Compare commits

...

461 Commits

Author SHA1 Message Date
Onur Solmaz
44e4fc2b51 fix(ui): prune persisted live tool cards 2026-06-03 11:16:32 +08:00
Onur Solmaz
c1898ef7a4 fix(ui): keep live stream below prompt 2026-06-03 11:09:26 +08:00
Onur Solmaz
38fdc4c934 fix(ui): retain stream segment tool context 2026-06-03 02:02:46 +08:00
Onur Solmaz
ccbd43262b fix(ui): pair recovered stream segments with tools 2026-06-03 01:55:00 +08:00
Onur Solmaz
e924b4f958 test(ui): update stream retention timing expectation 2026-06-03 01:47:36 +08:00
Onur Solmaz
0cd1d1808b fix(ui): retain live tools during history catchup 2026-06-03 01:40:55 +08:00
Onur Solmaz
8628fa6345 fix(ui): pair recovered streams with tools 2026-06-03 01:36:04 +08:00
Onur Solmaz
e516dda48f fix(ui): preserve stream recovery ordering 2026-06-03 01:28:18 +08:00
Onur Solmaz
a3ac037c72 fix(ui): match persisted tool block ids 2026-06-03 01:18:50 +08:00
Onur Solmaz
7b44d414a8 fix(ui): scope tool stream catch-up 2026-06-03 01:12:18 +08:00
Onur Solmaz
c42652dbf5 fix(ui): avoid duplicated source reply streams 2026-06-03 01:06:49 +08:00
Onur Solmaz
5d1e3d127a fix(ui): materialize orphaned stream segments 2026-06-03 01:00:11 +08:00
Onur Solmaz
d52bb7393a fix(ui): dedupe roleless terminal stream text 2026-06-03 00:54:45 +08:00
Onur Solmaz
9400c1a5c6 fix(ui): preserve segmented stream reloads 2026-06-03 00:49:57 +08:00
Onur Solmaz
3db9a290c2 fix(ui): avoid duplicated stream tails 2026-06-03 00:43:58 +08:00
Onur Solmaz
4baddea5b4 fix(ui): retain segmented stream text 2026-06-03 00:39:57 +08:00
Onur Solmaz
0f611fe438 fix(ui): preserve error terminal payloads 2026-06-03 00:32:40 +08:00
Onur Solmaz
e05e0fa0f4 fix(ui): clear caught-up tool streams 2026-06-03 00:28:34 +08:00
Onur Solmaz
4d993997e5 fix(ui): scope stream dedupe to current turn 2026-06-03 00:17:43 +08:00
Onur Solmaz
f3cefb8b05 fix(ui): preserve visible chat stream text 2026-06-03 00:10:57 +08:00
Vincent Koc
388dc56ba5 test(gateway): defer sidecars in tools invoke e2e 2026-06-02 17:41:19 +02:00
Vincent Koc
6c7644268f fix(test): stabilize ARM extension timer tests 2026-06-02 07:53:25 -07:00
Peter Steinberger
c8d21fe7f0 fix: recover suspicious gateway startup configs (#89480) 2026-06-02 10:12:35 -04:00
Bryan Tegomoh, MD, MPH
00d846daf7 fix(kimi): strip anthropic cache markers
Closes #76612

Co-authored-by: Bryan Tegomoh <bryan.tegomoh@gmail.com>
2026-06-02 09:59:36 -04:00
Shakker
1b9860aa56 fix: restore Skill Workshop view switcher 2026-06-02 14:59:19 +01:00
Peter Steinberger
97d4d5effb docs(changelog): note update repair stall handling 2026-06-02 14:57:01 +01:00
Peter Steinberger
12c6ef6d57 fix(update): keep plugin repair fetch failures nonblocking 2026-06-02 14:55:55 +01:00
Vincent Koc
96277245dc fix(test): isolate gateway CPU QA state 2026-06-02 15:27:16 +02:00
Peter Steinberger
eef24d452f fix(models): preserve provider prompt cache boundaries
Split Anthropic system prompts at the cache boundary so only stable prefixes get cache_control, strip the internal marker when cache control is disabled, and keep OpenAI-compatible Anthropic cache-control routes from caching dynamic suffixes.\n\nFixes #89386.
2026-06-02 09:19:52 -04:00
Peter Steinberger
c3baec7136 docs: clarify autoreview follow-up scope 2026-06-02 06:15:51 -07:00
Coder
4bb86877e2 fix(google): forward Gemini stop sequences
Forward configured stop sequences to Gemini generationConfig.stopSequences in the bundled Google transport, matching the shared Google provider behavior and the @google/genai request contract.\n\nThanks @coder999999999.
2026-06-02 09:02:27 -04:00
Coy Geek
3509f7613e fix: audit and repair hooks token reuse with Gateway auth
Keep startup non-breaking for existing installs when hooks.token reuses Gateway auth, but surface a startup warning, critical security audit finding, and doctor --fix repair that rotates persisted hooks.token.

Closes #87376.

Co-authored-by: Coy Geek <65363919+coygeek@users.noreply.github.com>
2026-06-02 08:58:40 -04:00
Vincent Koc
36c1a3e006 fix(memory): avoid optional vector status dereference 2026-06-02 14:53:35 +02:00
Vincent Koc
212eaead01 fix(memory): force provider-none indexes to FTS-only vectors 2026-06-02 14:53:35 +02:00
Vincent Koc
984c3ded9a fix(scripts): avoid dead child assignment in fd repro 2026-06-02 14:53:35 +02:00
Vincent Koc
0b7c94a5e1 fix(memory): initialize provider-none lifecycle during sync 2026-06-02 14:53:35 +02:00
Vincent Koc
0b61add479 fix(memory): report provider-none probes as FTS-only 2026-06-02 14:53:35 +02:00
Vincent Koc
2d11402208 fix(scripts): avoid spread in runtime output collection 2026-06-02 14:53:35 +02:00
Vincent Koc
f6e8a1b2a8 fix(scripts): clean memory fd temp dirs after preindex failures 2026-06-02 14:53:35 +02:00
Vincent Koc
5a4f868de0 fix(memory): scope provider-none FTS bypass 2026-06-02 14:53:34 +02:00
Vincent Koc
4115f0c82f fix(scripts): keep watch proof asset copies out of idle window 2026-06-02 14:53:34 +02:00
Vincent Koc
cd0af35e5c fix(memory): keep FTS-only sync offline 2026-06-02 14:53:34 +02:00
Alix-007
1824aa07a0 fix(mistral): enable prompt cache keys
Enable Mistral prompt cache keys without long-retention forwarding. Update cached-read pricing and doctor migration for existing Mistral provider config. Fixes #83709.
2026-06-02 08:52:12 -04:00
Peter Steinberger
5259fa4495 fix(llm): keep OpenAI-compatible reasoning streams active 2026-06-02 08:40:03 -04:00
Peter Steinberger
2ffeca1d78 docs: document Android notification picker helpers 2026-06-02 08:38:23 -04:00
NVIDIAN
895dccd058 fix(agents): gate finalize hooks before delivery
Run `before_agent_finalize` for embedded agents before terminal delivery so revise decisions can retry without leaking a final assistant reply.

The embedded subscription now defers terminal assistant events, block replies, and lifecycle delivery until the pre-terminal gate resolves; accepted revise decisions suppress delivery, while hook failures and continue decisions finalize normally. It also preserves existing replay-invalid liveness behavior while still preventing revise after side-effecting turns.

Closes #87585

Co-authored-by: ai-hpc <mail.speedy.hpc@hotmail.com>
2026-06-02 08:27:36 -04:00
Peter Steinberger
06434d85a0 fix(llm): gate OpenAI-compatible reasoning output
Replaces #89343 because the contributor fork did not allow maintainer edits.

Co-authored-by: zz327455573 <327455573@qq.com>
2026-06-02 08:24:34 -04:00
Peter Steinberger
a326faa10c fix: recover corrupt managed npm installs 2026-06-02 05:21:19 -07:00
Peter Steinberger
6467ddd7ed fix(qqbot): migrate state stores to sqlite kv
Move QQBot credential backups, gateway sessions, known-user records, and ref-index rows into plugin SQLite KV stores. Import shipped JSON/JSONL state files on first use and keep auxiliary known-user/ref-index state best-effort so message delivery is not blocked by cache persistence failures.
2026-06-02 08:15:19 -04:00
Peter Steinberger
95880ae21c fix: align auth health status after Codex sidecar merge 2026-06-02 05:14:52 -07:00
Vincent Koc
d830e4affc fix(testing): probe plugin CLI help while installed 2026-06-02 14:01:18 +02:00
兰之
10d10faa25 feat(plugin-sdk): add resolve_exec_env hook
Summary:
- Add the plugin SDK `resolve_exec_env` hook for bounded exec environment contributions.
- Wire resolved exec env through exec preparation/final execution without exposing plugin env values to generic tool hooks.
- Cover lazy exec loading, host and command rewrites, node/gateway execution, filtering, and EXEC shell snapshot cache behavior.

Verification:
- `pnpm changed:lanes --json`
- `node scripts/run-vitest.mjs src/agents/bash-tools.exec.resolve-env-hook.test.ts src/agents/agent-tool-definition-adapter.test.ts src/agents/agent-tool-definition-adapter.after-tool-call.test.ts src/agents/shell-snapshot.test.ts src/plugins/hook-resolve-exec-env.test.ts`
- `pnpm check:test-types`
- `pnpm lint src/agents/bash-tools.exec.ts src/agents/bash-tools.exec.resolve-env-hook.test.ts`
- `.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main`
- PR CI clean on 1bbad8d071: https://github.com/openclaw/openclaw/actions/runs/26817910293

Co-authored-by: Lanzhi <lizhan3@xiaomi.com>
2026-06-02 08:00:42 -04:00
Andy Ye
e992af4b6e fix: surface unresolved OAuth sidecar auth failures
Surface stale Codex OAuth sidecar references as unresolved auth failures in auth health, model status, and gateway status instead of hiding them as generic missing auth.

Also refresh the running gateway after doctor auth-profile repairs by reloading secrets/runtime auth snapshots and then refreshing the model auth-status cache.

Thanks @TurboTheTurtle.

Fixes #84252.
2026-06-02 07:56:14 -04:00
Yzx
b1bdc29d33 fix(providers): use native reasoning mode for Gemini instead of tagged (#89379)
* fix(providers): use native reasoning mode for direct Gemini API, keep CLI tagged

Gemini 2.5+ delivers reasoning via native thinkingParts (thinkingConfig.
includeThoughts). Having tagged mode active at the same time injects a
<think>…</think>/<final>…</final> directive into the system prompt; the
model opens a <think> block before a tool call, never closes it, and
returns an empty post-tool turn (content:[], payloads=0 error, #69220).

Fix: override resolveReasoningOutputMode in buildGoogleProvider() only —
not in the shared GOOGLE_GEMINI_PROVIDER_HOOKS. The Gemini CLI backend
(google-gemini-cli) runs gemini --output-format json and parses a text
response field, not native thought parts; it must stay on tagged mode.
A regression test confirms google-gemini-cli remains "tagged".

Also remove the dead BUILTIN_REASONING_OUTPUT_MODES entry keyed on
"google-generative-ai" from provider-utils.ts — that string is only
ever the transport model.api value, never the provider id passed to
resolveReasoningOutputMode, so the map was unreachable.

Fixes #69220

* docs: clarify Gemini reasoning output modes

* fix(google): keep Antigravity reasoning tagged

* fix(google): default direct reasoning checks to native

* fix(google): import reasoning context from plugin entry

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-06-02 07:46:08 -04:00
Sebastien Tardif
e7aac172d5 fix(codex): clear stale context-engine projection after overflow retry
Fixes #88355.

When a resumed Codex context-engine thread overflows and OpenClaw retries on a fresh native thread, clear the stale thread-bootstrap projection metadata from the fresh binding. This prevents later turns from treating that fresh thread as already projected when it only received the bare retry prompt.

Verification:
- Autoreview clean: no accepted/actionable findings reported.
- CI run 26717883204 green on head 5438f8ad34.
2026-06-02 07:33:48 -04:00
Vincent Koc
4b7f39e406 refactor(gateway): derive connection auth options 2026-06-02 13:24:17 +02:00
Vincent Koc
335c3a8d31 refactor(gateway): share node agent dispatch 2026-06-02 13:24:17 +02:00
Vincent Koc
fd6b3255f8 refactor(gateway): share embedding remote options 2026-06-02 13:24:17 +02:00
Dirk
355cbc5071 fix(google): add missing gemini-3.1-flash-lite to google-vertex catalog (#89400)
* fix(google): add gemini-3.1-flash-lite to provider catalog

Adds the missing gemini-3.1-flash-lite model definition to the
GOOGLE_GEMINI_TEXT_MODELS array. This resolves the ProviderFailoverError
when configuring google-vertex/gemini-3.1-flash-lite.

