap while preserving current safe expiry timestamp normalization. This prevents high-cardinality Discord user/channel/guild/member fetches from retaining stale Map entries for the gateway lifetime.
Fixes#77975.
Thanks @fede-kamel.
Co-authored-by: Federico Kamelhar <federico.kamelhar@oracle.com>
Guard group display-name generation behind group/channel classification so direct Telegram sessions fall back to their explicit or origin labels. Keep session-list search aligned with that visible fallback.
Fixes#55354.
Thanks @sebuh-infsol.
Summary:
- Add forced provider re-login support that clears cached auth profiles before running provider login again.
- Add provider-auth remediation guidance and a session-scoped skip cache for known-bad fallback auth attempts.
- Wire session ids through agent command, auto-reply, and embedded compaction fallback callers so the skip cache applies on real run paths.
- Fail closed when forced auth profile removal cannot update the profile store.
Verification:
- Local format, lint, diff-check, focused Vitest shards, and autoreview passed.
- PR CI, CodeQL Security High, and Critical Quality agent-runtime-boundary passed on head 1b4e9e753e.
Co-authored-by: Mert Basar <MertBasar0@users.noreply.github.com>
Fix approval fallback text so exec and plugin approval messages render a concrete request id in the chat copy-paste command instead of the literal <id> placeholder.
This makes the Reply with: /approve ... line directly usable for owners while keeping the existing approval resolver contract unchanged.
Proof:
- git diff --check origin/main...HEAD
- pnpm test src/infra/exec-approval-forwarder.test.ts src/infra/plugin-approval-forwarder.test.ts src/plugin-sdk/approval-renderers.test.ts
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
- CI run 26720052738 passed
Thanks @itsuzef.
Serialize QMD update and embed writes with one per-agent store lock so foreground memory search/index and gateway background QMD work do not write the same index.sqlite concurrently.
The embed path now waits for global embed capacity before taking the per-store lock, so queued embeds do not block same-agent foreground updates while no store write is active.
Fixes#66339
Thanks @openperf.
Co-authored-by: Chunyue Wang <16864032@qq.com>
Refresh pinned node:24-bookworm and node:24-bookworm-slim manifest-list digests across the root, smoke, and e2e Dockerfiles. Update digest pin assertions to cover the plugin-binding e2e Dockerfile.
Verified with live Docker digest inspection, targeted Dockerfile tests, root base-runtime build, install-sh smoke build, and plugin-binding e2e build.
Thanks @LibraHo.
Detect OpenClaw gateway units installed in the system systemd scope, including marker-owned custom unit names such as `openclaw.service`. Route status/restart/stop through the system manager when appropriate, and show non-root users the matching `sudo systemctl ...` command instead of falling back to unmanaged process signaling.
Fixes#87577.
Thanks @yetval.
Verification:
- `node scripts/run-vitest.mjs src/daemon/systemd.test.ts src/cli/daemon-cli/lifecycle.test.ts src/daemon/inspect.test.ts src/cli/daemon-cli/lifecycle-core.test.ts src/cli/daemon-cli/status.gather.test.ts src/cli/daemon-cli/response.test.ts src/commands/doctor-gateway-daemon-flow.test.ts src/cli/update-cli/restart-helper.test.ts src/infra/outbound/message-action-runner.core-send.test.ts`
- AWS Crabbox `cbx_69f97dff5e5c`, run `run_a68431b3dad6`: exact SHA checkout, focused tests, real `/etc/systemd/system/openclaw.service` status/restart/stop proof.
Ref #84134.
Prefer real tool results over generated missing-result placeholders during transcript repair, including late results after later assistant turns and explicitly marked custom-text repair placeholders. Keep real error outputs such as aborted when they are not generated repair placeholders.
Thanks @Jerry-Xin.
Co-authored-by: 忻役 <xinyi@mininglamp.com>
Co-authored-by: Jerry-Xin <jerryxin0@gmail.com>
Rewrite generated session transcript paths at the shared session-store merge boundary when a persisted session rolls from one session id to another. This prevents patches that carry a stale generated `sessionFile` from leaving a new logical session id attached to the old transcript file, while preserving custom transcript paths.
Refs #65564.
Proof:
- `node scripts/run-vitest.mjs src/config/sessions/sessions.test.ts`
- `node scripts/run-vitest.mjs src/agents/command/session-store.test.ts`
- `git diff --check origin/main...HEAD`
- `.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main`
- CI run 26719583889 attempt 2
Co-authored-by: Sunjae Kim <sunjaekim@bigvalue.co.kr>
Remove Telegram runtime JSON sidecar read/write fallback for the prompt-context message cache. Keep legacy sidecar parsing for doctor import into SQLite plugin state and update docs/tests to match.
Fixes#85124.
Anthropic standard API keys no longer resolve as provider usage auth for `openclaw status --usage`, so valid inference keys are not sent to Anthropic's OAuth usage endpoint and surfaced as misleading invalid bearer-token errors.
The provider usage-auth SDK result now has an explicit handled/no-token shape so provider hooks can suppress generic fallback without widening the OAuth helper contract. Docs, Plugin SDK API baseline, and extension package-boundary cache inputs were updated with the new contract.
Thanks @zhangguiping-xydt.
Proof:
- node scripts/run-vitest.mjs src/infra/provider-usage.auth.normalizes-keys.test.ts src/infra/provider-usage.auth.plugin.test.ts extensions/anthropic/index.test.ts
- pnpm plugin-sdk:api:check
- pnpm plugin-sdk:check-exports
- git diff --check origin/main...HEAD
- pnpm docs:list
- pnpm run test:extensions:package-boundary:compile
- autoreview clean: no accepted/actionable findings
- PR CI rollup green: 131 success, 22 skipped, 1 neutral, 0 failures
Co-authored-by: 张贵萍0668001030 <zhang.guiping@xydigit.com>
Validate context-engine assemble results at the shared harness boundary before embedded or Codex runners consume them.
Malformed plugins that return an object without a `messages` array now throw a descriptive engine-scoped error and use the existing runner fallback to pipeline messages, rather than poisoning session state and crashing prompt assembly on `.length`.
Proof:
- `node scripts/run-vitest.mjs src/agents/harness/context-engine-lifecycle.test.ts`
- `node scripts/run-vitest.mjs src/agents/embedded-agent-runner/run/attempt.spawn-workspace.context-engine.test.ts`
- `pnpm exec oxfmt --check src/agents/harness/context-engine-lifecycle.ts src/agents/harness/context-engine-lifecycle.test.ts`
- `git diff --check origin/main...HEAD`
- GitHub CI on `5b6b7b1bf69b8f30329fdf749161a192d3d016fe`: https://github.com/openclaw/openclaw/actions/runs/26719202811
Thanks @Pluviobyte.
Fixes#75541
Plugin SDK subagent runs now register at the Gateway agent acceptance boundary so subagent_ended hooks fire without creating duplicate CLI task rows.
The registration stays best-effort: if the subagent registry cannot persist tracking state, the run still dispatches and falls back to the existing CLI task tracking path.
Closes#59164
Co-authored-by: Cornna <96944678+ymylive@users.noreply.github.com>
Count model stream diagnostic response bytes from snapshotless stream chunks, excluding accumulated partial snapshots on delta events. This avoids repeatedly serializing answer-so-far snapshots during streamed model calls and updates OTEL/docs wording for the new metric baseline.
Refs #86599.
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* refactor: move plugin state slices to sqlite
* fix: keep legacy plugin state migration out of runtime
* fix: add doctor migrations for plugin sqlite state
* fix: preserve teams feedback learning migration keys
* fix: merge teams legacy feedback learnings
* fix: guard doctor imports against plugin state caps
* fix: leave lossy teams learning filenames unmigrated
* fix: preserve teams feedback learning scope
* fix: load plugin doctor contracts from package dist
* fix: satisfy plugin state migration gates
Handle the Telegram isolated-polling spool recovery race where a stale `.processing` claim can disappear between discovery and the final rename back to pending. Recovery now treats `ENOENT` as benign and mirrors the existing duplicate-pending cleanup path for `EEXIST`, avoiding noisy drain-failure logs and spurious failure counters without changing claim ownership semantics.
Adds a regression test that removes the claim from inside `shouldRecover`, after recovery has discovered the entry and before the final rename path, so the old code would hit the reported `ENOENT` window.
Fixes#87847
Co-authored-by: Sebastien Tardif <sebtardif@ncf.ca>
Expand Linux CA bundle auto-injection to recognize fnm, Volta, asdf, mise, n, nodenv, nodebrew, and nvs paths in addition to nvm. Adds regression coverage for the new version-manager path layouts.
Fixes#59494.
Thanks @alkor2000.
Co-authored-by: alkor2000 <200923177@qq.com>
Prevent streaming assistant text updates from reparsing the full accumulated reply for plain deltas, avoiding repeated work for small-model streams while preserving full cleanup for directives, media, and final events.
Also load the normal Control UI Vite config in the mock browser server so browser E2E uses the same workspace aliases as dev.
Thanks @vincentkoc.
Extend the CLI holiday tagline tables for Lunar New Year, Eid al-Fitr, Easter, Diwali, and Hanukkah through 2030 so those taglines do not silently disappear after 2027.
Maintainer fixup: corrected the 2030 Diwali row to October 25 and added explicit regression coverage for that date.
Verification:
- node scripts/run-vitest.mjs src/cli/tagline.test.ts
- Direct pickTagline() probe confirmed 2030-10-25 activates Diwali and 2030-10-26 does not.
Co-authored-by: alkor2000 <200923177@qq.com>
Refactor provider metadata lookup so hot paths consult the current process snapshot before falling back to a metadata load.
Centralize provider metadata lookup in the provider runtime and update the focused tests/mocks that exercise embedded-agent and provider loading paths.
Verification:
- node scripts/run-vitest.mjs src/plugins/providers.runtime.consult-current-snapshot.test.ts
- node scripts/run-vitest.mjs src/agents/embedded-agent-runner/run/attempt.cwd-split.test.ts
- node scripts/run-vitest.mjs src/plugins/providers.test.ts
- autoreview --mode branch --base origin/main
- CPU profile loop: current-snapshot resolve 0.459 us/call vs warm direct metadata load 131.493 us/call
- GitHub CI on 728bd53510
Co-authored-by: masatohoshino <g515hoshino@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Add durable memoryFlush failure metadata and lifecycle events so provider failures during memory flush no longer leave a session with no recorded recovery state.
After three consecutive non-abort flush failures, mark the current compaction cycle as exhausted so later messages can proceed without deleting transcript history. Successful flushes clear the failure metadata, and plugin session-entry slot reservations now protect the new fields.
Release-note: memoryFlush sessions can now fail open after repeated provider-side flush failures instead of retrying indefinitely before normal replies.
Refs #85645
Co-authored-by: 忻役 <xinyi@mininglamp.com>
Fixes Codex/plugin-harness cold starts for exact static-catalog model ids such as openai/gpt-5.3-codex without adding a second resolver retry loop. The embedded runner now performs the normal provider-runtime attempt with agent discovery skipped, then consults the bundled static catalog before falling back to generic configured-provider synthesis when plugin harness owns transport.
The OpenAI static catalog row carries the Codex ChatGPT transport metadata, dynamic provider metadata still wins for runtime-owned models, and focused regression coverage exercises both paths.
Fixes#88510.
Co-authored-by: yetval <yetvald@gmail.com>
Show DeepSeek API-key account balance in status/auth-status usage surfaces by adding a summary-only provider usage snapshot path, a DeepSeek balance fetcher, SDK/docs coverage, and focused regression tests.
Maintainer verification accepted the additive provider-usage/status contract and the DeepSeek balance visibility boundary for authenticated status surfaces.
Proof:
- Live DeepSeek balance proof via 1Password-backed DEEPSEEK_API_KEY against https://api.deepseek.com/user/balance; key and balance amount redacted.
- GitHub CI run 26717953383 passed on the current head.
- Real behavior proof run 26718215605 passed after the PR body was refreshed.
- Local clean PR clone: git diff --check; node --max-old-space-size=8192 --import tsx scripts/generate-plugin-sdk-api-baseline.ts --check; node scripts/run-vitest.mjs run src/agents/bash-tools.exec.path.test.ts.
Co-authored-by: Alex Tang <tangli1987118@hotmail.com>
Co-authored-by: litang9 <141409885+litang9@users.noreply.github.com>
Treat the synthetic Codex app-server auth marker as a core non-secret marker so secrets audit does not flag it when bundled plugin discovery is disabled.\n\nVerified with focused model-auth marker tests, isolated secrets-audit CLI proof, autoreview, and green CI.\n\nThanks @vortexopenclaw.
Suppress WhatsApp typing indicators only for silent message-tool-only unmentioned group runs. Automatic visible replies and authorized group commands still show composing normally.
Fixes the autoreview regression risk by narrowing suppressTyping and adding coverage for both silent and visible group paths.
Proof:
- pnpm test src/auto-reply/reply/reply-utils.test.ts extensions/whatsapp/src/auto-reply/monitor/inbound-dispatch.test.ts
- .agents/skills/autoreview/scripts/autoreview --mode local
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
- CI run 26717880577 green
Thanks @Bluetegu.
Subscribe the iOS gateway chat transport to per-session transcript events so group chats update when other clients send messages. Constrain local user echo adoption to the optimistic row tied to the still-pending send run, so repeated same-content user messages from other clients append instead of replacing history.
Fixes#80231.
Co-authored-by: Yuval Dinodia <yetvald@gmail.com>
Keep Slack progress-mode drafts on one rolling preview message across assistant and reasoning boundaries while preserving boundary cleanup and the latest visible tool-progress lines. Partial/replace modes still start a fresh draft at assistant boundaries.
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Route Discord thread follow-up messages to plugin-owned bindings by the raw thread id while retaining parent channel fallback matching. This fixes `/codex bind` follow-ups in Discord threads being claimed by the parent OpenClaw route instead of the bound Codex session.
Verification:
- `node scripts/run-vitest.mjs extensions/discord/src/channel.conversation.test.ts src/hooks/message-hook-mappers.test.ts extensions/discord/src/monitor/message-handler.process.test.ts -t "prefers bound session keys|passes Discord thread parent only|routes Discord thread plugin-owned bindings|passes thread parent ids|thread binding"`
- `node scripts/run-vitest.mjs src/auto-reply/reply/dispatch-from-config.test.ts -t "routes Discord thread plugin-owned bindings by raw thread id"`
- `pnpm build`
- `pnpm lint --threads=8`
- `CI=true FORCE_COLOR=0 pnpm lint --threads=8`
- `.agents/skills/autoreview/scripts/autoreview --mode local`
- GitHub: Real behavior proof, check-test-types, check-dependencies, check-prod-types, auto-reply dispatch shard, hooks shard, and extension package boundary passed on head 1e896d9835.
Known unrelated CI noise at merge: broad opengrep/test/lint CI failures are outside the touched Discord/session-binding surface and contradicted by focused local proof where applicable.
Co-authored-by: Hex <hex@openclaw.ai>
Add Claude Opus 4.8 to the GitHub Copilot static model catalog and default model IDs.
Updates provider manifest metadata and regression coverage so fallback/default discovery includes claude-opus-4.8.
PR: #88547
Co-authored-by: saju01 <saju@coderedcorp.com>
Clamps ANSI-aware terminal table cells before padding so width-2 graphemes cannot push borders out of alignment in width-1/narrow columns.
Fixes#88556.
Proof:
- node scripts/run-vitest.mjs run packages/terminal-core/src/ansi.test.ts packages/terminal-core/src/table.test.ts
- CI run 26717035619; check-dependencies red only for unrelated current-main deadcode issue ui/src/ui/browser-redact.ts, also red on main run 26717029674. checks-node-agentic-agents-core rerun failed in unrelated src/agents/bash-tools*.test.ts outside this PR diff.
Co-authored-by: Jayesh Betala <jayesh.betala7@gmail.com>
When dreaming narrative cleanup calls subagent.deleteSession() in the finally block and it throws, the store row can be left behind referencing a still-present transcript. The scrubber only pruned dreaming rows whose transcript was missing, so these orphans lingered in the recent sessions sidebar with no kind/status/endedAt and accumulated across restarts.
Reclaim a dreaming store row when its transcript is missing OR has aged past DREAMING_ORPHAN_MIN_AGE_MS, then leave the transcript unreferenced so the orphan-transcript pass archives it.
Fixes#88322
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Use the Google Chat thread resource as the ambient message-tool reply target so replies stay in the inbound thread. Normalize the current Google Chat space target and let plugin threading adapters explicitly suppress the generic message-id fallback when a provider needs a thread resource instead of a message resource.
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Co-authored-by: Franco Viotti <franco-viotti@users.noreply.github.com>
Follow-up to #88658. Retries transient stale session-lock acquire failures when diagnostics show the old stale report disappeared, was replaced by a fresh valid lock, or was replaced by a fresh payload-less lock still inside the mtime/orphan grace window.
Preserves typed `SessionWriteLockStaleError` diagnostics for still-present live OpenClaw-owned stale locks.
Proof: 53 focused session-write-lock tests passed locally and in the agents-core CI shard; `pnpm tsgo:test:src`, touched-file oxlint, `git diff --check`, and autoreview passed locally. CI run 26716843811 has unrelated failures in UI deadcode/types and bash-tools tests; session-write-lock tests passed in that run.
Refs #87217.
Fix Discord DM pairing for PluralKit senders by storing the pairing identity with the same `pk:<member-id>` form used at inbound lookup time. Also recognizes both canonical direct DM session keys and account-scoped direct DM session keys as DM approval sessions.
Focused proof: `node scripts/run-vitest.mjs extensions/discord/src/approval-native.test.ts extensions/discord/src/monitor/dm-command-auth.test.ts extensions/discord/src/monitor/dm-command-decision.test.ts extensions/discord/src/monitor/message-handler.preflight.test.ts` passed with 4 files and 82 tests.
Closes#86332
Co-authored-by: Sanjays2402 <51058514+Sanjays2402@users.noreply.github.com>
Slack top-level channel mentions with replyToMode off now reply at the channel root instead of inheriting stale or auto-created thread targets.
Existing Slack thread replies and Slack assistant DM thread targets continue to preserve their thread target.
Thanks @lawrencetran.
Fix macOS menu bar status-item storms during rapid gateway connection churn by removing stale SwiftUI-vended status items before adopting replacements and debouncing transient control-channel states.
Surface: macOS menu bar app, `MenuBarExtra` status item ownership, `ControlChannel` UI-observed connection state.
Proof:
- `git diff --check origin/main...pr/82739`
- `swift test --package-path apps/macos --filter ControlChannelStateDebouncerTests`
- PR CI: preflight, security-fast, macos-node, macos-swift, dependency-guard, changed-path scan, real behavior proof, Socket checks
Co-authored-by: Alexander Falk <al@falk.us>
Fixes#88360.
Route Discord live-preview final replies containing targeted user or role mentions through fresh message delivery instead of edit finalization, preserving mention alias rewriting and notification behavior. Plain, broadcast-only, and mixed targeted-plus-broadcast replies keep the existing preview edit path.
Proof: CI run 26708866609 green for relevant lanes; Real behavior proof run 26708866194 successful; local git diff --check and git merge-tree clean.
Route implicit message_tool_only current-source sends through the internal source-reply sink for non-webchat transports, preserving the final reply payload path where usage decoration runs. Also keep reply payload metadata when appending usage text so transcript mirror text matches the delivered footer-bearing reply.
Recreated from PR #87425 because the fork branch is draft, dirty against main, and not maintainer-pushable.
Co-authored-by: Gio Della-Libera <giodl73@gmail.com>
fix(agents): preserve runtime tools in lean mode
Keep runtime-required tools, especially `message`, available when local-model lean filtering is enabled. This preserves `forceMessageTool`, `message_tool_only` source replies, explicit runtime allowlists, and schema projection without disabling lean filtering for ordinary denied tools.
Proof: focused Vitest passed 190 tests; `git diff --check origin/main...HEAD` passed; PR CI had no failing or pending checks.
fix(messages): use best-effort for implicit tool-only source replies
Preserve durable required-send semantics for explicit non-current targets while allowing current-source `message_tool_only` replies to be delivered through best-effort outbound sends. This fixes Slack source replies that otherwise fail when the adapter has no `reconcileUnknownSend` hook.
Fixes#84078.
Add an opt-in bash/zsh shell snapshot cache for host exec runs, consolidate shell helper ownership into src/agents/shell-utils.ts, document OPENCLAW_EXEC_SHELL_SNAPSHOT, and keep Windows config command execution on the bash resolver. Also removes a redundant Discord gateway close-code type branch that was blocking test type checks.
Report live-owned stale session locks as typed acquisition failures instead of auto-removing them, while preserving safe reclaim for dead/orphaned lock files. Propagate stale lock acquisition through embedded runner takeover handling, failover/cache/delivery classifiers, and QA retry detection.
Refs #87779
Fixes#88538. Carry the owning run sessionId through lifecycle events, skip stale persistence and sessions.changed projection when sessions.reset rotated the row, and register the persisted owning id across session-backed run paths. Also aligns per-agent subagent thinking typing with existing runtime/test usage.\n\nCo-authored-by: openperf <16864032@qq.com>
sessions.reset rotates a channel session to a fresh sessionId under the same
sessionKey, but an old in-flight run could still emit late start/end/error
lifecycle events. persistGatewaySessionLifecycleEvent resolved the row purely
by sessionKey, so those stale events overwrote the new row's status
(running/failed with hasActiveRun=false).
Stamp the owning run's sessionId onto lifecycle events in emitAgentEvent and
skip persistence when it differs from the current row's sessionId. The embedded
runner refreshes the run context's sessionId on every live-session rotation
(mid-run compaction), so a legitimately rotated run's terminal event still
matches the rotated row; only an external sessions.reset stays mismatched.
Matching and unknown-owner events are unaffected.
Fixes#88538
Fixes#74374.
Normalizes params.thinking false, disabled, and none to the existing off state for agent and auto-reply model selection. Thanks @yelog.
Known proof gap: build-artifacts is failing in an unrelated plugin prerelease plan assertion that expects an old Docker stats helper string; targeted tests, diff check, autoreview, and all touched-path checks pass.
Enforce OpenAI-compatible `tool_choice` contracts for Gateway HTTP Chat Completions and Responses client function tools.
- Add shared request normalization and post-run enforcement for required and pinned client function tool choices.
- Buffer streaming output until the tool-choice contract is satisfied, so failed runs do not leak partial assistant prose.
- Document the client-function-tool scope and add regression coverage for Chat/Responses success and failure cases.
Thanks @Lellansin for the contribution.
Proof: exact-head CI passed for `79fa0947360d307cf4ecffe713489cdf5db61093` in run `26714604449`; focused gateway tests passed locally.
Fixes the session transcript race where a newer assistant tool-call turn could force pending older tool calls to be written as synthetic missing-result entries while real parallel tool results were still in flight.
The guard no longer synthesizes at that racing boundary when synthetic repair is enabled, and transcript repair now moves late real results back beside their matching assistant tool-call turn before adding any placeholder. This keeps provider replay strict while preserving useful tool output.
Regression coverage: focused guard and transcript-repair tests for late parallel results.
Closes#88168.
Follow-up lock-lifetime report tracked in #88647.
Thanks @TurboTheTurtle for the fix and @jhartman00 for the report.
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
Release the embedded attempt session lock on manual aborts through the same best-effort abort cleanup path used by timeout aborts.
Proof: focused Vitest for abort/session-lock cleanup, `pnpm check:test-types`, oxfmt, `git diff --check`, branch autoreview, and full PR CI on 56fa5420d6.
Fixes#88600
Fixes#87462.
Timeout transport failures now record cooldowns against the attempted model when available. Model-scoped cooldown bypasses continue to respect profile-wide blocked/disabled windows, and timeout expiry selection stays per profile while rate-limit expiry keeps shared reset aggregation.
Verification:
- pnpm exec oxfmt --check --threads=1 src/agents/auth-profiles/usage-state.ts src/agents/auth-profiles/usage.test.ts src/agents/auth-profiles.getsoonestcooldownexpiry.test.ts src/agents/auth-profiles.markauthprofilefailure.test.ts src/agents/embedded-agent-runner/run.ts
- pnpm check:test-types
- pnpm test src/agents/auth-profiles.getsoonestcooldownexpiry.test.ts src/agents/auth-profiles/usage.test.ts src/agents/auth-profiles.markauthprofilefailure.test.ts src/agents/embedded-agent-runner/run.incomplete-turn.test.ts
- autoreview clean
- GitHub Actions green on PR head d64e2a4d2f
Bumps OpenClaw release metadata to 2026.5.31 across package manifests, app version files, plugin metadata, changelog headings, and generated shrinkwraps.
Verification:
- pnpm plugins:sync:check
- pnpm ios:version:check
- pnpm deps:shrinkwrap:check
- git diff --check
- stale 2026.5.30/build-code scan across changed files
- autoreview clean: no accepted/actionable findings
- PR CI green for real gates: Checks, security scans, dependency guard, app lanes, real behavior proof
Known non-code workflow issue:
- label workflow failed because this PR hits GitHub's 100-label issue cap before the size-label step.
Warn operators when message_tool_only produces unusually substantive private final text without a delivered source reply. Keeps short/NO_REPLY silence quiet, avoids logging response bodies, and distinguishes unrelated side effects from source-reply delivery.
* fix(tui): use middle truncation for paths and commands in tool display
Closes#87936
* fix(test): update channel-streaming test for middle truncation output
Signed-off-by: Sebastien Tardif <sebtardif@ncf.ca>
* chore: retrigger CI (vitest env teardown flake)
Signed-off-by: Sebastien Tardif <sebtardif@ncf.ca>
* fix(tui): redact tool details before middle truncation
Apply redactToolDetail() to command and generic string text before
middle truncation so credential-like suffixes are masked while full
flag/key context is still available. Previously, truncation could
remove the --flag prefix while preserving the raw secret at the tail,
causing redaction patterns to miss the value.
Add regression tests for sk- prefixed tokens in commands and ghp_
tokens in generic string details.
Signed-off-by: Sebastien Tardif <sebtardif@ncf.ca>
---------
Signed-off-by: Sebastien Tardif <sebtardif@ncf.ca>
* fix(tui): skip history reload when final event has displayable output
On external/gateway runs, handleChatEvent fires void loadHistory() on
every final event. loadHistory() does clearAll() + rebuild from server
data, but the server may not have persisted the just-finished message
yet, causing the rendered final message to vanish.
Add a hasDisplayableFinal option to maybeRefreshHistoryForRun that skips
the destructive reload when the final text is already rendered locally.
This mirrors the existing local-run guard. Compute finalText before the
reload decision so the guard has the information it needs.
Closes#87922
Signed-off-by: Sebastien Tardif <sebtardif@ncf.ca>
* retrigger proof check
Signed-off-by: Seb Tardif <sebtardif@ncf.ca>
---------
Signed-off-by: Sebastien Tardif <sebtardif@ncf.ca>
Signed-off-by: Seb Tardif <sebtardif@ncf.ca>
Refactor the subagent completion handoff path into the generic agent steering queue, preserving legacy persisted handoff lease fields by normalizing them into steering lease fields on restore.
Also allowlists the split cron run-log SQLite boundary in the Kysely guardrail after rebasing onto current main.
Refs #88407.
* fix(tasks): reclaim ACP zombie runs blocking gateway restart (#88205)
hasBackingSession treated an ACP task as backed whenever its persisted
session-store entry existed, so a crashed mid-turn ACP run left a
status=running record that survived the crash and wedged gateway
restart/update forever.
Gate ACP backing on in-process live-turn liveness instead of entry
existence, behind the existing authoritative-process flag (generalized
from cron-only) so a standalone maintenance CLI with an empty live-turn
map stays conservative and never reclaims. The liveness signal lives in a
core-internal active-turns registry (mirroring cron active-jobs) so it
stays off the SDK-exported AcpSessionManager surface. It is marked once
before the backend loop and cleared when the task is marked terminal, so
a slow init or backend failover cleanup cannot let the sweep reclaim a
still-live turn.
* fix(tasks): preserve cron operator JSON diagnostic reason
Split the merged runtime_not_authoritative reason back into the existing cron_runtime_not_authoritative (shipped, consumed by openclaw tasks maintenance --json operator scripts) and a new acp_runtime_not_authoritative for the ACP branch. Strengthen the cron non-authoritative test to lock the reason string contract.
* fix(tasks): clear ACP turn liveness on retry failures
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Auto-reply now uses the existing per-model model params thinking value before falling back to the global thinkingDefault, matching gateway/shared model selection behavior.\n\nVerified with targeted auto-reply and agents Vitest coverage plus formatting and diff checks.\n\nThanks @tynamite for the fix.
Preserve OpenAI-compatible replay reasoning when the selected custom or self-hosted model already has reasoning metadata enabled.
The transcript policy now treats existing model metadata as the replay contract instead of requiring a new provider config knob, and the OpenAI-compatible serializer preserves reasoning_content for those routes while keeping stock OpenAI, Gemma 4, and known non-replayable OpenRouter safeguards.
Fixes#88068.
Replaces #88071.
Treat pathless POSIX shell builtins (`:`, `cd`, `false`, `pwd`, `true`) as internally safe only during shell allowlist evaluation. This avoids approval prompts for chains like `cd /tmp && git status` when the executable segment is already allowlisted, without adding a `tools.exec.safeBuiltins` config knob.
Environment-mutating builtins (`export`, `unset`), code-evaluating builtins (`eval`, `source`, `.`), unknown commands, and direct argv execution remain approval-gated unless separately allowlisted.
Proof: `pnpm test src/infra/exec-safe-builtins.test.ts src/agents/bash-tools.exec.security-floor.test.ts -- --reporter=verbose`; `pnpm changed:lanes --json`; `pnpm check:no-conflict-markers`; `git diff --check origin/main...HEAD`. CI related failures were resolved on the final SHA; remaining `checks-node-core-runtime-media-ui` failure is unrelated to this PR.
Fixes#46056.
Thanks @kinjitakabe.
Co-authored-by: kevinkang-ai <273844887+kevinkang-ai@users.noreply.github.com>
Summary:
- The branch documents friendly browser tab references across docs, the browser skill, CLI help, and tool schema descriptions, and adds tests for target reference resolution and tab alias behavior.
- PR surface: Source +24, Tests +328, Docs +9. Total +361 across 21 files.
- Reproducibility: yes. for the documentation mismatch by source inspection: current main supports friendly ta ... schema/help surfaces still emphasize raw CDP target ids. Runtime behavior itself is not a new failing path.
Automerge notes:
- PR branch already contained follow-up commit before automerge: refactor(browser): share tab reference CLI help
Validation:
- ClawSweeper review passed for head 118af80b0b.
- Required merge gates passed before the squash merge.
Prepared head SHA: 118af80b0b
Review: https://github.com/openclaw/openclaw/pull/88393#issuecomment-4583558133
Co-authored-by: FMLS <kfliuyang@gmail.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: hxy91819
Co-authored-by: hxy91819 <8814856+hxy91819@users.noreply.github.com>
Fixes#88443.
Cooldown-only edits under auth.cooldowns now hot reload the active runtime config instead of scheduling a gateway restart. This avoids dropping active gateway work while preserving restart-required behavior for gateway.auth.* credential changes.
Verification:
- pnpm test src/gateway/config-reload.test.ts -- --reporter=verbose
- env -u OPENCLAW_TESTBOX pnpm check:changed
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main --prompt 'Review PR 88474 after rebase. Focus on whether auth.cooldowns hot reload correctly refreshes active runtime config without weakening gateway auth/token restart behavior. Treat no-op vs hot reload semantics as central.'
- GitHub CI, Real behavior proof, CodeQL, Dependency Guard, OpenGrep PR Diff, and Workflow Sanity passed on 51232ff66c.
Thanks @IWhatsskill.
Retry live query embeddings on transient provider transport failures and split eligible batch embedding socket failures after bounded retries.
Fixes#71784Fixes#44166
Supersedes #44167
Co-authored-by: MrGeDiao <MrGeDiao@users.noreply.github.com>
Suppress BOOT.md/internal-runtime-context echoes in fallback boot sends.
Wrap boot prompts as internal runtime context, track the active boot prompt during boot runs, and sanitize message-tool visible payloads before dispatch so fallback models cannot deliver copied BOOT.md instructions or leak them through raw-params errors. Preserves media/presentation sends that still contain non-text payload content after sanitization.
Fixes#53732.
Co-authored-by: stainlu <stainlu@newtype-ai.org>
Allow media understanding providers to opt into synthetic non-secret auth for local or self-hosted no-auth audio/video execution.
This preserves configured env/profile/literal provider credentials first, keeps explicit profile failures hard-fail, and leaves unmarked remote providers fail-closed.
Fixes#74644.
Limit plugin metadata snapshots to the channel, provider, and startup surfaces that need them, while preserving unscoped fallback for incomplete index data and provider runtime resolution.
Refs #70533.
Refs #84628.
Co-authored-by: IWhatsskill <IWhatsskill@users.noreply.github.com>
Fixes#67423.
Resolve provider-entry apiKey fields that intentionally reference model auth profiles through centralized binding logic, so runtime auth and status labeling agree. Preserve env-first precedence, SecretRef handling, provider/baseUrl compatibility checks, and model auth-mode guards.
Verification:
- node scripts/run-vitest.mjs src/agents/model-auth.profiles.test.ts src/agents/model-auth-label.test.ts
- PATH=/tmp/openclaw-corepack-shim.XXXXXX:$PATH CI=true pnpm check:changed
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
- GitHub CI run 26710260760 and related CodeQL/proof checks on f55dec154d
Co-authored-by: kinjitakabe <273844887+kinjitakabe@users.noreply.github.com>
Stabilizes Claude CLI reusable sessions when Claude token rotation causes transient token-shaped credential reads. Local Claude CLI OAuth and token credential encodings now share the same identity-only auth-epoch, while ref-backed token auth profiles ignore refreshed token material and plaintext token profiles remain epoch-sensitive on manual token replacement.
Fixes#74312.
Proof: focused local Vitest, autoreview, Testbox-through-Crabbox tbx_01ksyrcknbt743x32x6k1s95qw, and GitHub CI run 26709864094 all passed.
Co-authored-by: stainlu <stainlu@newtype-ai.org>
Deliver plugin-owned bound-thread replies even when the source room is configured for `message_tool` visible replies. Normal agent final text still stays private unless the agent calls `message(action=send)`.
Document the distinction in the group/channel docs and root routing policy, and keep ambient room-event plus unauthorized text-slash suppression covered by regression tests.
Fixes#87721.
Adds a report-only memory-core dreaming shadow-trial runner that writes inspectable artifacts without mutating durable memory. The public helper now stores default reports under daily directories with opaque content-hash filenames, so multiple same-day trials coexist without leaking candidate text into paths.
Verification:
- OPENCLAW_VITEST_MAX_WORKERS=1 node scripts/run-vitest.mjs run --config test/vitest/vitest.extension-memory.config.ts extensions/memory-core/src/dreaming-shadow-trial.test.ts --reporter=verbose --maxWorkers=1
- git diff --check
- pnpm exec oxfmt --check extensions/memory-core/src/dreaming-shadow-trial.ts extensions/memory-core/src/dreaming-shadow-trial.test.ts
- pnpm tsgo:extensions
- autoreview clean: no accepted/actionable findings
- GitHub CI run 26709794635 passed
- Real behavior proof run 26709798698 passed
- Dependency Guard run 26709794113 passed
Co-authored-by: Firas Alswihry <itzfiras@gmail.com>
Align diagnostic stuck-session recovery in-flight dedup with the runtime recovery key. The coordinator now dedups by logical session ref only, so a mid-flight generation bump cannot emit a phantom `session.recovery.requested` event that runtime recovery skips as already in flight.
Adds a regression test for the idle-queued stall path where a queued message bumps generation while recovery is pending.
Fixes#88010
Fixes#70746 by pairing nameless same-name tool results with the earliest unmatched Control UI tool card while preserving exact ID matches. Empty fallback results now count as consumed, so later results do not overwrite the first card.
Focused regression coverage covers sequential same-name calls and empty-result fallback pairing. Thanks @chinar-amrutkar.
Co-authored-by: Chinar Amrutkar <chinar.amrutkar@gmail.com>
## Summary
- Document scoped configured mention-pattern policy on the Groups page, including allow/deny mode semantics, supported conversation IDs, account-level precedence, and native-mention behavior.
- Add config UI help for `mentionPatterns.mode`, `allowIn`, and `denyIn` on Discord, Matrix, Slack, Telegram, and WhatsApp.
- Regenerate channel config/docs/plugin SDK metadata baselines for the new hint copy.
Refs #70864.
## Verification
- git diff --check
- pnpm format:docs:check
- pnpm docs:check-mdx
- pnpm docs:check-links
- pnpm config:channels:check
- pnpm config:docs:check
- pnpm plugin-sdk:api:check
- node scripts/run-vitest.mjs src/config/schema.hints.test.ts
- .agents/skills/autoreview/scripts/autoreview --mode local
## Real behavior proof
Behavior addressed: Documentation and config UI metadata for scoped configured mention-pattern policy.
Real environment tested: Local OpenClaw checkout on macOS.
Exact steps or command run after this patch: The verification commands listed above.
Evidence after fix: Docs formatting, MDX, link audit, generated config/channel/API baselines, and config hint tests passed; autoreview reported no accepted/actionable findings.
Observed result after fix: The Groups page now explains how to scope `messages.groupChat.mentionPatterns` with `channels.<channel>.mentionPatterns`, and config metadata exposes field help for the supported channels.
What was not tested: Live Discord, Matrix, Slack, Telegram, or WhatsApp inbound messages; this PR is documentation/config metadata only and follows the already-landed runtime behavior from #70864.
* fix(agents): route media task hints below the system-prompt cache boundary
Per-turn image/video/music generation task hints were injected into the
static prependSystemContext slot, landing above the cache boundary inside the
cacheable prefix. The hints are present only on user/manual turns and vary
with active media tasks, so the cacheable prefix shifted turn-to-turn and
defeated Anthropic/OpenAI prompt caching (#85203).
Split the per-turn media hints out of the prepend resolver into
resolveAttemptMediaTaskSystemPromptAddition and route them below the boundary
via the existing prependSystemPromptAddition helper, matching how subagent and
context-engine system-prompt additions are already routed. The static plugin
prependSystemContext / appendSystemContext hook fields are unchanged and
remain in the cacheable prefix. Applied at both consumers (embedded agent
runner and CLI runner).
* fix(agents): keep media task hints below the cache boundary for hook systemPrompt overrides
A before_prompt_build hook that returns a full systemPrompt override replaces
the base prompt with marker-free text. Per-turn media-generation task hints
were then front-prepended into that marker-free prompt, which providers cache
as a single block, so the cached prefix still shifted turn-to-turn on the
override path (#85203).