Fixes #89390

* test(google): cover Gemini flash lite catalog row

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-06-02 07:21:50 -04:00
Peter Steinberger
b4dfa950b5 refactor: tighten agent harness surfaces
Refactor the agent harness surface after PR #88821 by moving compaction dispatch into its own module, splitting the harness type into explicit capability interfaces, and renaming the private agent-core class declaration to `CoreAgentHarness` while preserving the exported `AgentHarness` contract.

Verification:
- `node scripts/run-vitest.mjs src/agents/harness/selection.test.ts src/agents/command/cli-compaction.test.ts src/agents/embedded-agent-runner/compact.hooks.test.ts packages/agent-core/src/agent-loop.test.ts packages/agent-core/src/harness/messages.test.ts`
- `pnpm build`
- autoreview clean
- `pnpm check:changed` passed on Testbox `tbx_01kt407hq8sv1csm287pdj3fmp`
- PR CI merge state `CLEAN`
2026-06-02 07:20:43 -04:00
Mukunda Rao Katta
2d61521bd3 fix(update): pin post-core plugin compatibility to the downgraded core version (#87914) (#87952)
* fix(update): pin post-core plugin compatibility to the downgraded core version (#87914)

* fix(update): force plugin compatibility repair on rollback

* style(update): clarify downgrade compatibility note

* fix(plugins): resolve compatible prerelease plugin downgrades

* fix(plugins): honor host gates during npm downgrade repair

* fix(plugins): keep prerelease downgrade fallback on channel

---------

Co-authored-by: Gio Della-Libera <giodl73@gmail.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-06-02 07:13:26 -04:00
Dallin Romney
30b9e123b8 fix: repeat doctor state migration repairs
Stabilize repeated `openclaw doctor --fix` state repairs for legacy plugin state and installed plugin index migrations.

- Import legacy-only plugin-state sidecar rows before deciding whether live conflicts require keeping the sidecar.
- Drop expired sidecar rows only when the sidecar can be archived, avoiding repeated false migration changes.
- Let richer current install records cover legacy records only when durable legacy fields are actually preserved, without erasing npm selector intent or malformed legacy metadata.

Proof:
- `node scripts/run-vitest.mjs src/commands/doctor-state-migrations.test.ts`
- `git diff --check origin/main...HEAD`
- `.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main`
- PR CI clean for head `5f3a7e0749372a40cabd7a090cae155997481b71`

Co-authored-by: Dallin Romney <dallinromney@gmail.com>
2026-06-02 07:13:02 -04:00
Coy Geek
a14be505ff fix(qqbot): isolate credential backups by state root
QQBot credential backups now resolve under the active OpenClaw state directory instead of the old home-global QQBot data path. This keeps isolated gateway profiles from restoring each other's QQBot appId/clientSecret backups while preserving per-state-root recovery.

Proof: focused QQBot path/storage-laziness Vitest suite passed on Node 24.15.0, focused oxlint passed, source-runtime two-root backup proof passed, exact-head CI run 26814565282 passed, and ClawSweeper re-review run 26815054980 marked proof sufficient.

Closes #84313.

Co-authored-by: Coy Geek <65363919+coygeek@users.noreply.github.com>
2026-06-02 07:11:01 -04:00
charles-openclaw
2c48dd2277 fix(sessions): preserve corrupt-header transcripts
Fixes #89037.

Co-authored-by: Charles <charles-openclaw@9bcfae.inboxapi.ai>
2026-06-02 07:02:09 -04:00
Hussein Nourelddine
4a285d529a feat(status): detect external plugin version drift
Surface active official external plugin version drift in gateway status diagnostics so users can see when a host/package update left npm or ClawHub plugins behind the running local gateway. The advisory uses the daemon service install records, compares against the running gateway version, gives detailed fix commands in deep status, and avoids local-state drift checks for remote gateway mode or explicit status probe URLs.

Co-authored-by: Hussein Nourelddine <hussein@gptc.com.kw>
2026-06-02 06:59:23 -04:00
Vincent Koc
07821e4bb8 refactor(gateway): share secret ref input resolution 2026-06-02 12:52:02 +02:00
Vincent Koc
4bae78858f refactor(gateway): share runtime service helpers 2026-06-02 12:52:02 +02:00
Andy Ye
1db2c2a3e0 Treat soft plugin repair warnings as nonfatal (#84431)
* Treat soft plugin repair warnings as nonfatal

* fix: scope plugin repair convergence failures

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-06-02 06:51:11 -04:00
NVIDIAN
eb417bc672 fix(messages): preserve inbound audio for message-tool TTS
Preserve inbound-audio context for message-tool TTS across embedded reply runs, CLI MCP loopback, and queued follow-up paths.

Thanks @ai-hpc.

Co-authored-by: ai-hpc <mail.speedy.hpc@hotmail.com>
2026-06-02 06:45:34 -04:00
Peter Steinberger
5d6216a7f1 fix: detect shrinkwrapped npm installs
Fixes status/update detection for npm-installed OpenClaw packages that ship npm-shrinkwrap while preserving pnpm and Bun install ownership.

Fixes #87732.
Supersedes #88283.

Proof: focused infra Vitest shard, autoreview clean, Crabbox install matrix, and PR CI all green.
2026-06-02 06:39:22 -04:00
Bek
bce3d5bf92 trace: Correlate channel diagnostics into one trace
Correlates channel receive, agent lifecycle, model attempt diagnostics, and outbound delivery diagnostics into one trace waterfall so channel message runs can be inspected end-to-end.

Maintainer follow-up removed the internal `AgentHarnessV2` adapter surface and kept the harness path canonical through `src/agents/harness/lifecycle.ts`.

Proof:
- PR checks passed on `04e9189c15480d53663d533a04c9883164b4dd54`.
- `node scripts/run-vitest.mjs src/agents/harness/lifecycle.test.ts src/agents/harness/selection.test.ts src/channels/turn/kernel.test.ts`
- `pnpm check:changed` Testbox `tbx_01kt3xtrm70qc7nb90cqv5rah1`

Thanks @bek91.

Co-authored-by: Bek <bek.akhmedov@gmail.com>
2026-06-02 06:38:00 -04:00
LiLan0125
ad9f7f9a59 fix(diagnostics): requeue stuck session lane after recovery
Reset the session command lane when stuck-session recovery aborts and drains a ghost embedded run but queued lane work remains. This preserves pending user messages by using the existing lane recovery pump instead of leaving them stranded after recovery reports success.

Adds focused regression coverage for the abort=true, drained=true, queuedCount=1 path.

Fixes #89208.
Supersedes #89293.
Thanks @LiLan0125.

Co-authored-by: 李兰 0668001394 <li.lan3@xydigit.com>
2026-06-02 06:36:19 -04:00
Gio Della-Libera
a25338f2b7 fix(discord): accumulate reasoning progress deltas
Fix Discord progress-mode reasoning streams so delta chunks accumulate before display formatting, preserving raw Thinking/Reasoning-prefixed content and balanced truncation.\n\nFixes #83983.\n\nThanks @giodl73-repo for the fix and live Discord proof.
2026-06-02 06:35:29 -04:00
Bek
6997453098 fix: guard in-band macOS launchd stop
Summary:
- guard macOS launchd stop/restart against in-band service relaunch loops
- centralize current-service detection for launchd stop and restart handoff
- preserve external launchd label stop overrides while fixing inherited XPC restart handoff

Verification:
- node scripts/run-vitest.mjs src/daemon/launchd.test.ts src/daemon/launchd-current-service.test.ts src/daemon/launchd-restart-handoff.test.ts
- .agents/skills/autoreview/scripts/autoreview --mode local
- pnpm check:changed via Blacksmith Testbox through Crabbox: tbx_01kt3xkmfqhnzghfxdn62fa8qm

Closes #89174

Co-authored-by: Bek <bek.akhmedov@gmail.com>
2026-06-02 06:27:36 -04:00
Vincent Koc
c35fda3cfa refactor(gateway): derive websocket runtime params 2026-06-02 12:20:48 +02:00
Vincent Koc
8ea6b5d5b2 fix(scripts): clean package-boundary prep process groups 2026-06-02 12:15:53 +02:00
NVIDIAN
a02a7aaddb fix(codex): trace app-server thread lifecycle timing
Fixes #84640.
2026-06-02 06:11:58 -04:00
Pavan Kumar Gondhi
19fb9f1299 fix: redact trajectory exports consistently (#89354)
* fix trajectory export redaction

* fix trajectory export top-level redaction

* fix trajectory export key redaction

* fix trajectory export structural key redaction
2026-06-02 15:41:44 +05:30
兰之
2664f59519 fix(cron): reject blank delivery targets
Reject whitespace-only cron delivery target strings before cron input normalization can trim and drop them, so bad delivery targets return INVALID_REQUEST instead of behaving as omitted fields.

Keep explicit null update clears for delivery, failure destination, and completion destination fields.

Co-authored-by: gaozixiang1 <gaozixiang1@xiaomi.com>
Co-authored-by: Lanzhi <lizhan3@xiaomi.com>
2026-06-02 06:10:19 -04:00
兰之
1cca70940c fix: hide sessions_spawn timeout overrides
Remove model-facing per-call timeout overrides from sessions_spawn while keeping operator-controlled timeout behavior through agents.defaults.subagents.runTimeoutSeconds.

Reject stale camelCase and snake_case timeout arguments, update ACP/native timeout propagation, refresh docs and prompt snapshots, and cap ACP runtime option timeouts to the ACP control-plane maximum without shortening gateway dispatch or registry tracking.

Proof:
- node --import tsx - runtime probe against src/agents/tools/sessions-spawn-tool.ts
- node scripts/run-vitest.mjs src/agents/tools/sessions-spawn-tool.test.ts src/agents/acp-spawn.test.ts src/agents/openclaw-tools.subagents.sessions-spawn.lifecycle.test.ts
- pnpm docs:list
- git diff --check origin/main...HEAD
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
- .agents/skills/autoreview/scripts/autoreview --mode local
- GitHub checks: 132 pass, 30 skipped

Co-authored-by: Lanzhi <lizhan3@xiaomi.com>
Co-authored-by: chenhaoqiang <chenhaoqiang@xiaomi.com>
2026-06-02 06:09:02 -04:00
兰之
43d0aaec3d fix(agents): honor provider idle timeout for unlimited runs
Honor explicit provider/model request timeoutSeconds when the agent run timeout is the no-timeout sentinel, and keep explicit run timeout overrides from being capped by agent defaults.

Verification:
- pnpm test src/agents/embedded-agent-runner/run/llm-idle-timeout.test.ts -- --reporter=verbose
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
- CI run 26812803642 passed on the rebased PR head
- Real behavior proof run 26812917801 passed after maintainer proof override

Co-authored-by: zhongqiongbo1 <zhongqiongbo1@xiaomi.com>
Co-authored-by: Lanzhi <lizhan3@xiaomi.com>
2026-06-02 06:08:56 -04:00
Vincent Koc
5487855815 refactor(gateway): share talk relay session lifecycle 2026-06-02 11:57:08 +02:00
Vincent Koc
45f7aec156 refactor(gateway): share transcript path comparison 2026-06-02 11:57:08 +02:00
Vincent Koc
286c8e3632 fix(build): parallelize startup metadata rendering 2026-06-02 11:50:49 +02:00
Vincent Koc
e24582d53c fix(crabbox): preflight sparse sync disk space 2026-06-02 11:42:14 +02:00
Vincent Koc
3e9b197bd0 test(gateway): share node invoke acknowledgement 2026-06-02 11:24:01 +02:00
Vincent Koc
601ab84f35 test(gateway): share configured global session stores 2026-06-02 11:13:36 +02:00
clawsweeper[bot]
abc3fa0396 fix(memory-core): keep startup cron retries quiet (#89075)
Summary:
- The branch adds a memory-core `startup_retry` reconciliation mode and regression tests for quiet startup retries, retry-window exhaustion, and live-config retry semantics.
- PR surface: Source +9, Tests +114. Total +123 across 2 files.
- Reproducibility: yes. from source: current main routes the first startup retry through runtime reconciliatio ... st expects the warn-level `cron service unavailable` log. I did not execute tests in this read-only review.

Automerge notes:
- Ran the ClawSweeper repair loop before final review.
- Included post-review commit in the final squash: fix(memory-core): keep startup cron retries quiet

Validation:
- ClawSweeper review passed for head 7220f940d0.
- Required merge gates passed before the squash merge.

Prepared head SHA: 7220f940d0
Review: https://github.com/openclaw/openclaw/pull/89075#issuecomment-4592446250

Co-authored-by: bennewell35 <newelljben@gmail.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>
2026-06-02 09:09:52 +00:00
Ayaan Zaidi
db576c4a2d refactor(agents): trim native compaction ownership follow-up 2026-06-02 14:39:35 +05:30
Cameron Beeley
5e52a9b513 docs(cli-backends): document ownsNativeCompaction opt-out contract 2026-06-02 14:39:35 +05:30
Cameron Beeley
3d7523b618 feat(agents): generalized native compaction ownership for CLI backends
Add `ownsNativeCompaction` capability to CliBackendPlugin so backends
that manage their own transcript compaction (e.g. Claude Code) can
declare it once and OpenClaw defers instead of fighting or failing.

Today only Codex declares compaction ownership (via the embedded runner
path + agentHarnessId). Claude-cli never reaches that path because it
runs as a CLI subprocess with no harness id set, so the safeguard
summarizer fires and hard-fails the turn.

This PR:
- Adds `ownsNativeCompaction?: boolean` to the backend plugin type
- Propagates it through all 4 backend resolution paths
- In `runCliTurnCompactionLifecycle`, when a backend declares ownership
  but has no harness endpoint, returns a no-op instead of falling
  through to the safeguard
- Sets the flag on claude-cli (first adopter)

Codex's existing native-harness path is unchanged: when
`isNativeHarnessCompactionSession` matches, the harness compaction
endpoint is still called as before.

Generalizes the partial fix in #87785 (codex-scoped) to a capability
any backend can opt into.
2026-06-02 14:39:35 +05:30
Vincent Koc
afbf895af0 test(gateway): share runtime state fixture 2026-06-02 10:55:01 +02:00
Vincent Koc
af9bad9fe7 fix(gateway): avoid sync Control UI asset reads 2026-06-02 10:53:31 +02:00
Vincent Koc
3995d57797 refactor(gateway): share fast-path secrets prepare args 2026-06-02 10:44:55 +02:00
Vincent Koc
dcf21ac3ad fix(e2e): isolate release scenario mock state 2026-06-02 10:42:22 +02:00
Vincent Koc
e128efa13a fix(e2e): isolate OpenAI web search smoke logs 2026-06-02 10:34:44 +02:00
Vincent Koc
7f1c991e44 fix(scripts): forward wrapper hangup signals 2026-06-02 10:23:18 +02:00
Vincent Koc
a682e64813 refactor(gateway): share plugin install diff walk 2026-06-02 10:15:06 +02:00
Ayaan Zaidi
e31f351923 fix(android): classify updated system apps 2026-06-02 13:44:45 +05:30
Tosko4
5f505236a6 docs(android): document device apps command 2026-06-02 13:44:45 +05:30
Tosko4
3d1ec37129 feat(android): add installed apps node command 2026-06-02 13:44:45 +05:30
Vincent Koc
6c8e065e3b test(gateway): share scheduled service activation setup 2026-06-02 09:59:09 +02:00
Vincent Koc
cd3887c28a fix(scripts): cancel timed-out response bodies 2026-06-02 09:49:02 +02:00
Vincent Koc
92d363773e test(gateway): reuse record assertions in artifact tests 2026-06-02 09:39:01 +02:00
Vincent Koc
4d3411349b test(gateway): reuse deferred helper in lane tests 2026-06-02 09:28:53 +02:00
Vincent Koc
5912b9e738 fix(gateway): return mcp oversized body errors 2026-06-02 09:25:38 +02:00
Vincent Koc
64d01ff8a8 test(gateway): share deferred helper 2026-06-02 09:12:31 +02:00
Vincent Koc
06f973dd4f test(gateway): share record assertion helpers 2026-06-02 09:02:54 +02:00
Sliverp
0552ec899f fix(qqbot): allow RFC2544 benchmark range for token fetch (#88984) (#89015)
* fix(qqbot): allow RFC2544 benchmark range for token fetch (#88984)

QQ Bot `bots.qq.com` token-fetch path was failing for users whose DNS resolver maps the hostname into the RFC 2544 benchmark range `198.18.0.0/15` (commonly seen with fake-IP proxy stacks: sing-box, Clash, Surge, WSL2 DNS). The default SSRF guard treats that range as private and blocks the request, surfacing as "Network error getting access_token: Blocked: resolves to private/internal/special-use IP address".

Pass a host-scoped `SsrFPolicy` (`allowRfc2544BenchmarkRange: true`) to the single hard-coded `TOKEN_URL` request, mirroring the existing `QQBOT_MEDIA_SSRF_POLICY` pattern used by the media path. Because `TOKEN_URL` is a const and not user-controlled, the relaxation cannot widen attack surface to other hosts.

Adds a regression test asserting `policy: { allowRfc2544BenchmarkRange: true }` is forwarded into `fetchWithSsrFGuard`, and updates the existing equality assertion accordingly.

Fixes #88984

* fix(qqbot): scope token ssrf policy
2026-06-02 15:00:39 +08:00
Vincent Koc
f37ce4ed9b fix(gateway): report pending drain pruning revisions 2026-06-02 08:55:47 +02:00
Dallin Romney
20e0d068a7 fix: bundle private llm core declarations (#89336) 2026-06-01 23:51:38 -07:00
Vincent Koc
c0400397df test(gateway): share agent image request helpers 2026-06-02 08:38:48 +02:00
Peter Steinberger
732d6972d7 fix: repair model provider edge cases
Repairs a batch of narrow model/provider edge cases:

- honor OpenAI and Anthropic base URL environment overrides when provider config does not set an explicit base URL
- preserve OpenRouter Anthropic cache retention while stripping unsupported transport options
- allow apply_patch for non-OpenAI providers when the tool config otherwise permits it
- prune stale same-provider model selections from configure/model picker state
- expose GitHub Copilot bundled thinking policy metadata to offline/provider-policy lookups
- repair additive SQLite shared-state upgrades for existing databases
- keep same-size rotated log readers from reusing stale content in CI tooling

Proof:

- GitHub PR checks green on exact head 46514909b0
- Crabbox delegated Blacksmith Testbox tbx_01kt3em5r9vd7g0bnykrff6jdk exited 0
- Focused local Vitest/oxlint/format proof recorded in PR body and land-ready comment

Fixes #80347.
Fixes #88357.
Fixes #45269.
Supersedes #74427, #74432, #79370, #79894, #80366, and #88359.
2026-06-02 02:35:12 -04:00
Vincent Koc
438eb26d39 fix(ci): keep crabbox sync checkouts alive 2026-06-02 08:29:50 +02:00
Vincent Koc
fd1e314e59 test(gateway): share boot run helpers 2026-06-02 08:23:03 +02:00
Onur Solmaz
a4b4fed412 fix(memory): validate memory index identity
* docs: add memory index identity plan

* fix(memory): validate memory index identity

* fix(memory): align status index identity with vector probe

* fix(memory): fail closed on stale fts-only search

* fix(memory): clear sessions-only identity reindex dirty state

* fix(memory): gate targeted session sync by index identity

* fix(memory): clear resolved index identity dirtiness

* fix(memory): block search on missing index identity

* fix(memory): preserve dirty events during identity reindex

* fix(memory): resolve provider aliases for index identity

* fix(memory): report missing identity states accurately

* fix(memory): mark missing session index identity dirty

* test(memory): expose provider alias resolver in mocks

* chore(memory): remove scratch implementation plan

* fix(memory): avoid automatic full reindex on provider cutover

* docs(memory): plan no-schema cutover repair

* fix(memory): pause vector search on index identity mismatch

* fix(memory): freeze dirty identity sync writes

* fix(memory): skip paused-index search retry

* test(memory): keep retry tests on same provider identity

* fix(memory): surface paused index recall

* chore(memory): remove scratch plan from pr

* fix(memory): preserve paused session dirtiness

* fix(memory): make paused recall warning explicit

* docs(memory): document explicit index repair
2026-06-02 14:22:25 +08:00
Abner Shang
5be282e459 fix(backup): accept root-relative hardlink targets (#89328) 2026-06-01 23:09:21 -07:00
Vincent Koc
4df832412e fix(ci): normalize macos crabbox locale 2026-06-02 08:06:54 +02:00
Vincent Koc
3901f48b0e test(gateway): share channel health fixtures 2026-06-02 07:57:14 +02:00
Vincent Koc
85d2dd8ed2 refactor(gateway): share session history snapshot build 2026-06-02 07:46:38 +02:00
Vincent Koc
46bd5ebd11 refactor(gateway): share realtime tool result broadcast 2026-06-02 07:37:52 +02:00
Vincent Koc
5c93de3e7f refactor(gateway): share hook dispatch session policy 2026-06-02 07:28:31 +02:00
Vincent Koc
b579c0a65b fix(llm): normalize streaming json args 2026-06-02 07:24:19 +02:00
Vincent Koc
94adfc8d10 test(gateway): share node catalog fixtures 2026-06-02 07:13:17 +02:00
Vincent Koc
6883351085 fix(e2e): detect same-size log rotation 2026-06-02 07:11:57 +02:00
Vincent Koc
93fd17447a fix(talk): preserve null lifecycle payloads 2026-06-02 07:05:05 +02:00
Vincent Koc
ebf20241bd test(gateway): share deferred test helper 2026-06-02 06:53:31 +02:00
Vincent Koc
16808524cb refactor: share mcp loopback scope params 2026-06-02 06:44:47 +02:00
Vincent Koc
58de2b689f fix(nodes): preserve falsy event payloads 2026-06-02 06:39:00 +02:00
Vincent Koc
55467f0b94 refactor: share config write response flow 2026-06-02 06:32:06 +02:00
Vincent Koc
6ba25c10dc fix(build): cap tsdown heap on native Windows 2026-06-02 06:25:27 +02:00
Vincent Koc
3419cf5a0d fix(codex): preserve null sandbox rpc results 2026-06-02 06:23:53 +02:00
Peter Steinberger
265926aa47 fix: honor channel model overrides in agent ingress 2026-06-02 00:20:21 -04:00
clawsweeper[bot]
63ed9adfe9 fix(auto-reply): guard missing dispatcher getFailedCounts without weakening the SDK type (#89318)
Summary:
- Adds defensive failed-count reads in auto-reply/ACP accounting and Feishu fallback paths, plus a focused regression test, while keeping `ReplyDispatcher.getFailedCounts` required.
- PR surface: Source +24, Tests +35. Total +59 across 5 files.
- Reproducibility: yes. from source inspection. Current main calls `dispatcher.getFailedCounts().final` and si ... issing that method follows a clear TypeError path; the source PR also supplied terminal before/after proof.

Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(auto-reply): guard missing dispatcher getFailedCounts without wea…

Validation:
- ClawSweeper review passed for head 0bdfb4adeb.
- Required merge gates passed before the squash merge.

Prepared head SHA: 0bdfb4adeb
Review: https://github.com/openclaw/openclaw/pull/89318#issuecomment-4598624344

Co-authored-by: Alix-007 <li.long15@xydigit.com>
Co-authored-by: Claude Opus 4.8 <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>
2026-06-02 04:16:58 +00:00
Vincent Koc
e6b5083660 refactor: share gateway misc test helpers 2026-06-02 06:15:56 +02:00
WJzz1
6349af6502 docs: add ClawHub CLI page (#89297)
Summary:
- Adds `docs/clawhub/cli.md` documenting OpenClaw skill/plugin ClawHub commands plus standalone ClawHub publish, sync, and transfer workflows.
- PR surface: Docs +82. Total +82 across 1 file.
- Reproducibility: not applicable. this is a docs-only missing-route repair rather than a runtime bug. Source  ... rrent main lacks `docs/clawhub/cli.md` while navigation and existing docs already reference `/clawhub/cli`.

Automerge notes:
- PR branch already contained follow-up commit before automerge: docs: add ClawHub CLI page
- PR branch already contained follow-up commit before automerge: fix(clawsweeper): address review for automerge-openclaw-openclaw-8929…

Validation:
- ClawSweeper review passed for head 11e071c344.
- Required merge gates passed before the squash merge.

Prepared head SHA: 11e071c344
Review: https://github.com/openclaw/openclaw/pull/89297#issuecomment-4598332147

Co-authored-by: Wang-Yeah623 <205193123+Wang-Yeah623@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>
2026-06-02 04:13:50 +00:00
Vincent Koc
ffbd02fe8e fix(agents): preserve null node payloads 2026-06-02 06:03:06 +02:00
Vincent Koc
75bc80bb42 refactor: share exec approval iOS push fixtures 2026-06-02 06:02:15 +02:00
Vincent Koc
1e7a0d8987 refactor: share startup auth test helpers 2026-06-02 05:47:24 +02:00
Vincent Koc
39f319c7a4 fix(e2e): preserve gateway null payloads 2026-06-02 05:44:37 +02:00
Vincent Koc
7c4fb1bd2c refactor: share session search test helpers 2026-06-02 05:42:38 +02:00
Vincent Koc
7d5d62511f fix(e2e): preserve null rpc results 2026-06-02 05:33:07 +02:00
Vincent Koc
cc6a6f5682 refactor: share readiness test fixtures 2026-06-02 05:32:25 +02:00
Vincent Koc
7a8d307bdc refactor: share node invoke approval test helpers 2026-06-02 05:24:23 +02:00
Peter Steinberger
b7d363cadf fix(agents): bypass stale auth for plugin harnesses
Explicit non-Codex plugin harness runtimes now bypass stale OpenClaw provider auth cooldowns before harness startup, while Codex/OpenClaw and missing-harness gates remain fail-closed. Fixes #85105.
2026-06-01 23:22:54 -04:00
Vincent Koc
68b4dd1816 fix(crabbox): serialize macos node bootstrap 2026-06-02 05:21:16 +02:00
Vincent Koc
0e16e72091 refactor: share session reset hook test helpers 2026-06-02 05:16:03 +02:00
Peter Steinberger
9ead0ae921 fix: repair live model inference edge cases
Fix live model inference edge cases across provider streaming, model switching, outbound delivery, and gateway tool resolution.