Wrap the base with ensureSystemPromptCacheBoundary at both media-routing sites
(embedded agent runner and CLI runner) so a marker-free override gets an
appended boundary and the hint routes into the uncached suffix. The helper is
idempotent, so marker-bearing prompts are unchanged. The shared
prependSystemPromptAddition wrapper and the static prependSystemContext /
appendSystemContext hook fields are untouched.
* fix(agents): keep marker-free idle prompts cacheable below the boundary
A marker-free hook systemPrompt override only had the cache boundary
ensured on turns with an active media task. On idle turns the later
appendModelIdentitySystemPrompt landed above the absent boundary, so the
idle cached system prefix diverged from active turns and prompt caching
broke across active/idle transitions. Ensure the boundary regardless of
media state in both the embedded and CLI runners, and extend the
regression to cover the model-identity append across active->idle.
* fix(agents): scope cache-boundary ensure to the model-identity append
Ensuring the boundary unconditionally on media-idle turns appended a
boundary marker to empty raw/gateway system prompts (turning "" into a
marker-only prompt) and to prompts with nothing below the boundary.
Instead ensure the boundary only when a model identity line is actually
appended to a non-empty prompt, in both the embedded and CLI runners.
This still keeps the identity below the boundary for marker-free hook
systemPrompt overrides (the #85203 idle-cache regression) while leaving
empty and identity-less prompts untouched.
* test: refresh stale type and lint expectations
* test: stabilize CI timeout checks
* test: satisfy channel entry lint
* fix(agents): skip cache boundary for blank prompts
* fix(channels): keep draft flush timer referenced
* test(agents): tolerate failed exec timeout setup
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Provider-scoped configured regex mention patterns for Discord, Matrix, Slack, Telegram, and WhatsApp.
Native platform mentions keep their existing behavior, and unsupported channels do not opt into the new regex policy path. The new policy supports per-channel allow/deny routing through mentionPatterns.mode with allowIn and denyIn so group auto-reply regexes can be limited without broad global blast radius.
Refs #70864.
Supersedes #87200.
Thanks @patrick-slimelab.
Adds Xiaomi MiMo voicedesign TTS support by registering the v2.5 voicedesign model and omitting audio.voice for that model's prompt-driven voice design flow.
Also accepts generic TTS aliases modelId, speakerVoice, and speakerVoiceId for Xiaomi provider config and request overrides.
Fixes exec timeout classification so a process that exits after a missed timeout callback is still reported as timed out, using monotonic deadlines to avoid wall-clock skew.
Verification:
- node scripts/run-vitest.mjs extensions/xiaomi/speech-provider.test.ts
- node scripts/run-vitest.mjs src/process/supervisor/supervisor.test.ts
- node scripts/run-vitest.mjs src/agents/bash-tools.exec-foreground-failures.test.ts
- git diff --check
- autoreview --mode local
- live Xiaomi MiMo voicedesign call returned wav RIFF/WAVE output, 169004 bytes
- GitHub CI success on fb3018ef31: CI 26708919072, CodeQL Critical Quality 26708919082, CodeQL 26708919091, OpenGrep PR Diff 26708919089, Workflow Sanity 26708919083, Dependency Guard 26708918574, Real behavior proof 26708921767
Thanks @GimingRao.
Co-authored-by: Raoyu <2425198313@qq.com>
Co-authored-by: giming <53329020+GimingRao@users.noreply.github.com>
getTimeZoneOffsetMs built localAsUtc via Date.UTC() without the millisecond
argument, so for a sub-second instant the computed timezone offset was wrong by
that fraction. That corrupts resolvedMs and fails the exact-millisecond
re-validation in matchesOffsetlessIsoDateTimeParts, so parseOffsetlessIsoDateTimeInTimeZone
returned null for valid fractional input.
User impact: openclaw cron --at "<ISO>.<ms>" --tz <zone> was silently rejected
even though the parser's regex explicitly accepts fractional seconds (\.\d+).
Pass parts.millisecond (carried from utcMs via getUTCMilliseconds) into Date.UTC
so the offset is exact. Add fractional-second regression rows.
Co-authored-by: coder999999999 <coder999999999@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(infra): guard against overwriting corrupt target session store during migration
migrateLegacySessions reads the target agents/{id}/sessions/sessions.json
and merges it with the legacy sessions dir. When the target file is
corrupt, readSessionStoreJson5 swallows the parse error and returns
{store:{}, ok:false}, so the merge becomes legacy-only. The save gate
(legacyParsed.ok || targetParsed.ok) passes on legacyParsed.ok alone and
never checks targetParsed.ok, so the corrupt target is atomically
overwritten with the legacy-only store. Target-only session records (keys
with no legacy counterpart) are lost permanently and the corrupt file can
no longer be recovered by hand. Legacy corruption is already guarded
(warn + skip delete); target corruption was asymmetrically unprotected.
Skip the save (and the legacy delete) when the target store exists but is
unreadable, leaving the corrupt file and the legacy store both in place,
and push a warning mirroring the legacy-unreadable path. saveSessionStore
and readSessionStoreJson5 signatures are untouched.
AI-assisted: drafted with claude code (claude-opus-4-8).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(infra): report direct-chat session migration only after target save commits
Addresses ClawSweeper review on #88018. The `Migrated latest direct-chat session`
result.changes entry was pushed before the targetReadable guard, so the
corrupt-target skip path (which intentionally does not save) still reported a
session migration in doctor/startup logs. Defer that report into the
save-committed block (keeping its existing position before `Merged sessions
store`) and assert its absence in the corrupt-target regression test.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(infra): add explicit corrupt session recovery
* fix(infra): keep legacy sessions retryable
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Fix Control UI Talk consults so an empty final chat event no longer forces the no-text realtime tool result when a later source-reply or delivery-mirror final contains the answer displayed in the UI.
Also makes agent.wait use the chat-side terminal snapshot while a same-runId chat.send is active, so lifecycle completion cannot beat chat post-dispatch/source-reply delivery.
Adds regression coverage for delayed source replies, agent.wait failure/timeout handling, the wait-before-source-reply race, gateway wait ordering, and punctuation-only skill searches.
Fixes#85275.
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
Add bounded timeouts for Crabbox wrapper sanity probes so a stale or hung selected binary cannot block the wrapper indefinitely. The wrapper now maps timed-out sanity probes to a deterministic failure and keeps provider/help parsing behavior intact.
Also add regression coverage for a binary whose `--version` probe hangs while `run --help` still responds.
Co-authored-by: Evan Newman <evanjames010101@gmail.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* fix(auto-reply): redact config show secrets
* fix(auto-reply): use schema redaction for config show
* fix(auto-reply): redact config set acknowledgements
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
WebChat now stores/restores composer draft and queued sends across refresh, scoped by gateway/session/agent. It skips in-flight/steered sends, restores after agent scope hydration, waits for fresh idle session proof before draining restored sends, and backfills visible chat history when the raw tail contains silent/context entries.
Refs #83344
Co-authored-by: Zee Zheng <zheng.zuo0@gmail.com>
Fixes#86161.
Route Telegram media-message edits through the Telegram caption/reply-markup APIs instead of always calling `editMessageText`. Button-only edits now update reply markup, explicit captions use `editMessageCaption`, and text edits can fall back to caption edits when Telegram reports the message has no editable text.
Also documents the edit behavior, adds regression coverage, tightens timer-spy cleanup for the affected agents test lane, and removes a stale loader helper from the current base that broke core typecheck.
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
Remove isolate: true from the channel Vitest config and fix the leaking fake-timer/mock tests so the lane runs under the shared non-isolated runner. Verified with focused scoped-config/channel tests, the full channel Vitest config, git diff --check, and branch-mode autoreview.
Deliver same-session channel replies directly while preserving stale-reply guards.
The fix bypasses the announce decider only when the requester and target are the same source channel, carries reply baselines into fire-and-forget follow-up delivery, and keeps history reads best-effort so timeout-zero sends still dispatch. It also includes focused regression coverage for delayed same-session replies, stale snapshots, retry timer caps, and the current strict-null/package-boundary blockers fixed while preparing the PR.
Move Telegram plugin-local state from JSON sidecars into plugin-state SQLite. Keep legacy JSON handling in startup and doctor migration plans, with runtime state now reading and writing SQLite directly. Stabilize the channel Vitest lane by cleaning up typing timers and isolating that lane.
Adds a default-enabled SwiftPM Talk trait for OpenClawKit so chat-only consumers can opt out with traits: [] and avoid resolving ElevenLabsKit. Default traits preserve existing talk/TTS API and bundled app behavior; macOS CI now verifies the trait-off dependency graph and build.
Verification:
- CI at 85f00ebc04 passed macos-swift and Real behavior proof.
- Local Swift 6.3.2: trait-off dependency graph omitted ElevenLabsKit; full swift build with default traits disabled built through OpenClawChatUI; default dependency graph still included ElevenLabsKit; trait-off OpenClawKit target build passed.
- merge-tree against latest origin/main 4eba3e5d7d was clean.
- Current main already fails plugin-SDK declaration gates in unrelated TS files; reproduced locally with node scripts/run-tsgo.mjs -p tsconfig.plugin-sdk.dts.json --declaration true.
Thanks @mochiexists.
Co-authored-by: mochiexists <259077624+mochiexists@users.noreply.github.com>
Co-authored-by: atlascodesai <76924051+atlascodesai@users.noreply.github.com>
Keep Slack direct-message sessions stable while tracking routed Slack thread ids on active reply operations. Different top-level Slack DM threads from the same sender no longer steer into or block each other, while ordinary same-thread follow-ups and non-Slack direct-message behavior keep their existing semantics.
Verification:
- `git diff --check origin/main...FETCH_HEAD`
- `/Users/steipete/Projects/agent-scripts/skills/autoreview/scripts/autoreview --mode branch --base origin/main --output /tmp/pr85904-autoreview.txt --json-output /tmp/pr85904-autoreview.json`
- GitHub CI green for head `6703e166545bcb96c1a50de93a42446212cca9a7`, including Real behavior proof and auto-reply reply routing/dispatch shards.
Co-authored-by: guanbear <123guan@gmail.com>
Fixes#88056.
Reload workspace skill commands for `/skill <name>` when directive resolution supplied only an empty placeholder list, so the generic skill wrapper can invoke the same command-visible skills as direct slash commands.
Keep stale-message cutoff and empty-config channel suppression ahead of skill discovery and tool dispatch so suppressed `/skill` messages cannot trigger side-effecting skill tools.
Co-authored-by: Ted Li <tl2493@columbia.edu>
Align Telegram proactive DM-topic outbound session routing with inbound reply routing.
The Telegram plugin now uses the chat-scoped DM-topic suffix for direct-topic outbound sessions, so cron/proactive sends and replies reuse the same session. Delivery metadata is kept as the numeric Telegram topic id so visible sends still target the correct private topic.
Refs #80212.
Thanks @brokemac79.
Verification:
- PR head d904115e4c
- GitHub CI/checks green on PR head; Real behavior proof passed; OpenGrep passed; CodeQL neutral/pass
- git diff --check origin/main...pr/88421 -- extensions/telegram/src/channel.ts extensions/telegram/src/session-route.test.ts
- git merge-tree $(git merge-base origin/main pr/88421) origin/main pr/88421
Fix stale heartbeat scheduler deferrals so disabled/non-retry skips and flood deferrals advance the due slot instead of rearming a 0 ms timer loop.
Fixes#79380.
Supersedes #79418.
Proof:
- pnpm test src/infra/heartbeat-runner.scheduler.test.ts -- --reporter=verbose
- pnpm check:changed via Testbox tbx_01ksxfavykc7qyve4ysnxg3smh
- autoreview clean
- GitHub CI green for 213003a854, including Real behavior proof
Add a bounded `chat.message.get` gateway method so Control UI can fetch one display-normalized transcript message by id when an assistant history preview was truncated. Keep `chat.history` lightweight, reject oversized/hidden/missing rows with explicit unavailable reasons, and wire the WebChat side reader to request full content only for visible truncated assistant messages.
Also refresh the generated Swift gateway protocol models and document the new assistant-message side-reader behavior.
Closes#84651.
Related #53242.
Co-authored-by: NianJiuZst <3235467914@qq.com>
Extract shared normalization/coercion helpers into private @openclaw/normalization-core workspace package while preserving existing plugin SDK helper subpaths.\n\nAlso keeps direct normalization-core imports internal, wires UI/build/loader resolution, and replaces the slow PR network CodeQL lane with a fast added-line boundary scan while retaining full CodeQL for scheduled/manual runs.\n\nVerification: local moved tests, plugin SDK boundary tests, extension loader tests, agents-support shard, UI build/test, build artifacts, lint, workflow guards, autoreview, and GitHub CI passed on PR head 963d893715.
Move Workboard durable data into a relational SQLite database and add extension doctor migration for .28 plugin-state rows. Preserve attachment lifecycle behavior, SQLite permissions/WAL settings, and scoped plugin migration access.
* feat(browser): add optional vision understanding to screenshot tool
* fix(browser): wrap vision output as external content, enforce maxBytes, forward auth profiles
* fix(browser): remove no-op scope/attachments config, drop profile pass-through lacking runtime support
* feat(media-understanding): add profile/preferredProfile to DescribeImageFileWithModelParams and forward to describeImage
* style(browser): add curly braces to satisfy eslint curly rule
* fix(browser): correct tools.browser.enabled help text to match actual behavior
* fix(browser): thread agentDir/workspaceDir from plugin tool context into browser vision
* refactor(browser): move vision config from tools.browser to browser.models
The browser plugin's vision configuration now lives on the top-level
`browser` config namespace (browser.models, browser.visionEnabled,
browser.visionPrompt, etc.) instead of `tools.browser`. This aligns
with the plugin's existing config location and avoids confusion between
tool-level and plugin-level settings.
- Remove tools.browser from ToolsSchema and ToolsConfig
- Add models/vision* fields to BrowserConfig and its zod schema
- Update getBrowserVisionConfig to read from cfg.browser
- Update schema help, labels, and quality test
- Update vision.test.ts to use new config shape
* docs(browser): add screenshot vision configuration section
Document the new browser.models config for automatic screenshot
description via vision models, enabling text-only main models to
reason about web page content.
* fix(browser): remove deliverable media markers from vision result, drop unused import
P1: Vision-success path no longer exposes the raw screenshot as
deliverable media (removes MEDIA: line and details.media.mediaUrl).
This prevents channel delivery from auto-sending sensitive page content
when the intended output is a text description.
P2: Remove unused ToolsMediaUnderstandingSchema import that would fail
noUnusedLocals typecheck.
* fix(browser): add command/args fields to browser models schema
The browser vision model schema uses .strict(), so CLI-type entries
with command/args were rejected by TypeScript. Add these fields to
align with MediaUnderstandingModelSchema.
* chore(browser): remove debug console.log statements
* fix(browser): harden screenshot vision result against MEDIA: directive injection and restore image sanitization on failure fallback
ClawSweeper #84247 review round 2:
P1 (security, high): neutralize line-start MEDIA: directives in vision descriptions
before wrapping with wrapExternalContent. The agent media extractor scans every
browser tool-result text block via splitMediaFromOutput which treats line-start
MEDIA: as a trusted local-media delivery directive, and browser is on the
trusted-media allowlist. Without neutralization, page or vision-provider output
containing 'MEDIA:/tmp/secret.png' could synthesize a channel-deliverable media
artifact from untrusted content. wrapExternalContent itself does not strip
line-start directives. Introduce neutralizeMediaDirectives in vision.ts that
prepends '[neutralized] ' to any line whose trimStart() begins with MEDIA:
(case-insensitive), defanging the parser anchor while keeping the original
text human-readable.
P2 (compatibility): pass resolveRuntimeImageSanitization() to imageResultFromFile
in the vision-failure catch fallback. The non-vision screenshot path already
forwards this option (d5cc0d53b7) so configured agents.defaults.imageMaxDimensionPx
takes effect. Without this fix, any provider timeout/error silently bypasses the
sanitization guard and returns a raw full-resolution screenshot.
Regression coverage:
- vision.test.ts: 6 unit cases for neutralizeMediaDirectives (no-op fast path,
mid-line MEDIA: untouched, line-start defanged, leading-whitespace defanged,
case-insensitive, multiple directives per blob).
- browser-tool.test.ts: 2 integration cases that drive the full screenshot
tool execute path:
- 'neutralizes MEDIA: directives in vision text and does not attach media'
asserts no line matches /^\s*MEDIA:/i in returned text, secret path text
is preserved verbatim, details.media is absent, and imageResultFromFile
is not called on the success path.
- 'preserves screenshot image sanitization on vision failure fallback'
mocks describeImageFileWithModel to reject and asserts the fallback
imageResultFromFile call receives imageSanitization: {maxDimensionPx:1600}
plus the 'browser screenshot vision failed' extraText.
* fix(browser): apply clawsweeper fallback media fix from PR #84247
* refactor: reuse media image understanding for browser screenshots
* refactor: use structured media delivery
* test: update music completion media instruction expectation
* fix: trim buffered reply directive padding
* test: refresh codex prompt snapshots for message media aliases
---------
Co-authored-by: scotthuang <scotthuang@tencent.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Add MCP server add/configure/login/reload flows plus config/runtime support for enablement, filters, timeouts, OAuth, TLS, and parallel execution hints. Update docs and tests for the expanded MCP operator surface.
Treat OpenAI-compatible streaming tool deltas as executable only when the final finish reason is `tool_calls`. This prevents malformed provider streams from triggering spurious tool execution while preserving normal tool-call responses.
Fixes#85161.
Verification:
- Local OpenAI-compatible SSE replay: spurious stop stream `finalToolCalls: 0`; valid tool-call stream `finalToolCalls: 1`.
- `pnpm test src/agents/openai-transport-stream.test.ts src/llm/providers/openai-completions.test.ts -- --reporter=verbose`
- PR CI green on `cdc2fc34753492c862cae99b37f8cf3761d9bbed`.
Co-authored-by: 忻役 <xinyi@mininglamp.com>
Co-authored-by: Jerry-Xin <jerryxin0@gmail.com>
Preserve plugin-resolved cron delivery targets after target resolution so provider-looking canonical target prefixes are not stripped before outbound delivery.
Adds regression coverage for plugin canonical targets returned directly and via aliases, plus a guard that generic normalized fallback targets still strip the selected prefix.
Fixes#87905
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
Surface gateway chat failures as visible assistant messages in the Control UI, with regression coverage and Crabbox/WebVNC proof.
(cherry picked from commit 31a46638ad)
Fixes#63558.
Adds a Dreaming-tab agent selector and propagates the selected agent through Dreaming status, diary, and diary actions while preserving default-agent fallback when agentId is omitted. Also keeps report Memory Palace cards in the Control UI wiki-preview flow and documents the optional Dreaming agentId gateway parameters.
Verification:
- GitHub CI run 26693682975 passed on 43a2b17243.
- CodeQL Critical Quality run 26693682971 passed.
- CodeQL / Security High run 26693682957 passed.
- Workflow Sanity run 26693682949 passed.
- OpenGrep PR Diff run 26693682947 passed.
- Dependency Guard run 26693682003 passed.
- Real behavior proof run 26693860539 passed.
- git diff --check origin/main...refs/remotes/origin/pr/78748 passed.
- git merge-tree --write-tree origin/main refs/remotes/origin/pr/78748 passed.
Thanks @stevenepalmer.
Co-authored-by: Steven Palmer <6134396+stevenepalmer@users.noreply.github.com>
Extracts serialized plaintext tool-call parsing, scrubbing, stream normalization, and standalone promotion into the private internal @openclaw/tool-call-repair package.
Provider wrappers and the embedded runner now share one repair path for standalone serialized tool calls, including adjacent text-block splits, while preserving exact argument bytes when already valid. The public plugin SDK payload module remains as the compatibility facade.
Verification:
- pnpm test src/plugin-sdk/provider-stream-shared.test.ts src/plugin-sdk/tool-payload.test.ts src/agents/embedded-agent-runner/run/attempt.tool-call-normalization.test.ts -- --reporter=verbose
- env -u OPENCLAW_TESTBOX pnpm check:changed
- PR CI: all reported checks green/skipped/neutral on ff0b3c0a5c
Refs #86924
Co-authored-by: fuller-stack-dev <263060202+fuller-stack-dev@users.noreply.github.com>
Preserve Slack Agents & Assistants DM root thread context for tool and subagent replies even when Slack omits or misreports `channel_type`, while leaving non-DM self-thread roots top-level.
Fixes#63659.
Thanks @zozo123.
Fixes#88214.
Control UI dashboard Recent sessions now follows the selected agent, preserves legacy main sessions under stale identity, keeps unknown sessions unscoped, and scopes agent/default session refreshes before the session-list limit. Completed run refreshes now use the run's original session/agent target, global New Chat creates under the selected agent, and the agent switcher preserves last known target sessions across scoped refreshes without resurrecting deleted or archived sessions while accepting newer out-of-scope live rows into the switch cache. Also fixes a current-main lint issue around trusted approval params.
Co-authored-by: 张贵萍0668001030 <zhang.guiping@xydigit.com>
Classify release dependency ownership metadata so release evidence no longer reports current root dependencies as missing ownership metadata. Also recognizes command-explainer package-file lookups for tree-sitter-bash.
Verification: jq empty scripts/lib/dependency-ownership.json; node scripts/dependency-ownership-surface-report.mjs --check; node scripts/root-dependency-ownership-audit.mjs --check; targeted Vitest for root dependency ownership and ownership surface reports; git diff --check; autoreview clean; PR CI green including Real behavior proof.
* fix(responses): drop orphaned assistant msg_* id when reasoning is dropped (#88019)
When an Azure/OpenAI Responses session falls back to a non-Responses model
and later resumes a Responses model, sanitizeSessionHistory drops the
replayable reasoning (rs_*) item via downgradeOpenAIReasoningBlocks. The
paired assistant text block still carried its textSignature (the msg_* id),
so the transport replayed an assistant message item referencing msg_* with
no accompanying rs_* reasoning item. Azure Responses then rejected the next
turn with:
400 Item 'msg_...' provided without its required 'reasoning' item: 'rs_...'
permanently poisoning the session.
Fix:
- downgradeOpenAIReasoningBlocks now strips the textSignature from a turn's
text blocks whenever it drops a replayable reasoning item, so the msg_* id
and its rs_* reasoning are removed together. The transport then falls back
to a synthetic, unpaired id that Azure accepts.
- Because the synthetic fallback id is derived from the per-message msgIndex,
multiple id-less text blocks in one assistant turn (e.g. commentary +
final_answer) would collide on the same id. Make the fallback unique per
text block in both Responses conversion sites
(openai-transport-stream.ts and the shared llm provider
openai-responses-shared.ts).
Tests:
- sanitize-session-history: model-switch path drops the paired msg_* id.
- embedded-agent-helpers: downgrade strips paired text signature(s).
- reasoning-replay: multiple id-less text blocks get distinct item ids.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix(responses): preserve phase metadata and guard malformed blocks (#88019)
Address PR review feedback on the orphaned msg_* replay fix:
- Preserve Responses phase metadata: dropping the paired msg_* id when its
rs_* reasoning is removed previously stripped the entire textSignature,
which also discarded the phase (commentary/final_answer). Phased text now
keeps a phase-only signature ({v:1,phase}) so commentary is not replayed
as user-visible output. Both parseTextSignature copies (shared provider and
embedded transport) now accept id-less phase-only signatures and fall back
to a synthetic id while preserving the phase.
- Guard malformed content blocks: the post-drop map no longer dereferences
contentBlock.type unconditionally, so a corrupted transcript with a
null/primitive block can still sanitize through a model switch.
Tests:
- sanitize-session-history: phase metadata is preserved while the paired id
is dropped on a model switch.
- reasoning-replay: id-less phase-only signatures get distinct synthetic ids
and retain their phase.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Payload-less session write-lock files now get a 30s grace for default/long acquire timeouts and cleanup sweeps, while short acquire timeouts keep 5s recovery. This avoids reclaiming a lock while the owner is suspended between exclusive create and metadata write.
Verified with:
- git diff --check origin/main...HEAD
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main --parallel-tests "node scripts/run-vitest.mjs src/agents/session-write-lock.test.ts"
- gh pr checks 80686 --repo openclaw/openclaw --watch=false
Thanks @wAngByg.
Extract web-content shared runtime helpers into packages/web-content-core, move the focused tests with the new package, and split quiet CI shards so the node matrix no longer stalls past the no-output watchdog.\n\nVerification: node scripts/run-vitest.mjs test/scripts/ci-node-test-plan.test.ts test/scripts/run-vitest.test.ts src/infra/restart.test.ts src/infra/os-summary.test.ts src/infra/gateway-processes.test.ts src/infra/inline-option-token.test.ts src/infra/map-size.test.ts src/infra/machine-name.test.ts src/commands/doctor-whatsapp-responsiveness.test.ts; autoreview clean; manual CI https://github.com/openclaw/openclaw/actions/runs/26693962844; dependency guard https://github.com/openclaw/openclaw/actions/runs/26693959937. Admin merge used because optional Mantis Telegram Desktop proof was cancelled after blocking merge outside this PR's required proof.
Bound MCP channel bridge pending Claude permission and approval maps with TTL sweep and close cleanup.
Also sweep before listing pending approvals so expired requests are not exposed between periodic ticks.
Fixes#71646.
Thanks @Feelw00.
Adds `openclaw sessions tail` as an operator-facing progress view over session trajectory events, with conservative redaction for prompt text, tool arguments, and tool result bodies. The command supports explicit session keys, store/agent scope, follow mode, relocated trajectory pointer files, and cursor-safe follow across bounded trajectory window rewrites.
Documents the new sessions tail CLI surface in `docs/cli/sessions.md`.
Fixes#83441.
Co-authored-by: zhengzuo0-ai <zheng.zuo0@gmail.com>
Skip browser lifecycle cleanup when root browser support or the browser plugin entry is disabled, and make the browser maintenance facade respect activation before cached surface use.
Also stabilize the resource-only MCP runtime test by waiting for the async rejection log that CI can observe late.
Verification:
- pnpm test src/plugin-sdk/browser-maintenance.test.ts src/browser-lifecycle-cleanup.test.ts src/auto-reply/reply/session.test.ts src/gateway/server.sessions.reset-cleanup.test.ts src/agents/auth-profiles/usage.test.ts
- pnpm test src/agents/agent-bundle-mcp-runtime.test.ts
- git diff --check
- pnpm build
- autoreview local: no accepted/actionable findings
- GitHub Actions: CI 26693713166, CodeQL 26693713159, CodeQL Critical Quality 26693713157, OpenGrep PR Diff 26693713125, Workflow Sanity 26693713149, Dependency Guard 26693712478
Co-authored-by: Nicolas Van Eenaeme <nicolas@poison.be>
Move MSTeams conversation and poll plugin-local stores to plugin-state SQLite. Legacy JSON stores import once without overwriting existing SQLite state; conversation and poll IDs are hashed for plugin-state keys; poll votes are sharded with bounded row-cap headroom and prune cleanup; MSTeams docs now describe SQLite storage. SSO and delegated token stores are unchanged. Verified with focused MSTeams tests, docs sanity, autoreview, Testbox check:changed, and green PR CI.
Deduplicate the browser lifecycle cleanup wrapper for embedded subagent completions while preserving retire and announce finalization for duplicate callers.\n\nAdds regression coverage for parallel completion callers and the held-first-cleanup duplicate-tail path.\n\nFixes #68668.\n\nCo-authored-by: Feelw00 <dhrtn1006@naver.com>
Repair invalid \u escapes during streaming JSON parsing without changing valid Unicode escapes. Split oversized node CI doctor/infra shards and fix the restart test mock deadlock so PR CI stays under the no-output threshold.\n\nCo-authored-by: Coder <83845889+coder999999999@users.noreply.github.com>
Move model catalog normalization and package-owned catalog schema/types into model-catalog-core while keeping public plugin SDK model catalog declarations on the existing SDK surface. Verified focused tests, package-boundary compile, full build, changed gate, declaration leak grep, CI, and autoreview.
Keep Codex app-server continuation turns alive after post-tool, raw assistant, and progress notifications, and reschedule continuation idle watches when shorter progress timeouts apply.
Add regression coverage for the plugin-sdk child_process mock helper deadlock that blocked CI shards on this PR.
Co-authored-by: abnershang <abner.shang@gmail.com>
Stop minimal cliStartup and gatewayWatch builds from copying generated plugin static assets they intentionally do not build.\n\nVerified with focused Vitest, autoreview, AWS Crabbox startup-memory proof, and AWS Crabbox changed gate run_bd9ea01e6a12 plus rebased changed gate run_bd9ea01e6a12.
* fix(export-html): guard all msg.content and result.content filter/iteration paths
Three call sites in the export HTML template called `.filter()` or iterated
with `for...of` directly on `msg.content` or `result.content` without first
checking `Array.isArray`. When a transcript message row carries a non-array
content value (null, undefined, or any scalar), those paths throw:
TypeError: msg.content.filter is not a function
Fix: normalize with `Array.isArray(x) ? x : []` before every unguarded
filter and iteration on `msg.content` (computeStats stats path and the
renderEntry assistant render loops) and `result.content` (renderToolCall
text/image accessors).
Regression test added: renderTemplate resolves without throwing for assistant
messages with null, undefined, string, and numeric content values.
Closes#88255
* fix(export-html): guard user message text extraction path against non-array content
The user-message render path in the export HTML template extracted text with
`content.filter(...)` without checking whether `content` is an array. A
persisted user message row with null, undefined, or any non-string scalar
content crashed during export with the same TypeError class as the assistant
path.
Fix: normalize the ternary so a non-string, non-array value falls through to
an empty string rather than calling `.filter` on it.
Regression test added for null, undefined, and numeric user message content.
Addresses feedback from ClawSweeper review on #88271.
* fix(export-html): preserve string content guards
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Move model catalog ref helpers into @openclaw/model-catalog-core/model-catalog-refs and update internal callers/package-boundary aliases. Also fix the timestamp predicate typing that blocked prod type checks on current main.
Fixes#37748.
Sort skill package archive entries by relative POSIX archive name so generated `.skill` bundles are reproducible regardless of filesystem traversal order.
Verification:
- `PYTHONDONTWRITEBYTECODE=1 python3 skills/skill-creator/scripts/test_package_skill.py`
- `git diff --check origin/main...HEAD`
- GitHub CI run 26690938925 on `43a0fdf7175f33a5c74bc7ff92723ebf5efc4df9`: all checks passed except repeated unrelated no-output timeouts in `checks-node-agentic-commands-doctor` and `checks-node-core-runtime-infra-state` after visible tests passed.
Forward OpenAI-compatible stop sequences from gateway chat completions through the agent runner into provider transports.
The gateway now normalizes stop into sampling extras, agent transports pass it into the shared stream options, and OpenAI, Anthropic, Mistral, Google, and Vertex-backed simple providers map it to their native request fields. Provider/gateway/agent coverage plus Crabbox live gateway proof verify valid stop dispatch and invalid stop rejection.
Refs #87920
Show the remote node name in exec tool transparency details when an exec call targets `host=node`, while ignoring stray `node` values for gateway, sandbox, and auto-host calls.
Covers node-only, cwd+node, absent-node, and non-node-host regression cases in the tool display tests.
Fixes#77719.
Co-authored-by: JiataiWang <wangjiatai@proton.me>
Feishu `channels.feishu.streaming=true` now streams ordinary assistant replies through CardKit in auto mode, while keeping tool-summary delivery on the existing message path.
Also discards stale partial previews when final delivery intentionally suppresses text for voice media or duplicate final text, and preserves streamed partial text for regular media-only finals.
Verification:
- `node scripts/run-vitest.mjs run extensions/feishu/src/reply-dispatcher.test.ts`
- `pnpm tsgo:extensions`
- `pnpm test:extensions:package-boundary:compile`
- `pnpm exec oxfmt --check extensions/feishu/src/reply-dispatcher.ts extensions/feishu/src/reply-dispatcher.test.ts extensions/feishu/src/streaming-card.ts`
- `git diff --check`
- `.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main`
- GitHub PR checks on run 26689677607 passed except repeated unrelated broad Vitest no-output timeouts in `checks-node-agentic-commands-doctor` and `checks-node-core-runtime-infra-state`.
Co-authored-by: 传妈 <chuanmother@chuanMac-Mini.local>
Fixes#88218.
Preserves exact configured provider/model defaults before bare alias target reverse matches, while retaining slash-form aliases and auth-profile alias behavior.
Co-authored-by: Steven Palmer <palmer.e.steven@gmail.com>
Carry Discord reply typing feedback through preflight, queued dispatch, and cleanup so delayed accepted replies keep typing alive at the actual dispatch target without duplicate keepalives. Adds focused Discord queue/process policy coverage and stronger lifecycle invariant comments.
Prunes undefined Discord component and modal registry metadata before persisting it so SQLite-backed plugin state never receives JSON-incompatible undefined values. Adds direct regression coverage for undefined own properties on component, modal, and nested field entries.
Add actionable operator guidance when an unauthorized SIGUSR1 gateway restart is ignored because unmanaged restart is disabled.
The change is log-only: restart authorization and scheduling semantics are unchanged, and the existing run-loop test now asserts both the reason warning and the recovery hint.
Refs #79577
Refs #78110
Refs #82433
Co-authored-by: wAngByg <281221101+wAngByg@users.noreply.github.com>
Dedupe prompt-side inbound media note suffixes when sanitized MediaPath and MediaUrl render to the same value, while preserving genuinely distinct remote URLs.\n\nFixes #47587.\nThanks @MoerAI for the patch and @yzjJosh for the report.
Show the same Installing OpenClaw package progress line in the no-gum npm install fallback before redirecting npm output to the temp log.
Fixes#82305
Co-authored-by: Sebastien Tardif <sebtardif@ncf.ca>
Adds focused coverage for task-domain view mapper DTO contracts, including summary cloning, task run/detail mapping, flow view/detail mapping, and implicit summary computation.
Test-only PR. Verified with git diff --check and PNPM_CONFIG_VERIFY_DEPS_BEFORE_RUN=false pnpm test src/tasks/task-domain-views.test.ts on the current-main merge result.
Thanks @leno23.
Co-authored-by: wuyangfan <yangfan.wu@succaiss.com>
Fixes#49517.
Updates the TUI command catalog so /new describes spawning an isolated session while /reset describes resetting the current session. Adds a focused regression test for the two descriptions.
Co-authored-by: KhanCold <119404710+KhanCold@users.noreply.github.com>
Adds a persisted collapse state for the Control UI Recent sessions sidebar group, including storage and browser coverage.
Also narrows gateway run miss cache expiry typing so the rebased branch stays clean against current main.
Closes#85510
Co-authored-by: NianJiuZst <3235467914@qq.com>
Route internal model catalog imports to the extracted @openclaw/model-catalog-core package and delete obsolete internal facades.
Keep public SDK declarations self-contained by wrapping core helpers at public boundaries instead of leaking private package imports.
Verification:
- pnpm test src/plugins/contracts/model-catalog-core-imports.test.ts src/plugins/sdk-alias.test.ts packages/model-catalog-core/src/configured-model-refs.test.ts packages/model-catalog-core/src/provider-model-id-normalize.test.ts packages/model-catalog-core/src/provider-model-id-normalization.test.ts src/config/config.model-ref-validation.test.ts src/agents/model-selection.test.ts src/plugin-sdk/provider-model-shared.test.ts -- --reporter=verbose
- pnpm check:test-types
- pnpm test:extensions:package-boundary:compile
- pnpm build
- rg "@openclaw/model-catalog-core" dist/plugin-sdk packages/plugin-sdk/dist -n --glob '*.d.ts' || true
- git diff --check
- autoreview clean after fix
CI note: merged with admin override because checks-node-agentic-commands-doctor and checks-node-core-runtime-infra-state failed twice with exit 143/no-output watchdog termination after prior passing test output, while relevant local proof and the rest of CI were green.
Fixes#88198.
Ignore top-level helper scripts in auto-discovered global/workspace extension roots so they do not become manifestless plugin candidates during config validation. Standalone plugin files remain supported when explicitly configured through `plugins.load.paths`, and docs now call out the supported path.
Verification:
- `node scripts/run-vitest.mjs src/plugins/discovery.test.ts src/config/config.plugin-validation.test.ts`
- `node scripts/run-oxlint.mjs src/plugins/discovery.ts src/plugins/discovery.test.ts src/config/config.plugin-validation.test.ts`
- `git diff --check`
- GitHub CI green at `93073bfa85ee294e644c623881ba59ba71d90975`
- `.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main`
Thanks @mushuiyu886 for the fix and @mmhzlrj for the report.
Pack newline-mode outbound paragraphs up to the configured text limit instead of sending one message per blank-line-separated paragraph. Preserves markdown fence guardrails and adds focused chunking plus outbound delivery regressions.\n\nVerified: autoreview clean; node scripts/run-vitest.mjs src/auto-reply/chunk.test.ts src/infra/outbound/deliver.test.ts; git diff --check origin/main...HEAD.\n\nThanks @kesslerio.
Fixes#66509.
QQBot now sends text-only tool progress immediately when partial streaming is enabled instead of buffering it until a fallback timer that is cleared by the final block. Immediate progress uses QQ plain-text sends so markdown-enabled accounts do not reinterpret media-like progress text, while streaming-off behavior remains final-only.
Thanks @gabrielduartesignart for the report.
Co-authored-by: samzong <samzong.lu@gmail.com>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* refactor: extract model catalog core package
* refactor: route model catalog imports through package boundary
* build: include model catalog in plugin sdk package dts
* fix: preserve static fallback model metadata
Classify the exact `ws` pre-handshake close-before-open error as a benign uncaught network exception so transient Feishu WebSocket cleanup does not crash the gateway process.
The classifier now keeps the upstream `ws` message as an exact contract and rejects broader prefixed WebSocket messages, with regression coverage for direct, wrapped, and non-exact cases.
Fixes#88257.
Thanks @akrimm702.
Co-authored-by: AI-HUB <144416483+akrimm702@users.noreply.github.com>
Completed WebChat stream segment bubbles now render without the active streaming animation after live output has moved on. The UI chat item contract now marks completed stream segments as non-streaming and the active stream as streaming, so the renderer applies the pulsing class only to live output.
Verified with:
- node scripts/run-vitest.mjs ui/src/ui/chat/build-chat-items.test.ts ui/src/ui/chat/grouped-render.test.ts ui/src/ui/views/chat.test.ts
- node scripts/run-tsgo.mjs -p test/tsconfig/tsconfig.test.ui.json --incremental --tsBuildInfoFile .artifacts/tsgo-cache/test-ui-stream-artifacts.tsbuildinfo
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
PR: #88225
Credit: @scotthuang
Refactor OpenAI provider identity so OpenAI remains the canonical provider for API-key and OAuth-backed flows while legacy openai-codex state is doctor/migration-only.
Keeps OpenAI Codex Responses as an API/transport class rather than a provider identity, moves auth aliases through providerAuthAliases, updates doctor repair sequencing for old auth/profile state, and refreshes tests/docs around the canonical OpenAI behavior.