Includes live/provider issue fixes and leaves #89100 explicitly partial for the remaining FM-2 group routing case.
2026-06-01 23:03:27 -04:00
Vincent Koc
3128ec9858 refactor: share gateway probe test helpers 2026-06-02 04:59:36 +02:00
Vincent Koc
1ec291c682 fix(ios): require explicit gateway log target 2026-06-02 04:52:50 +02:00
Vincent Koc
9d9a6140a3 refactor: share sessions list changed test helpers 2026-06-02 04:48:54 +02:00
Vincent Koc
674bd6fc93 fix(mac): isolate build run logs 2026-06-02 04:47:00 +02:00
Peter Steinberger
b2a55a282a fix(update): do not fail core update on plugin repair fetch 2026-06-02 03:42:54 +01:00
Vincent Koc
3cf4c1ad69 refactor: share connect policy test helpers 2026-06-02 04:38:59 +02:00
Vincent Koc
fa9ce6ea0e fix(mac): isolate dmg resize limits 2026-06-02 04:32:38 +02:00
Vincent Koc
0f1f1a1fd7 refactor: share startup config recovery test helpers 2026-06-02 04:29:40 +02:00
Vincent Koc
d944aaa9ec fix(test): reject retired live shard 2026-06-02 04:20:53 +02:00
Vincent Koc
baade28397 refactor: share subagent delivery context test helpers 2026-06-02 04:20:09 +02:00
Vincent Koc
883c0f1254 fix(mac): scope restart log by worktree 2026-06-02 04:11:23 +02:00
Vincent Koc
793ab78ebb refactor: share cron validation test helpers 2026-06-02 04:08:21 +02:00
Peter Steinberger
57ea5aff81 test(release): expect cheap docker preflight 2026-06-02 03:03:48 +01:00
Vincent Koc
f1d65b3cd6 fix(e2e): isolate trash shim bin dir 2026-06-02 04:01:47 +02:00
Vincent Koc
e6b951a6a6 refactor: share operator approval client test setup 2026-06-02 03:58:27 +02:00
Vincent Koc
55e9194a4c perf(scripts): avoid duplicate build cache input hashing 2026-06-02 03:50:19 +02:00
Vincent Koc
8929838159 refactor: share gateway credentials test fixtures 2026-06-02 03:49:48 +02:00
Peter Steinberger
a355c8897d ci(release): keep docker preflight cheap 2026-06-02 02:48:41 +01:00
Vincent Koc
b06dc17537 refactor: share gateway e2e test setup 2026-06-02 03:40:29 +02:00
Vincent Koc
7967a3582c fix(e2e): isolate onboard gateway logs 2026-06-02 03:39:10 +02:00
Vincent Koc
2e6016fdec fix(ci): keep crabbox pnpm hydrate off tmpfs 2026-06-02 03:38:51 +02:00
Peter Steinberger
8a1a8ea8a3 ci(release): wait out live provider rate limits 2026-06-02 02:38:22 +01:00
Vincent Koc
4608f7dcf9 refactor: share probe auth test fixtures 2026-06-02 03:29:33 +02:00
Vincent Koc
49ac93bda6 refactor: share talk session response helpers 2026-06-02 03:20:00 +02:00
Peter Steinberger
f6653b9b35 fix(ci): retry live Docker image pulls 2026-06-02 02:08:26 +01:00
Vincent Koc
2f92fddef0 refactor: share node invoke wake test helpers 2026-06-02 03:02:03 +02:00
Vincent Koc
489efc8f5e refactor: share device token authz test fixtures 2026-06-02 02:58:38 +02:00
Vincent Koc
459abfc26b fix(e2e): isolate plugin sweep scratch files 2026-06-02 02:50:41 +02:00
Vincent Koc
340cc2c1e4 refactor: share session history test fixtures 2026-06-02 02:41:09 +02:00
Vincent Koc
be8cb5d4ea refactor: share agent wait dedupe test fixtures 2026-06-02 02:37:48 +02:00
Vincent Koc
222ade9fa6 fix(e2e): clean kitchen sink sweep state 2026-06-02 02:29:52 +02:00
Peter Steinberger
6667b9734a fix(ci): avoid rg dependency in changelog gate 2026-06-02 01:29:15 +01:00
Vincent Koc
ebbb2e8f01 refactor: share handshake auth helper test fixtures 2026-06-02 02:20:52 +02:00
Vincent Koc
dea3e835c5 refactor: share channel health policy test fixtures 2026-06-02 02:16:09 +02:00
Peter Steinberger
722af385d2 test(release): accept gateway schema rejection wrapper 2026-06-02 01:10:00 +01:00
Vincent Koc
dacd18a8aa refactor: share chat attachment test helpers 2026-06-02 02:00:15 +02:00
Vincent Koc
8a9acd2940 test(mac): exercise codesign entitlement use 2026-06-02 01:56:24 +02:00
Vincent Koc
bd8353dbaa fix(testing): fail plugin gauntlet on failed qa summaries 2026-06-02 01:52:00 +02:00
Vincent Koc
3baf78dd0a refactor: share node invoke approval test helpers 2026-06-02 01:51:08 +02:00
Vincent Koc
1ed7692d2f test(changelog): exercise attribution gate policy 2026-06-02 01:46:34 +02:00
Omar Shahine
12798eb789 fix(agents): avoid duplicate generated media fallback (#89220)
Treat targetless current-chat message-tool media telemetry as delivered for generated-media completion dedupe while preserving fallback delivery for mismatched provider/account/thread evidence.

Real behavior proof was added from the live iMessage generated-image run: inbound id 5805, exactly one outgoing media reply id 5806, and no follow-up generated-image fallback.

Co-authored-by: omarshahine <10343873+omarshahine@users.noreply.github.com>
Reviewed-by: @lobster
2026-06-01 16:46:14 -07:00
Omar Shahine
02192bd27f fix(imessage): keep typing active during tool work (#88948)
Keep iMessage native typing indicators alive through long tool-running gaps by bridging tool-start activity into the existing typing controller, while preserving typingMode and sendPolicy suppression semantics.

Real behavior proof was added from the live iMessage generated-image run: inbound id 5805, outgoing media reply id 5806, and requester-observed typing during the 84s tool path.

Co-authored-by: omarshahine <10343873+omarshahine@users.noreply.github.com>
Reviewed-by: @lobster
2026-06-01 16:45:46 -07:00
Vincent Koc
086274fd7e test(e2e): exercise onboard wizard exit status 2026-06-02 01:38:46 +02:00
Vincent Koc
ed07a7a2de refactor: share node pairing authz test setup 2026-06-02 01:33:11 +02:00
Vincent Koc
829fb5dcb3 fix(e2e): clean generated docker client state 2026-06-02 01:30:10 +02:00
Peter Steinberger
4c6285e8ff test(release): retry google tool-read failovers 2026-06-02 00:26:55 +01:00
Vincent Koc
7c52969d49 fix(e2e): clean plugin fixture servers on timeout 2026-06-02 01:17:08 +02:00
Vincent Koc
42d3acfc99 refactor: share ios approval push delivery 2026-06-02 01:09:58 +02:00
Vincent Koc
32f98d7fe8 fix(e2e): forward sighup in node watchdogs 2026-06-02 01:05:29 +02:00
Vincent Koc
4bd7421182 refactor: share gateway auth request guards 2026-06-02 00:56:06 +02:00
Vincent Koc
d91d8ff060 refactor: share chat abort test setup 2026-06-02 00:47:43 +02:00
Vincent Koc
af44fb9b6c fix(test): preserve vitest batch wrapper signals 2026-06-02 00:46:55 +02:00
Vincent Koc
45e0545e82 refactor: share gateway shutdown abort helpers 2026-06-02 00:44:16 +02:00
Peter Steinberger
2d17cb295d fix(discord): use libopus structured decode errors 2026-06-01 23:43:31 +01:00
Peter Steinberger
e8120a72e1 ci(release): retry quiet node shard stalls 2026-06-01 23:43:03 +01:00
Dallin Romney
0904f3e553 revert: undo gateway memory watch warning (#89246) 2026-06-01 15:32:42 -07:00
Vincent Koc
2770aa5f4c fix(scripts): clean boundary step process groups 2026-06-02 00:29:22 +02:00
Vincent Koc
285401ced8 refactor: share cli session history test helpers 2026-06-02 00:25:39 +02:00
Vincent Koc
64697fbe24 chore(release): add matrix plugin changelog 2026-06-02 00:23:41 +02:00
Vincent Koc
e9aae26b22 fix(test): clean live wrapper children 2026-06-02 00:19:53 +02:00
Vincent Koc
cb12a9af94 refactor: share node pairing request test helpers 2026-06-02 00:17:07 +02:00
Peter Steinberger
65d7fa2420 fix(memory): reattach Linux watchers on directory rename
(cherry picked from commit 0db7781514cc84fac4f3a999d24b4b747fc871f9)
2026-06-01 23:15:00 +01:00
Peter Steinberger
bd4a7f4119 fix(discord): classify corrupt opus packets structurally 2026-06-01 23:14:23 +01:00
Vincent Koc
14f61d0637 fix(test): clean delegated vitest runners 2026-06-02 00:09:20 +02:00
Vincent Koc
0f3a63b12e refactor: share preauth hardening test helpers 2026-06-02 00:07:53 +02:00
Peter Steinberger
a14eacf372 chore(release): set version 2026.6.2 2026-06-01 23:06:55 +01:00
Colin
646df2da83 fix skill workshop filtered fallback 2026-06-01 23:00:40 +01:00
Colin
211321ce5c address skill workshop review comments 2026-06-01 23:00:40 +01:00
Colin
a34e822cd4 fix skill workshop filtered navigation 2026-06-01 23:00:40 +01:00
Colin
8c180c9153 fix(ui): render skill workshop tab 2026-06-01 23:00:40 +01:00
Vincent Koc
990f0baff9 fix(e2e): scope gateway cleanup to tracked pid 2026-06-01 23:59:03 +02:00
Peter Steinberger
bd8baeb323 perf(gateway): narrow plugin lookup memo key 2026-06-01 22:58:46 +01:00
Vincent Koc
0771bbbd20 refactor: share discovery runtime test setup 2026-06-01 23:50:24 +02:00
Vincent Koc
74cf5c7e7d refactor: share session permission client setup 2026-06-01 23:48:17 +02:00
Vincent Koc
0cfd6b0504 fix(e2e): clean timed-out docker harness containers 2026-06-01 23:45:56 +02:00
Peter Steinberger
4e45010203 ci(release): fail fast on red release children
(cherry picked from commit 8d7038775f0a0a1bb5354ba6b6b708c6b2c3167b)
2026-06-01 22:42:53 +01:00
Vincent Koc
afdf9aaea0 refactor: share talk config test helpers 2026-06-01 23:34:51 +02:00
Vincent Koc
72ed2121f8 fix(scripts): guard delayed docker package kills 2026-06-01 23:33:00 +02:00
Dallin Romney
2405bbcbaf fix(memory): warn on gateway watcher FD risk (#89185)
* fix(memory): default gateway memory watch off

* fix(memory): warn on gateway watcher fd risk

* fix(config): avoid warning helper narrowing

* fix(config): remove redundant warning boolean cast

* docs(memory): clarify watcher default wording

* docs(memory): simplify watcher warning copy

* fix(config): scope watcher warning to local gateway
2026-06-01 14:23:25 -07:00
Vincent Koc
403190572b fix(e2e): isolate release media memory artifacts 2026-06-01 23:19:47 +02:00
Vincent Koc
67983a00c8 refactor: share session reset model test helpers 2026-06-01 23:12:52 +02:00
Vincent Koc
61aa499b53 test(scripts): trap test-state temp homes 2026-06-01 23:09:58 +02:00
Vincent Koc
420450b5cb fix(ci): timeout dependency guard GitHub requests 2026-06-01 22:59:55 +02:00
Kevin Lin
f8491b0fcf enhance(slack): route plugin approvals through native UI
Route Slack plugin approval delivery through the shared native approval route gates while preserving Slack Block Kit buttons and plugin resolver semantics.

Verification: Slack/native approval unit tests, Slack QA Lab, and live clawd native plugin approval via Slack desktop.
2026-06-01 13:55:59 -07:00
Vincent Koc
98e943ebdd refactor: share voicewake model test helpers 2026-06-01 22:53:29 +02:00
Vincent Koc
f8d5f162a1 fix(ui): terminate child on wrapper shutdown 2026-06-01 22:37:25 +02:00
Vincent Koc
a2fdd5bc70 refactor: share session delete lifecycle test helpers 2026-06-01 22:31:06 +02:00
Vincent Koc
2af2111ae0 refactor: share session history test helpers 2026-06-01 22:28:14 +02:00
Vincent Koc
c9d35c7172 fix(scripts): forward run-with-env termination 2026-06-01 22:24:34 +02:00
Dallin Romney
50b69e16dc fix(agents): dispatch auth failures by type (#89181) 2026-06-01 13:23:05 -07:00
Vincent Koc
fe97c6000c refactor: share browser auth test helpers 2026-06-01 22:19:07 +02:00
Dallin Romney
a99cbf29bd test: reset gateway timers at test boundaries (#89212) 2026-06-01 13:13:08 -07:00
Vyctor H. Brzezowski
05ea36a81f docs: refresh ClawHub showcase cards (#88734) 2026-06-01 13:08:56 -07:00
Vincent Koc
eb58c88598 refactor: share model catalog test helpers 2026-06-01 21:58:49 +02:00
Dallin Romney
5a67c5c556 fix(memory-core): reduce Linux watcher fan-out (#89188)
* fix(memory-core): reduce Linux watcher fan-out

* fix(memory-core): satisfy watcher type and lint checks

* fix(memory-core): harden Linux watcher subtree races
2026-06-01 12:54:30 -07:00
NianJiu
5a55135146 fix(memory): retry transient FileProvider-backed reads (#85351) 2026-06-01 12:40:20 -07:00
Vincent Koc
193988bc5b fix(e2e): isolate onboard temp artifacts 2026-06-01 21:25:03 +02:00
Vincent Koc
a20f57bf2e refactor: share startup auth test assertions 2026-06-01 21:16:55 +02:00
Vincent Koc
66f797b22c fix(e2e): wait for plugin update registry cleanup 2026-06-01 21:01:26 +02:00
Vincent Koc
65a805ac28 fix(e2e): harden web search cleanup 2026-06-01 20:35:33 +02:00
Vincent Koc
b18bab0bcc refactor: share session kill http test fixtures 2026-06-01 20:35:08 +02:00
Alexzhu
9ac30b587e Keep machine-readable CLI startup output parseable (#88689)
Constraint: CLI startup progress can render before Commander resolves a command's JSON output contract.

Rejected: Leaving Clack on its default stdout | contaminates JSON stdout when startup progress appears.

Confidence: high

Scope-risk: narrow

Directive: Keep progress output off stdout before full command parsing for machine-readable invocations.

Tested: git diff --check origin/main; OPENCLAW_HEAVY_CHECK_LOCK_SCOPE=worktree OPENCLAW_VITEST_MAX_WORKERS=1 node scripts/run-vitest.mjs src/cli/progress.test.ts src/cli/run-main.exit.test.ts; source CLI sessions --json parse proof.

Not-tested: broad pnpm check.
2026-06-01 11:33:22 -07:00
Peter Steinberger
82de264710 test(release): tolerate MiniMax portal nonce drift 2026-06-01 19:30:46 +01:00
Vincent Koc
7f7f0775ed fix(testing): keep crabbox sync checkouts durable 2026-06-01 20:30:08 +02:00
Vincent Koc
30819ed3da refactor: share http endpoint test scaffolding 2026-06-01 20:25:40 +02:00
Vincent Koc
1c3095e029 test(deps): clean dependency evidence temp roots 2026-06-01 20:20:42 +02:00
Vincent Koc
62cfc613f1 refactor: share startup early test inputs 2026-06-01 20:17:30 +02:00
Dallin Romney
64a946ac21 fix(agents): actionable copy for exhausted auth-profile failover (#85798)
* fix(agents): actionable copy for exhausted auth-profile failover

The pi-embedded runner threw a generic "No available auth profile for
<provider> (all in cooldown or unavailable)" message whenever every
configured profile was in cooldown, even though the failover machinery
had already resolved a concrete reason (auth, billing, rate_limit,
session_expired, etc.). The user-facing copy never used that reason and
never told the user how to recover.

Route the resolved reason through a single presenter
(`formatAuthProfileFailureMessage`) that composes a reason-specific
sentence with `buildProviderAuthRecoveryHint`, so FailoverError.message
ships with the right `openclaw models auth login --provider <id>` hint
when the cause is authentication/session/billing, and falls back to the
underlying provider error text otherwise. Helper moved out of
`src/commands/` into `src/agents/` because `src/agents/` cannot depend
on `src/commands/`.

* fix(agents): soften auth-profile failure copy for non-technical users

* refactor(agents): drop guidance re-export shim and de-brittle failure-copy tests

- Delete `src/commands/provider-auth-guidance.ts` and point doctor-auth, auth-choice.model-check, and models/list.status-command directly at `src/agents/provider-auth-recovery-hint.ts`. The cold-imports test moves with it.
- Rewrite `failure-copy.test.ts` to assert behavior (recovery-hint dispatch, provider mention, cause-suffix dedup) instead of pinning exact long copy strings, so wording tweaks no longer require a test update in two places.
2026-06-01 11:16:25 -07:00
Vincent Koc
96187089d4 refactor: share session history message fixtures 2026-06-01 20:05:18 +02:00
Vincent Koc
965e680603 test(control-ui): clean i18n timeout temp dirs 2026-06-01 20:03:05 +02:00
Vincent Koc
1cf39a2d6f refactor: table-drive lifecycle state tests 2026-06-01 19:57:35 +02:00
Vincent Koc
92b3d52e8a fix(e2e): isolate release media temp files 2026-06-01 19:56:05 +02:00
Dallin Romney
8ba6dfeaf6 fix(ci): restore dist cache before artifact builds (#89169) 2026-06-01 10:55:27 -07:00
Peter Steinberger
bddcf4448c fix(subagents): rotate steered restart sessions 2026-06-01 18:50:36 +01:00
Vincent Koc
c8a67768e3 fix(e2e): require expected web search rejection 2026-06-01 19:49:11 +02:00
Vincent Koc
26e61b2087 refactor: share single-row cache test helpers 2026-06-01 19:48:19 +02:00
Vincent Koc
ee48028028 fix(dev): clean tui pty watch children 2026-06-01 19:40:42 +02:00
Vincent Koc
3c324590ae refactor: share compaction checkpoint test helpers 2026-06-01 19:33:41 +02:00
Vincent Koc
ba88b7a178 fix(e2e): clean plugin lifecycle temp state 2026-06-01 19:27:04 +02:00
Vincent Koc
d767e296e2 refactor: share plugin node auth test helpers 2026-06-01 19:26:59 +02:00
Vincent Koc
83cd3cbe2a fix(e2e): bound bundled plugin lifecycle commands 2026-06-01 19:18:26 +02:00
Vincent Koc
16807824cc refactor: share node invoke approval test helpers 2026-06-01 19:18:14 +02:00
Dallin Romney
e3d24faecd fix: allow admins to approve dependency guard (#88966)
* fix: allow admins to approve dependency guard

* fix: auto-bypass trusted dependency authors
2026-06-01 10:17:14 -07:00
Peter Steinberger
469bec97ef test(codex): keep live subagent smoke lightweight 2026-06-01 18:09:48 +01:00
Vincent Koc
101db565ca refactor: share startup plugin test helpers 2026-06-01 19:09:39 +02:00
Vincent Koc
ef26e8dfce fix(repro): clean webchat tts proof artifacts 2026-06-01 19:04:12 +02:00
Vincent Koc
25c19e013a refactor: share startup memory test helpers 2026-06-01 19:00:26 +02:00
Vincent Koc
f2eea90dac fix(e2e): bound cron mcp probe waits 2026-06-01 18:52:13 +02:00
Vincent Koc
3113fe95ea refactor: share startup secrets test helpers 2026-06-01 18:49:58 +02:00
Vincent Koc
4e1f8b8ac7 fix(e2e): clean timed-out runtime commands 2026-06-01 18:43:25 +02:00
Vincent Koc
0b8f6b81e6 refactor: share probe request dispatch helper 2026-06-01 18:35:38 +02:00
Vincent Koc
ab1042d115 refactor: share talk transcription relay test setup 2026-06-01 18:34:05 +02:00
Peter Steinberger
9153aab037 fix(codex): abort app-server thread startup cleanly 2026-06-01 17:33:00 +01:00
Vincent Koc
285a792aa8 refactor: share maintenance test fixtures 2026-06-01 18:25:54 +02:00
Vincent Koc
a8bc1716dd fix(usage): skip empty timeseries scans 2026-06-01 18:20:52 +02:00
Vincent Koc
373ef81e83 refactor: share codex harness model assertions 2026-06-01 18:12:11 +02:00
Vincent Koc
c053b90290 refactor: share shared auth rotation test helpers 2026-06-01 18:10:57 +02:00
Pavan Kumar Gondhi
fbdf593778 fix: bound remote media reference reads [AI] (#88974)
* fix: bound remote media reference reads