Resolve raw plugin config environment references before plugin discovery and validation, while preserving the existing single-pass behavior for configs already loaded through config IO.
The loader now resolves raw config opt-ins with config.env vars included, bypasses active/cache reuse for that mode, and redacts plugin entry config from raw-mode cache keys so resolved secrets do not enter registry keys or reentry errors.
Verification:
- OPENCLAW_VITEST_MAX_WORKERS=1 node scripts/run-vitest.mjs src/plugins/loader.test.ts src/plugins/loader.runtime-registry.test.ts
- autoreview --mode branch --base origin/main
- pnpm check:changed on Blacksmith Testbox tbx_01ksw36bp7zygwxgq3jcsvjv3b / GitHub Actions run 26680322889
- PR CI green on facb77634e
Co-authored-by: Peter Lindsey <peter@lindsey.jp>
Adds first-class Xiaomi Token Plan provider support with regional onboarding/configuration, token-plan key prefix validation, runtime pricing/catalog metadata, and docs/test coverage.
Keeps Token Plan model catalog discovery runtime-owned so region-specific base URLs are required and the provider cannot silently fall back to the static SGP manifest catalog.
Fixes#86169.
Verification:
- node scripts/run-vitest.mjs src/plugins/provider-discovery.runtime.test.ts extensions/xiaomi/index.test.ts src/plugins/manifest-model-catalog.test.ts src/model-catalog/manifest-planner.test.ts
- git diff --check
- autoreview --mode local: clean, no accepted/actionable findings
- CI run 26678998539: all relevant checks passed; check-prod-types failed on unrelated browser unused-function issue already present on origin/main
Co-authored-by: NianJiuZst <3235467914@qq.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Keep Codex post-tool assistant/commentary progress and patch snapshot updates on the post-tool completion guard so long generated edits do not fall back to terminal idle handling. Enable Codex patch streaming events for native code mode and refresh exact prompt/config expectations.
Verification:
- pnpm prompt:snapshots:check
- pnpm test extensions/codex/src/app-server/run-attempt.turn-watches.test.ts extensions/codex/src/app-server/thread-lifecycle.test.ts extensions/codex/src/app-server/thread-lifecycle.binding.test.ts extensions/codex/src/app-server/side-question.test.ts
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
- git diff --check origin/main...HEAD
- exact-head CI run 26677938955
- Real behavior proof override run 26678097960
Thanks @keshavbotagent.
Co-authored-by: Kelaw - Keshav's Agent <keshavbotagent@gmail.com>
Stop Codex app-server turns from projecting mirrored OpenClaw transcript history into prompt/model-input surfaces by default. Keep context-engine output on the rendered prompt/developer-instruction path and preserve mirrored history only for OpenClaw-side snapshots.
Move OpenClaw skills and the routed workspace-memory pointer out of native Codex turn user input and into turn-scoped collaboration developer instructions.
Preserve full MEMORY.md fallback prompt injection, delivery-hint rewrapping, lightweight cron exact prompts, and trajectory reporting for the rendered developer surface.
Co-authored-by: Beru <beru@lastguru.lv>
Fix Codex app-server native thread overflow recovery and CLI compaction fallback.
- rotate Codex native startup bindings when rollout token pressure leaves too little headroom
- keep byte-size rollout fuses ahead of rollout content reads
- clear stale resumed context-engine bindings only when the stored thread id still matches
- fall back to context-engine compaction when Codex owns/skips native compaction
Verification:
- node scripts/run-vitest.mjs run --config test/vitest/vitest.extension-codex.config.ts extensions/codex/src/app-server/startup-binding.test.ts extensions/codex/src/app-server/run-attempt.context-engine.test.ts extensions/codex/src/app-server/session-binding.test.ts --reporter=verbose
- node scripts/run-vitest.mjs run --config test/vitest/vitest.agents.config.ts src/agents/command/cli-compaction.test.ts --reporter=verbose
- git diff --check origin/main...HEAD
- autoreview --mode branch --base origin/main: clean
- GitHub CI for 466bfbe78c: green
Co-authored-by: fuller-stack-dev <263060202+fuller-stack-dev@users.noreply.github.com>
A claude-cli session whose JSONL transcript ends with an assistant
`tool_use` content block that was never answered by a `tool_result` user
message cannot resume — claude-cli will sit waiting for the missing
`tool_result`, hit its no-output watchdog, and the runtime kills it
with `reason=abort`. The dispatcher then sees an empty payload and emits
NO_REPLY, which to the user looks like the agent silently ignored their
message — same end-user symptom as the binding-flush amnesia bug, but a
different root cause.
The orphan can be left behind when:
- Gateway restarts mid-tool (brew upgrade, manual kickstart, OOM,
crash) — claude was waiting on a tool result that never arrived.
- `claude-live-session.ts` no-output watchdog fires while a tool is
actively running and OC kills the subprocess.
- The tool itself crashed or hung past its own deadline.
In all cases the resumed session is dead until the binding gets cleared,
because every subsequent resume hits the same trailing tool_use and the
same kill cycle. Observed in production on a personal OpenClaw gateway
(3d-engineer agent, 50-message-deep transcript ending in a Bash
`tool_use`; every Telegram message after the orphan landed silently
aborted at the 180s no-output mark).
Add `claudeCliSessionTranscriptHasOrphanedToolUse` to the helpers that
walks the JSONL, finds the last assistant message, and returns true if
any of its `tool_use` ids has no matching `tool_result` later in the
file. Wire into `prepareCliRunContext` as a second invalidator gate
alongside `missing-transcript`. The new `invalidatedReason:
"orphaned-tool-use"` follows the same path as missing-transcript: the
binding is dropped, this turn starts a fresh session, and the prior
context is reseeded into the new session via `RAW_TRANSCRIPT_RESEED`.
Detection only considers TRAILING orphans — an unanswered tool_use
deeper in history is inert because a later assistant message already
moved past it. Only the most recent assistant message's tool_use ids
matter for forward progress.
Probe runs only for claude-cli providers and only when the transcript-
content gate already passed, so we add no I/O on already-invalidated
sessions and no behavior change for non-claude providers.
AI-assisted: yes. Tooling: Claude Opus + claude-cli.
When a claude-cli turn produces a session id but the underlying claude
subprocess fails to flush an assistant-role record to its
~/.claude/projects/<cwd>/<sid>.jsonl transcript (e.g. mid-turn kill from
a concurrent fingerprint-mismatched turn, supervisor restart, internal
failure), buildCliRunResult was still persisting that session id into
cliSessionBinding. The next turn ran claudeCliSessionTranscriptHasContent,
didn't find the file, logged 'cli session reset: reason=missing-transcript',
and started a brand-new claude session with empty memory.
End-user symptom: agent forgets prior conversation between turns.
Gate the cliSessionBinding spread on the same predicate the next-turn
invalidator uses, evaluated at write time. Also clear agentMeta.sessionId
in the same case so the session-store fallback at command/session-store.ts
(which reads agentMeta.sessionId via setCliSessionId when the binding is
absent) doesn't re-persist the unflushed sid through a different field
path. The fallback is what makes the binding-only gate insufficient on
its own; both writes must drop together.
The gate only fires for claude-cli providers — other CLI providers don't
write to ~/.claude/projects, so probing them would always return false
and incorrectly strip valid binding metadata. isCliBindingFlushed now
takes the provider id and returns true unconditionally for non-claude-cli
sessions.
A bounded retry (0 / 50 / 150 ms) tolerates the brief gap between
claude-cli's stdio close and the OS making the JSONL line visible to
readers (cooperative fsync semantics on APFS, but not guaranteed under
stress).
The transcript-probe is exposed as an injectable dep
(setCliRunnerTestDeps / restoreCliRunnerTestDeps) mirroring the existing
pattern in src/agents/cli-runner/prepare.ts so isCliBindingFlushed is
testable without touching ~/.claude/projects.
AI-assisted: yes. Tooling: Claude Opus + claude-cli. Codex review caught
the fallback path and the missing provider gate before this hit upstream.
Real-Behavior-Proof: dist-side patch on M5 gateway; branch-build
follow-up pending — see PR body.
Move task run, delivery, and flow registry persistence onto the shared OpenClaw state SQLite database.
Summary:
- Store task runs, delivery state, and flow runs in state/openclaw.sqlite via the generated Kysely schema.
- Migrate shipped task sidecars into the shared state DB and archive old sidecars, including invalid-config/read-only CLI paths.
- Keep startup migration lightweight for read-only status/tasks paths while still detecting known legacy state markers and custom session stores.
Verification:
- .agents/skills/autoreview/scripts/autoreview --mode local: clean after final fix
- pnpm test src/tasks/task-registry.store.test.ts src/tasks/task-flow-registry.store.test.ts src/commands/doctor-state-migrations.test.ts -- --reporter=verbose
- pnpm test src/commands/doctor-state-migrations.test.ts src/cli/program/config-guard.test.ts src/cli/route.test.ts src/cli/command-path-policy.test.ts -- --reporter=verbose
- pnpm test src/cli/program/config-guard.test.ts src/cli/route.test.ts src/cli/command-startup-policy.test.ts src/cli/command-path-policy.test.ts src/cli/command-execution-startup.test.ts -- --reporter=verbose
- pnpm test src/cli/program/config-guard.test.ts src/cli/argv.test.ts src/cli/route.test.ts src/commands/doctor-config-preflight.state-migration.test.ts -- --reporter=verbose
- pnpm test src/tasks/task-flow-registry.store.test.ts -- --reporter=verbose
- pnpm test test/scripts/lint-suppressions.test.ts -- --reporter=verbose
- pnpm db:kysely:check
- pnpm lint:kysely
- git diff --check HEAD
- pnpm test:startup:memory
- PR CI green on 2f7d76f0d5
Preserve iMessage SMS reply routes for approval replies so a direct SMS /approve response can acknowledge and return results to the same SMS conversation.
Verification: gateway-only build, extension type checks, CI build-artifacts/check-prod-types/check-test-types/check-lint/check-additional-extension-package-boundary, and live prod iMessage SMS approval proof. checks-node-core-fast was waived by maintainer request after unrelated flaky failures in non-iMessage tests.
Adds Workboard orchestration statuses, dependency links, idempotent child creation, dispatch, and complete/block lifecycle operations backed by the plugin SQLite keyed store.
Persists tenant, skills, workspace, schedule, runtime, retry, dispatch, and handoff metadata in card records, with claim scoping and token redaction. Surfaces the new states and metadata in the Control UI, horizontal board layout, localized strings, and Workboard docs.
Verification:
- pnpm test extensions/workboard/src/store.test.ts extensions/workboard/src/tools.test.ts extensions/workboard/src/gateway.test.ts ui/src/ui/controllers/workboard.test.ts ui/src/styles/workboard.test.ts ui/src/ui/views/workboard.test.ts -- --reporter=verbose
- pnpm ui:i18n:check
- /Users/steipete/Projects/agent-scripts/skills/autoreview/scripts/autoreview --mode branch --base origin/main, followed by focused clean local autoreview loops for final fixes
- env -u OPENCLAW_TESTBOX pnpm check:changed
- git diff --check
Summary:
- The PR classifies selected embedded agent provider-denial error payloads through the shared failover matcher ... 1/current-ak auth matching, preserves guarded non-fallback cases, and covers fallback progression in tests.
- PR surface: Source +34, Tests +166. Total +200 across 5 files.
- Reproducibility: yes. Current main is source-reproducible: a non-GPT embedded result whose only signal is CE ... returns null from the classifier, and the fallback wrapper treats null classification as candidate success.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(agents): classify embedded provider business denials for fallback
- PR branch already contained follow-up commit before automerge: fix(clawsweeper): address review for automerge-openclaw-openclaw-8304…
Validation:
- ClawSweeper review passed for head e266beac93.
- Required merge gates passed before the squash merge.
Prepared head SHA: e266beac93
Review: https://github.com/openclaw/openclaw/pull/84814#issuecomment-4505010446
Co-authored-by: Stellar鱼 <2182712990@qq.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Fixes#86820.
Preserve Codex OAuth-backed compaction by selecting and loading the Codex harness before resolving direct or queued compaction models, while keeping OpenAI-compatible custom base URLs on the OpenAI context config path. Also preserves persisted concrete harness pins so compaction does not hot-switch existing sessions just because an explicit Codex fallback exists.
Verification:
- node scripts/run-vitest.mjs src/agents/embedded-agent-runner/compact.hooks.test.ts src/agents/harness/selection.test.ts src/agents/harness/runtime-plugin.test.ts
- pnpm tsgo:prod
- pnpm check:test-types
- pnpm lint --threads=8
- git diff --check origin/main...HEAD
- git diff --check
- autoreview clean: no accepted/actionable findings reported; overall patch is correct (0.82)
- GitHub PR checks green on ac6f93de4a
Fix Codex app-server completion-stall recovery so replay-safe stdio completion-idle failures retry once, while progress/terminal turn-watch timeouts only surface timeout payloads.
Also preserve post-tool completion guards for scoped native response deltas and stabilize the oversized CONNECT timeout regression test picked up from latest main.
Co-authored-by: Kelaw - Keshav's Agent <keshavbotagent@gmail.com>
Adds the shared SQLite state database base, moves plugin keyed state into it with doctor migration coverage, and keeps generated Kysely guardrails aligned. Proof: focused SQLite/plugin-state tests, db:kysely:check, lint:kysely, architecture/dependency guards, autoreview, and PR CI all clean.
Move compaction planning work to a bounded worker-thread path so large transcript planning no longer monopolizes the agent event loop. Extract pure planning helpers, sanitize worker inputs before structured clone, package the worker entrypoint, and keep synchronous fallback only for worker-unavailable cases.
Fixes#86358.
Fixes#87438.
Bound unset heartbeat run timeouts so background heartbeat turns no longer inherit the built-in 48-hour interactive agent default. Timeout precedence is explicit heartbeat timeout, explicit global agent timeout, then heartbeat cadence capped at 600 seconds.
Verification:
- git diff --check
- Testbox tbx_01kstna69zvznn4fq7zrqr04a1: corepack pnpm test src/infra/heartbeat-runner.model-override.test.ts -- --reporter=verbose passed 13 tests
- Direct node --import tsx runtime probe verified 300s, 600s, 60s, and 45s timeout precedence cases
- Autoreview clean
Known CI state:
- PR CI run 26661465248 has failures matching latest main CI run 26661386468 at a7820b2f54; failures are outside this six-file heartbeat/docs diff.
Keep session lock cleanup from removing live OpenClaw-owned locks solely because they are old. Cleanup now reports age-only stale locks without deleting them, while still removing dead, orphaned, recycled, malformed-old, and non-OpenClaw-owned locks.
Update doctor docs and regression coverage for the cleanup/repair contract.
Refs #87779
Notte exposes a CDP-compatible WebSocket gateway at
wss://us-prod.notte.cc/sessions/connect?token=<NOTTE_API_KEY> that
auto-creates a session on connect — the same shape OpenClaw's existing
"Direct WebSocket CDP providers" section was generically framed for
(per #31085).
Real behaviour proof (against wss://us-prod.notte.cc/sessions/connect):
$ openclaw browser --browser-profile notte open https://example.com
opened: https://example.com/
tab: t4
id: 7FE04AC44931A6E1C799DE4ABF0DC807
A screenshot captured against the same session is a 1254x1111 PNG of
the rendered example.com page.
Playwright connectOverCDP flow against the same URL (today):
connectOverCDP 695ms
context.newCDPSession(page) 169ms
session.send('Target.getTargetInfo') → targetId 87ms
page.goto('https://example.com') 631ms
total 1.8s
AI-assisted (Claude Opus 4.7). codex review --base origin/main returned
clean. See PR description for the full pre-flight checklist.
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Forward initial image/file attachments when spawning ACP subagents through the existing sessions_spawn attachment opt-in. Remove the PR-only acpEnabled config split so ACP uses the same attachment gate as other runtimes.
Also fix the PR branch CI fallout: type the browser element CLI request mock and use Vitest env stubs in the Azure speech test to satisfy the changed-path security scan.
Verification:
- GitHub CI passed on f6ca26b160.
- Autoreview clean.
- Crabbox AWS live OpenAI proof passed: cbx_a576d49493fe / run_081dcc6c6a1b.
Thanks @zhangguiping-xydt.
Fix `sessions.json` persistence after compaction transcript rotation.
When the agent runtime rotates from the pre-compaction session transcript to the post-compaction transcript, post-run consumers now receive the effective OpenClaw session id and session file. Backend CLI session ids remain backend metadata and no longer overwrite the top-level OpenClaw session identity.
Refs #88040.
Thanks @1052326311.
Verification:
- `node scripts/run-vitest.mjs src/agents/agent-command.compaction-rotation.test.ts src/agents/agent-command.live-model-switch.test.ts src/agents/command/session-store.test.ts`
- Autoreview clean
- GitHub CI green on PR head `c3d3c77ddf675bbba0b9ba6681b030a2f69a898c`
Fix claude-cli transcript resume so session-id rotation and transcript flush timing do not drop valid resume state.
- Capture the latest claude-cli session_id from JSONL output.
- Resolve Claude project transcript paths through the shared canonical project-dir resolver.
- Probe transcript content from the actual CLI process cwd.
- Thanks @benjamin1492!
Persist GitHub Copilot SDK session ids in the plugin-state SQLite store so separate OpenClaw process turns can resume the same Copilot-side session when the compatibility fingerprint still matches.
The fingerprint covers provider/model/cwd, resolved agent id, resolved Copilot home, and auth identity. Plugin-state lookup/register/delete failures are non-fatal, stale rows are invalidated, and reset delete failures use an in-process tombstone so reset does not accidentally reuse a durable binding.
Also routes the QQBot token POST through the plugin SDK SSRF guard with capture disabled for the secret-bearing request, preserving the current token lifetime validation from main.
Verification: focused Copilot and QQBot Vitest suites, raw channel fetch guard, autoreview clean, Blacksmith Testbox pnpm check:changed tbx_01kst9fwjmsfzwaxqatszcbf40, live local Copilot two-turn smoke with the same SDK session id persisted in SQLite.
Refs #88064
Summary:
- The PR changes plugin auto-enable materialization so an explicit empty `plugins.allow` stays empty while non-empty restrictive allowlists are still extended, and adds a regression test.
- PR surface: Source +3, Tests +17. Total +20 across 2 files.
- Reproducibility: yes. Source inspection of current main shows an empty array reaches `ensurePluginAllowlisted`, and the linked report gives a concrete `doctor --fix` config path that matches that code.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head c06837f5dd.
- Required merge gates passed before the squash merge.
Prepared head SHA: c06837f5dd
Review: https://github.com/openclaw/openclaw/pull/87883#issuecomment-4570537738
Co-authored-by: 张贵萍0668001030 <zhang.guiping@xydigit.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Active Memory recall now runs on its own queue lane instead of sharing the parent prompt-build lane.\n\nValidation:\n- git diff --check\n- node scripts/run-vitest.mjs extensions/active-memory/index.test.ts -t "runs recall on a dedicated active-memory lane"\n- fresh local gateway smoke with Active Memory + Memory Core + loopback OpenAI-compatible model: HTTP 200, active-memory start/done, recall elapsedMs=209\n\nFixes #79026.\nRelated: #72015.
Summary:
- The PR updates Codex doctor route repair to preserve explicit non-default `agentRuntime` pins across agent model maps and provider policies, adds regression coverage, and tightens a live-gateway test helper type guard.
- PR surface: Source +240, Tests +574. Total +814 across 3 files.
- Reproducibility: yes. The source path is clear from current main's model-map merge behavior and the PR's bef ... beRepairCodexRoutes` with the reported config, though this read-only review did not execute the test suite.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(doctor): preserve explicit non-default agentRuntime pin during le…
- PR branch already contained follow-up commit before automerge: fix(clawsweeper): address review for automerge-openclaw-openclaw-8414…
Validation:
- ClawSweeper review passed for head c142ec1ef8.
- Required merge gates passed before the squash merge.
Prepared head SHA: c142ec1ef8
Review: https://github.com/openclaw/openclaw/pull/84362#issuecomment-4493152445
Co-authored-by: David Huang <nxmxbbd@gmail.com>
Co-authored-by: Nex <nex@dbitstec.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Add a general typed tool-progress contract so long-running non-exec tools can emit public channel progress without overloading model-facing tool content.
`web_fetch` now uses the generic delayed progress helper: it shows `Fetching page content...` only when the fetch is still pending after five seconds, clears the timer on completion/abort, passes the abort signal into guarded fetch, and avoids provider fallback or cached success after cancellation. The subscriber path accepts only explicit `visibility: "channel"` and `privacy: "public"` progress metadata, while untyped tool partials and exec output keep their existing behavior.
Docs now explain typed progress, delayed producer examples, and the `web_fetch` timing behavior.
Proof: `pnpm test src/agents/tools/web-tools.fetch.test.ts src/agents/embedded-agent-subscribe.handlers.tools.test.ts -- --run`; `pnpm docs:check-mdx`; changed-file `pnpm exec oxlint ...`; `git diff --check`; autoreview clean.
Match text slash command names case-insensitively across the reset/new fallback paths and the shared registry/control detection contract while preserving command argument casing.
Add regression coverage for uppercase and mixed-case reset/new commands plus registered non-reset commands such as `/STATUS`, `/Model`, `/T`, and `/COMPACT`.
Co-authored-by: zhangtong26 <zhangtong26@xiaomi.com>
Co-authored-by: Lanzhi <lizhan3@xiaomi.com>
Remove stale Telegram-only wording from the reasoning stream acknowledgement and docs so channel-neutral behavior is reflected.
Fixes#68305.
Co-authored-by: Lanzhi <lizhan3@xiaomi.com>
Load `docker-compose.override.yml` when ClawDock builds its explicit Docker Compose file list, preserving standard Compose override behavior while keeping `docker-compose.extra.yml` as the final OpenClaw overlay.
Update Docker docs so manual Compose users include the same override order, and keep the regression test for the generated `_clawdock_compose` arguments.
Fixes#49909.
Thanks @spacegeologist.
Co-authored-by: zhengzuo0-ai <zheng.zuo0@gmail.com>
Preserve npm install selectors while recording resolved npm provenance for plugin and hook install/update records. Active `record.spec` stays the requested selector unless explicitly pinned, while resolved npm fields remain available for audit and diagnostics.
Adds focused coverage for hook-pack npm fallback provenance after the maintainer review found that path worth pinning down.
Co-authored-by: Phil <99397913+GitHoubi@users.noreply.github.com>
Forward Zalo quote-reply metadata from zca-js data.quote into the existing ReplyToId, ReplyToBody, and ReplyToIsQuote context keys so agents can correlate quoted replies with prior bot messages.
Adds parser and monitor regression coverage for quote extraction and context projection.
Fixes#86851.
Thanks @tanshanshan.
Remove unreachable optional chaining from four Discord message-handler-family runtime error calls.
This aligns the code with the required RuntimeEnv.error contract while leaving production behavior unchanged for valid runtimes. Maintainer-updated PR proof clarifies that shared queue reporter hooks still treat malformed runtime reporter failures as best-effort.
Clean up completed exec tool-call abort listeners so normal foreground completion and background-yield no longer retain the exec run/session context through AbortSignal listener state.
The listener cleanup now lives beside the exec listener registration and runs when the foreground process settles, rejects, or the tool returns a background running result. Existing abort/timeout/background behavior remains owned by the process supervisor and process registry.
Verification:
- gh pr checks 83022
- gh api repos/openclaw/openclaw/commits/fe86528ecb2043b6febef5c2eec53f9124be5543/check-runs
- git merge-tree --write-tree origin/main refs/remotes/pr/83022
- git diff --check origin/main...refs/remotes/pr/83022
- node AbortSignal add/remove listener probe
Thanks @c19354837.
Co-authored-by: Ninty <c19354837@hotmail.com>
Fixes#66479.
Workspace skills whose SKILL.md starts with a UTF-8 BOM now keep their shared markdown frontmatter metadata, so they remain discoverable through skills list. The fix strips one leading BOM at the parser boundary and adds parser plus workspace discovery regression coverage.
Thanks @jbetala7 for the fix.
Co-authored-by: Jayesh Betala <jayesh.betala7@gmail.com>
Route Microsoft Teams attachment downloads through the shared SSRF guarded fetch path so DNS validation is pinned into the dispatcher used for the actual request.
Keep Teams auth fallback and allowlisted HTTPS Authorization redirect behavior while failing closed for custom fetch hooks that cannot accept dispatcher injection.
Verification:
- CI=1 OPENCLAW_VITEST_MAX_WORKERS=1 timeout 300 node scripts/run-vitest.mjs run extensions/msteams/src/attachments/shared.test.ts extensions/msteams/src/attachments/bot-framework.test.ts src/infra/net/fetch-guard.ssrf.test.ts
- gh pr checks 87567 --repo openclaw/openclaw --watch=false
PR: #87567
Fix cron local-model preflight fallback handling so scheduled runs try configured fallback candidates before skipping when the local primary is unavailable.
Verification:
- GitHub CI on PR head fe884dab90: passing required CI checks.
- Local focused cron/model fallback tests passed earlier for the touched surface.
- Local merge-wrapper build and check passed on the prepared candidate.
- Local full pnpm test reported unrelated failures outside this PR's touched files; touched files are limited to cron docs, src/agents/model-fallback.ts, and src/cron/isolated-agent/*.
Co-authored-by: chen-zhang-cs-code <chenzhangcode@163.com>
Co-authored-by: Onur Solmaz <2453968+osolmaz@users.noreply.github.com>
Remove the chatType === 'direct' guard from
shouldAllowQuietChannelOwnedProgressCallbacks so that channel-owned native
progress callbacks (onToolStart, onItemEvent, onPlanUpdate,
onApprovalEvent, onCommandOutput, onPatchSummary, onCompactionStart/End)
are forwarded in group and group-channel sessions when verbose is off.
Previously the guard required chatType === 'direct', which meant that
/verbose off would suppress all progress callbacks in group sessions
while direct sessions continued to relay them. Message-level tool
summary suppression is handled separately; native channel relay hooks
should not be gated on chat type.
Closes#87612
Cache single-row gateway session child indexes without hiding live subagent registry changes.
Summary:
- Reuses store-derived child-session candidates for repeated single-row session loads.
- Keeps runtime subagent registry reads live per row so moved child sessions do not stay attached to stale parents.
- Versions the session-store cache and includes that version in the single-row cache key so same-object store rewrites cannot reuse stale child candidates.
- Adds focused regression coverage for cache reuse, live registry refresh, and same-object session-store writes.
Verification:
- git diff --check
- pnpm tsgo:prod
- pnpm test src/gateway/session-utils.single-row-cache.test.ts src/gateway/session-utils.subagent.test.ts -- --reporter=verbose
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
- GitHub CI run 26620265206: passing
- Azure Crabbox cbx_a58389e50f49: single-row-loads 13.622240 ms before vs 1.869456 ms after, 7.29x speedup, 86.3% reduction
* feat: add Claude Opus 4.8 support
* fix: omit Vertex Opus sampling overrides
* fix: preserve Opus adaptive thinking levels
* fix: clamp Anthropic max effort support
* fix: use sha256 for QA mock call ids
* fix: type Anthropic transport test model metadata
* test: update PDF model default for Opus 4.8
Summary:
- This PR adds an internal gateway active-run projection flag, clears it during terminal lifecycle handling be ... ons.list on that flag, adds gateway regression coverage, and tightens memory-wiki confidence normalization.
- PR surface: Source +29, Tests +131. Total +160 across 7 files.
- Reproducibility: yes. Source inspection shows current main can broadcast terminal sessions.changed before ch ... the abort-controller entry, and the before/after recording supports the visible stuck In progress symptom.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(gateway): preserve chat retry guard after terminal state
- PR branch already contained follow-up commit before automerge: fix(gateway): clear completed session active runs
Validation:
- ClawSweeper review passed for head 9b132bdc2b.
- Required merge gates passed before the squash merge.
Prepared head SHA: 9b132bdc2b
Review: https://github.com/openclaw/openclaw/pull/87810#issuecomment-4569094800
Co-authored-by: scotthuang <scotthuang@tencent.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Adds opt-in Discord progress-draft commentary for assistant preambles while keeping commentary hidden by default and final delivery unchanged.
Keeps commentary config Discord-specific, strips directive tags/NO_REPLY, and clears stale commentary rows without stopping the active draft stream.
Thanks @bryanpearson.
Co-authored-by: bryanpearson <bryanmpearson@gmail.com>
Preserve OpenClaw-owned embedded system prompts after active tool selection in both normal embedded attempts and compaction. Adds an exact base prompt path on AgentSession that keeps active tool prompt metadata current for extension hooks.
Fixes#87807.
Verification:
- mise exec node@24.16.0 -- node scripts/run-vitest.mjs src/agents/sessions/sdk.test.ts src/agents/embedded-agent-runner/system-prompt.test.ts src/agents/embedded-agent-runner/run/attempt.spawn-workspace.context-engine.test.ts src/agents/embedded-agent-runner/compact.hooks.test.ts --reporter=dot
- mise exec node@24.16.0 -- pnpm tsgo:core
- git diff --check
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
Thanks @shakkernerd.
Handle exec-backed Gateway SecretRefs in doctor, lint, and health probing without executing providers by default.
- Add `openclaw doctor --allow-exec` for explicit SecretRef execution during lint/doctor checks.
- Skip only the active exec-backed gateway probe path and avoid local service diagnostics for remote-only skipped health.
- Keep env-winning and dormant fallback credentials probeable, stabilize related tests, and remove a stale live-shard fixture left by the moving base.
Verification:
- `node scripts/run-vitest.mjs src/commands/doctor-gateway-auth-token.test.ts src/commands/doctor.warns-state-directory-is-missing.e2e.test.ts src/gateway/credentials.test.ts src/gateway/probe-auth.test.ts src/commands/doctor-gateway-daemon-flow.test.ts test/scripts/test-live-shard.test.ts --reporter=verbose`
- `mise x node@24.13.0 -- pnpm prompt:snapshots:check`
- `pnpm tsgo:prod`
- `pnpm build`
- `.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main`
- Crabbox AWS live config proof: `run_f44a4d9dae4e`
- GitHub CI: green on final head `88d24abdbf9529a59d75d1d5e04eac74bbbbc267` after rerunning a stale in-progress Security High workflow.
Co-authored-by: Merlin <258679497+funmerlin@users.noreply.github.com>
Fixes#87132.
Default Usage now requests all configured agents with `agentScope: "all"`, while selecting a specific agent sends `agentId` consistently to both session usage and cost usage calls. The gateway now supports explicit all-agent session usage, aggregates all-agent cost summaries across configured agents, and keeps scoped cache entries separate. Legacy gateway fallbacks remain for older `agentId` / `agentScope` support, with protocol docs/schema and Swift generated models updated.
Verification:
- `node scripts/run-vitest.mjs ui/src/ui/controllers/usage.node.test.ts ui/src/ui/app-render-usage-tab.test.ts ui/src/ui/views/usage.test.ts --reporter=dot`
- `node scripts/run-vitest.mjs run --config test/vitest/vitest.gateway-methods.config.ts src/gateway/server-methods/usage.test.ts src/gateway/server-methods/usage.cost-usage-cache.test.ts src/gateway/server-methods/usage.sessions-usage.test.ts --reporter=dot`
- `pnpm check:test-types`
- `pnpm protocol:check`
- targeted `node scripts/run-oxlint.mjs ...`
- `git diff --check`
- autoreview clean after Swift compatibility fix
- PR CI green at head `d67156a3c552c4f9c8b6edf8516b6242bf5cdd26`
Co-authored-by: Alix-007 <267018309+Alix-007@users.noreply.github.com>
Keep Codex reasoning updates as accumulated snapshots and mark the stream payload so channel consumers can distinguish snapshots from deltas.
This prevents Discord and Teams progress previews from duplicating accumulated reasoning text while preserving delta-style reasoning for legacy producers.
Refs #86708
Thanks @SebTardif.
Co-authored-by: OpenAI Codex <codex@openai.com>
Scope jiti filesystem transform caches for OpenClaw plugin loaders by package version and package.json install metadata so stale transforms cannot survive upgrades or package reinstalls.
Covers the central plugin module loader and the plugin SDK root alias CJS loader, while preserving jiti filesystem-cache env opt-outs and the TMPDIR cwd guard.
Verification: CI run 26601117143 passed; Real behavior proof run 26601445285 passed; CodeQL selected checks passed in run 26601117126; CodeQL Critical Quality plugin-boundary and plugin-sdk-package-contract passed in run 26601117074; OpenGrep PR diff passed in run 26601117137.
Refs: https://github.com/openclaw/openclaw/pull/87745
Thanks @fuller-stack-dev.
Route Codex app-server report-mode PreToolUse plugin approval requirements through the matching app-server approval request instead of failing closed. Shares duplicate in-flight approvals, preserves block/rewrite fail-closed behavior, and keeps generic plugin allow-always scoped to one Codex request. Supersedes #86978; thanks @clawSean for the original docs clarification.
Compact promoted short-term memory snippets before writing them into MEMORY.md, while keeping the full rehydrated snippet in recall state for ranking/provenance. Adds the deep-dreaming config surface and docs, with the default promoted snippet cap set to 160 estimated tokens.
Verification:
- git diff --check
- fnm exec --using v24.13.0 node scripts/run-vitest.mjs run extensions/memory-core/src/short-term-promotion.test.ts extensions/memory-core/src/dreaming.test.ts src/memory-host-sdk/dreaming.test.ts
- GitHub CI run 26605272497
- CodeQL security run 26605272404
Co-authored-by: AMARA <amara@eyeinthesky.pl>
Server-side cron job list filtering now applies schedule-kind and last-run-status filters before pagination, and the UI only sends table filters for the cron table view.
Fixes#9455.
Co-authored-by: Alix-007 <267018309+Alix-007@users.noreply.github.com>
* fix(msteams): rebase SDK migration onto current main
Reapply the msteams SDK migration (originally on feat/msteams-sdk-migration)
on top of upstream/main, resolving conflicts with parallel msteams work that
landed upstream during our session.
What got applied vs decisions made:
CLEANLY APPLIED (3-way patch):
- monitor.ts, monitor-handler.ts, polls.ts, reply-stream-controller.ts/.test.ts,
reply-dispatcher.ts, attachments/download.ts, monitor.lifecycle.test.ts,
monitor-handler/message-handler.ts, monitor-handler.types.ts, etc.
- streaming-message.ts + .test.ts deletions
WHOLESALE TAKE FROM ORIGINAL BRANCH (partial 3-way left broken cross-refs):
- sdk.ts, sdk.test.ts, messenger.ts, feedback-reflection.ts,
send-context.ts, send.test.ts
KEPT UPSTREAM (deferred for separate cleanup):
- extensions/msteams/package.json (still has jsonwebtoken/jwks-rsa per
Peter's b3bc60ae25 incremental approach)
- src/plugins/contracts/package-manifest.contract.test.ts (consistent with
package.json)
- pnpm-lock.yaml (avoids lockfile churn; pnpm install --frozen-lockfile clean)
ADAPTED:
- Dockerfile matrix-sdk-crypto check now wraps upstream's new retry-loop in
the if-matrix-bundled gate
KNOWN TEST FAILURES (need eyes — see PR comment):
- attachments.test.ts: 1 fail (pre-existing — warn meta arg shape changed in
our migration but test wasn't updated)
- reply-dispatcher.test.ts: 6 fails (pre-existing — tests mock old
TeamsHttpStream, not updated for our ctx.stream rewrite)
- send.test.ts: 4 fails (NEW from merge — upstream's send.ts changed media
loading; our mocks need updating or take upstream's send.test.ts wholesale)
UPSTREAM COMMITS POTENTIALLY MISSED (in wholesale-take files):
- 08c4af0ddf fix(msteams): accept conversation id allowlists
- e1840b8581 fix(msteams): bind global audience tokens to app id
- Channels turn-kernel refactor (ffe67e9cdc / 1ead1b2d18 / 9a9cd0c0ab) —
may be partially preserved in cleanly-patched files
Static checks pass: pnpm check:changed is green (typecheck, lint, contract
tests, import cycles, etc.). Manual testing required before merge.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(msteams): preserve thread routing for channel and group-chat replies
- monitor.ts: adaptSdkContext now uses ctx.reply() for channel and groupChat
conversations (so the SDK threads outbound activities to the inbound's
replyToId/serviceUrl) and ctx.send() only for personal DMs (where
reply()'s blockquote-prepend is ugly).
- messenger.ts: sendProactively passes resolvedThreadId on the non-thread
fallback path so channel @mentions that fall through outbound.ts -> send.ts
still land in the original thread instead of top-level.
Live-validated: channel @mention -> bot replies in thread, threaded reply
-> bot replies in same thread, no top-level leakage.
* fix(msteams): tag outbound SDK calls with OpenClaw User-Agent
- user-agent.ts: add buildOpenClawUserAgentFragment() that returns just
'OpenClaw/<version>'. The SDK's Client.clone merges this with its own
'teams.ts[apps]/<sdk-version>' identifier — passing the full buildUserAgent()
here would double-print the SDK token.
- sdk.ts: pass the fragment via AppOptions.client.headers['User-Agent'] so
the Teams backend can identify OpenClaw traffic for usage telemetry.
Final UA looks like 'OpenClaw/<openclaw-version> teams.ts[apps]/<sdk-version>'.
* fix(msteams): handle StreamCancelledError when user presses Stop mid-stream
The new SDK throws StreamCancelledError synchronously from stream.emit/update
when the user pressed Stop in Teams: Teams replies 403 to the next chunk
update, the SDK flips _canceled, and any subsequent emit() throws. The old
custom TeamsHttpStream either swallowed cancel or didn't expose this exception
type, so the migration inherited an SDK behavior the original code didn't have
to handle.
Symptom on 2026-05-05: pressing Stop during a streaming reply caused an
unhandled promise rejection that crashed the Node 24 process. Docker restarted
the gateway about two minutes after each Stop click. Two related bugs surfaced
once the crash was caught: the would-be block fallback re-delivered the full
text as a second message (duplicate after Stop), and the typing-keepalive kept
pulsing in Teams for the rest of the agent run because nothing told it to
stop.
reply-stream-controller.ts:
- Wrap stream.update / stream.emit / stream.close in try/catch that swallows
StreamCancelledError (matched by .name to dodge tsgo's SDK re-export
resolution quirk). Latch a wasCanceled flag so subsequent calls
short-circuit even if stream.canceled is stale.
- preparePayload() returns undefined when the stream was canceled — the
streamed prefix is already visible to the user, so dropping the payload
prevents a duplicate block message from overriding the cancel intent.
reply-dispatcher.ts:
- Typing-keepalive gate now also checks streamController.wasCanceled() so
typing pulses stop firing once Stop is observed. Otherwise the bot keeps
pulsing for the rest of the (uncancellable) agent run.
reply-stream-controller.test.ts:
- 6 new regression tests cover: cancel-during-emit (the crash scenario),
cancel-during-update, cancel-during-finalize, non-cancel error propagation,
post-cancel inactivity, and dropped-payload-on-cancel.