* fix: remove unreachable video timeout wiring

* test: cover remote video reference handoff
2026-06-01 21:35:40 +05:30
Vincent Koc
488b65ab87 refactor: share session reset test helpers 2026-06-01 18:00:39 +02:00
Peter Steinberger
6668eb8225 test(codex): drop unused live harness helper 2026-06-01 16:56:48 +01:00
Vincent Koc
72436217ff fix(e2e): isolate MCP channel client temp state 2026-06-01 17:51:04 +02:00
Peter Steinberger
460cf7ed75 test(codex): avoid sessions list wait in live harness start probe 2026-06-01 16:49:20 +01:00
Vincent Koc
461999c060 fix(dev): clean Telegram flow previews on failure 2026-06-01 17:37:15 +02:00
Vincent Koc
9cb347e4c3 fix(dev): close gateway smoke websocket on failures 2026-06-01 17:26:15 +02:00
Vincent Koc
1d7e5f48ed fix(dev): close stalled gateway websocket handshakes 2026-06-01 17:18:40 +02:00
Vincent Koc
1fd2259e28 refactor: share config patch test helpers 2026-06-01 17:15:48 +02:00
Peter Steinberger
3f54d150b3 test(openrouter): stabilize music timeout clamp assertion 2026-06-01 16:09:23 +01:00
Vincent Koc
a9866a405c test(agents): align provider auth alias fixtures 2026-06-01 17:08:31 +02:00
Vincent Koc
0b9187c780 test(gateway): fix node invoke capture race 2026-06-01 17:08:31 +02:00
Vincent Koc
b1ec23e05f fix(e2e): escalate stuck PTY children 2026-06-01 17:07:42 +02:00
Vincent Koc
050f0c0af6 refactor: share device pair authz test helpers 2026-06-01 16:58:10 +02:00
Vincent Koc
dfeb5b81ca fix(e2e): harden Parallels helper cleanup 2026-06-01 16:57:27 +02:00
Vincent Koc
d9f6e03e32 refactor: share silent reconnect test helpers 2026-06-01 16:54:10 +02:00
Peter Steinberger
fed7d1f385 test(release): stabilize beta validation regressions 2026-06-01 15:47:56 +01:00
Vincent Koc
0a9e594420 fix(scripts): clean Anthropic prompt probe temp state 2026-06-01 16:47:27 +02:00
Sally O'Malley
c1ce51546e fix(ui): clear chat composer after send (#89106) 2026-06-01 10:42:35 -04:00
Vincent Koc
1b928592ef refactor: share startup recovery test helpers 2026-06-01 16:37:09 +02:00
Vincent Koc
12087ac9d4 test(e2e): exercise Parallels smoke cleanup path 2026-06-01 16:33:11 +02:00
Peter Steinberger
00caead80a test: close oxlint signal readiness race 2026-06-01 10:26:08 -04:00
Peter Steinberger
4b54a423f0 test: harden changed-gate assertions 2026-06-01 10:26:08 -04:00
Peter Steinberger
bdd6cf3d5e test: stabilize order-sensitive assertions 2026-06-01 10:26:08 -04:00
Peter Steinberger
cb7a4239ef fix: stabilize full-suite regressions 2026-06-01 10:26:08 -04:00
Peter Steinberger
b226a752a1 test: stabilize slow shard regressions 2026-06-01 10:26:08 -04:00
Vincent Koc
110f7d55e3 fix(scripts): clean Z.AI fallback repro temp state 2026-06-01 16:25:05 +02:00
Vincent Koc
645c7dc40b refactor: share gateway misc test helpers 2026-06-01 16:18:22 +02:00
Vincent Koc
a4847297b8 fix(ci): clean check-changed pnpm shim temp dirs 2026-06-01 16:16:26 +02:00
Vincent Koc
4253517070 refactor: share node allowlist test helpers 2026-06-01 16:14:59 +02:00
Peter Steinberger
e8c126eaf2 fix(ci): use QA runtime build for release checks 2026-06-01 15:12:50 +01:00
Peter Steinberger
2075d19923 test(gateway): scope lazy server mock 2026-06-01 15:12:50 +01:00
Vincent Koc
9e58ef1c82 test(scripts): clean session log temp roots 2026-06-01 16:00:41 +02:00
Vincent Koc
eaeccf5fdf refactor: share node registry system run test helpers 2026-06-01 16:00:36 +02:00
Vincent Koc
2c0e835b48 test(codex): clean up fake timer spies 2026-06-01 14:57:47 +01:00
Vincent Koc
b942a958b3 test(qa): cover QA lab help runtime boundary 2026-06-01 15:54:16 +02:00
Vincent Koc
42bcf9cd0b fix(test): keep runtime tests raw-sync safe 2026-06-01 15:53:37 +02:00
Vincent Koc
a0fbb6cfe2 fix(test): keep app parity checks sparse safe 2026-06-01 15:53:37 +02:00
Vincent Koc
408fa6e951 fix(test): stabilize watch-node shutdown tests 2026-06-01 15:53:37 +02:00
Vincent Koc
671909d6d3 refactor: share server aux reload test helpers 2026-06-01 15:51:05 +02:00
Vincent Koc
409f78a1ea fix(e2e): clean OTEL collector startup failures 2026-06-01 15:46:02 +02:00
Vincent Koc
3e592a8bd7 refactor: share mcp http loopback test helpers 2026-06-01 15:39:28 +02:00
Vincent Koc
e895479a21 fix(ci): fail gateway watch spawn errors promptly 2026-06-01 15:38:16 +02:00
Peter Steinberger
930bc9691b fix(ci): page CI timing job reads 2026-06-01 14:33:39 +01:00
Vincent Koc
b9f181635f fix(ci): fail gateway CPU spawn errors 2026-06-01 15:27:13 +02:00
Vincent Koc
c2aaf8afec refactor: share sessions patch test helpers 2026-06-01 15:17:55 +02:00
Vincent Koc
cbc5f277bb refactor: share session reset hook test helpers 2026-06-01 15:11:10 +02:00
Vincent Koc
44b388f863 fix(e2e): keep kitchen-sink process snapshots wide 2026-06-01 15:09:33 +02:00
Vincent Koc
c0e49a2c52 fix(e2e): catch runtime package-manager descendants 2026-06-01 14:58:39 +02:00
Peter Steinberger
c1e132195d test(release): activate manifest channels in bundle smoke 2026-06-01 13:51:38 +01:00
Vincent Koc
5bd8dbd0b8 refactor: share system run approval test helpers 2026-06-01 14:44:46 +02:00
Vincent Koc
421ea1f458 fix(e2e): bound Parallels host VM commands 2026-06-01 14:41:46 +02:00
Vincent Koc
1f91e97353 refactor: share startup secrets test helpers 2026-06-01 14:31:58 +02:00
Vincent Koc
d4f6e0a1f2 fix(docs): clean link audit temp docs 2026-06-01 14:26:21 +02:00
Peter Steinberger
ec2455a842 test(memory): drive timeout tests with explicit fake clocks
(cherry picked from commit d75eea53c9)
2026-06-01 13:12:07 +01:00
Vincent Koc
1742f3f77c refactor: share mcp http test helpers 2026-06-01 14:10:41 +02:00
Vincent Koc
5117f457bb fix(ci): clean gateway watch temp home 2026-06-01 14:09:58 +02:00
Vincent Koc
8fe5e83462 refactor: share sessions list changed test helpers 2026-06-01 14:00:20 +02:00
Vincent Koc
27097bed65 fix(ci): bound deadcode knip scan 2026-06-01 13:57:16 +02:00
Vincent Koc
1849a86dd2 refactor: share session history revocation helpers 2026-06-01 13:47:39 +02:00
Vincent Koc
5280d1d95d fix(e2e): stream Parallels phase logs 2026-06-01 13:46:21 +02:00
Vincent Koc
bcdc93d651 refactor: share auth compat backend scope assertion 2026-06-01 13:31:03 +02:00
Vincent Koc
0751b6f2c9 fix(e2e): bound upgrade survivor config commands 2026-06-01 13:30:23 +02:00
Peter Steinberger
7d9fae5b3a fix(memory): keep embedding timeout watchdog active
(cherry picked from commit 591f310869)
2026-06-01 12:29:27 +01:00
Vincent Koc
a595aba60e refactor: share sessions send result assertions 2026-06-01 13:21:09 +02:00
Vincent Koc
75645aec08 fix(e2e): clean Telegram proof child processes 2026-06-01 13:20:03 +02:00
Vincent Koc
d10d71cdb6 fix(codex): stabilize app-server cleanup tests 2026-06-01 13:15:05 +02:00
Vincent Koc
c69a8d633d perf(control-ui): hydrate chat startup state
Add a combined chat.startup gateway method for Control UI startup hydration so first chat load can receive history and agents in one RPC, while falling back to chat.history for older/unadvertised gateways. Verified with focused UI/gateway tests, tsgo/oxlint/diff checks, clean autoreview, and Testbox changed gate tbx_01kt1dt6fqdtdbprsk48z8fn71.
2026-06-01 12:14:19 +01:00
Vincent Koc
d8ebbedf45 refactor: share plugin http auth request assertions 2026-06-01 13:10:09 +02:00
Peter Steinberger
9ed1766696 test(whatsapp): align direct last-route envelope
(cherry picked from commit 5d902b0f20)
2026-06-01 12:04:51 +01:00
Vincent Koc
bed0fb7bad refactor: share session resolve assertions 2026-06-01 13:00:51 +02:00
Vincent Koc
db6fc20559 fix(e2e): clean Windows background smoke timeouts 2026-06-01 12:55:15 +02:00
Vincent Koc
1364acbe4c refactor: share gateway http stage error assertions 2026-06-01 12:45:20 +02:00
Vincent Koc
d2988e0248 refactor: share preview resolve alias fixtures 2026-06-01 12:42:30 +02:00
Vincent Koc
8c8c8c8e32 perf(control-ui): prioritize first connect startup (#89030)
* perf(control-ui): prioritize first connect startup

* fix(control-ui): close connect timing gaps

* fix(control-ui): default embeds strict before bootstrap

* fix(control-ui): keep bootstrap identity deferred

* fix(control-ui): gate startup chat on bootstrap

* fix(control-ui): restore composer after hello

* fix(control-ui): restore drafts before hello
2026-06-01 11:41:22 +01:00
Vincent Koc
8bee3be90a fix(e2e): bound Parallels fresh lanes 2026-06-01 12:34:29 +02:00
Vincent Koc
87d890003d refactor: share shutdown drain session setup 2026-06-01 12:31:32 +02:00
Peter Steinberger
aed7de306e fix(qa-matrix): detect sqlite dedupe commits by payload
(cherry picked from commit 2fc497e67b)
2026-06-01 11:27:10 +01:00
Vincent Koc
859cb52b44 refactor: share unauthorized response assertions 2026-06-01 12:22:58 +02:00
Vincent Koc
4685a84e9b fix(e2e): bound bundled runtime gateway cleanup 2026-06-01 12:19:37 +02:00
Vincent Koc
f30235bed2 test: fix gateway test type fixtures 2026-06-01 12:13:36 +02:00
Vincent Koc
4f8f6c7693 refactor: share thinking e2e session setup 2026-06-01 12:13:36 +02:00
Peter Steinberger
055063f06b fix(qa-matrix): read sqlite inbound dedupe state 2026-06-01 11:07:53 +01:00
Vincent Koc
dac33c8ecb fix(e2e): cap pty transcript output 2026-06-01 11:49:58 +02:00
Vincent Koc
75ebf1c870 refactor: share device token authz test helpers 2026-06-01 11:49:06 +02:00
Vincent Koc
e4a32b9e8e lint(e2e): remove redundant channel fallback 2026-06-01 11:38:28 +02:00
Vincent Koc
22e3b2e94e fix(dev): wait for watch-node shutdown 2026-06-01 11:38:28 +02:00
Peter Steinberger
729420c34a test: split slow vitest shards 2026-06-01 05:34:59 -04:00
Peter Steinberger
0b5be66ef7 perf(gateway): trim startup plugin planning work 2026-06-01 10:33:28 +01:00
Peter Steinberger
8e28c773fe chore(release): prepare 2026.6.1 2026-06-01 10:30:15 +01:00
Vincent Koc
2dcb681f38 refactor: share session search test fixtures 2026-06-01 11:28:59 +02:00
Peter Steinberger
e733774e3c fix(test): repair telegram prerelease blockers 2026-06-01 10:26:12 +01:00
Mason Huang
004835f4c7 fix(plugins): block untrusted workspace setup-only channel loads (#86953)
Summary:
- This PR blocks disabled workspace-origin channel plugins from setup-only scoped imports, rejects their channel registrations at registry assembly, documents the trust rule, and adds regression coverage.
- PR surface: Source +46, Tests +610, Docs +13. Total +669 across 22 files.
- Reproducibility: yes. source inspection gives a high-confidence reproduction path: current main's setup-only ... ce channel plugin can be imported before this PR. I did not run the repro locally in this read-only review.

Automerge notes:
- PR branch already contained follow-up commit before automerge: test(plugins): cover workspace channel registry guard
- PR branch already contained follow-up commit before automerge: fix(plugins): isolate setup channel registration errors
- PR branch already contained follow-up commit before automerge: fix(channels): mark raw catalog listing internal
- PR branch already contained follow-up commit before automerge: test(channels): cover trusted catalog filtering
- PR branch already contained follow-up commit before automerge: test(channels): mock raw catalog helper
- PR branch already contained follow-up commit before automerge: docs(changelog): credit setup channel hardening

Validation:
- ClawSweeper review passed for head 11438bc1a0.
- Required merge gates passed before the squash merge.

Prepared head SHA: 11438bc1a0
Review: https://github.com/openclaw/openclaw/pull/86953#issuecomment-4545730044