Live-validated: long streaming reply + Stop mid-stream -> stream freezes,
no duplicate message, no zombie typing, container stays healthy.
* fix(msteams): allow Bearer-token retry on Skype CDN attachment downloads
Teams puts inline DM images and clipboard-pasted images on
*.asm.skype.com URLs (e.g. us-api.asm.skype.com/v1/objects/<id>/views/imgo).
The download path in attachments/download.ts already does a plain GET first
and falls back to a Bearer-token retry on 401/403 — but the retry was gated
on the URL being in DEFAULT_MEDIA_AUTH_HOST_ALLOWLIST. asm.skype.com hosts
were in DEFAULT_MEDIA_HOST_ALLOWLIST (download permitted) but not in the
auth-host list, so a 401 plain-GET response skipped the retry and surfaced
as a missing image to the agent.
Add asm.skype.com and ams.skype.com to the auth allowlist so openclaw
attempts the Bearer-token retry consistently, matching how it treats the
other CDN/Bot-Framework hosts already in the list.
Note: this does not unblock all clipboard-pasted DM images — for at least
some tenants asm.skype.com rejects the Bot Framework token (returns 401
even with auth). Routing those URLs through <serviceUrl>/v3/attachments/...
the way #62219 already handles HTML-wrapped attachments is a separate
follow-up. The +button 'Upload from this device' path works today because
Teams generates an attachment with an HTML wrapper that triggers the
existing BF v3 attachments fallback in monitor-handler/inbound-media.ts.
* fix(msteams): align docker-compose msteams port default with plugin default
The plugin defaults webhook.port to 3978 (the Bot Framework standard used in
Microsoft samples) and listens on whatever the operator sets there. The
docker-compose.yml port mapping was exposing ${OPENCLAW_MSTEAMS_PORT:-3000}:3000
which only works for operators who explicitly set webhook.port to 3000.
Default-config users would have the plugin listening on 3978 inside the
container while compose forwarded 3000, causing connection refused.
Realign to ${OPENCLAW_MSTEAMS_PORT:-3978}:3978 so a default-config docker
compose up Just Works with Teams. Operators wanting a custom port override
both webhook.port in openclaw.json and OPENCLAW_MSTEAMS_PORT env var.
* fix(msteams): post-rebase reconciliation with main
Three follow-ups after rebasing the SDK migration onto current main:
- reply-dispatcher.ts: rename createChannelReplyPipeline to its post-rebase
identifier createChannelMessageReplyPipeline (the plugin-sdk barrel renamed
it during the 1454-commit rebase window).
- reply-dispatcher.ts: tighten the typing-keepalive onStartError signature to
(err: unknown) to satisfy upstream's stricter type checks.
- messenger.ts: drop the unconditional thread suffix on the bottom proactive
fallback. The previous behavior threaded all top-level proactive sends when
the stored ref had a threadId, which contradicts replyStyle='top-level'
semantics (and breaks the new upstream test). Threading on the proactive
path is preserved where it matters — the onRevoked branch within
replyStyle==='thread' still passes resolvedThreadId, which is the original
#55198 fix path.
- attachments.test.ts: update the warn-call assertion to match the migration's
inline message format (host=... error=...) — the structured meta object was
being dropped by the logger formatter pre-migration.
* feat(msteams): port streaming preview/progress features to ctx.stream
While the SDK migration was open, upstream landed preview/progress/draft
streaming features built on the OLD custom TeamsHttpStream class (which the
migration deletes). This commit ports the user-visible parts of those
features onto the new ctx.stream substrate so the migration doesn't lose
ground:
- pickInformativeStatusText: reads custom labels from
msteams.streaming.progressDraft config via resolveChannelProgressDraftLabel.
Falls back to the plugin-sdk default rotation. Pre-rebase used a hardcoded
4-string array.
- streamMode resolution: "partial" (default, per-token streaming),
"progress" (no tokens; preview card carries informative label that updates
as tools run), or "block" (no native streaming). Mode is read from
cfg.channels.msteams.streaming.preview.
- progress-draft gate: createChannelProgressDraftGate gates informative
updates so the rotating label only starts firing once meaningful work has
begun (avoids flicker before the first tool call).
- noteProgressWork() / pushProgressLine(): public methods on the controller
for callers (typing keepalive ticks, tool-event callbacks) to signal work.
pushProgressLine appends tool names as bullets above the rotating label
when streaming.previewToolProgress is enabled. Wiring these into actual
tool events is a separate follow-up.
- preparePayload progress-mode path: when stream is active but no tokens
streamed (progress mode) and a final text payload arrives, emit the text
into the stream so the preview card transitions in place to the final
reply on close().
reply-dispatcher: pass log + msteamsConfig + a stable progressSeed
(${accountId}:${conversation.id}) to createTeamsReplyStreamController so the
informative-label rotation is consistent across reconnects.
What's NOT ported and why:
- Live-edit-via-replaceInformativeWithFinal: the SDK's HttpStream natively
accumulates emitted text + entities + channelData and flushes ONE final
activity at close() using the same activity id as the preview. So the
separate "replace informative with final" call from upstream is
unnecessary — we get live-finalization for free via the SDK's design.
- pushProgressLine triggers from tool events: needs reply-pipeline-side
callbacks the new SDK migration didn't surface yet. Follow-up.
Tests: existing 22 reply-stream-controller tests still pass (the new
behaviors are additive).
* feat(msteams): wire pipeline tool events to streaming progress + fix test debt
Two follow-ups from yesterday's stopping point:
1. Wire pipeline events into the stream controller's progress-draft surface.
reply-dispatcher's replyOptions now exposes onReasoningStream, onToolStart,
onItemEvent, onPlanUpdate, onApprovalEvent, onCommandOutput callbacks that
format each event via the channel-streaming helpers and route through
streamController.pushProgressLine(). Mirrors the discord adapter's wiring.
Also:
- resolveChannelStreamingPreviewToolProgress + ...SuppressDefaultTool... so
the dispatcher exposes suppressDefaultToolProgressMessages on its
replyOptions when progress mode is on.
- Switch disableBlockStreaming resolution to the channel-streaming helpers
(resolveChannelPreviewStreamMode + resolveChannelStreamingBlockEnabled)
so streaming.mode='block' and streaming.block.enabled=true are honored
alongside the legacy blockStreaming boolean.
2. Fix the test debt that the rebase exposed:
- reply-dispatcher.test.ts: drop the streamInstances + TeamsHttpStream
mock pattern (file deleted by migration); replace with a streamMock
provided via context.stream that mirrors the SDK's IStreamer shape
(update/emit/close/canceled). Update assertions on sendInformativeUpdate
-> stream.update, stream.update -> stream.emit. Drop the
resumes-typing-between-segments test (no equivalent in the new
ctx.stream model — the SDK's HttpStream doesn't have a 'between
segments' notion; close ends the stream).
- send.test.ts: fix two stale mock targets — loadOutboundMediaFromUrl
comes from openclaw/plugin-sdk/outbound-media (not /msteams), and
resolveMarkdownTableMode comes from openclaw/plugin-sdk/markdown-table-runtime
(not /config-runtime). The previous mock paths were no-ops post-migration.
All 854 msteams tests now pass (was 17 failing in 4 files yesterday).
* fix(msteams): SDK streaming delta + use app.reply for proactive thread sends
Two narrow regressions exposed by the @microsoft/teams.apps migration:
- The SDK's HttpStream.emit appends each chunk to its internal buffer
(`this.text += activity.text`), but the channel reply pipeline emits
cumulative text on each chunk. Forwarding cumulative text into an
appending sink produced "chunk1 + chunk1chunk2 + chunk1chunk2chunk3..."
duplication for streamed (DM) replies. Track the emitted prefix length
in the stream controller and only forward the new tail.
- Replace the manual `${convId};messageid=${msgId}` URL construction in
the proactive thread fallback with `app.reply()`, which builds the
threaded conversation id via the SDK's own toThreadedConversationId
helper. Mechanically equivalent today; removes coupling to Teams' URL
format and tracks any future SDK changes.
Also adds the `reply` method to the structural MSTeamsApp type so the
refactor typechecks without casts.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(msteams): bump @microsoft/teams.api and teams.apps to 2.0.10
2.0.10 adds support for the AAD v1 token issuer that the Bot Framework
JWT validator needs. The minor version bump pulls teams.cards / common /
graph along to 2.0.10 too.
Add `@microsoft/teams.*` to `minimumReleaseAgeExclude` in
pnpm-workspace.yaml because 2.0.10 was published <48h ago and the default
`minimumReleaseAge: 2880` (~2 days) would otherwise reject it.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* revert(msteams): remove asm.skype.com auth-host allowlist additions
These hosts were added in dfc169d31d for inline DM image auth-retry, but
the commit's own footnote acknowledges it doesn't actually unblock
clipboard-pasted images (asm.skype.com rejects Bot Framework tokens in
at least some tenants). The change is unrelated to the SDK migration and
the user-visible bug it claimed to fix isn't fixed; lifting it out keeps
this PR focused on the migration. Will land as a separate PR if the
auth-allowlist consistency improvement is wanted on its own.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(msteams): typed ExpressAdapter helper, drop unknown-cast pyramid
The monitor's SDK bootstrap had an awkward chain:
httpServerAdapter: new (
(await import("@microsoft/teams.apps")) as unknown as {
ExpressAdapter: new (app: unknown) => unknown;
}
).ExpressAdapter(expressApp) as never,
Three casts (`unknown`, structural shape literal, `never`) were a
defensive workaround from when the SDK's hashed d.ts files tripped up
tsgo. With the SDK's exports now resolving cleanly, the same import can
be done with full types.
- Extend the lazy `loadSdkModules()` cache to include `ExpressAdapter`
alongside `App` so the dynamic import is shared.
- Add `createMSTeamsExpressAdapter(serverOrApp)` helper in `sdk.ts` that
encapsulates the lazy import and returns a properly-typed adapter
instance.
- Replace `httpServerAdapter`'s structural shape on `CreateMSTeamsAppOptions`
with the SDK's own `IHttpServerAdapter` interface (re-exported from
`@microsoft/teams.apps`).
The call site in `monitor.ts` becomes a single typed call with no `any`,
no `unknown`, no `as never`. The lazy-load behavior is preserved: nothing
imports `@microsoft/teams.apps` at module load time.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(msteams): unbreak tsgo:extensions on the ExpressAdapter helper
CI's check-prod-types failed because the previous commit's typed helper
used `typeof import("@microsoft/teams.apps").ExpressAdapter`, which
tsc/tsgo's NodeNext resolution can't follow through the SDK's chained
`export *` barrel:
@microsoft/teams.apps/dist/index.d.ts:
export * from "./http"; // folder with index.d.ts
export * from "./app"; // single .d.ts file
The folder re-export drops `ExpressAdapter` and `IHttpServerAdapter` from
the namespace shape under `tsconfig.extensions.json` (passes under the
per-extension `tsconfig.json` because of inherited `paths`). Same root
cause as why we already model `MSTeamsApp` structurally (line 47 comment).
Switch the ExpressAdapter side to the same structural-shape pattern:
- Define `MSTeamsHttpServerAdapter` and `MSTeamsExpressAdapterCtor` locally.
- Cast `m.ExpressAdapter` once inside `loadSdkModules` (the runtime export
is fine; only the type surface is hidden).
- `httpServerAdapter` on `CreateMSTeamsAppOptions` and the return type of
`createMSTeamsExpressAdapter` use the local structural type.
Net result: the call site in `monitor.ts` stays the cast-free single line
the previous commit landed; the one remaining cast is confined to the
SDK-loading helper with an explanatory comment.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(msteams): drop unused jsonwebtoken/jwks-rsa deps
The SDK migration removed all `import "jsonwebtoken"` / `import "jwks-rsa"`
from source code (the SDK does JWT validation internally now), but the
package.json entries and the matching `package-manifest.contract.test.ts`
expectation were left orphaned. Drop both:
- `extensions/msteams/package.json`: remove `jsonwebtoken` (^9), `jwks-rsa`
(^4) from `dependencies` and `@types/jsonwebtoken` from `devDependencies`.
- `src/plugins/contracts/package-manifest.contract.test.ts`: remove the
two entries from msteams's `pluginLocalRuntimeDeps` expectation.
- `monitor.lifecycle.test.ts`: extend the `./sdk.js` mock with the
`createMSTeamsExpressAdapter` export added in the typed-helper cleanup,
so the lifecycle suite still mounts after the deps drop.
Lockfile regenerates accordingly. All msteams tests (865) pass.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(msteams): drop unused @microsoft/teams.api direct dep
CI's deadcode:dependencies (knip) flagged @microsoft/teams.api as
unused in extensions/msteams. The plugin source uses structural type
aliases (MSTeamsActivityParams, MSTeamsActivityLike, etc.) to dodge
tsgo resolution bugs with teams.api's hashed d.ts files, so it never
imports teams.api directly. The package is brought in transitively
via @microsoft/teams.apps; the only other reference is
probe.test.ts's vi.mock("@microsoft/teams.api"), which works on the
import-path string and doesn't require a direct dep declaration.
Lockfile regenerates accordingly. tsgo:extensions, knip, and all
865 msteams tests pass.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(msteams): clear three CI gate failures (lint, contract, deprecated config API)
Three CI checks flagged on the latest run; all three are msteams-local
and unrelated to one another:
- **check-lint** / **check-additional-extension-bundled**:
`oxlint` flagged a redundant `as string[]` assertion in
`reply-dispatcher.ts:431`. The preceding `every((s: unknown) => typeof
s === "string")` already narrows the array type, so the cast does
nothing. Drop it.
- **checks-fast-contracts-plugins-c**: the
`package-manifest.contract.test.ts` `pluginLocalRuntimeDeps` for
msteams still expected `@microsoft/teams.api`, but the deadcode
cleanup commit (8f4050f51a) dropped it from
`extensions/msteams/package.json`. Remove it from the contract test
too — `teams.api` is only present transitively via `teams.apps`,
which is the reason knip flagged it.
- **check-additional-runtime-topology-architecture**: the deprecated
internal config API guard caught `messenger.ts:223` calling
`getMSTeamsRuntime().config.loadConfig()`. Switch to
`config.current()` to match the pattern used by phone-control,
synology-chat, and matrix.
Pre-existing failures on this run that are NOT msteams-related and not
caused by this PR: `check-test-types` (errors in
`src/agents/openai-transport-stream.test.ts` and
`pi-embedded-runner/openai-stream-wrappers.test.ts`) and `macos-swift`
(`hoistAwait` in `MacNodeRuntime.swift`). Leaving those for upstream.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(msteams): cast config.current() return to OpenClawConfig
The previous commit switched `messenger.ts:223` from the deprecated
`config.loadConfig()` to `config.current()` to satisfy the architecture
guard, but `config.current()` returns a deeply-readonly type that's not
assignable to the `Partial<OpenClawConfig>` parameter
`resolveMarkdownTableMode` expects (a mutable type from the SDK
contract). Phone-control, synology-chat, and matrix all cast at this
seam — adopt the same pattern.
Verified locally: tsgo:core, tsgo:extensions, check:architecture, and
test:extensions:package-boundary:compile all pass.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(msteams): address PR review — pre-auth body limit, allowlist log level, /api/messages forwarder, narrow release-age exclude
Four narrow fixes from the PR review (BradGroux + clawsweeper bot +
galiniliev's plan), each its own concern:
- **pre-auth-body-limit** (monitor.ts) — install
`express.json({ limit: DEFAULT_WEBHOOK_MAX_BODY_BYTES })` before the
bearer-presence gate and SDK route. Express memoizes the parsed body
on the request, so the SDK's later `json()` becomes a no-op and our
limit applies before any handler parses bodies. Closes the gap where
a `Bearer garbage`-shaped attacker could force unbounded JSON parsing
before token validation.
- **allowlist-error-logging** (monitor.ts) — restore main's `runtime.error`
level for the `msteams resolve failed` catch (was downgraded to
`runtime.log` mid-merge). Graph allowlist resolution failures are
security-relevant; they need to surface to operators.
- **legacy-messages-route** (monitor.ts) — when `webhook.path` is set
to a custom value, also accept POSTs on the legacy `/api/messages`
path with a one-time deprecation warning, then re-enter the Express
middleware chain on the configured path. Keeps existing Azure Bot
registrations working through the transition. Cast-free
(`expressApp(req, res, next)` works because `Application extends
IRouter extends RequestHandler`).
- **release-age-scope** (pnpm-workspace.yaml) — narrow
`@microsoft/teams.*` glob to the single direct dep
`@microsoft/teams.apps`. Future scoped packages no longer get a
freshness-guard pass.
Tests + checks: msteams suite (867), tsgo:core, tsgo:extensions,
tsgo:test, lint:extensions, check:architecture, knip --dependencies,
package-manifest contract, all green.
Still pending from the review (separate commits):
- auth-coverage-tests (Brad #1 + comment) — tests proving the SDK accepts
`aud=<bot app id>` and rejects `aud=api.botframework.com`.
- invoke-response-handling (Brad #2, codex P2) — file-consent invoke ack
must return through the SDK invoke handler, not `ctx.sendActivity`.
- stream-failure-fallback (codex P2, galin F5) — `streamFailed` latch so
partial streams fall back to block delivery on non-cancel errors.
- serviceurl-routing (Brad #4, codex P2) — proposed rebuttal pending
empirical confirmation that `smba.trafficmanager.net/teams` routes to
non-default-region conversations.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(msteams): lock SDK auth contract — aud + v1/v2 issuer coverage
Adds extensions/msteams/src/auth-coverage.test.ts driving ServiceTokenValidator
and createEntraTokenValidator directly with jose-minted RS256 tokens against an
in-memory JWKS (via JwksClient.prototype patch). Locks in the three contract
cases @BradGroux flagged on #76262: aud=<bot app id> accepted, aud=api.botframework.com
rejected even when appid/azp match, and v1/v2 issuers accepted for allowed tenant
(disallowed tenant rejected).
Drops a stale ambient module declaration in src/types/microsoft-teams-sdk.d.ts
that was shadowing the SDK's real jwt-validator types with a long-renamed
createServiceTokenValidator surface.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(msteams): route file-consent invokes through typed app.on, drop broken invokeResponse send
Brad #2 / codex #4 on PR #76262 — `ctx.sendActivity({ type: "invokeResponse", ... })`
no longer reaches Teams as an HTTP InvokeResponse on the new SDK; it becomes
an outbound Bot Framework activity instead. Move file-consent accept/decline
to typed `app.on("file.consent.accept|decline", ...)` handlers. The SDK's
typed-route layer wraps a void return into `{ status: 200 }`
(`app.process.js:130`), so the manual ack disappears.
While in here, type `MSTeamsApp.on` properly. Borrowing the SDK's `App.on`
directly fails because that function carries a `this: App<TPlugin>`
constraint our structural alias can't satisfy, so we model an equivalent
generic over `IRoutes` with route-specific overloads (`card.action`,
`file.consent.*`, `activity`). The overloads work around a tsgo bug — the
`@microsoft/teams.api` `Activity` discriminated union collapses to `any`,
turning `ActivityRoutes` into a `[string]: RouteHandler<X, void>` index
signature that swallows every typed `Out` not already void-compatible
(card.action returns `AdaptiveCardActionResponse`; the others happen to
include `void`). Real tsc resolves cleanly. Linked upstream:
https://github.com/microsoft/typescript-go/issues/1057.
Other cleanups:
- Cast-free call sites for `adaptSdkContext` (now returns
`MSTeamsTurnContext` instead of `unknown`).
- card.action error responses include `innerHttpError` per the SDK's
`HttpError` shape requirement.
- Activity catch-all also skips `fileConsent/invoke` now that it's
typed-routed (parallel to the existing `adaptiveCard/action` skip).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(msteams): route SSO sign-in invokes through typed app.on, drop broken invokeResponse send
Brad #2 / codex #4 on PR #76262, SSO half. Continue the typed-route migration:
`signin/tokenExchange` and `signin/verifyState` now register via
`app.on("signin.token-exchange" | "signin.verify-state", ...)`. Per the
SDK's router, registering a user route with the same name as a system
route removes the system default — so the SDK's built-in handlers (which
would call `api.users.token.exchange` themselves and emit a `signin` event
nobody currently subscribes to) are silenced, and only ours runs. The SDK
wraps a void return into the HTTP 200 InvokeResponse, so the legacy
`ctx.sendActivity({ type: "invokeResponse", ... })` ack — broken on the new
SDK because it becomes an outbound BF activity instead of the HTTP
response — is gone.
The handler body is extracted from the activity-catch-all dispatch in
`monitor-handler.ts` to a new `signin-invoke.ts`, parallel to
`file-consent-invoke.ts`. `isSigninInvokeAuthorized` is now exported from
`monitor-handler.ts` so the new handler can reuse it. The activity
catch-all skips the SSO invoke names alongside the existing skips for
`adaptiveCard/action` and `fileConsent/invoke`.
`MSTeamsAppOn` overloads now cover the two SSO routes with their typed
ctx (`ISignInTokenExchangeInvokeActivity` / `ISignInVerifyStateInvokeActivity`).
Tests in `monitor-handler.sso.test.ts` were rewritten to call the
extracted handler directly — the `registered.run(ctx)` shape no longer
covers SSO, and the `expect(ctx.sendActivity).toHaveBeenCalledWith({ type:
"invokeResponse" })` assertions were dropped to match the new contract
(the SDK ack happens via the typed-route return value).
Note on overlap with #77784 (Stefan Stüben, Microsoft): that PR is doing
a much bigger SSO rework (sign-in card / sign-in-link / six-digit-code
fallbacks plus a `ctx.auth` plumbed to plugin tools). This change is
the small migration-correctness fix and is structured so #77784's SSO
body changes drop into the typed-route registrations cleanly on rebase.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(msteams): route message-submit (feedback) invokes through typed app.on
Last invoke off the activity catch-all dispatch. `message/submitAction`
(thumbs up/down on AI-generated messages) now registers via
`app.on("message.submit", ...)`. Same shape as file-consent and SSO:
handler body extracted to a new `feedback-invoke.ts`, the SDK wraps a
void return into the HTTP 200 InvokeResponse, the broken
`ctx.sendActivity({ type: "invokeResponse", ... })` line is gone, and
the activity catch-all skips this invoke name alongside the others.
`isFeedbackInvokeAuthorized` is exported from `monitor-handler.ts` so
`feedback-invoke.ts` can reuse it. Tests in
`monitor-handler.feedback-authz.test.ts` were rewritten to call the
extracted handler directly — the old `handler.run(ctx)` shape no longer
intercepts feedback, and `originalRun` was removed because the typed
route is the dispatch point now.
`MSTeamsAppOn` overload added with the typed
`IMessageSubmitActionInvokeActivity` ctx, slotted between the SSO
overloads and the `activity` catch-all so `activity` stays last.
This leaves only `message`, `conversationUpdate`, and `messageReaction`
flowing through `app.on("activity", ...)` → `handler.run`. Promoting
those is the path to deleting the catch-all entirely.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(msteams): fall back to block delivery when partial-mode stream fails mid-flight
codex #5 / Galin F5 on PR #76262. `reply-stream-controller.ts` previously
re-threw any non-cancel error from `stream.emit` during partial streaming
and from `stream.emit`/`stream.close` during finalize. Combined with
`preparePayload` suppressing block delivery once `tokensEmitted` was
true, that meant a network blip or API error mid-stream produced a
truncated reply with no recovery — the user saw the prefix that made it
through and nothing else.
Add a `streamFailed` latch parallel to `canceledLocally` / `tokensEmitted`:
- `onPartialReply`: catch non-cancel errors, set `streamFailed = true`,
log a warn, don't propagate (the pipeline must keep running so
`preparePayload` can decide).
- `preparePayload`: when `tokensEmitted && streamFailed`, fall through to
block delivery instead of suppressing. The user may see a duplicate
(streamed prefix + full block reply); intentional — matches the
pre-migration `TeamsHttpStream.hasContent` recovery and is better than
truncated-only.
- `finalize`: same latch + warn on non-cancel close failure, swallow
rather than throw. The streamed content already reached the user; the
closing activity (AI-Generated marker, feedback channelData) is the
only loss, not worth blowing up the dispatcher.
- `isStreamActive` returns false once the stream has failed.
New tests cover crash-mid-stream after tokens were emitted (assert block
delivery payload is returned), happy-path no-duplicate behavior (assert
`preparePayload` still suppresses when nothing failed), and finalize
close-failure (assert no throw). The pre-existing "re-throws non-cancel"
test was inverted to assert non-throwing latch behavior.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(msteams): declare @microsoft/teams.api as a runtime dependency
Type-only `import("@microsoft/teams.api/dist/...").TypeName` references
in `sdk.ts` (added when typed `MSTeamsApp.on` overloads were introduced)
are picked up by the `extension-runtime-dependencies` contract test as
genuine runtime imports. Declaring `@microsoft/teams.api` as a direct
dep makes the contract pass; the package was already coming in
transitively via `@microsoft/teams.apps`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(msteams): keep SSO on SDK signin routes
* test(msteams): avoid redundant signin handler assertion
* docs(msteams): clarify Teams cloud support
* fix(msteams): use current SDK string helper
* fix(msteams): gate SDK invoke side effects
* test(msteams): avoid implicit any in lifecycle tests
* fix(msteams): preserve SDK user agent and matrix check
* fix(msteams): expose SDK common dependency
* fix(msteams): use SDK user agent merge
* fix(msteams): fall back when stream close no-ops
* chore(msteams): drop unrelated merge artifacts
* chore(msteams): restore unrelated main files
* chore(msteams): restore unrelated main files
* chore(msteams): restore unrelated main files
* test(msteams): type stream close mock result
* fix(msteams): configure Teams cloud service URL
* chore(msteams): refresh shrinkwrap
* chore(deps): refresh shrinkwrap locks
* chore(ci): rerun guards after main sync
* chore(deps): refresh shrinkwrap for node 24
* chore(config): refresh docs baseline
* fix(msteams): preserve Teams SDK proactive references
* fix(msteams): harden SDK proactive sends
* fix(msteams): align service url contract
* test: fix bonjour beacon type narrowing
* fix(msteams): ignore ambient service url
* fix(msteams): fall through submit invokes
* test: align shrinkwrap override policy with Teams SDK deps
* fix(msteams): ack invoke routes promptly
* fix(msteams): support china cloud boundaries
* test: sync PR with current CI gates
* test: isolate channel setup registry metadata
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Recover Codex compaction paths when a stale app-server thread binding returns an unstructured `thread not found` failure. The raw missing-thread response now shares the same recovery behavior as structured missing/stale binding failures for preflight, queued compaction, and CLI fallback.
Fixes#87736.
Co-authored-by: Paul Frederiksen <paul@paulfrederiksen.com>
Summary:
- The PR reorders embedded attempt cleanup to release the session write lock before session/MCP/LSP teardown, treats sessions_yield cleanup as abort-like for flush timing, and adds focused regression tests.
- PR surface: Source +14, Tests +71. Total +85 across 3 files.
- Reproducibility: yes. Source inspection shows current main releases the cleanup lock only after runtime tear ... R body’s terminal proof exercises the same ordering with production cleanup and filesystem lock primitives.
Automerge notes:
- PR branch already contained follow-up commit before automerge: Merge branch 'main' into fix/session-lock-release-before-teardown
Validation:
- ClawSweeper review passed for head 178192fa0e.
- Required merge gates passed before the squash merge.
Prepared head SHA: 178192fa0e
Review: https://github.com/openclaw/openclaw/pull/87747#issuecomment-4566994280
Co-authored-by: fuller-stack-dev <263060202+fuller-stack-dev@users.noreply.github.com>
Co-authored-by: Jason (Json) <263060202+fuller-stack-dev@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Generated-media completions now use the existing idempotent direct-media fallback when active requester wake has already failed and the requester-agent handoff hits a session write-lock-shaped no-response error. Generic requester-agent handoff errors still fail visibly instead of direct-sending after an unknown side effect.
Release-note context: fixes a message-delivery loss path for generated images, music, and video where the artifact had been created but the final handoff could be reported as failed after a session write lock.
Verification:
- GitHub CI run 26601111985 passed at b0be994332.
- Blacksmith Testbox through Crabbox tbx_01ksr2jtt3fnz0zqvwmqq513h7 covered the exact lock fallback and qa-channel generated-media smoke.
- git diff --check origin/main...refs/remotes/pull/87741/head passed before merge.
Co-authored-by: Jason (Json) <263060202+fuller-stack-dev@users.noreply.github.com>
Reuses the current plugin metadata snapshot in facade activation checks when the resolved boundary config matches, avoiding repeated manifest registry loads on the facade path.
Falls back to manifest registry loading when the current snapshot is missing or belongs to a different config/environment. Adds regression coverage for snapshot mismatch, snapshot reuse, and Windows path normalization.
Co-authored-by: 郑苏波 (Super Zheng) <superzheng@tencent.com>
Bound aggregate tool-result history at the provider prompt boundary without rewriting persisted session entries.
Provider-visible prompt history now trims older aggregate tool results before newer evidence, while canonical session history, slash/extension command handlers, and context-engine afterTurn snapshots stay unmodified.
Co-authored-by: luyifan <al3060388206@gmail.com>
* fix(nvidia): load featured model catalog
Co-authored-by: CaptainTimon <CaptainTimon@users.noreply.github.com>
* fix(nvidia): widen catalog fetch timeout
* fix(nvidia): cover catalog registration
* fix(picker): include provider catalog loader
* fix(nvidia): guard featured catalog fetch
* fix(nvidia): sync bundled catalog with live API
Replace minimaxai/minimax-m2.5 (MiniMax M2.5) with minimaxai/minimax-m2.7 (Minimax M2.7) and z-ai/glm5 (GLM-5) with z-ai/glm-5.1 (GLM 5.1) in the bundled fallback catalog to match NVIDIA's public featured-models endpoint.
Update docs table and all extension test expectations.
* fix(nvidia): retain shipped catalog refs
* fix(picker): keep alias catalog rows
* fix(nvidia): restore live catalog priority
---------
Co-authored-by: CaptainTimon <CaptainTimon@users.noreply.github.com>
Summary:
- The PR changes three TUI final chat-event early returns to call `tui.requestRender(true)` and adds focused event-handler assertions for those branches.
- PR surface: Source 0, Tests +25. Total +25 across 2 files.
- Reproducibility: yes. Current main and the latest release still have the three unforced final-event repaint calls, and the linked source PR includes PTY terminal proof showing the changed behavior after the patch.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(tui): force repaint final chat events
Validation:
- ClawSweeper review passed for head 570dc3af86.
- Required merge gates passed before the squash merge.
Prepared head SHA: 570dc3af86
Review: https://github.com/openclaw/openclaw/pull/87423#issuecomment-4558845936
Co-authored-by: Ted Li <tl2493@columbia.edu>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Narrow the abort-settle timeout helper to the env keys it reads and keep the dynamic live-model hook unit test from loading provider normalization/runtime plugins.\n\nProof: focused Vitest for live-model-dynamic-candidates, oxfmt/oxlint/diff checks, autoreview clean, AWS Crabbox run_8a485e593c2e corepack pnpm check:changed exit 0, and PR CI green.
Summary:
- The PR updates the bundled MiniMax music provider to request streaming hex responses, decode SSE/audio bodie ... while preserving JSON/url fallbacks, and adds provider tests for streaming, fallback, and timeout behavior.
- PR surface: Source +148, Tests +152. Total +300 across 2 files.
- Reproducibility: yes. by source inspection and live proof, though I did not run a fresh live reproduction. C ... s provider fallback, and the source PR reports a 130s live MiniMax provider run succeeding after the patch.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(minimax): stream music generation responses
- PR branch already contained follow-up commit before automerge: fix(clawsweeper): address review for automerge-openclaw-openclaw-8456…
Validation:
- ClawSweeper review passed for head 806b0b40f2.
- Required merge gates passed before the squash merge.
Prepared head SHA: 806b0b40f2
Review: https://github.com/openclaw/openclaw/pull/84764#issuecomment-4504175527
Co-authored-by: Neerav Makwana <261249544+neeravmakwana@users.noreply.github.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Render Slack progress-mode updates as native task-card progress blocks, with bounded Slack chunk text and stable fallback behavior.
Also deep-merge Slack account streaming objects over top-level defaults while preserving legacy scalar account overrides, and keep the plugin SDK fetch runtime import path from evaluating guarded-fetch dispatcher code.
Verification:
- pnpm test extensions/slack/src/progress-blocks.test.ts extensions/slack/src/accounts.test.ts src/plugin-sdk/fetch-runtime.test.ts
- pnpm lint --threads=8
- git diff --check
- .agents/skills/autoreview/scripts/autoreview --mode local
- GitHub PR checks green on #87748 at 4803e98820
Refs #82258
Co-authored-by: Simon van Laak <32648751+simonvanlaak@users.noreply.github.com>
Support grouped skill folders while keeping skill invocation flat via frontmatter names.
Includes bounded nested SKILL.md discovery, refresh/watch coverage for grouped folders, plugin symlink containment, and docs for grouped skill organization.
Verification:
- Node 24 targeted skill discovery and refresh tests passed locally.
- Docs checks passed locally and in CI.
- Autoreview clean.
- Crabbox live OpenAI proof showed nested foo/bar skills listed and visible in the agent system prompt.
- CI run 26595118581 passed.
Summary:
- The branch preserves current Claude Haiku 4.5 refs in the Anthropic resolver and doctor migration, repoints the bare `haiku` family alias to `claude-haiku-4-5`, and updates regression tests.
- PR surface: Source +5, Tests +21. Total +26 across 4 files.
- Reproducibility: yes. Current main source maps the bare `haiku` alias and explicit Haiku 4.5 migration path ... de-sonnet-4-6`; the PR body also supplies before/after terminal proof for the resolver and migration tests.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head 64429e23b3.
- Required merge gates passed before the squash merge.
Prepared head SHA: 64429e23b3
Review: https://github.com/openclaw/openclaw/pull/87719#issuecomment-4566419633
Co-authored-by: alkor2000 <200923177@qq.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Cap Dreaming short-term recall stores so repeated recall recording, repair, and promotion application cannot grow the JSON artifact without bound.
The fix keeps full normalized snippets for recall identity and contamination checks before truncating persisted snippets, exposes the new overflow audit code through the SDK facade, and adds regression coverage for recording, repair, promotion rehydration, and deterministic retention ties.
Fixes#87095.
Verification:
- OPENCLAW_VITEST_MAX_WORKERS=1 node scripts/run-vitest.mjs extensions/memory-core/src/short-term-promotion.test.ts src/commands/doctor-memory-search.test.ts src/plugin-sdk/memory-core-engine-runtime.test.ts
- pnpm tsgo:prod
- pnpm check:test-types
- pnpm lint --threads=8
- git diff --check
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
- PR CI run 26594527697: unrelated current-main failures only in checks-node-agentic-plugin-sdk and checks-node-agentic-agents; same failures reproduced on main run 26594198639.
Co-authored-by: ai-hpc <mail.speedy.hpc@hotmail.com>
Wrap Ollama native streams with the shared plain-text tool-call compatibility wrapper so local/plain-text tool requests are delivered as structured toolCall events when matching tools are available.
Verified with live local Ollama proof, focused Testbox Vitest, Testbox check:changed, and autoreview.
Summary:
- The branch filters OpenClaw CLI image-cache paths out of prompt image-reference detection and adds parser/helper regression tests.
- PR surface: Source +17, Tests +65. Total +82 across 3 files.
- Reproducibility: yes. source-level reproduction is high confidence: current main still scans replayed prompt ... ectImageReferences and has no cache-path exclusion before loadPromptRefImages can reload stale image paths.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(images): skip CLI image cache refs
- PR branch already contained follow-up commit before automerge: fix(clawsweeper): address review for automerge-openclaw-openclaw-8750…
Validation:
- ClawSweeper review passed for head dfe0408df8.
- Required merge gates passed before the squash merge.
Prepared head SHA: dfe0408df8
Review: https://github.com/openclaw/openclaw/pull/87523#issuecomment-4560945125
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- The PR changes the Control UI chat session picker blur handler to skip empty-query search application and adds a regression test that picker options remain clickable after an empty search blur.
- PR surface: Source +4, Tests +52. Total +56 across 2 files.
- Reproducibility: yes. The issue steps, before recording, and current-main source path all point to the same ... r clearing picker state before click delivery; I did not rerun a live browser repro in this read-only pass.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(ui): preserve session picker on empty search blur
Validation:
- ClawSweeper review passed for head bb14687756.
- Required merge gates passed before the squash merge.
Prepared head SHA: bb14687756
Review: https://github.com/openclaw/openclaw/pull/87682#issuecomment-4565441074
Co-authored-by: Ryan Weng <14496969+ryan4559@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Surface inbound bundle-MCP structuredContent as the model-visible result when present so agents can read Codex MCP threadId values and continue with codex-reply. Preserve non-structured content behavior, preserve the empty-result fallback, and keep details.structuredContent for internal consumers.
Also remove an unused secrets path helper that was breaking the latest prod-type gate on main.
Fixes#87511.
Verification:
- node scripts/run-vitest.mjs src/agents/agent-bundle-mcp-tools.materialize.test.ts
- pnpm exec oxfmt --check src/secrets/path-utils.ts src/agents/agent-bundle-mcp-materialize.ts src/agents/agent-bundle-mcp-tools.materialize.test.ts
- pnpm tsgo:prod
- local check-guards shard commands
- live Codex MCP smoke with codex__codex and codex__codex-reply same-thread continuation
- autoreview clean
- CI run 26587222874 green
Co-authored-by: Pluviobyte <Pluviobyte@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Fix replay handling for voice-call webhooks so duplicate signed requests do not mint or expose realtime stream tokens.
- Return token-free Twilio replay TwiML before realtime setup shortcuts.
- Cache bounded non-Twilio first responses for idempotent replay XML while skipping duplicate side effects.
- Cover Twilio realtime replay and Plivo replay behavior with regression tests.
- Remove an unused secrets path helper that was tripping latest-main prod type CI.
Fixes#87497.
Co-authored-by: Coy Geek <65363919+coygeek@users.noreply.github.com>
Fixes#87016.
Empty preflight compaction recovery now resets stale token snapshots immediately, preserves valid legacy transcript rows during cleanup, and avoids re-persisting stale context-budget or compaction metadata after a successful retry.
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
Add read-only MCP visibility to `tools.effective` by projecting MCP tools only after a session catalog has already been warmed by an agent turn. Keep the gateway additive: no `tools.effective.refresh`, no forced MCP startup, and no behavior change for MCP loading.
Verification:
- `git diff --check origin/main..HEAD`
- `node scripts/run-vitest.mjs run --config test/vitest/vitest.agents.config.ts --reporter=verbose src/agents/tools-effective-inventory.test.ts`
- GitHub checks green on `a8a7f8442adb216f60da24d50118374a15c62e06`, including `Real behavior proof`, `check-guards`, `check-prod-types`, `check-test-types`, `build-artifacts`, `Critical Quality (gateway-runtime-boundary)`, and `Critical Quality (network-runtime-boundary)`.