Co-authored-by: masonxhuang <masonxhuang@tencent.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Mason Huang <masonxhuang@tencent.com>
Co-authored-by: Sebastien Tardif <sebtardif@ncf.ca>
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: hxy91819
Co-authored-by: hxy91819 <8814856+hxy91819@users.noreply.github.com>
2026-06-01 09:25:56 +00:00
Vincent Koc
97d373ff37 perf(ui): speed up first global chat sends
Speed up Control UI first global chat sends by letting safe literal-global startup refresh use the fresh hello default before agents.list finishes, while keeping stale carried/cached agent ids out of that fast path. Adds chat history/send and gateway chat.send timing markers for the next latency pass.
2026-06-01 10:25:22 +01:00
Vincent Koc
3119f08009 fix(scripts): bound shrinkwrap npm commands 2026-06-01 11:23:20 +02:00
Peter Steinberger
9d55fc4579 fix(plugins): skip peer links in rollback snapshots 2026-06-01 10:18:30 +01:00
Vincent Koc
2bac970abc refactor: share node invoke policy test setup 2026-06-01 11:17:38 +02:00
Vincent Koc
f8e9ba3718 fix(codex): prevent aborted app-server turn handles 2026-06-01 10:12:36 +01:00
Vincent Koc
26aaf03719 fix(scripts): clean control ui i18n timeouts 2026-06-01 11:10:57 +02:00
Vincent Koc
e85be626a4 refactor: share plugin runtime scope test setup 2026-06-01 11:07:29 +02:00
Vincent Koc
9cb052ccef refactor: share plugin http route test setup 2026-06-01 10:56:09 +02:00
Peter Steinberger
637b073119 test(ui): update gateway session chat mock 2026-06-01 04:53:51 -04:00
Vincent Koc
174e7711f3 fix(build): clean CLI startup metadata timeouts 2026-06-01 10:52:27 +02:00
Vincent Koc
b13af38f99 perf(ui): trace chat first output latency
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.
2026-06-01 09:47:45 +01:00
Vincent Koc
4094c94a8f refactor: share event loop health expectation 2026-06-01 10:47:05 +02:00
Peter Steinberger
32113e38ab perf(ci): speed up prompt snapshot checks 2026-06-01 04:44:41 -04:00
Peter Steinberger
07a425aa14 fix: preserve colon slash commands 2026-06-01 09:41:19 +01:00
Vincent Koc
db5bb1cbe7 refactor: share auth state test setup 2026-06-01 10:38:12 +02:00
Vincent Koc
947dde976c fix(release): bound plugin npm verification commands 2026-06-01 10:36:46 +02:00
Peter Steinberger
1d4c1ba56d fix: harden memory envelope sanitization
Co-authored-by: amittell <mittell@me.com>
2026-06-01 09:30:08 +01:00
Vincent Koc
de3ee3daa6 refactor: share auth context test helpers 2026-06-01 10:24:04 +02:00
Vincent Koc
61574eb50b perf(ui): keep chat draft local while typing (#88998) 2026-06-01 09:19:53 +01:00
Vincent Koc
e680604577 fix(e2e): clean telegram credential timeouts 2026-06-01 10:13:57 +02:00
Vincent Koc
2ea7c518a5 test(agents): avoid provider runtime in subagent spawn tests 2026-06-01 09:13:36 +01:00
Vincent Koc
7f95733bee refactor: share handshake locality test inputs 2026-06-01 10:12:30 +02:00
Peter Steinberger
a4196a4445 fix(ci): cache plugin sdk declarations safely 2026-06-01 04:09:07 -04:00
Vincent Koc
688634ccb9 refactor: share ws health test harness setup 2026-06-01 10:01:27 +02:00
Vincent Koc
060d4a4d2d test(gateway): widen live helper connect budget 2026-06-01 09:00:47 +01:00
Vincent Koc
f2d0fe6417 fix(release): clean cross-os process groups 2026-06-01 10:00:23 +02:00
Vincent Koc
6627b4fbdd perf(ui): guard chat composer controls
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.
2026-06-01 08:56:14 +01:00
Peter Steinberger
3b64ea83e8 fix: migrate legacy OpenAI Codex lastGood auth state 2026-06-01 03:47:43 -04:00
Vincent Koc
1d62f4c014 fix(ci): satisfy scripts lint spread rule 2026-06-01 08:45:42 +01:00
Vincent Koc
3feeb95668 refactor: share minimal gateway test helpers 2026-06-01 09:44:48 +02:00
Vincent Koc
402e2bb81a perf(ui): guard chat transcript rerenders
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.
2026-06-01 08:41:04 +01:00
Peter Steinberger
bc470713bb fix(e2e): enable smoke-tested plugin channels 2026-06-01 08:38:50 +01:00
Vincent Koc
3322212f14 fix(ci): tolerate pnpm workspace state on Windows hydrate 2026-06-01 09:36:41 +02:00
Peter Steinberger
7591dc6f4b test(telegram): reset spooled polling handler state 2026-06-01 08:36:32 +01:00
Vincent Koc
6640d57b64 refactor: share websocket connection test harness 2026-06-01 09:29:43 +02:00
Vincent Koc
ac734d8e16 fix(e2e): clean package candidate timeouts 2026-06-01 09:22:07 +02:00
Vincent Koc
0ece07cc20 fix(test): wait for telegram timer flushes
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
2026-06-01 08:17:33 +01:00
Vincent Koc
5e09113ede refactor: share selected global session test setup 2026-06-01 09:14:31 +02:00
Vincent Koc
bff66a3e49 perf(ui): skip closed slash menu rerenders
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.
2026-06-01 08:14:16 +01:00
Vincent Koc
8071b06634 perf(ui): debounce chat draft persistence
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.
2026-06-01 08:04:23 +01:00
Vincent Koc
61ffd6bc66 fix(ci): bootstrap raw changed gates from clean checkouts 2026-06-01 08:01:11 +01:00
Vincent Koc
474ec157bc test(scripts): use runner vitest resolver in expectations 2026-06-01 08:01:11 +01:00
Vincent Koc
1377fd82a9 refactor: share openai compat http test helpers 2026-06-01 08:55:28 +02:00
Vincent Koc
8fdb1d0f55 fix(e2e): stream Parallels fresh logs 2026-06-01 08:54:22 +02:00
Vincent Koc
68bfacae03 test(ci): wait for MCP tools list log 2026-06-01 07:49:01 +01:00
Vincent Koc
371617f9ed refactor: share gateway error response assertions 2026-06-01 08:42:59 +02:00
Vincent Koc
69b2c8bd15 perf(ui): record pending send paint timing (#88960) 2026-06-01 07:42:24 +01:00
Vincent Koc
c11ff35841 fix(e2e): bound Parallels update logs 2026-06-01 08:42:08 +02:00
Vincent Koc
ddbd595f2f fix(ci): link Windows hydrate node modules 2026-06-01 08:38:25 +02:00
Vincent Koc
01124cfca9 fix(e2e): clean secret proof timeouts 2026-06-01 08:30:17 +02:00
Vincent Koc
e8f3bce9f0 fix(ci): exempt child process test helper from sdk guard 2026-06-01 07:27:47 +01:00
Vincent Koc
cb0ad281ce perf(ui): cache chat transcript renders (#88952) 2026-06-01 07:27:08 +01:00
Vincent Koc
c429a3c472 fix(codex): skip stale bootstrap history without engine 2026-06-01 07:26:08 +01:00
Vincent Koc
444bdc4286 refactor: share child process test mock helper 2026-06-01 08:22:25 +02:00
Vincent Koc
28550c3847 fix(e2e): harden Parallels host timeouts 2026-06-01 08:15:34 +02:00
Vincent Koc
3e91c688ae fix(ui): scroll pending sends into view
Scroll the chat thread as soon as a submitted pending send is enqueued, so delayed `chat.send` ACKs no longer leave the user's just-sent message below the viewport.

Verification:
- focused UI Vitest suite: 86 tests passed
- oxlint, core tsgo, core-test tsgo, diff check
- Testbox changed gate: tbx_01kt0wspy1ks5wpb6kp5gr0512
- branch autoreview clean
2026-06-01 07:14:07 +01:00
Vincent Koc
4d49a76039 test(secrets): secure plugin exec fixtures 2026-06-01 07:11:28 +01:00
Vincent Koc
988ec0234e fix(agents): validate shell snapshots with trusted env 2026-06-01 07:11:28 +01:00
Vincent Koc
9a7e0d43da fix(codex): accept legacy app-server auth provider 2026-06-01 07:11:28 +01:00
Vincent Koc
f55ff8dd1b fix(codex): skip stale bootstrap history without engine 2026-06-01 07:11:28 +01:00
Vincent Koc
5314a39ee5 refactor: share usage UTC range assertions 2026-06-01 08:03:23 +02:00
Vincent Koc
44cad6f8a4 refactor: simplify wake APNs test mock 2026-06-01 07:59:17 +02:00
Vincent Koc
275caeb5f5 fix(ui): render pending sends in chat thread
Render submitted Control UI sends directly in the chat thread before the Gateway acknowledges `chat.send`.

Pending sends now share acknowledged user-message content rendering for text and attachments, stay searchable with active chat filters, and failed queued sends remain queue-only.

Verification:
- focused UI Vitest suite: 201 tests passed
- oxlint, core tsgo, core-test tsgo, diff check
- Testbox changed gate: tbx_01kt0vnr2bv55aa6x588r77x0z
- autoreview clean
2026-06-01 06:57:05 +01:00
Peter Steinberger
0f2732b066 test(release): isolate telegram extension vitest lane 2026-06-01 06:54:55 +01:00
Vincent Koc
59f1472bd5 refactor: share error coercion helper 2026-06-01 07:41:19 +02:00
Vincent Koc
630f0d6938 refactor: share push test response assertions 2026-06-01 07:36:51 +02:00
Peter Steinberger
6173a4babb docs(plugin-sdk): refresh API baseline 2026-06-01 06:29:51 +01:00
Vincent Koc
6a1b2e6463 refactor: share skills handler test helper 2026-06-01 07:27:52 +02:00
Vincent Koc
fb9e091852 fix(e2e): harden plugin gauntlet cleanup 2026-06-01 07:27:35 +02:00
Peter Steinberger
00399d6c75 test(release): repair beta validation blockers 2026-06-01 06:27:02 +01:00
Peter Steinberger
b23ace1d04 fix(agents): strip streamed reasoning tags (#88924) 2026-06-01 01:26:29 -04:00
Peter Steinberger
db4990d260 refactor: compact copilot sessions through sdk state
Route Copilot compaction through SDK-backed state, remove marker sidecars, preserve auth/session binding behavior in SQLite-backed plugin state, and route Copilot CLI budget compaction through native harness compaction.
2026-06-01 01:18:46 -04:00
Vincent Koc
4550cfa6a7 fix(qa): run plugin MCP probes from repo root 2026-06-01 07:13:24 +02:00
Chunyue Wang
c0195f7ed5 fix(diagnostics): clear embedded-run activity when recovery declares lane idle (#88820)
* 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>
2026-06-01 01:07:35 -04:00
Tosko4
785849d395 fix(android): add notification app picker 2026-06-01 10:37:19 +05:30
Vincent Koc
12d5043913 refactor: share chat parentid test helpers 2026-06-01 07:06:05 +02:00
Peter Steinberger
d925249ac0 docs(plugin-sdk): refresh API baseline hash 2026-06-01 06:05:37 +01:00
Vincent Koc
74a075077c fix(e2e): harden docker all cleanup 2026-06-01 07:05:15 +02:00
Peter Steinberger
4e57546a87 test(memory): isolate qmd timer state in prerelease shard 2026-06-01 06:03:43 +01:00
Neerav Makwana
711ab45025 fix(agents): clear legacy auto fallback pins (#87484)
* 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>
2026-06-01 01:03:31 -04:00
Vincent Koc
e7e21caa20 fix(ui): keep first control chat sends responsive
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.
2026-06-01 05:59:04 +01:00
amittell
945faf8e67 fix(memory-lancedb): reject envelope metadata sludge
Summary:
- Strip memory-lancedb envelope and metadata sludge before auto-capture/recall, including pending history wrappers, current-message reply context, message-tool delivery hints, media annotations, and marker-free channel envelopes.
- Expose bundled chat-channel IDs/prefixes through the plugin SDK so sanitizer matching follows the channel catalog.
- Refactor cron tool schemas to fresh factory instances while preserving runtime nullable clears and provider-facing OpenAPI projection.

Verification:
- git diff --check origin/main...HEAD
- ./node_modules/.bin/oxfmt --check src/plugin-sdk/chat-channel-ids.ts src/plugin-sdk/chat-channel-ids.test.ts extensions/memory-lancedb/index.ts extensions/memory-lancedb/index.test.ts src/agents/tools/cron-tool.ts src/agents/tools/cron-tool.schema.test.ts
- pnpm plugin-sdk:api:check
- node scripts/run-vitest.mjs run src/plugin-sdk/chat-channel-ids.test.ts extensions/memory-lancedb src/agents/tools/cron-tool.schema.test.ts src/agents/tools/cron-tool.test.ts --reporter=dot
- pnpm lint:extensions --threads=8
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
- GitHub checks on 62d1da1257: 139 pass, 0 pending, 0 fail, 22 skipped.
2026-06-01 00:57:25 -04:00
Vincent Koc
1aa1a70ac5 test(installer): isolate install shell HOME 2026-06-01 05:55:34 +01:00
1175 changed files with 61642 additions and 22424 deletions

View File

@@ -22,6 +22,8 @@ Use when:
- Read dependency docs/source/types when the finding depends on external behavior.
- Reject unrealistic edge cases, speculative risks, broad rewrites, and fixes that over-complicate the codebase.
- Prefer small fixes at the right ownership boundary; no refactor unless it clearly improves the bug class.
- When an accepted finding shows a bug class or repeated pattern, inspect the current PR scope for sibling instances before fixing.
- Fix the scoped bug class at once when practical; stop at touched surfaces, owner boundaries, and clear follow-up territory.
- Keep going until structured review returns no accepted/actionable findings.
- If a review-triggered fix changes code, rerun focused tests and rerun the structured review helper.
- For security-audit suppression changes, verify accepted findings remain auditable: suppressed findings stay in structured output, active output keeps an unsuppressible suppression notice, and aggregate findings cannot hide unrelated active risk.