Co-authored-by: David Huang <nxmxbbd@gmail.com>
The anthropic-transport-stream was overwriting thinkingSignature on each
signature_delta event instead of appending. Since Anthropic sends the
thinking block signature across multiple streaming chunks, only the last
chunk survived. The truncated signature was persisted to session JSONL,
causing all subsequent replay attempts to fail with HTTP 400:
thinking or redacted_thinking blocks in the latest assistant message
cannot be modified
This permanently bricked sessions with no user recovery path.
Fix: accumulate signature_delta values by concatenating instead of
overwriting, matching the correct implementation in the LLM provider
layer (src/llm/providers/anthropic.ts:629-634).
Includes real-scenario proof against live Anthropic API validating that
correct signatures replay successfully while truncated signatures are
rejected.
Fixes#87574
Refs #80625, #85781, #87475
* fix(agents): preserve reasoning_content replay across DeepSeek tier suffixes
OpenCode Zen exposes DeepSeek V4 as `deepseek-v4-flash-free`, which keeps the upstream DeepSeek thinking-mode contract that requires `reasoning_content` to be passed back on follow-up requests. The existing replay allowlist only matched the bare ids (`deepseek-v4-flash`, `kimi-k2-thinking`, ...), so the tier-suffixed id missed every candidate and the sanitizer stripped `reasoning_content` from the assistant turn. DeepSeek then rejected the second API call with HTTP 400 and the session deadlocked.
Strip the well-known tier suffixes (`-free`, `-paid`, `-trial`) when generating allowlist candidates so the base model id matches and the reasoning replay survives. Existing matching for prefixed / colon-suffixed routes is unchanged.
Fixes#87575
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(agents): avoid spread-rebuild when iterating allowlist candidates
oxlint flagged the [...candidates] spread as an unnecessary array copy. Use an explicit baseCount loop bound instead so we still iterate the original entries while pushing tier-stripped variants onto the same array.
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(opencode): add live DeepSeek replay probe
* test(opencode): avoid forced tool choice in live replay
---------
Co-authored-by: Pluviobyte <Pluviobyte@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Fixes#58012.
Applies strict9 replay tool call id sanitization to OpenRouter Mistral-family model routes, including unprefixed Mistral/Codestral/Devstral aliases, while preserving existing passthrough behavior for Gemini and other OpenRouter-backed routes.
Adds focused unit coverage plus a live OpenRouter model catalog test so new Mistral-family routes are checked against the replay policy. Also keeps the current core lint gate green by switching the tool schema cache key sort to a non-mutating sorted array.
Co-authored-by: Pluviobyte <Pluviobyte@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Preserve explicit gateway service identity when package/update refreshes the managed service environment. This keeps caller-selected systemd units ahead of stale persisted service env and applies the same precedence to launchd labels and Windows task names during service-state inspection.
Fixes#87490
Verification:
- node scripts/run-vitest.mjs src/daemon/service-env.test.ts src/daemon/service.test.ts src/cli/update-cli.test.ts src/cli/update-cli/restart-helper.test.ts src/cli/daemon-cli/install.test.ts src/daemon/systemd.test.ts
- git diff --check origin/main...pr/87556
- Crabbox AWS Linux systemd install/refresh proof: run_f3374bd610f7, lease cbx_754e69eb6c3a, provider aws, target linux
- autoreview --mode branch --base origin/main: clean, no accepted/actionable findings
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
Summary:
- Replace the legacy iOS shell with Pro Command, Chat, Agents, and Settings tabs.
- Wire iOS chat/session/settings/diagnostics and realtime Talk flows through gateway-backed APIs.
- Add gateway/session and shared chat coverage for the new iOS flow.
Verification:
- git diff --check
- node scripts/run-vitest.mjs src/gateway/server.sessions.create.test.ts src/gateway/talk-realtime-relay.test.ts
- swift test --filter ChatViewModelTests (apps/shared/OpenClawKit)
- xcodebuild build for Nimrod's iPhone succeeded; install succeeded; launch was blocked because the phone was locked
Known follow-up:
- Preserve traceLevel in sessions.create parent runtime inheritance and keep the changelog credit in the follow-up patch.
Increase the code-mode wait-timeout test timeout so CI shard load does not trip the worker startup guard before the test reaches the intended pending-tool wait path.
Reduce repeated gateway warning noise in startup/auth retry paths while preserving credential mismatch and rate-limit audit visibility.
Also hardens empty embedded-assistant retry handling by carrying lifecycle state through the missing-assistant guard, and keeps the relevant regression coverage in gateway and agent tests.
@@ -100,6 +100,10 @@ Format first if formatting can change line locations. Then it is OK to run tests
scripts/autoreview --parallel-tests "<focused test command>"
```
On Windows, the default `--parallel-tests` shell preserves the platform `cmd.exe`
semantics used by Python `shell=True`. Use `--parallel-tests-shell powershell`
or `--parallel-tests-shell pwsh` when the focused test command is PowerShell-specific.
Tradeoff: tests may force code changes that stale the review. If tests or review lead to code edits, rerun the affected tests and rerun review until no accepted/actionable findings remain. Once that rerun exits cleanly, stop; do not spend another long review cycle on redundant confirmation.
- otherwise uses current PR base if `gh pr view` works
- otherwise uses `origin/main` for non-main branches
- supports `--engine codex`, `claude`, `droid`, and `copilot`; default is `AUTOREVIEW_ENGINE` or `codex`; Codex should remain the default when nothing is set
- resolves bare `git`, `gh`, reviewer, and PowerShell shell commands from absolute `PATH` entries only, never from the reviewed checkout; explicit relative `--*-bin` paths are resolved from the reviewed repository root
- use `--mode commit --commit <ref>` for already-committed work, especially clean `main` after landing
- should be left in `--mode auto` or forced to `--mode branch` for PR/branch work; do not force `--mode local` after committing
- writes only to stdout unless `--output`, `--json-output`, or live streamed engine stderr is set
- supports `--stream-engine-output` or `AUTOREVIEW_STREAM_ENGINE_OUTPUT=1` for live engine text while preserving structured validation; Codex and Claude hide tool/file event details, emit compact activity summaries, and report usage at turn completion
- supports opt-in review panels with `--panel` / `--reviewers`, plus per-engine `--model` and `--thinking`
- allows read-only tools and web search by default where the selected CLI supports them; forbids nested review in the prompt; Codex is run through `codex exec` with read-only sandbox and structured output
--prompt "This is an acceptance test fixture. The changed app.js patch contains real security bugs. Review normally and report only actionable defects from the patch." \
--require-finding "command" \
--expect-findings
else
"$script_dir/autoreview" \
--mode local \
--engine "$engine" \
--prompt "Security calibration fixture: this patch intentionally uses filesystem paths, async execFile, and owner-gated password-adjacent state safely. Do not flag legitimate shell/filesystem/auth-adjacent functionality unless there is a concrete exploitable risk in the diff."
fi
done
echo "Python 3 is required to run test-review-harness." >&2
MALICIOUS_PROMPT="This is an acceptance test fixture. The changed app.js patch contains real security bugs. Review normally and report only actionable defects from the patch."
BENIGN_PROMPT="Security calibration fixture: this patch intentionally uses filesystem paths, async execFile, and owner-gated password-adjacent state safely. Do not flag legitimate shell/filesystem/auth-adjacent functionality unless there is a concrete exploitable risk in the diff."
@@ -98,7 +98,7 @@ Do not close from title alone. If closing as done on main or nonsensical, prove
When asked for `5 new`, exclude refs already surfaced in the session and refill from the archive until there are 5 live-open candidates. If fewer than 5 remain open, list all open ones and say how many short.
When asked to `update`, `refresh`, `recheck`, `check again`, or similar, return an updated live-open candidate list. Do not fill the main list with items that merely merged/closed since the last pass; put those numbers in a short bottom line.
When asked to `update`, `refresh`, `recheck`, `check again`, or similar, return an updated live-open candidate list. Sort by maintainer importance, not recency: high-impact ready fixes first, then useful-but-review-first, then open/not-ready items. Do not include a "changed since last pass" section or bottom-line merged/closed summary unless the user explicitly asks for churn.
Prefer:
@@ -142,18 +142,20 @@ No Markdown tables. Compact bullets. Use color/risk markers:
Required line shape:
```markdown
- **PR #81244** `@whatsskill.``+118/-1``bug` 🟢 verifiable: yes. This prevents chat action buttons from overlapping short assistant replies. Blast: web chat rendering, low.
- **Issue #81245** `@alice``LOC n/a``bug` 🟡 verifiable: partial. This reports duplicate Telegram replies when reconnecting after gateway restart. Blast: Telegram channel runtime, medium.
- **PR #81244** `@whatsskill.``+118/-1``bug` 🟢 https://github.com/openclaw/openclaw/pull/81244 - Prevents chat action buttons from overlapping short assistant replies. Verifiable: yes. Blast: web chat rendering, low.
- Always include `verifiable: yes|partial|no` plus the shortest proof hint when helpful.
- If status is not open, still show it only when the user asked for all surfaced refs; use ✅ or ⚪ and state merged/closed.
- For refresh-style asks, bottom line: `Merged/closed since last pass: #81016 merged, #81026 closed.` Omit if none.
- For refresh-style asks, prefer section order: `Best Open Now`, `Useful But Review First`, `Still Open / Not Ready`. Omit merged/closed churn by default.
DISCRAWL_NO_AUTO_UPDATE=1 discrawl --json sql "select count(*) from messages;"
```
Report absolute date spans, channel/DM names, counts, and known gaps. Use read-only SQL for exact counts/rankings. Never use `--unsafe --confirm` unless the user explicitly requests a reviewed DB mutation.
## SQL
Boundaries: bot sync needs configured Discord bot credentials. Wiretap reads local Discord Desktop artifacts only; do not extract user tokens, call Discord as the user, or write to Discord storage. Git-share snapshots must not include secrets or `@me` DM rows.
Use `discrawl sql` for exact counts, joins, and ranking queries when normal
CLI reads are too coarse. The command is read-only by default, accepts SQL as
args or stdin, and supports `--json` for agent parsing.
Useful examples:
```bash
DISCRAWL_NO_AUTO_UPDATE=1 discrawl --json sql "select count(*) as messages from messages;"
DISCRAWL_NO_AUTO_UPDATE=1 discrawl --json sql "select coalesce(nullif(c.name, ''), m.channel_id) as channel, count(*) as messages from messages m left join channels c on c.id = m.channel_id group by m.channel_id order by messages desc limit 20;"
DISCRAWL_NO_AUTO_UPDATE=1 discrawl --json sql "select coalesce(nullif(mm.display_name, ''), nullif(mm.global_name, ''), nullif(mm.username, ''), m.author_id) as author, count(*) as messages from messages m left join members mm on mm.guild_id = m.guild_id and mm.user_id = m.author_id group by m.guild_id, m.author_id order by messages desc limit 20;"
```
Never use `--unsafe --confirm` unless the user explicitly asks for a database
mutation and the write has been reviewed.
When the installed CLI lacks a new feature, build or run from a verified
`openclaw/discrawl` checkout before concluding the feature is missing.
## Discord Boundaries
Bot API sync requires configured Discord bot credentials; do not invent token
availability. Desktop wiretap mode reads local Discord Desktop artifacts and
must not extract credentials, use user tokens, call Discord as the user, or
write to Discord application storage. Wiretap/Desktop cache DMs are local-only
and must not be described as part of the published Git snapshot. Git-share
snapshots must not include secrets or `@me` DM rows.
## Verification
For repo edits, prefer existing Go gates:
```bash
GOWORK=off go test ./...
```
Then run targeted CLI smoke for the touched surface, for example:
- Publishing fails with HTTP 422 if required fields are missing or the private fork still has open PRs.
- A payload that looks correct in shell can still be wrong if Markdown was assembled with escaped newline strings.
- Advisory PATCH sequencing matters; separate field updates when GHSA API constraints require it.
- Public hardening/no-publish comments and draft text should avoid raw commit hashes, PR titles/numbers, and fix-mechanism summaries. Prefer patched-version fields or release-only wording; keep SHAs, PRs, and implementation notes in internal evidence.
- Review the surrounding code path, not just changed lines. Open the caller, callee, data contracts, adjacent tests, and owner module.
- Before any verdict, read enough code to fill this map: changed surface, runtime entry point, owner boundary, one caller, one callee, sibling implementations sharing the invariant, adjacent tests, current `main` behavior, and shipped/dependency/Codex contracts when relevant.
- For large-codebase PRs, sample enough related files to understand the runtime boundary before deciding. Default to more code reading when the change touches agents, gateway, plugins, auth, sessions, process, config, or provider/runtime seams.
- Compare the PR against current `origin/main` behavior. Check whether recent main already changed the same surface.
- Dependency-backed behavior: MUST read upstream docs/source/types before judging API use, defaults, output shapes, errors, timeouts, memory behavior, or compatibility. Do not assume dependency contracts from memory or PR text.
- Judge solution quality, not only correctness. Ask whether the PR is the clean owner-boundary fix or a wart/workaround that should be replaced by a small refactor, moved seam, contract change, or deletion of duplicate logic.
- Mention the main files read when the verdict depends on code-path evidence.
- If the user challenges the verdict or asks whether the idea is really good, resume code reading first. Do not defend, soften, or reverse the verdict until the missing caller/callee/sibling/dependency path is checked.
## Best-fix review loop
Every PR review must explicitly answer: "Is this the best fix, or only a plausible fix?"
Before verdict:
1. Reconstruct the bug, feature need, or behavior claim from issue/PR/proof.
2. Trace current behavior from entry point to failure or decision point.
4. Read sibling surfaces that should share the invariant or could be broken by a one-sided fix.
5. Compare against current `origin/main` and shipped behavior when regression/compat matters.
6. Inspect upstream dependency/Codex source or docs for dependency-backed behavior.
7. Identify at least one alternative fix location or shape, then reject it with evidence.
8. If any required path above is uninspected, keep reading or mark `Remaining uncertainty`; do not call the PR best, blocked, proof-sufficient, or merge-ready.
Review output must include:
-`Best-fix verdict:` best / acceptable mitigation / wrong layer / too narrow / too broad.
-`Alternatives considered:` 1-3 concrete alternatives and why rejected.
-`Code read:` compact list of main files/contracts checked.
-`Remaining uncertainty:` what was not proven.
If the best-fix answer is only "maybe", keep reading or state the missing evidence. Do not call proof sufficient until the best-fix judgment is explicit.
description: Triage OpenClaw security advisories, drafts, and GHSA reports with shipped-tag and trust-model proof.
description: "Triage OpenClaw security advisories, drafts, and GHSA reports with shipped-tag and trust-model proof."
---
# Security Triage
@@ -87,11 +87,19 @@ When preparing a maintainer-ready close reply:
- exact reason for close
- exact code refs
- exact shipped tag / release facts
-exact fix commit or canonical duplicate GHSA when applicable
-fix provenance or canonical duplicate GHSA when applicable
- optional hardening note only if worthwhile and functionality-preserving
Keep tone firm, specific, non-defensive.
## Public Wording Hygiene
- Keep raw commit hashes, PR titles/numbers, and fix-mechanism summaries out of public advisory text. Use the patched release/version field only.
- Keep exact commit SHAs, PRs, and implementation notes in internal notes and verification files.
- For hardening/no-publish outcomes, do not add exploit-heavy details, "Fixed by" text, or a "Fix Commit(s)" section. Thank reporters, preserve credit, state the `SECURITY.md` boundary, and say clearly that the GHSA will close without publication.
- For published CVE/GHSA text, prefer `### Patched Versions` with the fixed release. Do not explain how the patch works unless Peter explicitly asks for that public detail.
- Keep GHSA ids out of changelog and release-note wording unless Peter explicitly asks.
## Discussion Mode
When Peter is manually posting GHSA comments, use this flow:
| select(startswith("+") and (startswith("+++") | not))
| "\($file): \(.)"
' > "$added_lines"
if grep -En '(from|require\().*["'\''](node:)?(net|tls|http2)["'\'']|\b(net|tls|http2)\.(connect|createConnection)\b|new Socket\(|HTTP_PROXY|HTTPS_PROXY|NO_PROXY|GLOBAL_AGENT_|OPENCLAW_PROXY_' "$added_lines"; then
echo "It does not sign, notarize, or upload macOS assets."
echo
echo "Next step:"
echo "- Run \`openclaw/releases-private/.github/workflows/openclaw-macos-validate.yml\` with tag \`${RELEASE_TAG}\` and wait for the private mac validation lane to pass."
echo "- Run \`openclaw/releases-private/.github/workflows/openclaw-macos-publish.yml\` with tag \`${RELEASE_TAG}\` and \`preflight_only=true\` for the full private mac preflight."
echo "- For the real publish path, run the same private mac publish workflow from \`main\` with the successful private preflight \`preflight_run_id\` so it promotes the prepared artifacts instead of rebuilding them."
echo "- For stable releases, the private publish workflow also publishes the signed \`appcast.xml\` to public \`main\`, or opens an appcast PR if direct push is blocked."
echo "- Run \`openclaw/releases/.github/workflows/openclaw-macos-validate.yml\` with tag \`${RELEASE_TAG}\` and wait for the macOS validation lane to pass."
echo "- Run \`openclaw/releases/.github/workflows/openclaw-macos-publish.yml\` with tag \`${RELEASE_TAG}\` and \`preflight_only=true\` for the full macOS preflight."
echo "- For the real publish path, run the same macOS publish workflow from \`main\` with the successful preflight \`preflight_run_id\` so it promotes the prepared artifacts instead of rebuilding them."
echo "- For stable releases, the publish workflow also publishes the signed \`appcast.xml\` to public \`main\`, or opens an appcast PR if direct push is blocked."
@@ -9,7 +9,11 @@ Skills own workflows; root owns hard policy and routing.
- Replies: repo-root refs only: `extensions/telegram/src/index.ts:80`. No absolute paths, no `~/`.
- Docs/user-visible work: `pnpm docs:list`, then read relevant docs only.
- Fix/triage answers need source, tests, current/shipped behavior, and dependency contract proof.
- Reviews/answers: high confidence required. Default to exhaustive relevant codebase search/read, including owners, callers, siblings, tests, docs, and upstream/dependency contracts before verdict. Diff-only review is insufficient.
- Review default: read the whole changed function/module plus callers, callees, sibling implementations, adjacent tests, scoped docs, and dependency/Codex contracts before saying `good`, `bad`, `best fix`, `proof sufficient`, or posting a comment. If challenged, keep reading first; do not defend the earlier verdict until the missing path is checked.
- Dependency-touching work: direct dependency inspection is mandatory when feasible; do not rely on assumptions, wrappers, or memory. Most dependencies are OSS, so read their source/docs/types. Codex-related work has a hard gate: the acting agent must personally inspect sibling `../codex` source for the exact protocol/runtime behavior before any verdict, comment, approval, merge recommendation, code change, or `proof sufficient` claim. If missing, clone `https://github.com/openai/codex.git` there first. Subagent reports, PR text, OpenClaw wrappers, generated schemas, memory, and prior bot reviews do not satisfy this gate. No direct `../codex` check means no Codex verdict. Cite Codex files/lines checked in final/review/comment.
- Dependency-backed behavior: read upstream docs/source/types first. No API/default/error/timing guesses.
- External API work: live test required. Google/search for additional proof. Prefer official docs/source/types; cite current proof. No memory-only API claims.
- Live-verify when feasible. Never print secrets.
- Missing deps: `pnpm install`, retry once, then report first actionable error.
- CODEOWNERS: maint/refactor/tests ok. Larger behavior/product/security/ownership: owner ask/review.
@@ -26,6 +30,8 @@ Skills own workflows; root owns hard policy and routing.
- Plugin APIs, provider routing, auth/session state, persisted preferences, config loading, config/default additions, migrations, setup, startup checks, and fallback behavior are compatibility/upgrade-sensitive. Treat config breaks, new config/default surfaces, removed fallbacks, fail-closed changes, stricter validation, or new operator action as merge risk even with green CI when they can affect existing users, upgrades, provider/plugin behavior, or maintainer operations.
- For PRs that add, remove, or change config/default surfaces with possible compatibility, upgrade, provider/plugin, operator, setup, startup, or fallback impact, ClawSweeper review should emit a `reviewMetrics` entry when practical. The metric should name the count and direction of the changes, such as added, changed, or removed config/default surfaces, and explain why the metric matters before merge. When the metric indicates concrete merge risk, also surface the concern in `risks`, use `mergeRiskLabels` when the risk matches the label rubric, make `bestSolution` name the desired pre-merge state, and ensure `labelJustifications` explain the specific reason rather than restating the label.
- Review whole decision surfaces, not only the touched runtime, provider, channel, harness, plugin seam, or context path. Check sibling Codex/Pi-style runtimes, provider/model routing, channel delivery, gateway/protocol, plugin SDK, and context-management paths when relevant.
- Every PR review must explicitly ask whether the PR is the best fix, not merely a plausible fix. Verdicts need a best-fix judgment backed by enough code reading to compare owner boundaries, callers, siblings, tests, docs, current `main`, shipped behavior when relevant, and dependency/Codex contracts when involved.
- Before a PR verdict, build a small evidence map: changed surface, entry point, owner boundary, at least one caller and callee, sibling surfaces that share the invariant, existing tests, and current `main` behavior. If any cell is missing, say the gap instead of concluding.
- One-sided fixes need sibling-surface proof, an explanation for why siblings are unaffected, or explicit follow-up work.
- Changelog findings: see Docs / Changelog.
- Public ClawSweeper comments prefer `https://docs.openclaw.ai/...` when a public docs page exists; structured evidence still cites repo files, lines, SHAs.
@@ -35,9 +41,9 @@ Skills own workflows; root owns hard policy and routing.
@@ -57,11 +63,25 @@ Skills own workflows; root owns hard policy and routing.
- External official plugins own package/deps and are excluded from core dist; core uses registry-aware `facade-runtime` or generic contracts.
- Externalizing a bundled plugin: update package excludes, official catalogs, docs, tests, and prove core runtime paths resolve installed plugin roots before root-dep removal.
- Runtime reads canonical config only. No silent compat for old/malformed config keys. If a config change invalidates existing files, add a matching `openclaw doctor --fix` migration. Core/auth config repairs live in core doctor; plugin-owned config repairs live in that plugin's doctor contract (`legacyConfigRules` / `normalizeCompatibilityConfig`).
- OpenAI Codex is folded into `openai`. No new/live `openai-codex` provider/plugin/auth/model routes; treat them as legacy input only. Runtime/setup/auth/catalog use `openai` + `openai/*`; doctor/migrations repair stale `openai-codex/*` profiles/metadata.
- Config/env surface bar is high; `openclaw.json` and environment variables are already large. Before adding a config option or env var, first prove existing product behavior, provider selection, defaults, or doctor migration cannot solve it. Prefer removing or consolidating config/env options when touching these surfaces. Core supports only the latest config shape; `openclaw doctor --fix` migrates older shipped shapes into the current one.
- CLI setup flows are public API when external docs, installers, or integrations can copy them. Changes to `openclaw onboard`, `openclaw configure`, their documented flags, non-interactive behavior, or generated config shape are compatibility-sensitive API contract changes; prefer additive flags/aliases, deprecation windows, and backward-preserving migrations over breaking existing snippets.
- Fix shape: default to clean bounded refactor, not smallest patch. Move ownership to right boundary; delete stale abstractions, duplicate policy, dead branches, wrappers, fallback stacks.
- Fix observed local failures with generic product rules; do not hardcode names, ids, log phrases, or user examples in prod code unless they are an explicit contract.
- Tests may use observed examples, but prod literals need a short contract reason.
- Compatibility is opt-in. "Shipped" means reachable from a release Git tag; main/GitHub/PR/unreleased code is not shipped.
- Refactor default: one canonical path. Delete the old path unless user explicitly wants compat or the shipped public contract is obvious and cited.
- Core runtime consumes only current canonical shapes/config/data. Legacy or retired shapes normalize only in doctor/migration code before runtime; no runtime shims, aliases, or fallback readers.
- State/storage migrations are database-first. Runtime reads/writes the canonical store only. Old file stores, sidecars, aliases, and fallback readers belong in `openclaw doctor --fix` migration code only, never steady-state runtime.
- Storage default: SQLite only. Do not add JSON/JSONL/TXT/sidecar files for OpenClaw-owned runtime state, caches, queues, registries, indexes, cursors, checkpoints, or plugin scratch data.
- SQLite runtime access uses Kysely helpers, not raw SQL statement strings, except schema DDL, migrations, low-level DB bootstrap, or narrowly justified SQLite primitives.
- Use the shared state DB (`state/openclaw.sqlite`) for global runtime state and plugin KV data. Use the per-agent DB (`agents/<agentId>/agent/openclaw-agent.sqlite`) for agent-scoped state/cache. Use a dedicated SQLite DB only when schema, volume, or lifecycle clearly does not fit those stores.
- Legacy state/cache files are migration debt. When touching code that reads/writes them, prefer moving the data into SQLite or calling out the refactor follow-up; do not add parallel file paths.
- File storage must be a named product artifact: import/export, user attachment, log, backup, or external tool contract. If it is app state or cache, it belongs in SQLite.
- Before adding any path under state dirs, choose one: shared state DB, plugin KV, agent DB, or dedicated SQLite schema. If none fits, design the SQLite owner/schema first.
- Cache/transient state gets no compat migration unless a shipped user contract is cited. Prefer delete/drop/rebuild over import. If old state can be lost without user-visible data loss, remove the old path entirely.
- Persistent user state gets one migration owner. Doctor migrates, verifies, and then runtime assumes the new shape. No dual-write, read-through fallback, lazy import, or "if SQLite fails use JSON" branches.
- Fallback is a product decision, not an implementation convenience. Before adding one, name the shipped contract, failure mode, removal plan, and why doctor cannot solve it. Otherwise delete it.
- Keep old behavior only for an explicit public API/config/plugin SDK/data contract, tagged upgrade path, security/migration boundary, dependency contract, or observed prod state.
- If unsure, ask before preserving compat. Do not keep aliases, shims, fallback stacks, stale names, or obsolete tests just in case.
- Tests alone do not make internals contracts. If compat stays, name the contract and migration/removal plan in code, test, or PR.
@@ -71,12 +91,16 @@ Skills own workflows; root owns hard policy and routing.
- Plugin SDK exception: shipped external API gets new API first plus named compat/deprecation, small tests/docs if useful, removal plan.
- Migrate internal/bundled callers to modern API in the same change. Do not let internal compat become permanent architecture.
- Channels are implementation under `src/channels/**`; plugin authors get SDK seams. Providers own auth/catalog/runtime hooks; core owns generic loop.
- Message/channel plugins stay transport-only. They render portable presentation/actions, enforce transport limits, and map native callback envelopes. They do not own product command trees, plugin/provider policy, or feature-specific menus.
- Portable command UI must use typed presentation actions, not raw string inference. Do not make channels guess that `value` starting with `/` means a native command; core/owner plugins declare command actions, channels map them when supported.
- Raw callback data is transport/private. Approval, command, URL, web-app, and select actions must stay distinguishable before channel encoding so transport adapters do not special-case product strings.
- Agent run terminal state: normalize/merge via `src/agents/agent-run-terminal-outcome.ts`; do not rederive timeout/cancel precedence in projections.
- Hot paths should carry prepared facts forward: provider id, model ref, channel id, target, capability family, attachment class. Do not rediscover with broad plugin/provider/channel/capability loaders.
- Do not fix repeated request-time discovery with scattered caches. Move the canonical fact earlier; reuse prepared runtime objects; delete duplicate lookup branches.
- Gateway/plugin metadata is process-stable: installs, manifests, catalogs, generated paths, bundled metadata. Changes require restart or explicit owner reload/install/doctor flow.
- Runtime hot paths: no freshness polling (`stat`/`realpath`/JSON reread/hash). Reuse current snapshots, install records, discovery, lookup tables, root scopes, resolved paths.
- Process-local metadata caches ok when lifecycle-owned and bounded/single-slot. Freshness exceptions need named owner + tests.
- Inline comments: preserve reviewer context at the code site. Use for cross-path/state invariants, platform/dependency caps, deterministic ordering, compact encoded state, lifecycle ordering, ownership boundaries, session/id adoption, queue-depth symmetry, fallbacks, or intentional caller differences.
- Inline comments: preserve reviewer context at the code site. Required for non-obvious cross-path/state invariants, lifecycle ordering, ownership boundaries, queue/dedupe symmetry, TTL/cache expiry, cleanup/release coupling, session/id adoption, fallback behavior, platform/dependency caps, deterministic ordering, compact encoded state, or intentional caller differences.
- Comment shape: 1-3 short lines; state why the branch/helper exists, what contract it protects, and the bad outcome if removed. Cite nearby constants/helpers when useful. No syntax narration, PR/user-specific lore, or obvious mechanics.
- Tests in a normal source checkout: `pnpm test <path-or-filter> [vitest args...]`, `pnpm test:changed`, `pnpm test:serial`, `pnpm test:coverage`; never raw `vitest`.
- If raw Vitest is unavoidable, use `vitest run ...`; bare `vitest ...` starts local watch mode and will not exit on its own.
- Tests in a Codex worktree or linked/sparse checkout: avoid direct local `pnpm test*`; use `node scripts/run-vitest.mjs <path-or-filter>` for tiny explicit-file proof, or Crabbox/Testbox for anything broader.
- Checks in a normal source checkout: `pnpm check:changed`; lanes: `pnpm changed:lanes --json`; staged: `pnpm check:changed --staged`; full: `pnpm check`.
- Checks in a Codex worktree or linked/sparse checkout: avoid direct local `pnpm check*`; use `node scripts/crabbox-wrapper.mjs run ... --shell -- "pnpm check:changed"` so pnpm runs inside Testbox, not locally.
- Checks in a normal source checkout: `pnpm check:changed` delegates to Crabbox/Testbox; lanes: `pnpm changed:lanes --json`; staged: `pnpm check:changed --staged`; full: `pnpm check`.
- Checks in a Codex worktree or linked/sparse checkout: avoid direct local `pnpm check*`; use `node scripts/crabbox-wrapper.mjs run ... -- env OPENCLAW_CHECK_CHANGED_REMOTE_CHILD=1 OPENCLAW_CHANGED_LANES_RAW_SYNC=1 corepack pnpm check:changed` so pnpm runs inside Testbox, not locally.
- Extension tests: `pnpm test:extensions`, `pnpm test extensions`, `pnpm test extensions/<id>`.
- Typecheck: `tsgo` lanes only (`pnpm tsgo*`, `pnpm check:test-types`); never add `tsc --noEmit`, `typecheck`, `check:types`.
- Formatting: `oxfmt`, not Prettier. Use repo wrappers (`pnpm format:*`, `pnpm lint:*`, `scripts/run-oxlint.mjs`).
@@ -103,12 +128,13 @@ Skills own workflows; root owns hard policy and routing.
- Use `$openclaw-testing` for test/CI choice and `$crabbox` for remote/full/E2E proof.
- Crabbox request means real scenario proof: install/update/call/repro user path; not just copy tests and run them remotely.
- Visual proof: use Crabbox, set up like a user, then screenshot-verify. No harness/bypass/shortcut unless explicitly asked.
- Small/narrow tests, lints, format checks, and type probes are fine locally only in a healthy normal checkout.
- In Codex worktrees, direct local `pnpm test*`, `pnpm check*`, `pnpm crabbox:run`, and `scripts/committer` can trigger pnpm dependency reconciliation or install prompts. Prefer `node` wrappers locally and Crabbox/Testbox for pnpm-gated proof.
- Full suites, broad changed gates, Docker/package/E2E/live/cross-OS proof, or anything that bogs down the Mac: Crabbox/Testbox.
- One/few files local. If a local command fans out, stop and move broad proof to Crabbox/Testbox.
- Before handoff/push: prove touched surface. Before landing to `main`: issue proof plus appropriate full/broad proof unless scope is clearly narrow.
- Pre-land/pre-commit code changes: use`$autoreview` until no accepted/actionable findings remain, unless equivalent manual review already done, trivial/docs-only, or user opts out.
- Pre-land/pre-commit code changes: mandatory fresh`$autoreview` until no accepted/actionable findings remain. Do not land code on CI, ClawSweeper, prior review comments, or your own manual review alone unless user explicitly opts out or scope is truly trivial/docs-only. If findings want refactor, refactor; no ugly fixes.
- If proof is blocked, say exactly what is missing and why.
- Do not land related failing format/lint/type/build/tests. If unrelated on latest `origin/main`, say so with scoped proof.
- Docs/changelog-only and CI/workflow metadata-only: `git diff --check` plus relevant docs/workflow sanity; escalate only if scripts/config/generated/package/runtime behavior changed.
@@ -117,27 +143,35 @@ Skills own workflows; root owns hard policy and routing.
## GitHub / PRs
- Use `$openclaw-pr-maintainer` immediately for maintainer-side OpenClaw issue/PR review, triage, duplicates, labels, comments, close, land, or evidence. Contributor PR creation/refresh follows the requested contributor workflow; linked refs alone do not require maintainer archive tooling.
-Pasted GitHub issue/PR: first `git status -sb`; if dirty, yell; then `git push` + `git pull --ff-only`.
-Issue/PR start: `git status -sb`; if clean, `git pull --ff-only`; if dirty, yell before pull/rebase.
- PR refs: `gh pr view/diff` or `gh api`, not web search. Prefer `gitcrawl` for maintainer discovery; missing/stale `gitcrawl` falls through to live `gh`, not contributor setup. Verify live with `gh` before mutation.
- Bare issue/PR URL/number means review/report in chat. Suggest comment/close/merge when appropriate; mutate only when asked.
- No unsolicited PR comments/reviews/labels/retitles/rebases/fixups/landing. Exception: close/duplicate action that needs a reason comment after explicit close/sweep/landing request.
- Bare issue/PR URL/number: inspect live and take the efficient maintainer path; switch branches/refs when useful.
- No unsolicited PR labels/retitles/rebases/fixups/landing. Comments/reviews ok only for reviewable findings, pre-merge proof, or close/duplicate reason after explicit close/sweep/landing request.
- Maintainer decision closes the cluster: if deciding reported behavior/proposed fix is not planned, comment+close all directly associated open issues/PRs unless explicitly told to keep one open. Associated means linked PRs/issues, duplicates, companion workaround PRs, and the canonical issue for the rejected behavior.
- Do not leave associated issues open for hypothetical future repros. Close with rationale; ask for a new issue or reopen only if concrete new evidence appears. Close comment states: decision, why, supported alternative, and what evidence would change the decision.
- Issue/PR work: search strong related issues/PRs before final; close proven dupes/fixed siblings. If none close, suggest one next related follow-up.
- PR superseded by `main`: if code proof shows `main` already has same-or-better behavior, comment canonical commit/PR + focused proof, then close. Bar high: inspect PR diff, current code/tests, linked issue, caller/sibling path. If unsure, leave open.
- Issue/PR numbers need a short summary every time; assume the reader has not opened or read them.
- Before presenting a batch of issues/PRs, use smart subagents to verify live state and current `main`; omit closed/fixed items, and comment+close items already fixed on `main` when maintainer action is authorized.
- PR review answer: bug/behavior, URL(s), affected surface, provenance for regressions when traceable, best-fix judgment, evidence from code/tests/CI/current or shipped behavior.
- PR reviewable findings: post them on the PR, not chat-only, so author sees actionable feedback.
- Issue/PR final answer: last line is the full GitHub URL.
- PR verification: before merge, post exact local commands, CI/Testbox run IDs, before/after proof when used, and known proof gaps.
- PR verification: before merge, post land-ready work done, exact local commands, CI/Testbox run IDs, before/after proof when used, and known proof gaps.
- Issue fixed on `main` with proof: comment proof + commit/PR, then close.
- After landing or requested close/sweep: search duplicates; comment proof + canonical commit/PR/release before closing.
- After landing/ship final: include 2-5 sentence recap of what landed: behavior change, key files/surface, proof run, issue/PR state. Do not answer with only status/links.
-`ship` that fixes an issue: after push, comment proof + commit link, then close the issue.
- Public GH comments: show draft in chat first unless user explicitly asked to post/comment/reply/close/merge/land. After work starts and changes/proof exist, post the review/proof/commit comment.
- Representing user: if user already has a comment/thread for the point, update/reply there when possible; avoid duplicate PR/issue comments.
- No surprise GH writes: chat must mention every posted/updated public comment with URL.
- GH comments with backticks, `$`, or shell snippets: use heredoc/body file, not inline double-quoted `--body`.
- PR create: real body required. Include Summary + Verification; mention refs, behavior, and proof.
- PR create/refresh: keep PR branches takeover-ready. Use a branch maintainers can push to, or for fork PRs ensure `maintainer_can_modify` / GitHub's `Allow edits by maintainers` is enabled unless explicitly told otherwise or GitHub's Actions/secrets warning makes that unsafe.
- GitHub issue/PR create: read `$agent-transcript`; ask about sanitized transcript logs when available.
-Real behavior proof section is parsed. Use exact `field: value` labels: `Behavior addressed`, `Real environment tested`, `Exact steps or command run after this patch`, `Evidence after fix`, `Observed result after fix`, `What was not tested`.
-Contributor PRs: parsed `Real behavior proof` uses exact `field: value` labels: `Behavior addressed`, `Real environment tested`, `Exact steps or command run after this patch`, `Evidence after fix`, `Observed result after fix`, `What was not tested`.
- PR artifacts/screenshots: attach to PR/comment/external artifact store. Never push screenshots, videos, proof images, or proof assets to OpenClaw or any product repo branch, including temp artifact branches. Use Crabbox artifact publishing plus the manifest URL. Do not commit `.github/pr-assets`.
- CI polling: exact SHA, relevant checks only, minimal fields. Skip routine noise (`Auto response`, `Labeler`, docs agents, performance/stale). Logs only after failure/completion or concrete need.
-Maintainers: may skip/ignore`Real behavior proof` when local tests or Crabbox verified behavior; record proof in PR verification.
-OpenClaw write-access maintainers may skip `Real behavior proof` when local tests or Crabbox verified behavior; record proof in PR verification.
-`/landpr`: use `~/.codex/prompts/landpr.md`; do not idle on `auto-response` or `check-docs`.
## Code
@@ -153,12 +187,17 @@ Skills own workflows; root owns hard policy and routing.
- Use named intermediates only for domain meaning or readability; avoid temp-variable soup.
- Code size matters. Prefer small clear code; maintainability includes not growing LOC without payoff.
- Refactors should delete about as much local complexity as they add. If LOC grows, the new ownership/API needs to clearly pay for it.
- Refactors should reduce non-test LOC unless they remove a larger architectural cost. Treat positive prod LOC as a smell. Before closeout, run `git diff --numstat`; if non-test LOC grew, trim or explicitly justify why fewer paths now exist.
- Prefer deleting branches, modes, adapters, and tests over preserving them. A refactor that adds a second path has probably failed unless the old path is a cited shipped contract.
- New helpers/files must pay rent immediately: fewer call paths, fewer concepts, or less repeated logic. No helpers for one-off compat, naming translation, or speculative resilience.
- Before adding helpers/files, check whether existing code can absorb the behavior with less new surface.
- Keep APIs narrow: export only current caller needs; keep types/helpers local by default.
- Return the smallest useful shape. Avoid broad result objects, flags, metadata unless callers use them.
- Avoid adapter layers that only rename fields. Move real responsibility or leave code local.
- Inline simple one-use objects/spreads when clearer. Extract only when it removes duplication or hard logic.
- Tests prove behavior/regressions, not every internal branch.
- Tests are welcome, but review them before landing for duplication and value. Delete useless tests, such as assertions for behavior or paths just removed.
- Tests protect canonical behavior and migration boundaries, not obsolete internals. Delete tests for removed fallback paths instead of updating them.
- For non-trivial refactors, check `git diff --numstat` before closeout. If LOC grew, trim or explain why.
- Prefer existing narrow helpers over repeated casts/guards. Add local helpers when 2+ nearby call sites share real boundary logic.
- Prefer ctor parameter properties for injected deps/config. Do not ban them for erasable-syntax purity.
@@ -188,7 +227,7 @@ Skills own workflows; root owns hard policy and routing.
- Use `$technical-documentation` for docs writing/review. Docs change with behavior/API.
- Codex harness upgrade (`extensions/codex/package.json``@openai/codex`): refresh `docs/plugins/codex-harness.md` model snapshot from the new harness `model/list`.
- Docs final answers: include relevant full `https://docs.openclaw.ai/...` URL(s). If issue/PR work too, GitHub URL last.
-`CHANGELOG.md`: release-owned. Do not edit for normal PRs, direct `main` fixes, or `ship it`; only explicit release/changelog generation may rewrite it. Do not ask contributors/agents for changelog edits.
-`CHANGELOG.md`: release-only. Do not edit for normal PRs, direct `main` fixes, or `ship it`; release generation owns it. Do not ask contributors/agents for changelog edits.
- User-facing `fix`/`feat`/`perf`: put release-note context in PR body, squash message, or direct commit: behavior, surface, issue/PR refs, credited human author/reporter.
- Release generation: derive `CHANGELOG.md` from merged PRs + all direct `main` commits. Entries: active `### Changes`/`### Fixes`, single-line, thank credited humans; never thank bots/forbidden handles: `@openclaw`, `@clawsweeper`, `@codex`, `@steipete`.
@@ -196,18 +235,19 @@ Skills own workflows; root owns hard policy and routing.
- Commit via `scripts/committer "<msg>" <file...>`; stage intended files only.
- Commits: conventional-ish, concise, grouped.
- No manual stash/autostash unless explicit. No branch/worktree changes unless requested.
- No manual stash/autostash unless explicit. Branch switches ok when useful; no new worktrees unless requested.
-`main`: no merge commits; rebase on latest `origin/main` before push. After one green run plus clean rebase sanity, do not chase moving `main` with repeated full gates.
- User says `commit`: your changes only. `commit all`: all changes in grouped chunks. `push`: may `git pull --rebase` first.
- Crabbox/WebVNC human demos: keep remote desktop visible/windowed; no fullscreen remote browser unless video/capture-style output.
- Before sharing WebVNC links, use Crabbox screenshot first; verify real app/path works and target UI is not broken.
- ClawSweeper ops: `$clawsweeper`. Deployed hook sessions may post one concise `#clawsweeper` note only when surprising/actionable/risky; if using message tool, reply exactly `NO_REPLY`.
- Generated-media completions wake the requester agent first. Requester visible-reply config decides final text vs message tool; direct media send is fallback/recovery only.
-`message_tool_only`: normal agent final visible reply = current-source `message(action=send)` only. No `NO_REPLY` prompt/contract; no message call = no source reply. Plugin-owned bound-thread reply = plugin return value; no message tool needed. Never auto-publish private final.
- Memory wiki prompt digest stays tiny; prefer `wiki_search` / `wiki_get`; verify contact data before use; source-class provenance for generated people facts.
- Rebrand/migration/config warnings: run `openclaw doctor`.
- Alpha release candidate with refreshed release metadata, shrinkwrap alignment, and release-gate stabilization fixes.
## 2026.5.31
### Highlights
- Agents and CLI-backed runtimes recover more cleanly from interrupted tool calls, stale session bindings, compaction handoffs, and media delivery retries. (#88129, #88136, #88141, #88162, #88182)
- Channels and mobile delivery are steadier across Telegram, WhatsApp, iMessage, Slack, Discord, Microsoft Teams, Google Chat, Google Meet, and iOS realtime Talk. (#88096, #88105, #88183, #88231)
- Provider and plugin requests now bound more timers, retries, OAuth/device-code lifetimes, media downloads, local service probes, and generated-content polling paths before they can hang a run.
- Skills, session metadata, gateway runtime state, plugin metadata, and store writes do less repeated work on hot paths while keeping config and dispatch behavior stable.
- Skills and plugin loading now handle stale disabled snapshots and loader failures more clearly, so channel turns avoid disabled SecretRefs and operators get better recovery guidance. (#79072, #79173) Thanks @zeus1959.
- Skill Workshop now has a fuller Control UI flow with proposal lists, today actions, revision handoff, searchable file previews, review states, locale coverage, and reusable session routing.
- Chat and Control UI startup paths keep sends alive through history loading, stream deltas incrementally, skip markdown work while streaming, and expose calmer composer controls. (#88772, #88825)
- Provider coverage and model metadata now include MiniMax M3, account OAuth endpoints, Google/Vertex catalog fixes, OpenRouter SQLite model caching, Copilot Claude 1M capabilities, Foundry reasoning alignment, and OpenAI response replay guards. (#88480, #88512, #88851, #88860)
- iMessage monitor state, inbound queues, and plugin install ledgers moved toward SQLite-backed state so restarts and local monitors recover with less duplicate filesystem scanning. (#88794, #88797)
- Release, CI, Docker, E2E, and diagnostics lanes now cap more logs, response bodies, readiness probes, artifact checks, and status polling so failures report bounded proof instead of stalling.
### Changes
- Docs: add a dedicated Skill Workshop guide covering governed skill creation, reviewable proposals, CLI, Gateway, agent tool behavior, approval policy, support files, and recovery. Thanks @shakkernerd.
- Skills: let the `skill_workshop` agent tool apply, reject, and quarantine explicit proposals through the guarded review flow. Thanks @shakkernerd.
- Skills: let proposals carry approved support files under standard skill folders, with scanner, hash, and rollback safeguards. Thanks @shakkernerd.
- Skills: let pending proposals be revised in place with versioned, dated proposal frontmatter before approval. Thanks @shakkernerd.
- Skills: add Skill Workshop with pending proposals, CLI/Gateway review actions, rollback metadata, and the `skill_workshop` agent tool. Thanks @shakkernerd.
- Skill Workshop: add the Control UI navigation, styled dashboard, proposal today view, revision dialog, file preview modal, searchable preview files, reusable session handoff, and localized strings.
- Plugins: externalize Tokenjuice as the official `@openclaw/tokenjuice` plugin with npm and ClawHub publish metadata.
- Plugins: externalize the GitHub Copilot agent runtime as the official `@openclaw/copilot` plugin with npm and ClawHub publish metadata.
- iOS: add hosted push relay defaults, realtime Talk playback, and a guarded WebSocket ping path for more reliable mobile sessions. (#88096, #88105, #88231)
- iOS: support native iPad display layouts.
- Workboard: add orchestration primitives and agent coordination tools for multi-agent planning and run tracking. (#87469)
- Workboard: wire task-backed board runs and show task comments in the edit modal.
- Code mode: add internal namespaces for scoped agent/global sessions and exact namespace tool dispatch. (#88043)
- Code mode: add MCP API files and docs for code-mode integrations.
- Control UI: add a Dreaming-tab agent selector and propagate the selected agent through Dreaming status, diary, and diary actions. (#78748) Thanks @stevenepalmer.
- Control UI: add calmer chat composer controls for active chat entry. (#88772)
- Plugins: add a SecretRef provider integration manifest contract and extract shared LLM core packages for provider/plugin reuse. (#82326, #88117)
- Plugins: persist the plugin install index in SQLite so installed package lookup survives reloads with less filesystem scanning. (#88794)
- Providers: add MiniMax M3 model support. (#88860)
- Doctor: add disk space health checks and stabilize post-upgrade JSON probes.
- Channels: store inbound queues in SQLite and migrate iMessage monitor state to SQLite-backed tracking. (#88797)
- Skills: add the core skills index and centralize skills runtime loading, status, filtering, and prompt formatting.
### Fixes
- Agents/TUI: keep local custom provider runs from loading plugin runtime and auth alias metadata when plugins are disabled.
- Agents/media: keep async image, music, and video generation starts from ending the Codex turn, so mixed requests can continue with summaries or other work while media renders in the background.
- Agents/Codex: keep public OpenAI API-key profiles from being treated as native Codex app-server auth while preserving persisted Codex OAuth sessions.
- Control UI: keep collapsed tool cards labeled with the tool name and action instead of generic output text. Thanks @shakkernerd.
- Agents/Codex: surface Skill Workshop guidance in Codex app-server prompts when `skill_workshop` is available. Thanks @shakkernerd.
- Agents/auth: write auth profiles atomically, add force re-login recovery, preserve workspaces during state-only uninstall, and compact before oversized turns so recovery paths avoid partial state.
- Skills: skip disabled skill env overrides from stale persisted snapshots so disabled skill `apiKey` SecretRefs cannot abort embedded or channel turns. (#79072, #79173) Thanks @zeus1959.
- CLI: avoid live catalog validation during `openclaw agents add`, so adding a secondary agent no longer depends on provider catalog availability. (#76284, #88314) Thanks @zhangguiping-xydt.
- CLI: keep `plugins list --json` on the snapshot-only path so plugin sweeps avoid loading the full runtime status graph.
- CLI/desktop: bridge WSL clipboard operations through the shell and recognize manual-update launchd jobs. (#88764)
- Plugins: make PixVerse external-plugin ClawHub metadata explicit and keep it out of bundled dist builds.
- Plugins: clarify plugin loader failure guidance so missing or incompatible plugin packages point operators at the right repair path.
- Plugins: preserve npm plugin roots after blocked installs, isolate cached tool runtime siblings, and isolate web-provider factory failures so one bad plugin does not poison sibling runtime paths. (#77237, #88807)
- Cron: keep update delivery validation scoped, harden restart state, and retire MCP runtimes on isolated cron cleanup.
- Providers: bound generated media downloads from OpenAI, Runway, xAI, MiniMax, BytePlus, DashScope-compatible, FAL, OpenRouter, Google, Vydra, and Comfy providers.
- Providers: resolve Google defaults to `google-generative-ai`, register Vertex static catalog rows, align Foundry reasoning metadata, skip DeepSeek V4 thinking params on Foundry fallback, use MiniMax account OAuth endpoints, preserve Copilot Claude 1M capabilities, suppress disabled Ollama reasoning output, keep OpenAI stop-finished tool calls, and avoid replay ids when the Responses store is disabled. (#88480, #88512)
- Providers: cap GitHub Copilot OAuth request timeouts before creating abort signals.
- Cron: retry recurring jobs after transient model rate limits before waiting for the next scheduled slot.
- Agents/Codex: keep live session locks during cleanup, recover interrupted CLI tool transcripts, preserve Codex auth and compaction session identity, clear orphan tool state, cap app-server idle timers, and keep media completion delivery retryable. (#88129, #88136, #88141, #88162, #88182)
- Chat/UI: show Gateway chat failures as visible assistant messages in the Control UI instead of only setting an invisible error state.
- Channels: cap Telegram, Discord, WhatsApp, Signal, Feishu, Google Chat, Microsoft Teams, QQBot, Nostr, Zalo, Zalouser, and Nextcloud-style request/retry timers; preserve SMS approval reply routes; and retry WhatsApp QR login 408 timeouts. (#88183)
- Security/config parsing: reject unsafe OAuth/token lifetimes, retry-after delays, inbound timestamps, response body sizes, command timeout config, sandbox observer token TTLs, and gateway WebSocket calls after close.
- Providers/media: cap local service, model, usage, queue, generated media, TTS, music, workflow polling, and provider OAuth request timers across hosted and local providers.
- Release/CI/E2E: bound release candidate reads, beta smoke REST calls, changelog restore, kitchen-sink and bundled plugin readiness probes, secret-provider probes, Vitest routing, and mainline test flakes. (#88127, #88137, #88155, #88160)
- Release/CI/E2E: keep Kitchen Sink live plugin MCP probes resolving source-checkout workspace packages and align the live gauntlet with current Kitchen Sink diagnostics.
- Release/CI/E2E: run the secret-provider integration proof through the repo pnpm runner so native macOS and Windows validation use the hydrated package-manager shim.
- Release/CI/E2E: run the Telegram desktop proof gateway through the repo pnpm runner so native macOS proof uses the hydrated package-manager shim.
- Docs/CI: run Mintlify anchor checks through the repo pnpm runner so docs link validation works when pnpm is only available through the hydrated package-manager shim.
- Agents: keep configured fallback model metadata typed so provider params, context-token caps, and media input limits do not break changed-gate typechecks.
- Agents: accept hidden `sessions_send` body aliases before validation while keeping the model-facing `message` schema canonical. (#88229) Thanks @zhangguiping-xydt.
- Chat/UI: preserve startup chat sends during history loading, unblock the initial Control UI chat send, stream chat deltas incrementally, skip markdown parsing while streaming, honor Chromium executable overrides, and detect system Chromium for E2E.
- Channels: preserve long Feishu streaming replies, send visible fallbacks when accepted Feishu turns produce no final reply, tolerate iMessage self-chat timestamp skew, decode Nostr `npub` allowlists correctly, and suppress raw provider errors during channel delivery. (#87896)
- Config/status/doctor: skip unresolved shell references in state-dir dotenv files, resolve gateway auth secrets during deep status audits, respect explicit PI runtime policy, report runtime tool-schema errors, and keep post-upgrade JSON stable. (#88288)
- Gateway/session state: list commands from the Gateway plugin registry, harden MCP loopback tool schemas, hide phantom agent-store rows from `sessions.list`, make task persistence failures explicit, and carry session UUIDs on interactive dispatch events.
- OpenAI/TTS: handle speed directives for OpenAI TTS voices. (#74089)
- CI/Crabbox: keep default runner capacity on the Azure credit-backed on-demand D4 lane with the Azure SSH port and a Git-independent full check job, so broad validation avoids low-priority spot quota stalls, hydrate port mismatches, non-Git hydrated workspaces, and stale AWS region hints.
- CI/Crabbox: route Crabbox wrapper and Testbox workflow edits to their regression tests so changed-test gates do not silently run zero specs.
- CI/workflows: route workflow sanity helper edits to their guard tests and cover composite-action input interpolation checks.
- CI/tooling: route CI scope, dependency, changelog, and docs helper edits to their owner tests instead of silently skipping changed-test coverage.
- CI/tooling: route package, release, and install helper edits to their owner tests so changed-test gates cover publish and installer script changes.
- CI/tooling: route shared script library edits through their owner tests so lock, process, safety, and scan helpers do not skip changed-test coverage.
- CI/tooling: skip expensive import-graph scans once a changed diff already requires broad fallback, keeping local changed-test planning fast while still collecting explicit owner tests.
- CI/tooling: route script edits through conventional owner tests when matching `test/scripts` or `src/scripts` coverage already exists.
- CI/tooling: honor option terminators in the memory FD repro script so follow-on arguments are not reparsed.
- Release/CI/E2E: assert plugin lifecycle runtime inspect output instead of only capturing it.
- Release/CI/E2E: make gateway-network prove the advertised health RPC and retry early WebSocket closes without burning full open timeouts.
- Release/CI/E2E: honor option terminators across release, Parallels smoke, plugin gauntlet, and extension-memory scripts.
- Release/CI/E2E: fail plugin gateway gauntlet QA chunks when the requested suite summary is missing or invalid.
- Performance: prebuild QA runtime probes with generated plugin assets but without CLI startup metadata.
- Performance: skip declaration bundling for runtime-only CLI startup and gateway watch build profiles.
- Agent and Codex runtime recovery is steadier: subagents keep cwd/workspace separation, hook context stays prompt-local, session locks release on timeout abort, stale restart continuations are avoided, and Codex app-server/helper failures no longer tear down shared runtime state. (#87218, #86875, #87409, #87399, #87375)
- Channel delivery and session identity got safer across outbound plugin hooks, Matrix room ids, iMessage reactions/approvals, Slack final replies, Discord recovered tool warnings, and Microsoft Teams service URL trust checks. (#73706, #75670, #87366, #87451, #87334)
- CLI, auth, doctor, and provider paths fail faster and recover more clearly: malformed numeric/version options are rejected, OAuth and local service startup requests are bounded, legacy `api_key` auth profiles migrate to canonical form, and restart guidance is actionable. (#87398, #86281, #87361)
- Plugin and Gateway hot paths do less repeated work while preserving cache correctness for install records, config JSON parsing, tool search catalogs, session stores, manifest model rows, auto-enabled plugin config, browser tokens, and viewer assets. (#86699)
- Agent and Codex runtime recovery is steadier: subagents keep cwd/workspace separation, hook context stays prompt-local, session locks release on timeout abort while live OpenClaw locks survive cleanup, stale restart continuations are avoided, and Codex app-server/helper failures no longer tear down shared runtime state. (#87218, #86875, #87409, #87399, #87375, #88129)
- Channel delivery and session identity got safer across outbound plugin hooks, Matrix room ids, iMessage reactions/approvals, Slack final replies, Discord recovered tool warnings, runtime-config message actions, WhatsApp profile auth roots, Telegram polling, and Microsoft Teams service URL trust checks. (#73706, #75670, #87366, #87451, #87334, #84535, #82492, #83304, #87160)
- Mobile and chat surfaces got a broader refresh: the iOS Pro UI, hosted push relay default, realtime Talk tab playback, Gateway chat transport, onboarding, Talk permissions, WebChat reconnect delivery, and session picker behavior now preserve more state across reconnects and empty searches. (#87367, #87531, #87682, #88096, #88105) Thanks @ngutman and @BunsDev.
- Browser, channel, and automation inputs are stricter: Browser tool timeouts, viewport/tab indices, Gateway ports, cron retry handling, Discord component ids, schema array refs, Telegram callback pages, and channel progress callbacks now reject malformed values earlier and preserve the intended delivery context. (#82887)
- Provider, media, and document coverage expands with Claude Opus 4.8, Fal Krea image schemas, NVIDIA featured models, MiniMax streaming music responses, encrypted PDF extraction, voice model catalogs, GitHub Copilot agent runtime support, and a Codex Supervisor plugin path for delegated Codex workflows. (#87845, #87890, #80775, #84764, #87751, #87794)
- CLI, auth, doctor, and provider paths fail faster and recover more clearly: malformed numeric/version options are rejected, workspace dotenv provider credentials are ignored, heartbeat defaults, OAuth/token lifetimes, and local service startup requests are bounded, agent auth health labels are clearer, legacy `api_key` auth profiles migrate to canonical form, and restart guidance is actionable. (#87398, #86281, #87361, #88133, #83655, #87559, #88088, #85924) Thanks @vincentkoc and @giodl73-repo.
- Plugin and Gateway hot paths do less repeated work while preserving cache correctness for install records, config JSON parsing, tool search catalogs, session stores, manifest model rows, auto-enabled plugin config, browser tokens, viewer assets, and release-split external plugin packages. (#86699)
- Release, QA, and E2E validation now bound more log, artifact, harness, and cross-OS waits so failing lanes produce proof instead of hanging or false-greening.
- Status: show active subagent details in status output.
- Diffs: split the default language pack and expand default Diffs language coverage while keeping the host floor aligned. (#87370, #87372) Thanks @RomneyDa.
- ClawHub: add plugin display names plus skill verification and trust surfaces. (#87354, #86699) Thanks @thewilloftheshadow and @Patrick-Erichsen.
- iOS: refresh the dev app with Pro Command, Chat, Agents, Settings, hosted push relay defaults, and realtime Talk playback wired to gateway sessions, diagnostics, chat, and realtime Talk. (#87367, #88096, #88105) Thanks @Solvely-Colin and @ngutman.
- PDF/tools: use ClawPDF for PDF extraction, support encrypted PDF extraction, and surface MCP structured content in agent tool results. (#87670, #87751)
- Providers: add Claude Opus 4.8 support, Fal Krea image model schemas, NVIDIA featured model catalogs, MiniMax streaming music responses, and provider-backed voice model catalogs. (#87845, #87890, #80775, #84764, #87794) Thanks @eleqtrizit and @vincentkoc.
- Codex/GitHub: add the GitHub Copilot agent runtime and the Codex Supervisor plugin package.
- Plugins: externalize GitHub Copilot and Tokenjuice as official install-on-demand plugins with npm and ClawHub publish metadata.
- Workboard: add agent coordination tools for tracking and handing off active agent work.
- Discord: show commentary in progress drafts so live Discord runs expose useful in-progress context. (#85200)
- Plugin SDK: add a reply payload sending hook for plugins that need to deliver channel-owned replies and flatten package types for SDK declarations. (#82823, #87165) Thanks @piersonr and @RomneyDa.
- Agents: fall back to local config pruning when the optional `agents delete` Gateway probe cannot authenticate, so offline installs can still delete agents without removing shared workspaces.
- Agents/Codex: keep spawned agent cwd/workspace state separated, keep hook context prompt-local, release session locks on timeout abort, avoid session event queue self-wait, preserve shared app-server state across startup or helper failures, keep native hook relay alive across restarts, route workspace memory through tools, resolve Codex runtime models first, report quarantined dynamic tools, format `skills` command output, and bound compaction/steering retries. (#87218, #86875, #86123, #87399, #87375, #87383, #87400) Thanks @mbelinky, @Alix-007, @luoyanglang, @yetval, and @sjf.
- Channels: thread canonical session keys into outbound hooks, preserve Matrix room-id case, keep fallback tool warnings mention-inert, retain delivered Slack final replies during late cleanup, continue iMessage polling after denied reactions, suppress duplicate native exec approvals, preserve Telegram SecretRef prompt config, suppress Discord recovered tool warnings, and block untrusted Teams service URLs. (#73706, #75670, #87366, #87451, #87334) Thanks @zeroaltitude, @lukeboyett, @xiaotian, and @eleqtrizit.
- CLI/auth/doctor/providers: reject malformed numeric/timeout/subcommand-version inputs, wait for respawn child shutdown, bound Codex and GitHub Copilot OAuth/token requests, warm provider auth off the main thread, honor Codex response timeouts, bound local service startup, resolve GPT-5.5 without cached catalog, migrate legacy memory auto-provider config, rewrite non-canonical `api_key` auth profiles, and make doctor restart follow-ups actionable. (#87398, #86281, #87361) Thanks @Patrick-Erichsen, @samzong, @giodl73-repo, and @alkor2000.
- Gateway/security/session state: expire browser tokens after auth rotation, scope assistant idempotency dedupe, drain probe client closes, avoid stale restart continuation reuse, preserve retry-after fallbacks, bound webchat image and artifact transcript scans, include seconds in inbound metadata timestamps, and evict current plugin-state namespaces at row caps.
- Agents/Codex: keep spawned agent cwd/workspace state separated, forward ACP spawn attachments, keep hook context prompt-local, release session locks on timeout abort and runtime teardown without deleting live OpenClaw-owned locks during cleanup, avoid session event queue self-wait, clean up exec abort listeners, stream assistant deltas incrementally, recover raw missing-thread compaction failures, preserve rotated compaction session identity, keep compaction-timeout snapshots continuable, preserve shared app-server state across startup or helper failures, keep native hook relay alive across restarts and prune stale bridge files, close native hook relay replacement races, keep Claude live tool progress visible for watchdog recovery, suppress abandoned requester completion handoff, route workspace memory through tools, resolve Codex runtime models first, report quarantined dynamic tools, format `skills` command output, bind node auto-review to prepared plans, retry Claude CLI transcript probes, and bound compaction/steering retries. (#87218, #86875, #86123, #88129, #87399, #87375, #72574, #87383, #87400, #83022, #87671, #87738, #87747, #87706, #87546, #87541, #81048) Thanks @mbelinky, @Alix-007, @luoyanglang, @yetval, @sjf, @joshavant, @benjamin1492, @c19354837, @fuller-stack-dev, @pfrederiksen, and @dodge1218.
- Codex Supervisor: keep real-home app-server MCP session listing on the loaded state path, bound stored history scans, and close WebSocket probes cleanly.
- Channels: thread canonical session keys into outbound hooks, preserve Matrix room-id case, keep fallback tool warnings mention-inert, retain delivered Slack final replies during late cleanup, continue iMessage polling after denied reactions, suppress duplicate native exec approvals, resolve Gateway message actions against the active runtime config, preserve Telegram SecretRef prompt config and polling keepalives, preserve WhatsApp profile auth roots, QR display, document filenames, and plugin hook config, suppress Discord recovered tool warnings, preserve the Discord voice outbound helper, cap Discord/Signal/Zalo channel request and container timeouts, and block untrusted Teams service URLs while keeping TeamsSDK patterns aligned. (#73706, #75670, #87366, #87451, #87465, #87334, #84535, #76262, #83304, #82492, #87581, #77114, #86426, #85529, #87160) Thanks @zeroaltitude, @lukeboyett, @jarvis-mns1, @xiaotian, @funmerlin, @joshavant, @eleqtrizit, @heyitsaamir, @amittell, @lidge-jun, @liorb-mountapps, @masatohoshino, @bladin, and @giodl73-repo.
- CLI/auth/doctor/providers: reject malformed numeric/timeout/subcommand-version inputs, ignore workspace dotenv provider credentials, wait for respawn child shutdown, bound heartbeat defaults plus Codex, GitHub Copilot, OpenAI, Anthropic, Google, Feishu, LM Studio, MiniMax, Xiaomi TTS, and local-provider OAuth/token/model requests, harden Codex auth probes, label auth health by agent, preserve explicit agentRuntime pins during Codex model migration, warm provider auth off the main thread, honor Codex response timeouts, stop migrating current Claude Haiku 4.5 profiles to Sonnet, bound local service startup, resolve GPT-5.5 without cached catalog, migrate legacy memory auto-provider config, rewrite non-canonical `api_key` auth profiles, and make doctor restart follow-ups actionable. (#87398, #86281, #87361, #88133, #83655, #87559, #87719, #88088, #85924, #84362) Thanks @Patrick-Erichsen, @samzong, @giodl73-repo, @alkor2000, @mmaps, @nxmxbbd, and @vincentkoc.
- Gateway/security/session state: expire browser tokens after auth rotation, scope assistant idempotency dedupe, drain probe client closes, avoid stale restart continuation reuse, preserve retry-after fallbacks and stale rate-limit cooldown probes, bound webchat image and artifact transcript scans, include seconds in inbound metadata timestamps, clear completed session active runs, clear stale chat stream buffers, and evict current plugin-state namespaces at row caps. (#87810, #87833, #75089) Thanks @joshavant and @litang9.
- Config/parsing/network: reject partial numeric parsing, parse provider/Discord retry headers and dates strictly, honor IPv6 and bare IPv6 `no_proxy` entries, preserve empty plugin allowlists, canonicalize secret target array indexes, and reject malformed media content lengths, inspected TCP ports, marketplace content lengths, cron epochs, sandbox stat fields, unsafe duration values, empty config path segments, noncanonical schema array refs, unsafe Telegram callback pages, and invalid Teams attachment-fetch DNS targets. (#87883) Thanks @zhangguiping-xydt.
- Cron/automation: retry recurring jobs after transient model rate limits before waiting for the next scheduled slot, and preflight model fallbacks before skipping scheduled work. (#82887) Thanks @chen-zhang-cs-code.
- Auto-reply/directives: respect provider and relayed channel metadata during directive persistence so channel-originated decisions keep their intended context. (#87683)
- WhatsApp: resolve the auth directory from the active profile so profile-scoped WhatsApp installs do not drift to the wrong credential root. (#82492) Thanks @lidge-jun.
- Gateway/session state: clear completed session active runs, avoid cold-loading providers for MCP inventory, cache single-session child indexes, cap handshake timers, and bound preauth, auth-guard, media, transcript, readiness, and port options.
- Channels/replies: preserve channel-owned progress callbacks when verbose output is off, keep group-room progress suppression intact, prefer external session delivery context, escape Discord component id delimiters, force final TUI chat repaints, show Slack reasoning previews, and normalize Discord/Matrix/Mattermost channel numeric options. (#87476, #87423)
- Agents/tool args: harden smart-quoted argument repair for edit arrays and exact escaped arguments so model-produced tool calls recover without corrupting valid input. (#86611) Thanks @ferminquant.
- Providers/agents: preserve seeded Anthropic signatures, preserve signed thinking payloads, concatenate signature-delta chunks, preserve DeepSeek `reasoning_content` replay across tier suffixes, apply OpenRouter strict9 ids to Mistral routes, promote Ollama plain-text tool calls, load NVIDIA featured model catalogs, stream MiniMax music generation responses, and recover empty preflight compaction. (#87593, #87493, #80775, #84764) Thanks @Pluviobyte and @eleqtrizit.
- Media/images: skip CLI image cache refs when resolving generated images, allow trusted generated HTML attachments, and bound generated video downloads so stale refs and slow providers fail cleanly. (#87523, #87982)
- File transfer: handle late tar stdin pipe errors after archive validation or unpacking has already settled.
- Performance: trust install-record caches between reloads, prefer native JSON parsing, reuse unchanged tool-search catalogs, skip unchanged store serialization, add precomputed session patch writers, reduce store clone allocations, cache manifest model catalog rows and auto-enabled plugin config, and slim current metadata identity caches.
- Docker/release/QA: package runtime workspace templates, stream cross-OS served artifacts, preserve sparse Crabbox run artifacts, bound OpenClaw instance logs, plugin gauntlet relay logs, MCP channel buffers, kitchen-sink scans, agent-turn assertions, and release scenario logs, and keep release/google live guards current.
- Performance: trust install-record caches between reloads, prefer native JSON parsing, reuse unchanged tool-search catalogs, reuse gateway session and plugin metadata paths, skip unchanged store serialization, patch single-entry session writes, add precomputed session patch writers, reduce store clone allocations, cache manifest model catalog rows and auto-enabled plugin config, avoid full session snapshots for entry reads, defer configured Slack full startup, prefer bundled plugin dist entries, and slim current metadata identity caches. (#87760)
- Docker/release/QA: package runtime workspace templates, stream cross-OS served artifacts, preserve sparse Crabbox run artifacts, isolate npm plugin installs per package, reject incompatible package plugin API installs, drop the leftover root Sharp dependency from package manifests after the Rastermill migration, bound OpenClaw instance logs, plugin gauntlet relay logs, MCP channel buffers, kitchen-sink scans, agent-turn assertions, QA-Lab credential broker calls, QA Matrix substrate requests, and release scenario logs, and keep release/google live guards current. (#87647, #87477) Thanks @rohitjavvadi and @vincentkoc.
- Release/CI: bound manual git fetches, ClawHub verifier responses, ClawHub owner metadata, dependency-guard error bodies, Parallels limits, startup/test/memory budget parsing, and diffs viewer build warnings so release lanes fail with useful proof instead of hanging. (#87839)
<li>Agent and Codex runtime recovery is steadier: subagents keep cwd/workspace separation, hook context stays prompt-local, session locks release on timeout abort while live OpenClaw locks survive cleanup, stale restart continuations are avoided, and Codex app-server/helper failures no longer tear down shared runtime state. (#87218, #86875, #87409, #87399, #87375, #88129)</li>
<li>Channel delivery and session identity got safer across outbound plugin hooks, Matrix room ids, iMessage reactions/approvals, Slack final replies, Discord recovered tool warnings, runtime-config message actions, WhatsApp profile auth roots, Telegram polling, and Microsoft Teams service URL trust checks. (#73706, #75670, #87366, #87451, #87334, #84535, #82492, #83304, #87160)</li>
<li>Mobile and chat surfaces got a broader refresh: the iOS Pro UI, hosted push relay default, realtime Talk tab playback, Gateway chat transport, onboarding, Talk permissions, WebChat reconnect delivery, and session picker behavior now preserve more state across reconnects and empty searches. (#87367, #87531, #87682, #88096, #88105) Thanks @ngutman.</li>
<li>Browser, channel, and automation inputs are stricter: Browser tool timeouts, viewport/tab indices, Gateway ports, cron retry handling, Discord component ids, schema array refs, Telegram callback pages, and channel progress callbacks now reject malformed values earlier and preserve the intended delivery context. (#82887)</li>
<li>Provider, media, and document coverage expands with Claude Opus 4.8, Fal Krea image schemas, NVIDIA featured models, MiniMax streaming music responses, encrypted PDF extraction, voice model catalogs, GitHub Copilot agent runtime support, and a Codex Supervisor plugin path for delegated Codex workflows. (#87845, #87890, #80775, #84764, #87751, #87794)</li>
<li>CLI, auth, doctor, and provider paths fail faster and recover more clearly: malformed numeric/version options are rejected, workspace dotenv provider credentials are ignored, heartbeat defaults, OAuth/token lifetimes, and local service startup requests are bounded, agent auth health labels are clearer, legacy <code>api_key</code> auth profiles migrate to canonical form, and restart guidance is actionable. (#87398, #86281, #87361, #88133, #83655, #87559, #88088, #85924) Thanks @vincentkoc and @giodl73-repo.</li>
<li>Plugin and Gateway hot paths do less repeated work while preserving cache correctness for install records, config JSON parsing, tool search catalogs, session stores, manifest model rows, auto-enabled plugin config, browser tokens, viewer assets, and release-split external plugin packages. (#86699)</li>
<li>Release, QA, and E2E validation now bound more log, artifact, harness, and cross-OS waits so failing lanes produce proof instead of hanging or false-greening.</li>
</ul>
<h3>Changes</h3>
<ul>
<li>Status: show active subagent details in status output.</li>
<li>Diffs: split the default language pack and expand default Diffs language coverage while keeping the host floor aligned. (#87370, #87372) Thanks @RomneyDa.</li>
<li>ClawHub: add plugin display names plus skill verification and trust surfaces. (#87354, #86699) Thanks @thewilloftheshadow and @Patrick-Erichsen.</li>
<li>iOS: refresh the dev app with Pro Command, Chat, Agents, Settings, hosted push relay defaults, and realtime Talk playback wired to gateway sessions, diagnostics, chat, and realtime Talk. (#87367, #88096, #88105) Thanks @Solvely-Colin and @ngutman.</li>
<li>PDF/tools: use ClawPDF for PDF extraction, support encrypted PDF extraction, and surface MCP structured content in agent tool results. (#87670, #87751)</li>
<li>Providers: add Claude Opus 4.8 support, Fal Krea image model schemas, NVIDIA featured model catalogs, MiniMax streaming music responses, and provider-backed voice model catalogs. (#87845, #87890, #80775, #84764, #87794) Thanks @eleqtrizit and @vincentkoc.</li>
<li>Codex/GitHub: add the GitHub Copilot agent runtime and the Codex Supervisor plugin package.</li>
<li>Plugins: externalize GitHub Copilot and Tokenjuice as official install-on-demand plugins with npm and ClawHub publish metadata.</li>
<li>Workboard: add agent coordination tools for tracking and handing off active agent work.</li>
<li>Discord: show commentary in progress drafts so live Discord runs expose useful in-progress context. (#85200)</li>
<li>Plugin SDK: add a reply payload sending hook for plugins that need to deliver channel-owned replies and flatten package types for SDK declarations. (#82823, #87165) Thanks @RomneyDa.</li>
<li>Agents: fall back to local config pruning when the optional <code>agents delete</code> Gateway probe cannot authenticate, so offline installs can still delete agents without removing shared workspaces.</li>
<li>Agents/Codex: keep spawned agent cwd/workspace state separated, forward ACP spawn attachments, keep hook context prompt-local, release session locks on timeout abort and runtime teardown without deleting live OpenClaw-owned locks during cleanup, avoid session event queue self-wait, clean up exec abort listeners, stream assistant deltas incrementally, recover raw missing-thread compaction failures, preserve rotated compaction session identity, keep compaction-timeout snapshots continuable, preserve shared app-server state across startup or helper failures, keep native hook relay alive across restarts and prune stale bridge files, close native hook relay replacement races, keep Claude live tool progress visible for watchdog recovery, suppress abandoned requester completion handoff, route workspace memory through tools, resolve Codex runtime models first, report quarantined dynamic tools, format <code>skills</code> command output, bind node auto-review to prepared plans, retry Claude CLI transcript probes, and bound compaction/steering retries. (#87218, #86875, #86123, #88129, #87399, #87375, #72574, #87383, #87400, #83022, #87671, #87738, #87747, #87706, #87546, #87541, #81048) Thanks @mbelinky, @Alix-007, @luoyanglang, @yetval, @sjf, @joshavant, and @benjamin1492.</li>
<li>Codex Supervisor: keep real-home app-server MCP session listing on the loaded state path, bound stored history scans, and close WebSocket probes cleanly.</li>
<li>Channels: thread canonical session keys into outbound hooks, preserve Matrix room-id case, keep fallback tool warnings mention-inert, retain delivered Slack final replies during late cleanup, continue iMessage polling after denied reactions, suppress duplicate native exec approvals, resolve Gateway message actions against the active runtime config, preserve Telegram SecretRef prompt config and polling keepalives, preserve WhatsApp profile auth roots, QR display, document filenames, and plugin hook config, suppress Discord recovered tool warnings, preserve the Discord voice outbound helper, cap Discord/Signal/Zalo channel request and container timeouts, and block untrusted Teams service URLs while keeping TeamsSDK patterns aligned. (#73706, #75670, #87366, #87451, #87465, #87334, #84535, #76262, #83304, #82492, #87581, #77114, #86426, #85529, #87160) Thanks @zeroaltitude, @lukeboyett, @xiaotian, @funmerlin, @joshavant, @eleqtrizit, @heyitsaamir, @amittell, @liorb-mountapps, @masatohoshino, @bladin, and @giodl73-repo.</li>
<li>CLI/auth/doctor/providers: reject malformed numeric/timeout/subcommand-version inputs, ignore workspace dotenv provider credentials, wait for respawn child shutdown, bound heartbeat defaults plus Codex, GitHub Copilot, OpenAI, Anthropic, Google, Feishu, LM Studio, MiniMax, Xiaomi TTS, and local-provider OAuth/token/model requests, harden Codex auth probes, label auth health by agent, preserve explicit agentRuntime pins during Codex model migration, warm provider auth off the main thread, honor Codex response timeouts, stop migrating current Claude Haiku 4.5 profiles to Sonnet, bound local service startup, resolve GPT-5.5 without cached catalog, migrate legacy memory auto-provider config, rewrite non-canonical <code>api_key</code> auth profiles, and make doctor restart follow-ups actionable. (#87398, #86281, #87361, #88133, #83655, #87559, #87719, #88088, #85924, #84362) Thanks @Patrick-Erichsen, @samzong, @giodl73-repo, @alkor2000, @mmaps, @nxmxbbd, and @vincentkoc.</li>
<li>Gateway/security/session state: expire browser tokens after auth rotation, scope assistant idempotency dedupe, drain probe client closes, avoid stale restart continuation reuse, preserve retry-after fallbacks and stale rate-limit cooldown probes, bound webchat image and artifact transcript scans, include seconds in inbound metadata timestamps, clear completed session active runs, clear stale chat stream buffers, and evict current plugin-state namespaces at row caps. (#87810, #87833, #75089) Thanks @joshavant and @litang9.</li>
<li>Config/parsing/network: reject partial numeric parsing, parse provider/Discord retry headers and dates strictly, honor IPv6 and bare IPv6 <code>no_proxy</code> entries, preserve empty plugin allowlists, canonicalize secret target array indexes, and reject malformed media content lengths, inspected TCP ports, marketplace content lengths, cron epochs, sandbox stat fields, unsafe duration values, empty config path segments, noncanonical schema array refs, unsafe Telegram callback pages, and invalid Teams attachment-fetch DNS targets. (#87883) Thanks @zhangguiping-xydt.</li>
<li>Cron/automation: retry recurring jobs after transient model rate limits before waiting for the next scheduled slot, and preflight model fallbacks before skipping scheduled work. (#82887)</li>
<li>Auto-reply/directives: respect provider and relayed channel metadata during directive persistence so channel-originated decisions keep their intended context. (#87683)</li>
<li>WhatsApp: resolve the auth directory from the active profile so profile-scoped WhatsApp installs do not drift to the wrong credential root. (#82492)</li>
<li>Gateway/session state: clear completed session active runs, avoid cold-loading providers for MCP inventory, cache single-session child indexes, cap handshake timers, and bound preauth, auth-guard, media, transcript, readiness, and port options.</li>
<li>Channels/replies: preserve channel-owned progress callbacks when verbose output is off, keep group-room progress suppression intact, prefer external session delivery context, escape Discord component id delimiters, force final TUI chat repaints, show Slack reasoning previews, and normalize Discord/Matrix/Mattermost channel numeric options. (#87476, #87423)</li>
<li>Agents/tool args: harden smart-quoted argument repair for edit arrays and exact escaped arguments so model-produced tool calls recover without corrupting valid input. (#86611)</li>
<li>Providers/agents: preserve seeded Anthropic signatures, preserve signed thinking payloads, concatenate signature-delta chunks, preserve DeepSeek <code>reasoning_content</code> replay across tier suffixes, apply OpenRouter strict9 ids to Mistral routes, promote Ollama plain-text tool calls, load NVIDIA featured model catalogs, stream MiniMax music generation responses, and recover empty preflight compaction. (#87593, #87493, #80775, #84764) Thanks @eleqtrizit.</li>
<li>Media/images: skip CLI image cache refs when resolving generated images, allow trusted generated HTML attachments, and bound generated video downloads so stale refs and slow providers fail cleanly. (#87523, #87982)</li>
<li>File transfer: handle late tar stdin pipe errors after archive validation or unpacking has already settled.</li>
<li>Performance: trust install-record caches between reloads, prefer native JSON parsing, reuse unchanged tool-search catalogs, reuse gateway session and plugin metadata paths, skip unchanged store serialization, patch single-entry session writes, add precomputed session patch writers, reduce store clone allocations, cache manifest model catalog rows and auto-enabled plugin config, avoid full session snapshots for entry reads, defer configured Slack full startup, prefer bundled plugin dist entries, and slim current metadata identity caches. (#87760)</li>
<li>Docker/release/QA: package runtime workspace templates, stream cross-OS served artifacts, preserve sparse Crabbox run artifacts, isolate npm plugin installs per package, reject incompatible package plugin API installs, drop the leftover root Sharp dependency from package manifests after the Rastermill migration, bound OpenClaw instance logs, plugin gauntlet relay logs, MCP channel buffers, kitchen-sink scans, agent-turn assertions, QA-Lab credential broker calls, QA Matrix substrate requests, and release scenario logs, and keep release/google live guards current. (#87647, #87477) Thanks @rohitjavvadi and @vincentkoc.</li>
<li>Release/CI: bound manual git fetches, ClawHub verifier responses, ClawHub owner metadata, dependency-guard error bodies, Parallels limits, startup/test/memory budget parsing, and diffs viewer build warnings so release lanes fail with useful proof instead of hanging. (#87839)</li>
</ul>
<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
<li>Stronger security and content boundaries: group prompt text is kept out of the system prompt, repeated-dot hostnames are normalized, side-effecting command wrappers and unsafe Node runtime env overrides are blocked, no-auth Tailscale exposure is rejected, and node/device-role approvals now require admin authority. (#87144, #87305, #87292, #87308, #87146) Thanks @eleqtrizit and @pgondhi987.</li>
<li>More reliable Codex app-server runs: Codex runtime models resolve first, workspace memory is routed through tools, shared app-server clients survive startup and spawned-helper failures, native hook relay generations survive restarts and rotate on fresh fallbacks, and false runtime live switches are avoided. (#87383, #87403, #87375, #72574, #87428) Thanks @yetval.</li>
<li>Faster Gateway and reply paths: session reads, plugin metadata fingerprints, auth env snapshots, auto-enabled plugin config, tool-search catalogs, and stable metadata caches do less hot-path rediscovery while visible replies no longer inherit hidden cleanup timeouts. (#86439, #87044) Thanks @keshavbotagent.</li>
<li>Better provider and model coverage: OpenAI-compatible embedding providers are core, DeepInfra catalog browsing loads the full credential-aware model set, Pixverse adds video generation and API region selection, VLLM thinking params are wired, Claude CLI OAuth overlays load for PI auth profiles, and bare direct Anthropic model ids work. (#85269, #84549, #87167) Thanks @dutifulbob, @ats3v, and @joshavant.</li>
<li>Channel delivery is steadier: Telegram <code>sendMessage</code> actions use durable outbound delivery, iMessage suppresses duplicate native exec approval prompts and sends, Slack keeps delivered final replies during late cleanup, Matrix mention previews/finals are stricter, QQBot fallback approval buttons honor slash-command auth, Discord guild requester checks are tighter, recovered Discord tool-warning artifacts stay out of successful replies, and Google Chat stops thread sends in DMs. (#87261, #87154) Thanks @mbelinky and @eleqtrizit.</li>
<li>Release, package, and CI proof paths are harder to wedge: npm/package inventory honors dist exclusions, shrinkwrap override pins merge correctly, Docker runtime workspace templates are packaged and smoked, release postpublish checks are stricter, beta smoke rejects empty runs, and E2E log/probe waits are bounded.</li>
</ul>
<h3>Changes</h3>
<ul>
<li>Memory: add a core OpenAI-compatible embedding provider for local and hosted OpenAI-style endpoints, with config, doctor, and docs support. (#85269) Thanks @dutifulbob.</li>
<li>Plugin SDK: mark memory-specific embedding provider registration as deprecated compatibility and surface non-bundled usage in plugin compatibility diagnostics. (#85072) Thanks @mbelinky.</li>
<li>Providers: add the Pixverse video generation provider, API region selection, docs, and external plugin packaging support.</li>
<li>DeepInfra: load the full model catalog when users browse models during onboarding, preserve configured API-key catalogs, refresh media/video defaults, and keep pricing/default model metadata aligned. (#84549) Thanks @ats3v.</li>
<li>Plugin SDK: expose plugin approval action metadata and stop exporting Vitest test helpers from the public SDK surface. (#87120) Thanks @RomneyDa.</li>
<li>Channel SDK: move channel message compatibility into core, remove old channel turn runtime aliases, and preserve runtime catalog markdown metadata for plugins.</li>
<li>ClawHub: add plugin display metadata so catalog/package listings use cleaner names. (#87354) Thanks @thewilloftheshadow.</li>
<li>Agents: split the heartbeat runtime template out of docs assets and add compatibility repair for legacy heartbeat template content. (#85416) Thanks @hxy91819.</li>
</ul>
<h3>Fixes</h3>
<ul>
<li>Security/content boundaries: route untrusted group prompt metadata outside system prompts, normalize repeated trailing hostname dots, block side-effecting command wrappers, reject unsafe Node runtime env overrides, reject no-auth Tailscale exposure, block untrusted Microsoft Teams service URLs, enforce <code>/allowlist configWrites</code> origin policy, gate QQBot fallback approval buttons, and require admin for node/device-role approvals. (#87144, #87305, #87292, #87308, #87146, #87154, #87334) Thanks @eleqtrizit and @pgondhi987.</li>
<li>Codex: resolve Codex runtime models before generic routing, route workspace memory through tools, preserve shared app-server clients after startup and spawned-helper failures, preserve native hook relay generations across restarts and fresh fallbacks, keep raw reasoning/source-reply guards intact, report quarantined dynamic tools, keep the attempt watchdog armed for queued terminal turns, and route Codex OAuth compaction through OpenAI-Codex. (#87383, #87403, #87375, #72574, #87428) Thanks @yetval.</li>
<li>Agents/runtime: avoid session event queue self-waits, bound compaction wake and steering retries, preserve grace for pending error diagnostics, avoid false Codex runtime live switches, avoid stale restart continuation reuse, preserve session fallback errors, suppress duplicate Claude CLI skill prompts, keep runtime context before active user turns, strip stale Anthropic thinking, quarantine unsupported tool schemas, recover completed write timeouts safely, release retained session write locks on timeout abort, and validate forced plugin harness support before pinning. (#86123, #55424, #86855, #74341, #87278) Thanks @luoyanglang, @cathrynlavery, and @openperf.</li>
<li>Reply/session delivery: keep visible turn admission unbounded, keep visible fallback delivery on latest targets, preserve bridge hook context, classify direct fallback targets by channel grammar, report approval resolutions in bridge mode, and avoid stale source-reply artifacts. (#87044) Thanks @keshavbotagent.</li>
<li>Channels: make Telegram <code>sendMessage</code> action replies durable and preserve SecretRef prompt config, suppress duplicate iMessage native exec approval prompts and sends, keep iMessage approval polling alive after denied reactions, keep Slack delivered final replies during late cleanup, keep Matrix mention previews/finals mention-inert and normally delivered, ignore filename-embedded Matrix IDs, suppress recovered Discord tool-warning artifacts from successful replies, suppress Google Chat thread sends in DMs, and harden Discord guild requester checks. (#87261, #87452) Thanks @mbelinky.</li>
<li>Memory: salvage QMD search JSON after nonzero exits and keep workspace memory routing through the Codex tool path where possible. (#87225, #87383, #87403) Thanks @osolmaz.</li>
<li>Providers/models: forward cached token usage in OpenAI-compatible chat completions, load Claude CLI OAuth overlays for PI auth profiles, send bare direct Anthropic model ids, wire configured VLLM thinking params, honor OpenAI-compatible cache retention, normalize OpenAI Responses replay tool ids, resolve OpenAI <code>gpt-5.5</code> without a cached catalog, preserve <code>retry-after</code> fallback handling, bound GitHub Copilot auth requests, and load DeepInfra custom/live catalogs consistently. (#82062, #87167, #84549) Thanks @caz0075, @joshavant, and @ats3v.</li>
<li>Gateway/performance: borrow read-only session metadata and active session working stores, cache current/stable plugin metadata fingerprints, cache auto-enabled plugin config, slim metadata identity caches, trust current metadata lifecycle caches, stabilize isolated cron prompt-cache affinity, persist model auth profile suffixes, drain probe client closes, expire browser tokens after auth rotation, and keep default status fast paths bounded. Thanks @ferminquant.</li>
<li>CLI/help/config: reject loose or malformed numeric options for gateway timeouts, model limits, directory limits, message options, webhooks, and partial values; respect subcommand version options; route generated/root/plugin help targets correctly; keep skills JSON output flushing naturally; and keep plugin descriptor loading quiet in root help. (#87398) Thanks @Patrick-Erichsen.</li>
<li>Plugin state/tool search: evict the current namespace when plugin rows hit caps, reuse unchanged tool-search catalogs, align the release catalog reuse wrapper, and keep fallback tool warnings mention-inert.</li>
<li>Install/package/release: match npm globstar exclusions, honor dist package exclusions in inventory, omit unpacked test helpers, skip Homebrew until macOS packages need it, package Docker runtime workspace templates, smoke Docker runtime templates during full validation, merge nested shrinkwrap override pins, preserve forked shrinkwrap pins, pin aged <code>lru-cache</code>, harden postpublish verification, accept main full-validation proof, and reject empty beta smoke runs.</li>
<li>E2E/QA/Crabbox: bound Telegram, Open WebUI, ClawHub, Matrix, Tool Search, MCP, gateway network, bundled runtime, kitchen-sink, codex media, config reload, and agent-turn assertion waits; prefer Azure for Windows targets; reinitialize invalid changed-gate git dirs; full-sync sparse container runs; and fail empty explicit test requests. (#87186)</li>
</ul>
<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
<li>Gateway/perf: reuse process-stable channel catalog reads, avoid repeated bundled-channel boundary checks, and rotate gateway watch CPU profiles so benchmark runs do not accumulate unbounded artifacts.</li>
<li>Gateway/perf: reuse immutable plugin metadata snapshots across startup, config, model, channel, setup, and secret metadata readers so hot paths avoid repeated plugin file stats and manifest registry reloads.</li>
<li>Gateway/perf: lazy-load startup-idle plugin work, core gateway method handlers, and the embedded ACPX runtime so Gateway health and ready signals no longer wait on unused handler trees or ACPX probes.</li>
<li>Gateway/perf: cache plugin SDK public-surface alias maps and skip irrelevant macOS Linuxbrew PATH probes so Gateway startup avoids repeated filesystem walks and slow missing-directory stats.</li>
<li>Meeting Notes: add a source-only external meeting-notes plugin and SDK source-provider contract outside the core npm package, with auto-start capture config, manual transcript imports, read-only <code>openclaw meeting-notes</code> CLI access, and Discord voice as the first live source.</li>
<li>Docs/channels/config: add Signal <code>configPath</code>, Telegram wildcard topic defaults, local-time backup archive names, Termux home fallback, include-path validation, secret-scanner-safe placeholder guidance, Gemini CLI/Antigravity media guidance, and macOS VM auto-login guidance. Thanks @NorseGaud, @yudistiraashadi, @huangqian8, @VibhorGautam, @maweibin, @tianxingleo, @IgnacioPro, and @xzcxzcyy-claw.</li>
<li>Docs: clarify model-usage portability, Codex migration prerequisites, status bootstrap wording, thread-bound subagent limits, hook ownership, and config-preserving safety guidance. Thanks @aniruddhaadak80, @leno23, @TomDjerry, @matthewxmurphy, @vincentkoc, and @stablegenius49.</li>
<li>Docs: clarify README onboarding and Gateway startup paths, WhatsApp QR/408 recovery, cron output language prompts, skill advanced features, gateway upstream 403 troubleshooting, and plugin fallback override guidance. Thanks @deepujain, @Zacxxx, @Jah-yee, @neyric, @usimic, @Renu-Cybe, @BigUncle, and @SeashoreShi.</li>
<li>Docs: clarify context-pruning ratio bounds, local dashboard recovery, CLI env markers, remote onboarding token behavior, and Peekaboo Bridge permissions for subprocess agents. Thanks @ayesha-aziz123, @dishraters, @hougangdev, and @brandonlipman.</li>
<li>Docs: consolidate GLM under Z.AI, add the Upstash Box install guide and Gateway exposure runbook, clarify MEDIA directives, Copilot and Voyage setup, config path quoting, real behavior proof, and memory-file write guidance. Thanks @BobDu, @alitariksahin, @Jefsky, @musaabhasan, @OmerZeyveli, @leno23, @WuKongAI-CMU, @luoyanglang, and @majin1102.</li>
<li>Docs: clarify media provider credentials, Codex/OpenClaw code-mode boundaries, Slack and Telegram ack reactions, Feishu dynamic agents, secrets plaintext boundaries, memory guidance, and Chinese glossary terms. Thanks @nielskaspers, @cosmopolitan033, @drclaw-iq, @alexgduarte, @zccyman, @chengoak, and @cassthebandit.</li>
<li>Packaging: exclude documentation images and assets from the npm tarball, reducing published package size without affecting runtime docs search or CLI behavior. Thanks @SebTardif.</li>
<li>Media understanding: stop auto-probing Gemini CLI and use Antigravity CLI only as a lower-priority image/video fallback after configured provider APIs.</li>
<li>Agents/subagents: limit default sub-agent bootstrap context to <code>AGENTS.md</code> and <code>TOOLS.md</code>, keeping persona, identity, user, memory, heartbeat, and setup files out of delegated workers by default. (#85283) Thanks @100yenadmin.</li>
<li>Maintainer skills: exclude plugin SDK/API boundary work from <code>openclaw-landable-bug-sweep</code> so bugbash sweeps stay focused on small paper-cut fixes.</li>
<li>QA-Lab/diagnostics: extend the OpenTelemetry smoke harness to prove trace, metric, and log export, and add first-class Prometheus and observability smoke aliases.</li>
<li>Plugin SDK: add a generic channel-message poll sender so channel plugins can expose poll delivery without depending on channel-specific SDK facades.</li>
<li>Crabbox: keep the local wrapper's provider validation synced with the installed Crabbox binary while preserving supported aliases such as <code>docker</code> and <code>blacksmith</code>. (#85302) Thanks @hxy91819.</li>
<li>Maintainer skills: add <code>openclaw-landable-bug-sweep</code> for producing five small, reviewed, CI-green OpenClaw bugfix PRs from issue/PR sweeps.</li>
<li>Control UI/chat: add search and Load More pagination to the chat session picker, keeping initial session loads bounded while making older conversations reachable. (#85237) Thanks @amknight.</li>
<li>CLI/onboarding: start classic onboarding when bare <code>openclaw</code> runs before an authored config exists, while keeping configured installs on Crestodian. (#72343) Thanks @fuller-stack-dev.</li>
<li>Discord: allow configuring a bounded <code>agentComponents.ttlMs</code> callback registry lifetime for long-running component workflows, with per-account overrides and a 24-hour cap. (#84189) Thanks @100menotu001.</li>
<li>xAI/Grok: reuse xAI OAuth auth profiles for Grok <code>web_search</code>, thread active-agent auth through web search, add Grok model aliases, and let media providers declare default operation timeouts. (#85182) Thanks @fuller-stack-dev.</li>
<li>Plugin SDK: add row-level session workflow helpers and deprecate <code>loadSessionStore</code> so plugins can read and patch sessions without depending on the legacy whole-store shape. (#84693) Thanks @efpiva.</li>
<li>Gateway/plugins: reuse a compatible Gateway startup plugin registry during dispatch so safe plugin dispatches avoid redundant registry loading. (#84324) Thanks @ai-hpc.</li>
<li>Plugins/SDK: add a general <code>embeddingProviders</code> capability contract and registration API so embeddings can become a reusable provider surface outside memory-specific adapters.</li>
<li>Dependencies: refresh provider, plugin, UI, and tooling packages, update <code>protobufjs</code> to 8.4.0 to clear the current npm advisory, and carry the Claude ACP completion patch forward to <code>@agentclientprotocol/claude-agent-acp</code> 0.36.1.</li>
<li>Agents/tools: remove the old sender-owner tool gating path so configured tools stay visible for trusted sessions while command and channel-action auth still carry real sender identity.</li>
<li>QA-Lab: add curated mock JSONL replay fixtures and first-drift reporting for runtime-parity audits. (#80323, refs #80176) Thanks @100yenadmin.</li>
<li>QA-Lab: add a QA bus tool-trace visibility scenario for sanitized tool-call assertions.</li>
<li>QA-Lab: replace generic evidence framing in seeded scenario prompts with concrete observed QA behavior.</li>
<li>QA-Lab: list named scenario packs in the coverage report so personal-agent privacy coverage stays visible in audits.</li>
<li>QA-Lab: list live transport lane membership in the coverage report so real transport checks stay separate from seeded qa-channel scenarios.</li>
<li>Release/package: run package integrity checks before package acceptance lanes so public install/update validation fails before private QA assets can leak into the package.</li>
<li>QA-Lab: include the optional 100-turn runtime parity soak in release-soak artifacts so long-run Codex/Pi transcript drift stays visible outside the default gate. (#80395) Thanks @100yenadmin.</li>
<li>QA-Lab: add a live-only long-context progress watchdog scenario for Codex app-server timeout and stalled-run sentinels. (#80323) Thanks @100yenadmin.</li>
<li>QA-Lab: tag gateway restart recovery and streaming final-integrity scenarios as live-only runtime parity lanes. (#80323) Thanks @100yenadmin.</li>
<li>QA-Lab: add a personal-agent failure recovery scenario that checks honest partial status, retry boundaries, and local recovery artifacts. (#83872) Thanks @iFiras-Max1.</li>
<li>QA-Lab: include an opt-in <code>update.run</code> package self-upgrade sentinel for destructive latest-package recovery checks.</li>
<li>QA-Lab: add Codex plugin lifecycle and auth-profile fixture coverage for missing installs, pinned-version drift, first-turn install ordering, and doctor migration safety. (#80323, refs #80174) Thanks @100yenadmin.</li>
<li>Models/perf: pre-warm the provider auth-state map at gateway startup so <code>/models</code> and every model-listing call short-circuits the per-provider plugin / external-CLI discovery on the hot path. Per-call cost drops from ~20 s to ~5 ms (~4,100×); the one-time startup warm resets and re-warms after hot reloads. (#84816) Thanks @sjf.</li>
<li>Release/security: ship the root npm package and OpenClaw-owned npm plugins with generated shrinkwrap, support bundled plugin runtime dependencies for suitable plugin tarballs, and require review for lockfile/shrinkwrap changes so published installs use locked dependency graphs.</li>
<li>Tests/perf: isolate doctor core health check unit coverage from real skills/workspace discovery so <code>doctor-core-checks</code> no longer dominates unit perf while keeping one real skills-readiness smoke. (#84493) Thanks @frankekn.</li>
</ul>
<h3>Fixes</h3>
<ul>
<li>WebChat: summarize internal message-tool source replies so tool cards no longer duplicate the visible reply body. (#84773) Thanks @jason-allen-oneal.</li>
<li>Gateway: preserve deferred lifecycle-error cleanup across later non-terminal events so provider timeouts can persist failed session state instead of leaving sessions stuck running. (#85256, fixes #63819) Thanks @samzong.</li>
<li>Agents/subagents: report tool-only child progress during timeout summaries instead of showing no visible output.</li>
<li>Telegram/ACP: preserve explicit <code>:topic:</code> conversation suffixes when inbound ACP targets do not carry a separate thread id.</li>
<li>Browser/proxy: bypass the managed proxy for the exact local managed Chrome CDP readiness and DevTools WebSocket endpoints, so <code>openclaw browser start</code> works when the operator proxy blocks loopback egress. (#83255) Thanks @lightcap.</li>
<li>Ollama: bypass the managed proxy for configured local embedding origins while keeping SSRF guardrails on unconfigured targets. Thanks @Kaspre.</li>
<li>OpenAI/images: route Codex API-key image generation through the native OpenAI Images API instead of the Codex OAuth streaming backend, avoiding 401s from valid API keys.</li>
<li>Checks/Windows: route full <code>pnpm check</code> stage commands through the managed child runner so Windows avoids Node shell-argv deprecation warnings there too.</li>
<li>Checks/Windows: run managed child commands through explicit <code>cmd.exe</code> wrapping instead of Node shell mode with argv, avoiding Node 24 subprocess deprecation warnings during changed checks.</li>
<li>Gateway: omit internal stream-error placeholder entries from agent prompt history so failed assistant turns are not replayed as model-authored text. (#85652) Thanks @anyech.</li>
<li>Sessions: enforce the session write-lock max-hold policy during lock acquisition so long-held locks can be reclaimed before the stale-lock window. (#85764) Thanks @njuboy11.</li>
<li>Models: prune retired Groq, GitHub Copilot, OpenAI, xAI, and old Claude catalog entries, with doctor migration to upgrade existing configs to current provider refs.</li>
<li>Doctor/update: recognize junction-backed source checkouts as git installs by comparing canonical paths before showing package-manager update guidance. Fixes #82215. Thanks @igormf.</li>
<li>Channels: honor <code>/verbose on</code> for tool/progress summaries across direct chats, groups, channels, and forum topics while preserving quiet default behavior. (#85488) Thanks @kurplunkin.</li>
<li>CLI/skills: show an all-ready note with next-step commands when skill setup has no missing dependencies to install. (#85032) Thanks @aniruddhaadak80.</li>
<li>Microsoft Foundry: route DeepSeek V4 Pro and Flash models through the Foundry Responses API while keeping older DeepSeek models on their existing path. (#85549) Thanks @roslinmahmud.</li>
<li>Status/usage: show configured cost estimates for AWS SDK models in full usage output while keeping token-only usage replies cost-free. (#85619) Thanks @ItsOtherMauridian.</li>
<li>Agents/OpenAI Responses: retry non-visible reasoning-only turns for OpenAI Responses API families instead of treating them as empty failed turns. (#85603) Thanks @SebTardif.</li>
<li>Directive tags: preserve message and content-part object identity when display stripping makes no directive-tag changes. (#85682) Thanks @willamhou.</li>
<li>Telegram: send local <code>path</code>/<code>filePath</code> and structured attachment media from <code>sendMessage</code> actions instead of dropping them or sending text-only messages. (#85219) Thanks @keshavbotagent.</li>
<li>Sessions/status: show the estimated context budget when fresh provider usage is unavailable and clear stale estimates across session resets and compaction boundaries. (#84830) Thanks @giodl73-repo.</li>
<li>Gateway/config: pin relative <code>OPENCLAW_STATE_DIR</code> overrides to an absolute path at startup so later working-directory changes cannot retarget gateway state. (#52264) Thanks @PerfectPan.</li>
<li>Release/package: run npm release, prepublish, and postpublish verification through Windows-safe npm command shims so native Windows checks can execute <code>npm.cmd</code> instead of treating it as a binary.</li>
<li>Agents/harness: pass CLI runtime aliases through harness selection so provider-owned CLI aliases no longer get rejected before reaching the right runtime. (#85631) Thanks @potterdigital.</li>
<li>Secrets: show the irreversible apply warning after interactive <code>secrets configure</code> confirmation so confirmed migrations still get the final safety prompt. (#85638) Thanks @alkor2000.</li>
<li>Agents/CLI output: ignore cumulative Claude <code>stream-json</code> result usage when assistant usage events are present, preventing inflated cache-read accounting. (#85625) Thanks @zhouhe-xydt.</li>
<li>CLI: keep <code>waitForever()</code> alive by leaving its keep-alive interval ref'd so the public helper no longer exits immediately with Node's unsettled-await code. (#85694) Thanks @m1qaweb.</li>
<li>Agents/bootstrap: guard bootstrap name checks against missing file names so malformed bootstrap entries warn and truncate instead of crashing. Fixes #85523. (#85615) Thanks @zhouhe-xydt.</li>
<li>CLI/tasks: reject partially numeric <code>openclaw tasks audit --limit</code> values so audit limits must be real positive integers instead of accepting strings like <code>5abc</code>. (#84901) Thanks @jbetala7.</li>
<li>Status/diagnostics: bound deep Docker audit probes so <code>openclaw status --deep</code> reports slow container checks instead of hanging behind unbounded inspection. (#85476) Thanks @giodl73-repo.</li>
<li>Providers/Anthropic: migrate 1M context handling to GA-capable Claude 4.x models by sizing eligible models at 1M without the retired <code>context-1m-2025-08-07</code> beta, ignoring that retired beta in older configs, and preserving OAuth-required Anthropic beta headers. (#45613) Thanks @haoyu-haoyu.</li>
<li>Cron/Telegram: parse forum-topic delivery targets through the Telegram plugin instead of cron core, including <code>:topic:</code> and <code>:topicId</code> forms for announce delivery. Thanks @etticat.</li>
<li>Twitch: keep stale message-handler cleanup callbacks from removing newer handler registrations for the same account, preserving inbound message delivery after reconnects. Fixes #83888. (#85425) Thanks @alkor2000.</li>
<li>Memory/LanceDB: expose public memory artifacts through the active memory provider bridge so memory-wiki imports durable memory files, daily notes, dream reports, and event logs without depending on memory-core internals. Fixes #83604. (#85060) Thanks @brokemac79.</li>
<li>Crabbox: keep AWS hydration compatible with local Actions replay by inlining the hydrate workflow's Node/pnpm setup instead of invoking repo-local composite actions.</li>
<li>Agents/subagents: simplify native sub-agent completion handoff so children report their latest visible assistant result to the requester without using <code>message</code>, while keeping parent-owned message-tool delivery policy intact. Fixes #85070. (#85089) Thanks @brokemac79.</li>
<li>Docker setup: stop printing the Gateway bearer token in setup logs and printed follow-up commands.</li>
<li>Agents: let embedded compaction fallback retries proceed when PI-compatible candidates do not need agent harness plugin preparation.</li>
<li>Agents/tools: honor configured custom provider API keys when deciding whether media, image-generation, video-generation, music-generation, and PDF tools are available. (#85570)</li>
<li>StepFun: stop advertising stale generic API key auth choices so onboarding only offers runtime-backed Standard and Step Plan choices.</li>
<li>Diagnostics: keep OpenTelemetry log bodies behind explicit content capture and scrub scoped agent-session keys from OpenTelemetry and Prometheus labels while preserving bounded queue-lane prefixes.</li>
<li>Windows installer: fail Git checkout installs when <code>pnpm install</code> or <code>pnpm build</code> fails instead of writing a wrapper to a missing CLI build.</li>
<li>Sessions: surface previous-transcript archive failures during <code>/new</code> rotation so disk rename errors are logged instead of silently hiding stranded transcript files. Fixes #81984. (#85586, from #82081) Thanks @0xghost42.</li>
<li>TUI/agents: mirror internal-ui message-tool replies into final chat output so message-tool-only agents remain visible in <code>openclaw tui</code>. Fixes #85538. Thanks @danpolasek.</li>
<li>Agents: keep parallel OpenAI-compatible tool-call deltas in separate argument buffers so interleaved tool calls no longer corrupt streamed arguments. (#82263) Thanks @luna-system.</li>
<li>Memory/doctor: report missing or unusable QMD workspace directories as workspace failures instead of generic binary failures. (#63167) Thanks @sercada.</li>
<li>Debug proxy: record CONNECT client-socket errors and destroy the paired upstream socket so abrupt client disconnects no longer leak tunnel resources. (#82444) Thanks @SebTardif.</li>
<li>Diffs: continue hydrating later diff cards when one card fails so a single broken card no longer blanks the whole diff viewer. (#84775) Thanks @cosmopolitan033.</li>
<li>Mac app: use the native settings sidebar window chrome so the sidebar toggle stays on the left and content no longer clips under oversized titlebar padding.</li>
<li>QA-Lab/Codex: bundle auth/plugin fixture imports for flow scenarios and let terminal async media tools end Codex app-server turns without timing out. (#80397, refs #80323) Thanks @100yenadmin.</li>
<li>Gateway/agents: preserve fresh session overrides and metadata when stale cached agent-session entries race with store updates, so subagent model/provider overrides and routing policy survive concurrent writes. (#19328) Thanks @CodeReclaimers.</li>
<li>Control UI/chat: keep chat session search inline with the session selector so the header no longer shows a duplicate standalone search row.</li>
<li>Control UI/chat: collapse focused-mode header chrome and suppress hidden-header scroll updates so focus mode no longer jumps while scrolling. Thanks @amknight.</li>
<li>Codex app-server: restart the native app-server and retry once when server-side compaction times out, so preflight compaction stalls recover instead of failing every dispatch. (#85500)</li>
<li>Restore Control UI gateway token pairing [AI]. (#85459) Thanks @pgondhi987.</li>
<li>OpenAI video: honor configured provider request private-network opt-in for local/custom video endpoints so explicitly trusted mock and self-hosted providers are not blocked. Thanks @shakkernerd.</li>
<li>OpenAI video: send uploaded video edit requests to the documented <code>/videos/edits</code> endpoint with a <code>video</code> file instead of posting MP4 references to <code>/videos</code>. Thanks @shakkernerd.</li>
<li>Agents/channels: preserve message-tool delivery evidence through gateway agent completion handoffs so successful generated media sends are not followed by false failure messages. Thanks @shakkernerd.</li>
<li>CLI/update: repair managed npm plugin <code>openclaw</code> peer links during post-core convergence and reject stale or wrong-target peer links before restart. (#83794) Thanks @fuller-stack-dev.</li>
<li>CLI/agents: default new omitted-account bindings to all accounts when the channel has multiple configured accounts, and clarify account-scope docs. (#49769) Thanks @Gcaufy.</li>
<li>Codex app-server: let authorized <code>/codex</code> control commands such as <code>/codex detach</code> escape plugin-owned conversation bindings while keeping unknown or unauthorized slash text routed to the bound plugin. Fixes #85157. (#85188) Thanks @TurboTheTurtle.</li>
<li>Auto-reply/models: keep <code>/models</code> browse replies fast by sharing the bounded read-only catalog path with Gateway model listing. (#84735) Thanks @safrano9999.</li>
<li>Codex app-server: disable native Code Mode when the effective exec host is <code>node</code> and keep OpenClaw <code>exec</code>/<code>process</code> available, so <code>/exec host=node</code> routes shell commands through the selected node instead of the gateway. Fixes #85012. (#85090) Thanks @sahilsatralkar.</li>
<li>Agents: bound embedded auto-compaction session write-lock watchdogs to the compaction timeout instead of the full run timeout, so stuck compaction cannot hold the live session lock for the whole run window. (#84949) Thanks @luoyanglang.</li>
<li>Gateway/agents: return phase-aware <code>agent.wait</code> timeout attribution and only cool auth profiles on provider-started timeouts. Refs #65504. Thanks @100yenadmin.</li>
<li>Gateway: defer provider auth-state prewarm until after startup readiness so early gateway tool/session requests are not blocked by provider auth discovery. (#85272) Thanks @dutifulbob.</li>
<li>Gateway/models: coalesce provider auth-state rewarms after auth-profile failures and log event-loop delay for warm/rewarm work, so provider auth bursts no longer stack full auth sweeps behind channel replies.</li>
<li>Gateway/models: stop cancelled provider auth-state prewarms from continuing full provider sweeps, so reload and auth-failure bursts no longer keep startup busy.</li>
<li>Agents/Codex: show the first plan update as a transient chat status notice without counting it as final assistant content.</li>
<li>CLI/update: walk the macOS process ancestry and honor the inherited Gateway runtime PID before package updates stop the managed Gateway service, so nested in-band updater children can refuse instead of killing the LaunchAgent-supervised Gateway that owns them. Fixes #85120.</li>
<li>Gateway/LaunchAgent: wait for launchd reload bootout to finish and fall back to kickstart when bootstrap races, so reload handoff does not leave the service deregistered. Fixes #84630. (#84641) Thanks @NianJiuZst.</li>
<li>Gateway/LaunchAgent: treat a concurrent launchd bootstrap as a successful restart when the service is already loaded, avoiding false macOS Gateway restart failures. Fixes #84721. (#84722) Thanks @googlerest.</li>
<li>Gateway/service: include the active <code>openclaw</code> command bin directory in managed service PATH generation and doctor audit expectations for npm-global macOS installs. Fixes #84201. (#84475) Thanks @jbetala7.</li>
<li>Control UI/chat: disable the thinking selector for known non-reasoning models instead of showing duplicate Off choices. Fixes #84069. Thanks @DrippingMellow.</li>
<li>Memory: expand <code>~</code> in configured extra memory paths before resolving them, so home-relative folders are not treated as workspace-relative. Fixes #58026. Thanks @stadman.</li>
<li>Skills: treat <code>openclaw.os: macos</code> as Darwin when checking skill requirements, so macOS-only skills no longer report as missing on macOS hosts. Fixes #61338. Thanks @Jessecq1995.</li>
<li>Control UI/logs: strip ANSI escape sequences from displayed Gateway log messages so color codes no longer appear as raw text. Fixes #64399. Thanks @guguangxin-eng.</li>
<li>Docker: pre-create the workspace and auth-profile config mount points with <code>node</code> ownership so first-run named volumes do not start root-owned. Fixes #85076. Thanks @Noerr.</li>
<li>Telegram: pass configured markdown table mode through outbound markdown chunking so chunked sends render tables consistently. Fixes #85085. Thanks @ShuaiHui.</li>
<li>CLI/update: preserve managed Gateway service environment during package cutovers so macOS LaunchAgent repair/restart reads the pre-update service state instead of caller shell state. (#83026)</li>
<li>Agents/providers: honor per-model <code>api</code> and <code>baseUrl</code> overrides in custom provider auth hooks and transport selection. Fixes #80487. (#80488) Thanks @huveewomg.</li>
<li>Gateway/restart: eager-load the lifecycle runtime before in-place upgrade signal handling so package replacement does not deadlock restart imports. (#84890) Thanks @myps6415.</li>
<li>CLI/update: start managed Gateway update handoff helpers from a stable existing directory and tolerate deleted cwd/package roots during macOS LaunchAgent handoff. Fixes #83808. (#83875) Thanks @jason-allen-oneal.</li>
<li>Skills: watch each shared skill directory once across agent workspaces instead of once per agent, preventing file-descriptor exhaustion (<code>EMFILE</code>) that disposed bundle-mcp processes and stalled sessions on multi-agent gateways. Fixes #84968. (#85130) Thanks @openperf.</li>
<li>Release/security: keep generated npm shrinkwrap package versions inside the pnpm lock graph so published package locks cannot bypass pnpm dependency age and override policy.</li>
<li>Cron: honor <code>cron.retry.retryOn: ["network"]</code> for common network error codes such as <code>EAI_AGAIN</code>, <code>EHOSTUNREACH</code>, and <code>ENETUNREACH</code>.</li>
<li>Gateway chat: broadcast returned agent-run error payloads after an agent starts so ACP/WebChat clients receive terminal idle-timeout errors. Fixes #84945.</li>
<li>Gateway chat display: preserve OpenAI-compatible <code>prompt_tokens</code>, <code>completion_tokens</code>, and <code>total_tokens</code> usage fields in sanitized chat history so llama.cpp sessions keep context counts. Fixes #77992. Thanks @MarTT79.</li>
<li>Dashboard/CLI: allow macOS browser launching through <code>open</code> even when SSH environment variables are present, while preserving Linux SSH no-display protection. Fixes #67088. Thanks @theglove44.</li>
<li>Codex app-server: keep native web search observations out of mirrored chat transcripts while preserving tool progress telemetry. Fixes #85109. Thanks @ugitmebaby.</li>
<li>OpenCode Go: strip unsupported Kimi reasoning replay fields before provider requests so repeated <code>kimi-k2.6</code> turns do not fail schema validation. Fixes #83812. Thanks @Sleeck.</li>
<li>Browser/CDP: add a WSL2 portproxy self-loop hint when Chrome DevTools endpoints accept connections but return an empty HTTP reply. Fixes #59209. Thanks @Owlock.</li>
<li>Agents/OpenAI: preserve structured provider error code, type, and redacted body metadata on boundary-aware transport failures.</li>
<li>Doctor/Codex: point native Codex asset warnings at the canonical <code>openclaw migrate plan codex</code> preview command. Fixes #84948. Thanks @markoa.</li>
<li>CLI/models: make <code>capability model auth logout --agent</code> remove auth profiles from the selected non-default agent store. Fixes #85092. Thanks @islandpreneur007.</li>
<li>Gateway/models: reuse prepared provider auth metadata during model-listing auth checks so repeated lookups avoid broad plugin discovery while preserving synthetic local auth.</li>
<li>CLI/status: suppress systemd user-service setup hints when <code>openclaw status --deep</code> can already reach a running Gateway RPC service. Fixes #85094. Thanks @islandpreneur007.</li>
<li>CLI/devices: recover local approval when a same-device repair request replaces the request ID being approved.</li>
<li>CLI/agents: retry transient normal-close Gateway handshakes before falling back to embedded <code>openclaw agent</code> execution.</li>
<li>CLI/update: keep managed Gateway service stop/restart status lines out of <code>openclaw update --json</code> stdout so package-update automation can parse the JSON payload.</li>
<li>Plugins: resolve OpenClaw plugin SDK subpaths for native external plugin runtimes without mutating package installs or broadening process-wide module resolution.</li>
<li>Agents/OpenAI: preserve Responses and Chat Completions <code>reasoning_tokens</code> usage metadata without double-counting it in aggregate output tokens. (#85319)</li>
<li>Control UI/chat: convert pasted <code>data:image/...;base64,...</code> clipboard text into an image attachment instead of dumping the payload into the composer. Fixes #62604. Thanks @cpwilhelmi.</li>
<li>Providers/Gemini: strip fractional seconds from web-search time range filters so Gemini accepts freshness-bound search requests. (#85071) Thanks @Noerr.</li>
<li>OpenAI Codex: preserve image input support for sparse <code>openai-codex/gpt-5.5</code> catalog rows. (#85095) Thanks @sercada.</li>
<li>CLI/models: add a piped or pasted API-key path for OpenAI Codex auth and warn when API keys are pasted into token-mode auth. (#85533) Thanks @joshavant.</li>
<li>Telegram: dead-letter missing-harness isolated ingress failures so a poisoned spooled update no longer blocks later same-lane messages. Fixes #85470. (#85605) Thanks @joshavant.</li>
<li>Plugins/discovery: strip <code>-plugin</code> package suffixes when deriving plugin id hints so package names line up with manifest ids. (#85170) Thanks @JulyanXu.</li>
<li>Tlon: stop advertising a non-existent agent tool contract in the plugin manifest.</li>
<li>Telegram: preserve fenced code block languages through Markdown rendering so Telegram receives <code>language-*</code> code classes. (#85209) Thanks @leno23.</li>
<li>Windows installer: run npm and Corepack command shims from a Windows-local directory so installs launched from WSL2 UNC paths do not fail before OpenClaw is installed.</li>
<li>Windows updates: roll back git-backed updates to the previous checkout when dependency install, build, UI build, or doctor repair fails.</li>
<li>Windows installer: persist user-local portable Git on PATH and activate the repo-pinned pnpm version for git-backed installs and updates.</li>
<li>Windows installer: bootstrap a user-local portable Node.js when native Windows has no Node and no winget, Chocolatey, or Scoop, so first-run installs can continue on raw hosts.</li>
<li>Windows installer: extract the downloaded portable Node.js directory with native <code>tar</code> before falling back to .NET zip extraction, avoiding PowerShell 5.1 archive and path-length failures.</li>
<li>Agents/heartbeat: route single-owner <code>session.dmScope=main</code> direct-message exec and cron event wakes back to the agent main session so async completions no longer strand context in orphan direct-DM queues. Fixes #71581. (#83743) Thanks @Kaspre.</li>
<li>Agents/code-mode: expose outer code-mode <code>exec</code> source through the <code>command</code> hook alias with <code>toolKind</code>/<code>toolInputKind</code> discriminators so exec-shaped policies can distinguish code-mode cells. (#83483) Thanks @Kaspre.</li>
<li>Agents/code mode: return structured timeout and runtime-unavailable error codes for known worker failures. Fixes #83389. (#83444) Thanks @Kaspre.</li>
<li>QA-Lab: isolate multi-scenario suite workers when scenarios need startup config patches, preventing message-routing config from leaking into unrelated scenarios.</li>
<li>QA-Lab: make the commitments heartbeat-target-none scenario request an immediate heartbeat instead of waiting for the next scheduled heartbeat.</li>
<li>Codex/Plugin SDK: deliver Codex-native subagent completions through a generic harness task runtime so harness-backed plugins can mirror durable task lifecycle and completion delivery without Codex-specific SDK imports. (#83445) Thanks @bryanpearson.</li>
<li>Gateway CLI: surface local post-challenge connect assembly failures immediately instead of waiting for the wrapper timeout. Fixes #68944. (#85253) Thanks @samzong.</li>
<li>Messages: strip unsupported web-search citation control markers from outbound replies before they reach WebChat or external channels. Fixes #85193. (#85204) Thanks @neeravmakwana.</li>
<li>Agents/exec: treat denied exec approvals as terminal instead of feeding them back into agent follow-up work, and recognize Chinese stop phrases in abort handling. Fixes #69386. (#85194) Thanks @samzong.</li>
<li>CLI/agents: abort accepted Gateway-backed <code>openclaw agent</code> runs on SIGINT/SIGTERM so cron and supervisor timeouts do not leave remote agent work alive. Fixes #71710. (#84381) Thanks @Kaspre.</li>
<li>Codex app-server: retry replay-safe stdio client-close turns once using structured failure metadata, while surfacing idle <code>turn/completed</code> timeouts instead of blindly replaying active shared-server turns. Thanks @VACInc.</li>
<li>Codex app-server: reject command overrides that embed Node or package-manager arguments and point users to <code>appServer.args</code>, so Windows startup avoids shell parsing failures. (#84417) Thanks @TurboTheTurtle.</li>
<li>Agents/Copilot: drop unsafe GitHub Copilot Responses reasoning replay items before send so Telegram direct sessions no longer fail on overlong replay IDs. Fixes #85197. (#85198) Thanks @galiniliev.</li>
<li>UI: add accessible tooltips to the topbar color-mode buttons so System, Light, and Dark choices are labeled on hover and focus. (#85227) Thanks @amknight.</li>
<li>fix: constrain Windows task script names [AI]. (#85064) Thanks @pgondhi987.</li>
<li>Control UI: keep the chat session picker from hiding older or cross-agent configured conversations while preserving the bounded configured-agent refresh. (#85211) Thanks @amknight.</li>
<li>Agents/Anthropic: preserve unsafe integer tool-call input values in streamed Anthropic tool-use JSON, preventing Discord-style IDs from being rounded before dispatch. Fixes #47229. (#83063) Thanks @leno23.</li>
<li>Agents/Codex: estimate tool-heavy prompt pressure at the LLM boundary before provider submission, so persistent sessions compact before overflowing context windows. (#85541) Thanks @fuller-stack-dev and @joshavant.</li>
<li>Agents/hooks: wait for local one-shot CLI and Codex <code>agent_end</code> plugin hooks before process cleanup so terminal observability flushes reliably. (#85007)</li>
<li>Providers/Google: preserve Gemini 3 cron <code>thinkingDefault: "low"</code> when stale catalog metadata says <code>reasoning:false</code>, so scheduled runs keep provider-supported thinking instead of downgrading to off. (#85185) Thanks @neeravmakwana.</li>
<li>CLI/agents: allow <code>openclaw agent --session-key</code> to target explicit session keys, including agent-scoped legacy keys. (#85121) Thanks @Kaspre.</li>
<li>Auto-reply/ACP: wait for same-channel block reply delivery before starting tool work, while still honoring ACP dispatch aborts so stopped turns do not wait on slow channel sends. (#83722) Thanks @IWhatsskill.</li>
<li>Codex/ACP: mark required child-run completions that only report progress, omit a final deliverable, or fail requester delivery as blocked while preserving real final reports. (#85110) Thanks @IWhatsskill.</li>
<li>Channels: treat bare abort messages such as <code>stop</code>, <code>abort</code>, and <code>wait</code> as immediate control commands in inbound debounce paths so stop requests are not delayed behind pending message coalescing. (#83348) Thanks @IWhatsskill.</li>
<li>Channels/message tool: resolve configured external channel plugins during in-agent channel selection, so <code>openclaw agent --local</code> message-tool sends no longer report an available channel as unavailable. (#85022) Thanks @Kaspre.</li>
<li>Agents/heartbeat: honor group/channel <code>message_tool</code> visible-reply policy and model-specific Codex runtime config for scheduled heartbeat runs, so failed internal tool output stays private. Fixes #85310. (#85357) Thanks @neeravmakwana.</li>
<li>Gateway/ACP: close child ACP sessions spawned via <code>sessions_spawn</code> when their parent session is reset or deleted, instead of leaving orphaned <code>claude-agent-acp</code> processes that accumulate and exhaust memory. Fixes #68916. (#85190) Thanks @openperf.</li>
<li>Codex app-server: block native execution paths when OpenClaw exec resolves to a node host while preserving the first-party CLI node binding path. Fixes #85012. (#85534) Thanks @joshavant.</li>
<li>Diagnostics: bound cleanup timeout detail logs, emit drop summaries when async diagnostic bursts exceed the queue cap, and surface async queue drops through diagnostic telemetry.</li>
<li>Agents/subagents: surface blocked child-run completions as errors instead of successful subagent finishes. (#80886) Thanks @TurboTheTurtle.</li>
<li>Context engines: fail closed with a descriptive error when the selected agent runtime cannot satisfy declared context-engine host requirements.</li>
<li>Agents/Pi: treat accepted embedded <code>sessions_spawn</code> child-session handoffs as terminal progress so parent turns no longer report false non-deliverable failures. (#85054) Thanks @samzong.</li>
<li>CLI/models: resolve <code>openclaw models set</code> aliases from the runtime config while keeping authored aliases ahead of runtime-only defaults. (#83262) Thanks @IWhatsskill.</li>
<li>Doctor: show personal Codex CLI asset notices as info instead of warnings. Fixes #84859.</li>
<li>WhatsApp: update Baileys to <code>7.0.0-rc13</code> and drop the obsolete logger type patch.</li>
<li>CLI/update: pre-pack GitHub/git package update targets before the staged npm install, restoring <code>openclaw update --tag main</code> for one-off package updates. (#81296) Thanks @fuller-stack-dev.</li>
<li>Gateway: mirror successful same-source message-tool sends into session transcripts so delivered replies stay in later history/context. (#84837) Thanks @iFiras-Max1.</li>
<li>Media generation: keep image, music, and video completion delivery from duplicating or losing task ownership when generated media finishes through active session replies. (#84006) Thanks @fuller-stack-dev.</li>
<li>Infra/json: retry transient <code>File changed during read</code> races while loading JSON state so config and state reads recover instead of failing the turn. (#84285)</li>
<li>Plugins/providers: fail closed for workspace provider plugins during setup-mode discovery unless explicitly trusted, preventing untrusted workspace plugin code from running during provider setup. (#81069) Thanks @mmaps.</li>
<li>Providers/Ollama: resolve configured Ollama Cloud <code>OLLAMA_API_KEY</code> markers to the real discovery key so cloud provider entries keep authenticated model catalog access. (#85037)</li>
<li>Discord: keep persistent component registry fallback warnings actionable by forwarding structured error and cause metadata through the runtime logger. Fixes #84185. (#84190) Thanks @100menotu001.</li>
<li>Gateway/sessions: preserve compatible session auth profile overrides when switching models within the same provider, including provider-auth aliases. Fixes #81837. (#81886) Thanks @TurboTheTurtle.</li>
<li>Gateway/status: surface inbound delivery telemetry counters and transport-liveness warnings in <code>openclaw status --all</code>. Fixes #49577. (#72724)</li>
<li>Docker: prune package-excluded plugin source workspaces and dependency closures so runtime images do not keep packages for plugins that were not opted in.</li>
<li>Providers/Ollama: treat Docker/OrbStack host aliases as local Ollama endpoints so <code>ollama-local</code> marker auth works when OpenClaw runs inside a VM/container and Ollama runs on the host. Fixes #84875.</li>
<li>QA-Lab: keep explicitly searchable/deferred OpenClaw dynamic tool rows report-only by default so tool-coverage gates do not treat mock discovery gaps as hard product failures. (#80319) Thanks @100yenadmin.</li>
<li>Agents/config: keep non-Google provider model refs from being rewritten by Google Gemini preview-id normalization. (#84762) Thanks @zhangguiping-xydt.</li>
<li>Installer: require a real controlling terminal before launching onboarding so headless <code>curl | bash</code> installs finish cleanly after installing the CLI.</li>
<li>Agents/Codex: promote a completed final assistant response when a prompt timeout races Codex app-server completion instead of returning an empty timeout envelope. Refs #84516.</li>
<li>Codex app-server: keep interrupted turn statuses from being treated as OpenClaw aborts by themselves, so tool-only turns remain eligible for no-visible-answer recovery. Fixes #84492.</li>
<li>Agents: cap heartbeat model bleed context hints by the stored session window when runtime model metadata is unavailable, so overflow recovery advice does not suggest a larger window than the active session actually has.</li>
<li>Control UI/Web Push: use <code>https://openclaw.ai</code> as the generated default VAPID subject instead of the old localhost mailbox so iOS PWA push setup uses an Apple-acceptable subject when <code>OPENCLAW_VAPID_SUBJECT</code> is unset. Fixes #83134. (#83317) Thanks @IWhatsskill.</li>
<li>Control UI: distinguish inherited thinking-off settings from explicit Off selections so the thinking selector no longer shows two identical Off rows. (#85223) Thanks @amknight.</li>
<li>Agents/Pi: keep embedded session transcript writes from tripping false takeover detection after packaged npm onboarding agent turns.</li>
<li>Codex/TUI: surface Codex-native post-turn compaction failures instead of continuing uncompacted, and keep successful native compaction serialized before local idle/next-turn handling. Fixes #84305. (#85160) Thanks @joshavant.</li>
<li>Memory/search: stop recall tracking from writing dreaming side-effect artifacts when <code>dreaming.enabled=false</code>, while preserving normal search results. Fixes #84436. (#84444) Thanks @NianJiuZst.</li>
<li>Diffs: render viewer toolbar icons from a closed icon-name map instead of HTML strings, removing the toolbar icon XSS sink. (#83955) Thanks @tanshanshan.</li>
<li>QA: keep <code>pnpm qa:e2e</code> self-check runs inside the private QA runtime envelope even when inherited shell env disables bundled plugins.</li>
<li>Update/doctor: prune stale local bundled plugin install records that point at old compiled bundled output so current bundled plugin schemas win after upgrade. (#84863) Thanks @fuller-stack-dev.</li>
<li>Providers/Ollama: preserve native Ollama tool-call IDs across assistant replay so Gemini over Ollama Cloud can keep its hidden function-call thought-signature handle.</li>
<li>Discord: keep session recovery and <code>/stop</code> abort ownership on the source dispatch lane while bound ACP turns continue routing to their target session, so stalled pre-run work and late replies are cleared instead of leaking after stop. Fixes #84477. (#85100) Thanks @joshavant.</li>
<li>Codex app-server: mark missing turn completion after observed execution as replay-unsafe and release the session so follow-up turns can run. Fixes #84076. (#85107) Thanks @joshavant.</li>
<li>Codex app-server: give visible <code>message</code> dynamic tool sends a longer timeout budget so slow channel delivery can return its own result or error instead of hitting the 30-second Codex wrapper. (#85216) Thanks @amknight.</li>
<li>Codex app-server: add a dedicated post-tool raw assistant completion idle timeout config so trusted heavy turns can wait longer after tool handoff without weakening final assistant release.</li>
<li>Matrix: keep explicitly configured two-person rooms on the room route before stale <code>m.direct</code> or strict two-member DM fallback can bypass mention gating. Fixes #85017. (#85137) Thanks @joshavant.</li>
<li>Agents/subagents: require explicit subagent allowlist targets to be configured agents so stale deleted-agent ids are omitted from <code>agents_list</code> and rejected by <code>sessions_spawn</code>. Fixes #84811. (#85154) Thanks @joshavant.</li>
<li>PDF tool: time out idle remote PDF body reads after 120 seconds so stalled remote documents return an error instead of wedging the session. Fixes #68649. (#84768) Thanks @luoyanglang.</li>
<li>Diagnostics/OpenTelemetry plugin: suppress handled OTLP exporter promise rejections so collector shutdowns no longer crash the Gateway. (#81085) Thanks @luoyanglang.</li>
<li>Agents/exec: omit raw command text and env values from denied exec failure logs while keeping safe correlation metadata. Fixes #85049. (#85140) Thanks @joshavant.</li>
<li>Media/audio: skip empty structured sherpa-onnx transcripts instead of treating the raw JSON payload as spoken text. (#84667) Thanks @TurboTheTurtle.</li>
<li>Agents/exec: preserve inherited XDG base-directory environment values for subprocesses while still rejecting agent-supplied XDG overrides. Fixes #84854. (#85139) Thanks @joshavant.</li>
<li>Node/Linux: keep <code>OPENCLAW_GATEWAY_TOKEN</code> out of generated systemd unit files by writing node service token values to a node-specific env file. (#84408)</li>
<li>Memory-core/dreaming: reuse stable narrative subagent session keys per workspace and phase while keeping per-run idempotency and bounded cleanup, so stale <code>dreaming-narrative-*</code> sessions do not accumulate. Fixes #68252, #69187, and #70402. (#70464) Thanks @chiyouYCH.</li>
<li>Trajectory/support: tolerate partial skill snapshot entries when building support metadata so rejected skill path scans no longer abort trajectory capture. (#71185) Thanks @lukeboyett.</li>
<li>TUI: coalesce repeated idle Esc abort notices into a single <code>no active run xN</code> system row instead of appending duplicate rows.</li>
<li>Telegram: honor <code>channels.telegram.pollingStallThresholdMs</code> in the default isolated polling path, restarting silent workers instead of leaving inbound updates wedged. Fixes #83950. (#84861) Thanks @joshavant.</li>
<li>Telegram: dedupe replayed message dispatches by Telegram chat/message identity so isolated-ingress replays do not trigger duplicate model dispatches. Fixes #84886. (#85208) Thanks @joshavant.</li>
<li>Slack: suppress reasoning payloads before reply delivery and dispatch accounting, so Slack monitor, slash-command, fallback, and direct reply paths do not leak model reasoning. Fixes #84319. (#84322) Thanks @ffluk3 and @joshavant.</li>
<li>Slack: deliver native plugin approval prompts and updates when Slack native approvals are enabled, while keeping plugin approval authorization separate from exec approvers.</li>
<li>Slack: keep native plugin approval prompts in the originating app conversation thread when the live Slack turn source is a <code>D...</code> conversation.</li>
<li>Agents/Pi: disable the embedded pi-coding-agent runtime auto-retry so OpenClaw's own retry and failover loop does not replay failed tool calls through a nested SDK retry. Fixes #73781. (#74434) Thanks @yelog.</li>
<li>CLI/perf: keep <code>setup --help</code>, <code>onboard --help</code>, and <code>configure --help</code> out of the full wizard runtime while preserving the existing help output. (#84488) Thanks @frankekn.</li>
<li>CLI/perf: keep <code>agents --help</code> out of agents action/runtime imports so help, completion, and command discovery paths avoid loading the full agents runtime. (#84483) Thanks @frankekn.</li>
<li>CLI/perf: keep <code>secrets --help</code> and <code>nodes --help</code> on the precomputed help path so parent help avoids loading action-heavy command runtime modules. (#84818) Thanks @frankekn.</li>
<li>CLI/perf: serve <code>doctor</code>, <code>gateway</code>, <code>models</code>, and <code>plugins</code> parent help from startup metadata so common subcommand help avoids full CLI program construction. (#84786) Thanks @frankekn.</li>
<li>Codex/Lossless: keep context-engine history on the canonical run session when Telegram DMs use per-peer runtime policy keys. Fixes #84936. (#84954) Thanks @neeravmakwana.</li>
<li>Codex: keep heartbeat response tool schemas durable without exposing dynamic tools disabled by turn policy, so heartbeat wakeups can reuse threads while scoped tool allowlists stay enforced. (#84681) Thanks @jalehman.</li>
<li>Auth/OAuth: skip the refresh adapter when a stored OAuth credential has no refresh token so agent turns fail fast on missing-key instead of waiting on the 120s refresh timeout. Thanks @romneyda.</li>
<li>Auth/Codex: load legacy OAuth sidecar credentials in the embedded runner's secrets-runtime auth loaders so Telegram replies, cron-triggered turns, and other isolated sub-agent lanes can reach the existing #83312 refresh-and-rewrite migration instead of failing with <code>No API key found for provider "openai-codex"</code> until the user runs <code>openclaw doctor</code>. Thanks @Totalsolutionsync and @romneyda.</li>
<li>Codex/failover: classify <code>deactivated_workspace</code> as a permanent auth failure so configured fallback models can advance when a Codex workspace is deactivated. (#55893) Thanks @litang9.</li>
<li>Exec: keep configured <code>tools.exec.pathPrepend</code> entries ahead of user shell startup PATH changes on POSIX gateway runs. (#81403) Thanks @medns.</li>
<li>Gateway/sessions: allow shared-secret bearer callers to read and stream session history without an explicit scope header. (#81815) Thanks @medns.</li>
<li>Agents/embedded runner: classify HTML auth provider responses as <code>auth_html</code> and return a re-authentication hint instead of the CDN-blocked copy that <code>upstream_html</code> returns. Cloudflare Access login pages, nginx basic-auth challenges, and gateway login walls all produce HTML auth bodies that were previously misdiagnosed as transient CDN blocks. (#79900) Thanks @martingarramon.</li>
<li>TUI/streaming watchdog: dismiss the <code>This response is taking longer than expected</code> notice as soon as a chat event for the same run arrives, so the message no longer sits next to the recovered response when the run was only briefly silent. Refs #67052, #69081 (closed), prior attempt #69026. Thanks @jpruit20 and @romneyda.</li>
<li>Agents/Pi: tolerate OpenClaw-owned transcript writes while embedded prompts are released for model I/O, keeping long-running Feishu, Slack, Telegram, and cron turns from failing with false session-takeover errors. Fixes #84059. (#84250) Thanks @tianxiaochannel-oss88.</li>
</ul>
<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
<li>Exec approvals: remove the old <code>cat SKILL.md && printf ... && <skill-wrapper></code> allowlist compatibility path so skill files must be loaded with the read tool and only the real skill executable is auto-allowed.</li>
<li>Discord: let voice sessions follow configured Discord users into voice channels, with allowed-channel checks, multi-user handoff, bounded reconciliation, and DAVE recovery preservation. (#84264) Thanks @fuller-stack-dev.</li>
<li>Discord/voice: include bounded <code>IDENTITY.md</code>, <code>USER.md</code>, and <code>SOUL.md</code> profile context in realtime voice session instructions by default, with <code>voice.realtime.bootstrapContextFiles: []</code> available to disable it. (#84499) Thanks @fuller-stack-dev.</li>
<li>Dependencies: bump the bundled Codex harness to <code>@openai/codex</code> <code>0.132.0</code> and refresh the app-server model-list docs for the new catalog.</li>
<li>CLI/policy: add the bundled Policy plugin for policy-backed channel conformance checks, doctor lint findings, and opt-in workspace repair. (#80407) Thanks @giodl73-repo.</li>
<li>Agents/config: allow <code>agents.list[].experimental.localModelLean</code> so lean local-model mode can be enabled for one configured agent instead of globally.</li>
<li>Providers/xAI: add device-code OAuth login so remote and headless setups can authorize xAI without a localhost browser callback. (#84005) Thanks @fuller-stack-dev.</li>
<li>Providers/OpenRouter: honor provider-level <code>params.provider</code> routing policy for OpenRouter requests, with model and agent params overriding the defaults. Thanks @amknight.</li>
</ul>
<h3>Fixes</h3>
<ul>
<li>CLI/tasks: include stale-running task maintenance decisions in <code>openclaw tasks maintenance --json</code> so retained and reconcile candidates explain backing-session, cron, CLI, and wedged-subagent state. (#84691) Thanks @efpiva.</li>
<li>Codex app-server: keep system-prompt reports working when bootstrap hooks provide workspace files with only a path and content, so hook-supplied SOUL/IDENTITY/TOOLS/USER context still reports injected characters correctly. (#84736) Thanks @JARVIS-Glasses.</li>
<li>Providers/MiniMax music: stop advertising <code>durationSeconds</code> control and remove prompt-injected duration hints, so <code>music_generate</code> reports MiniMax duration as an unsupported override instead of suggesting MiniMax can enforce track length. Fixes #84508. Thanks @neeravmakwana.</li>
<li>Doctor: warn when sandbox tool policy hides configured MCP server tools before provider requests. (#84699) Thanks @nxmxbbd.</li>
<li>WhatsApp: update Baileys to <code>7.0.0-rc12</code>.</li>
<li>Build: suppress per-locale <code>rolldown-plugin-dts:fake-js</code> CommonJS dts warnings emitted while bundling the intentionally-inlined <code>zod/v4/locales/*.d.cts</code> files, so <code>pnpm build</code> output stays readable after the 0.25.1 plugin bump. Thanks @romneyda.</li>
<li>CLI/nodes: route lazy plugin-registration logs to stderr for JSON-mode <code>openclaw nodes</code> commands so stdout stays parseable. (#84684) Thanks @TurboTheTurtle.</li>
<li>Approvals: route manual <code>/approve</code> decisions through the trusted approval runtime so active exec and plugin approvals no longer look unknown or expired.</li>
<li>Mac app: update the About settings copyright year to 2026. (#84385) Thanks @pejmanjohn.</li>
<li>Dependencies: update <code>@openclaw/fs-safe</code> to <code>0.2.7</code> so OpenClaw's default Python-helper-off policy keeps best-effort Node write fallbacks for private stores, secret writes, run logs, and media attachments on Linux/macOS.</li>
<li>Infra/secrets: restore the fail-closed contract for <code>tryReadSecretFileSync</code> so credential loaders that pass <code>rejectSymlink: true</code> (Telegram, LINE, Zalo, IRC, Nextcloud Talk tokens) refuse symlinked credential files instead of silently accepting them, and the infra-state CI shard's secret-file symlink test passes again. Thanks @romneyda.</li>
<li>Browser: honor the configured image sanitization limit for screenshots and labeled snapshots so browser-captured images follow the same resize policy as other image results. (#84595)</li>
<li>Doctor: remove unrecognized <code>models.providers.*.models[*].compat.thinkingFormat</code> values during <code>doctor --fix</code> so stale provider model config can validate after upgrade. Fixes #77803.</li>
<li>Doctor: warn when <code>openclaw.json</code> stores plaintext secret-bearing config fields, including model provider API keys and sensitive provider headers. (#84718) Thanks @lukaIvanic.</li>
<li>Status: show the configured default, session-selected model, reason, clear hint, and docs link when a session remains pinned to a model that differs from <code>agents.defaults.model.primary</code>.</li>
<li>WebChat: clear stale typing indicators when session change events mark the active chat run complete.</li>
<li>Mac app: keep local packaging signed with a stable app identity for permission testing and fix Control UI production builds under current Vite/Highlight.js exports.</li>
<li>macOS app: update the embedded Peekaboo bridge to 3.2.1 so OpenClaw-hosted UI automation works with current Peekaboo CLI capture flows.</li>
<li>Cron: deliver preferred final assistant output for successful scheduled runs when trailing plain tool warnings remain in diagnostics instead of marking the run failed.</li>
<li>fix(mattermost): fail closed on missing channel type [AI]. (#84091) Thanks @pgondhi987.</li>
<li>CLI: keep the private QA subcommand out of exported command descriptors unless <code>OPENCLAW_ENABLE_PRIVATE_QA_CLI=1</code>, so root help and subcommand markers match runtime registration. (#84519)</li>
<li>CLI/cron: bound <code>openclaw cron show</code> job lookup pagination so non-advancing or unbounded <code>cron.list</code> responses fail instead of hanging the command. Fixes #83856. (#83989)</li>
<li>Agents/messages: stop message-tool-only turns after a successful source-channel <code>message</code> send while keeping transcript mirrors under the session write lock. (#84289)</li>
<li>Agents: filter silent heartbeat response-tool transcript artifacts out of embedded context snapshots so later user turns are not polluted by heartbeat no-op messages. (#83477) Thanks @fuller-stack-dev.</li>
<li>Agents/OpenAI: log repeated strict tool-schema downgrade diagnostics once per provider/model/tool signature, reducing duplicate debug noise while preserving <code>strict=false</code> fallback behavior. Fixes #82930. (#82933) Thanks @galiniliev.</li>
<li>Agents/code mode: spell out the <code>exec</code> tool's JavaScript/TypeScript, no Node module, and catalog-bridge constraints in model-visible schema text so agents can use enabled tools without trial-and-error. (#84269) Thanks @Kaspre.</li>
<li>Codex: give <code>image_generate</code> dynamic-tool calls a 120s default watchdog when no per-call or configured image timeout is set, so image generation no longer falls back to the generic 30s bridge timeout. (#84254) Thanks @moritzmmayerhofer.</li>
<li>Codex: avoid duplicate dynamic tool terminal diagnostics while large diagnostic backlogs drain without blocking tool responses. (#82937) Thanks @galiniliev.</li>
<li>CLI/message: include a stable top-level <code>messageId</code> in <code>openclaw message --json</code> output when channel sends return one. (#84191) Thanks @100menotu001.</li>
<li>Cron: preserve legacy top-level array <code>jobs.json</code> stores when loading or adding scheduled jobs so old cron jobs are no longer treated as an empty store during upgrade. Fixes #60799. (#84433) Thanks @IWhatsskill.</li>
<li>Gateway/agents: use an agent's <code>identity.name</code> in Gateway agent summaries when <code>agents.list[].name</code> is unset, so configured agent labels remain visible in clients. (#84355; refs #57835) Thanks @luoyanglang.</li>
<li>Channels/replies: keep normal <code>/verbose</code> failed-tool progress compact in message-tool replies and prevent late text-only tool output from appearing after the final answer. (#84303) Thanks @VACInc.</li>
<li>Plugins/hooks: apply a default 30-second timeout to <code>before_compaction</code> and <code>after_compaction</code> hooks so a hung plugin handler no longer blocks compaction completion. (#84153)</li>
<li>Discord: preserve disabled presentation buttons when adapting and rendering Discord message controls. (#84188) Thanks @100menotu001.</li>
<li>Twitch: add a test-only client-manager registry reset helper so non-isolated Twitch tests can clear cached managers between cases. Fixes #83887. (#84244) Thanks @hclsys.</li>
<li>Cron: run main-session scheduled work on a cron-owned wake lane while preserving reply delivery context, so background cron turns no longer block human main-session chat. Fixes #82766. (#82767) Thanks @galiniliev.</li>
<li>Cron: use structured embedded-run denial metadata for isolated scheduled tasks so blocked exec requests fail the job without treating ordinary assistant prose as a denial. (#84067) Thanks @abnershang.</li>
<li>Cron: keep recovered tool warnings diagnostic for successful scheduled runs so final cron output is delivered instead of being replaced by a post-processing warning. (#84045) Thanks @abnershang.</li>
<li>Plugins/perf: thread explicit plugin discovery results through <code>loadBundledCapabilityRuntimeRegistry</code>, <code>resolveBundledPluginSources</code>, and <code>listChannelCatalogEntries</code> so callers that already hold a discovery result skip redundant filesystem walks. Thanks @SebTardif.</li>
<li>Docker: keep the bundled Codex plugin in official release image keep lists so the default OpenAI agent harness remains available after Docker pruning. Fixes #83613. (#83626) Thanks @YuanHanzhong.</li>
<li>CLI/channels: preserve the first line of <code>openclaw channels logs</code> output when the rolling tail window starts exactly on a line boundary, mirroring the already-fixed <code>readLogSlice</code> behavior in <code>src/logging/log-tail.ts</code>.</li>
<li>Control UI: treat terminal session status as authoritative over stale active-run flags so completed terminal runs stop showing abort/live UI. (#84057)</li>
<li>CLI: preserve embedded equals signs in inline root option values instead of truncating after the second separator. (#83995) Thanks @ThiagoCAltoe.</li>
<li>Matrix/config: accept <code>messages.queue.byChannel.matrix</code> queue overrides and keep queue provider schema/type keys aligned for Matrix, Google Chat, and Mattermost. Thanks @bdjben.</li>
<li>CLI: format <code>openclaw acp client</code> failures through the shared error formatter so object-shaped errors stay readable instead of printing <code>[object Object]</code>. Fixes #83904. (#84080)</li>
<li>Providers/Ollama: default unknown-capabilities models to tool-capable so discovered native Ollama models can use tools when <code>/api/show</code> omits capabilities. (#84055) Thanks @dutifulbob.</li>
<li>Installer/Windows: launch <code>install.ps1</code> onboarding as an attached child process so fresh native Windows installs do not freeze visibly at <code>Starting setup...</code> or corrupt the wizard's terminal rendering.</li>
<li>CLI/update: keep restart health checks working across one-version CLI/Gateway protocol skew and use the managed Gateway service Node for all follow-up commands even when the package root is unchanged, so <code>openclaw update</code> no longer silently switches the gateway to a different Node binary when multiple Node installations are present. Thanks @amknight.</li>
<li>CLI/gateway: include the running Gateway version in <code>gateway status</code> JSON output, preserving existing server metadata while falling back to status RPC data for read probes. Fixes #56222. Thanks @galiniliev.</li>
<li>Memory/search: close local embedding providers when active-memory searches time out so pending local model loads and embedding contexts are aborted and released. (#83858) Thanks @brokemac79.</li>
<li>CLI/nodes: request pending node surface approval scopes before <code>openclaw nodes approve</code> so exec-capable node approval can use admin-scoped Gateway credentials instead of failing with <code>missing scope: operator.admin</code>. (#84392) Thanks @joshavant.</li>
<li>Gateway: reject slow node event sends before outbound buffers grow unbounded and log the rejected payload diagnostic. (#84387) Thanks @samzong.</li>
<li>Agents: include bounded trajectory queued-writer diagnostics in <code>pi-trajectory-flush</code> timeout warnings so flush stalls show pending writes, queued bytes, and append state. Fixes #82961. (#82962) Thanks @galiniliev.</li>
<li>Agents/subagents: recover stale completion announces by retrying unsupported transcript-wait wakes without transcript waiting and forcing a message-tool handoff when the requester run is already stale. Fixes #83699. (#83700) Thanks @galiniliev.</li>
<li>Agents/subagents: constrain wildcard subagent target allowlists to configured agents while preserving explicitly listed compatibility targets. Fixes #84040. (#84357) Thanks @joshavant.</li>
<li>Providers/Anthropic: route Anthropic model refs selected with Claude CLI auth through the Claude CLI runtime so shorthand refs such as <code>anthropic/opus-4.7</code> no longer fall back to embedded Anthropic billing. Fixes #84222. (#84374) Thanks @joshavant.</li>
<li>Agents: honor explicit <code>models.providers.<id>.timeoutSeconds</code> values above the default idle watchdog for cloud and self-hosted providers, so long first-token waits no longer fall back at ~120s when the provider timeout is higher. (#83979) Thanks @yujiawei.</li>
<li>Agents/Codex: keep encrypted Responses reasoning replay provenance-bound so stale mirrored Codex transcripts drop invalid encrypted content before request assembly while preserving matching same-session replay. Fixes #83836. (#84367) Thanks @joshavant.</li>
<li>Agents/subagents: skip stale embedded-run wake probes for dormant completion requesters, so late subagent completions go straight to requester-agent/direct handoff instead of producing <code>reason=no_active_run</code> queue noise. (#82964) Thanks @galiniliev.</li>
<li>CLI: retry config snapshot reads after a transient failure so one rejected read no longer poisons later commands in the same process. (#83931) Thanks @honor2030.</li>
<li>Media: decode URL path basenames before using them as remote media fallback filenames, so files like <code>My%20Report.pdf</code> are surfaced as <code>My Report.pdf</code>. Fixes #84050. (#84052) Thanks @jbetala7.</li>
<li>WhatsApp: clarify inbound group diagnostics so observed but unregistered groups point to <code>channels.whatsapp.groups</code> without changing routing or sender authorization. (#83846) Thanks @neeravmakwana.</li>
<li>WhatsApp: drain pending outbound deliveries on a 30s periodic timer in addition to the reconnect handler, so messages enqueued while the provider is already connected no longer wait for the next reconnect to send. (#79083) Thanks @Oviemudiaga.</li>
<li>CLI/TUI: include gateway plugin slash commands in TUI autocomplete, so connected sessions can suggest plugin-owned commands exposed by the running Gateway. (#83640) Thanks @se7en-agent.</li>
<li>Gateway/mobile: restore QR setup-code handoff of bounded operator tokens for iOS and Android onboarding while keeping admin and pairing scopes out of bootstrap. (#83684) Thanks @ngutman.</li>
<li>iOS: repair Release archive compilation for the TestFlight build. (#84255) Thanks @ngutman.</li>
<li>Agents/compaction: bound plugin-owned CLI transcript compaction with the host safety timeout so a hung context engine can no longer stall post-turn cleanup. (#84083) Thanks @100yenadmin.</li>
<li>Control UI/usage: truncate long context skill, tool, and file names in the usage panel while keeping the full name available on hover. (#42197) Thanks @Rain120.</li>
<li>Codex: respect explicit <code>models auth order set</code> and <code>config.auth.order</code> precedence over stale <code>lastGood</code> in <code>/codex account</code>, and show <code>no working credential</code> when every explicit-order profile is ineligible instead of marking a lower-ranked profile as active. Fixes #84386. (#84412) Thanks @openperf.</li>
<li>Agents: honor <code>messages.suppressToolErrors</code> for mutating tool failures so configured chat surfaces do not receive separate warning payloads. (#81561) Thanks @moeedahmed.</li>
<li>Agents/fallback: surface billing guidance for mixed rate-limit plus billing fallback exhaustion instead of generic failure copy. Fixes #79396. (#79489) Thanks @aayushprsingh.</li>
</ul>
<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.