View File

@@ -16,6 +16,10 @@ Use this with `$release-openclaw-maintainer` and `$openclaw-testing` when a rele
- Watch one parent run plus compact child summaries. Avoid broad `gh run view` polling loops; REST quota is easy to burn.
- Fetch logs only for failed or currently-blocking jobs. If quota is low, stop polling and wait for reset.
- Treat live-provider flakes separately from code failures: prove key validity, provider HTTP status, retry evidence, and exact failing lane before editing code.
- Full Release Validation parent monitors fail fast: once a required child job
fails, the parent cancels the remaining child matrix and prints the failed
job summary. Inspect that first red job instead of waiting for unrelated
matrix tails.
## Preflight
@@ -73,6 +77,9 @@ gh workflow run full-release-validation.yml \
```
Use `release_profile=stable` unless the operator explicitly asks for the broad advisory provider/media matrix. Use narrow `rerun_group` after focused fixes.
Publish with `openclaw-release-publish.yml` using `release_profile=from-validation`
unless a maintainer intentionally wants to cross-check a specific profile; the
publish workflow reads the effective profile from the full-validation manifest.
## Watch

View File

@@ -49,17 +49,21 @@ Use this skill for release and publish-time workflow. Load `$release-private` if
the next beta number until the matching npm package has actually published.
If a published beta needs a fix, commit the fix on the release branch and
increment to the next `-beta.N`.
- For a beta release train, run the fast local preflight first, publish the
beta to npm `beta`, then run the expensive published-package roster focused
on install/update/Docker/Parallels/NPM Telegram. If anything fails, fix it on
the release branch, commit/push/pull, increment beta number, and repeat. Run
the full expensive roster at least once before stable/latest promotion; for
later beta attempts, rerun only lanes whose evidence changed unless the fix
touches broad release, install/update, plugin, Docker, Parallels, or live QA
behavior. After each beta is published, scan current `main` once for critical
fixes that landed after the release branch cut and backport only important
low-risk fixes. Operators may authorize up to 4 autonomous beta attempts;
after 4 failed beta attempts, stop and report.
- For a beta release train, keep Full Release Validation as a pre-publish gate
unless the operator explicitly waives it. Run the fast local preflight, npm
preflight, full release validation, and performance in parallel where safe.
If anything fails before npm publish, fix it on the release branch,
forward-port the fix to `main`, move the unpublished beta tag/prerelease to
the fixed commit, and rerun the affected pre-publish gates. If anything fails
after npm publish, fix it, forward-port to `main`, increment beta number, and
repeat. After each beta publish, run the published-package roster focused on
install/update/Docker/Parallels/NPM Telegram. For later beta attempts, rerun
only lanes whose evidence changed unless the fix touches broad release,
install/update, plugin, Docker, Parallels, or live QA behavior. After each
beta is live, scan current `main` once for critical fixes that landed after
the release branch cut and backport only important low-risk fixes. Operators
may authorize up to 4 autonomous beta attempts; after 4 failed beta attempts,
stop and report.
- As soon as the release candidate SHA exists, dispatch `OpenClaw Performance`
with `target_ref=<release-sha>` in parallel with the other release work. Do
not wait for full release validation to start the performance signal.
@@ -468,8 +472,10 @@ node --import tsx scripts/openclaw-npm-postpublish-verify.ts <published-version>
- The npm workflow and the private mac publish workflow accept
`preflight_only=true` to run validation/build/package steps without uploading
public release assets.
- Real npm publish requires a prior successful npm preflight run id so the
publish job promotes the prepared tarball instead of rebuilding it.
- Real npm publish requires a prior successful npm preflight run id and the
successful Full Release Validation run id for the same tag/SHA so the publish
job promotes the prepared tarball instead of rebuilding it and attaches the
correct release evidence.
- Real private mac publish requires a prior successful private mac preflight
run id so the publish job promotes the prepared artifacts instead of
rebuilding or renotarizing them again.
@@ -499,11 +505,12 @@ node --import tsx scripts/openclaw-npm-postpublish-verify.ts <published-version>
instead of uploading public GitHub release assets.
- Private smoke-test runs upload ad-hoc, non-notarized build artifacts as
workflow artifacts and intentionally skip stable `appcast.xml` generation.
- For stable releases, npm preflight, public mac validation, private mac
validation, and private mac preflight must all pass before any real publish
run starts. For beta releases, npm preflight plus the selected Docker,
install/update, Parallels, and release-check lanes are sufficient unless mac
beta validation was explicitly requested.
- For stable releases, npm preflight, Full Release Validation, public mac
validation, private mac validation, and private mac preflight must all pass
before any real publish run starts. For beta releases, npm preflight and Full
Release Validation must pass before npm publish unless the operator explicitly
waives the full gate; mac beta validation is still only required when
requested.
- Real publish runs may be dispatched from `main` or from a
`release/YYYY.M.D` branch. For release-branch runs, the tag must be contained
in that release branch, and the real publish must reuse a successful preflight

View File

@@ -605,7 +605,19 @@ jobs:
restore-keys: |
${{ runner.os }}-build-all-v3-
- name: Restore dist build cache
id: dist_build_cache
uses: actions/cache/restore@v5
with:
path: |
dist/
dist-runtime/
extensions/*/src/host/**/.bundle.hash
extensions/*/src/host/**/*.bundle.js
key: ${{ runner.os }}-dist-build-${{ needs.preflight.outputs.checkout_revision }}
- name: Build dist
if: steps.dist_build_cache.outputs.cache-hit != 'true'
env:
NODE_OPTIONS: --max-old-space-size=8192
run: pnpm build:ci-artifacts
@@ -614,14 +626,6 @@ jobs:
if: needs.preflight.outputs.run_control_ui_i18n == 'true'
run: pnpm ui:i18n:check
- name: Cache dist build
uses: actions/cache@v5
with:
path: |
dist/
dist-runtime/
key: ${{ runner.os }}-dist-build-${{ needs.preflight.outputs.checkout_revision }}
- name: Pack built runtime artifacts
run: tar --posix -cf dist-runtime-build.tar.zst --use-compress-program zstdmt dist dist-runtime
@@ -751,6 +755,18 @@ jobs:
done
exit "$failures"
- name: Save dist build cache
if: steps.dist_build_cache.outputs.cache-hit != 'true'
uses: actions/cache/save@v5
continue-on-error: true
with:
path: |
dist/
dist-runtime/
extensions/*/src/host/**/.bundle.hash
extensions/*/src/host/**/*.bundle.js
key: ${{ steps.dist_build_cache.outputs.cache-primary-key }}
- name: Upload gateway watch regression artifacts
if: always() && needs.preflight.outputs.run_check_additional == 'true'
uses: actions/upload-artifact@v7
@@ -1151,7 +1167,8 @@ jobs:
OPENCLAW_NODE_TEST_CONFIGS_JSON: ${{ toJson(matrix.configs) }}
OPENCLAW_NODE_TEST_INCLUDE_PATTERNS_JSON: ${{ toJson(matrix.includePatterns) }}
OPENCLAW_VITEST_SHARD_NAME: ${{ matrix.shard_name }}
OPENCLAW_VITEST_NO_OUTPUT_TIMEOUT_MS: "900000"
OPENCLAW_VITEST_NO_OUTPUT_TIMEOUT_MS: "300000"
OPENCLAW_VITEST_NO_OUTPUT_RETRY: "1"
OPENCLAW_TEST_PROJECTS_PARALLEL: "2"
shell: bash
run: |

View File

@@ -32,11 +32,11 @@ permissions:
env:
FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
PNPM_CONFIG_CHILD_CONCURRENCY: "1"
PNPM_CONFIG_MODULES_DIR: "/tmp/openclaw-pnpm-node-modules"
PNPM_CONFIG_MODULES_DIR: "/var/tmp/openclaw-pnpm-node-modules"
PNPM_CONFIG_NETWORK_CONCURRENCY: "1"
PNPM_CONFIG_STORE_DIR: "/tmp/openclaw-pnpm-store"
PNPM_CONFIG_STORE_DIR: "/var/tmp/openclaw-pnpm-store"
PNPM_CONFIG_VERIFY_DEPS_BEFORE_RUN: "false"
PNPM_CONFIG_VIRTUAL_STORE_DIR: "/tmp/openclaw-pnpm-virtual-store"
PNPM_CONFIG_VIRTUAL_STORE_DIR: "/var/tmp/openclaw-pnpm-virtual-store"
jobs:
hydrate:
@@ -431,6 +431,25 @@ jobs:
if ($LASTEXITCODE -ne 0) {
exit $LASTEXITCODE
}
$workspaceNodeModules = Join-Path $workspace "node_modules"
if (Test-Path $workspaceNodeModules) {
$workspaceNodeModulesItem = Get-Item $workspaceNodeModules -Force
if (($workspaceNodeModulesItem.Attributes -band [System.IO.FileAttributes]::ReparsePoint) -eq 0) {
$nodeModulesChildren = @(Get-ChildItem -LiteralPath $workspaceNodeModules -Force)
$hasOnlyPnpmWorkspaceState = $nodeModulesChildren.Count -eq 1 -and $nodeModulesChildren[0].Name -eq ".pnpm-workspace-state-v1.json"
if ($nodeModulesChildren.Count -ne 0 -and -not $hasOnlyPnpmWorkspaceState) {
throw "workspace node_modules exists and is not a link: $workspaceNodeModules"
}
foreach ($nodeModulesChild in $nodeModulesChildren) {
Remove-Item -LiteralPath $nodeModulesChild.FullName -Force
}
Remove-Item -LiteralPath $workspaceNodeModules -Force
New-Item -ItemType Junction -Path $workspaceNodeModules -Target $env:PNPM_CONFIG_MODULES_DIR | Out-Null
}
} else {
New-Item -ItemType Junction -Path $workspaceNodeModules -Target $env:PNPM_CONFIG_MODULES_DIR | Out-Null
}
$corepackShimDir = Join-Path $nodeBin "node_modules\corepack\shims"
if (Test-Path $corepackShimDir) {
$env:PNPM_HOME = $corepackShimDir

View File

@@ -229,7 +229,7 @@ jobs:
needs: [resolve_target]
if: inputs.rerun_group == 'all'
runs-on: ubuntu-24.04
timeout-minutes: 45
timeout-minutes: 20
permissions:
contents: read
steps:
@@ -245,54 +245,11 @@ jobs:
DOCKER_BUILDKIT: "1"
run: |
set -euo pipefail
timeout --kill-after=30s 35m docker build \
timeout --kill-after=30s 15m docker build \
--target runtime-assets \
--build-arg OPENCLAW_EXTENSIONS="diagnostics-otel,codex" \
.
- name: Build and smoke test final Docker runtime image
env:
DOCKER_BUILDKIT: "1"
TARGET_SHA: ${{ needs.resolve_target.outputs.sha }}
run: |
set -euo pipefail
image_ref="openclaw-release-runtime-smoke:${TARGET_SHA}"
timeout --kill-after=30s 35m docker build \
--build-arg OPENCLAW_EXTENSIONS="diagnostics-otel,codex" \
-t "${image_ref}" \
.
docker run --rm --entrypoint /bin/sh "${image_ref}" -lc '
set -eu
test -f /app/src/agents/templates/HEARTBEAT.md
temp_root="$(mktemp -d)"
trap "rm -rf \"${temp_root}\"" EXIT
mkdir -p "${temp_root}/home" "${temp_root}/cwd"
cd "${temp_root}/cwd"
set +e
HOME="${temp_root}/home" \
USERPROFILE="${temp_root}/home" \
OPENCLAW_HOME="${temp_root}/home" \
OPENCLAW_NO_ONBOARD=1 \
OPENCLAW_SUPPRESS_NOTES=1 \
OPENCLAW_DISABLE_BUNDLED_PLUGINS=1 \
OPENCLAW_DISABLE_BUNDLED_ENTRY_SOURCE_FALLBACK=1 \
AWS_EC2_METADATA_DISABLED=true \
AWS_SHARED_CREDENTIALS_FILE="${temp_root}/home/.aws/credentials" \
AWS_CONFIG_FILE="${temp_root}/home/.aws/config" \
node /app/openclaw.mjs agent --message "workspace bootstrap smoke" --session-id "workspace-bootstrap-smoke" --local --timeout 1 --json \
>"${temp_root}/out.log" 2>&1
status="$?"
set -e
if grep -F "Missing workspace template:" "${temp_root}/out.log"; then
cat "${temp_root}/out.log"
exit 1
fi
test -f "${temp_root}/home/.openclaw/workspace/HEARTBEAT.md"
if [ "${status}" -ne 0 ]; then
cat "${temp_root}/out.log"
fi
'
normal_ci:
name: Run normal full CI
needs: [resolve_target, docker_runtime_assets_preflight]
@@ -380,6 +337,21 @@ jobs:
gh_with_retry api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}/jobs?per_page=100" --jq '.jobs[]'
}
fail_fast_failed_jobs() {
local failed_jobs_json
failed_jobs_json="$(
fetch_child_jobs |
jq -s '[.[] | select(.status == "completed" and .conclusion != "success" and .conclusion != "skipped")]'
)"
if jq -e 'length > 0' <<< "$failed_jobs_json" >/dev/null; then
echo "::error::${workflow} has failed child jobs before the workflow completed; cancelling the remaining matrix."
jq '.[] | {name, conclusion, url: .html_url}' <<< "$failed_jobs_json"
cancel_child
trap - EXIT INT TERM
exit 1
fi
}
cancel_child() {
if [[ -n "${run_id:-}" ]]; then
echo "Cancelling child workflow ${workflow}: ${run_id}" >&2
@@ -395,6 +367,9 @@ jobs:
break
fi
poll_count=$((poll_count + 1))
if (( poll_count % 2 == 0 )); then
fail_fast_failed_jobs
fi
if (( poll_count % 10 == 0 )); then
echo "Still waiting on ${workflow}: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
fetch_child_jobs | jq 'select(.status != "completed") | {name, status, url: .html_url}' || true
@@ -510,6 +485,21 @@ jobs:
gh_with_retry api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}/jobs?per_page=100" --jq '.jobs[]'
}
fail_fast_failed_jobs() {
local failed_jobs_json
failed_jobs_json="$(
fetch_child_jobs |
jq -s '[.[] | select(.status == "completed" and .conclusion != "success" and .conclusion != "skipped")]'
)"
if jq -e 'length > 0' <<< "$failed_jobs_json" >/dev/null; then
echo "::error::${workflow} has failed child jobs before the workflow completed; cancelling the remaining matrix."
jq '.[] | {name, conclusion, url: .html_url}' <<< "$failed_jobs_json"
cancel_child
trap - EXIT INT TERM
exit 1
fi
}
cancel_child() {
if [[ -n "${run_id:-}" ]]; then
echo "Cancelling child workflow ${workflow}: ${run_id}" >&2
@@ -525,6 +515,9 @@ jobs:
break
fi
poll_count=$((poll_count + 1))
if (( poll_count % 2 == 0 )); then
fail_fast_failed_jobs
fi
if (( poll_count % 10 == 0 )); then
echo "Still waiting on ${workflow}: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
fetch_child_jobs | jq 'select(.status != "completed") | {name, status, url: .html_url}' || true
@@ -690,6 +683,24 @@ jobs:
[[ "$saw_advisory" == "1" && "$failed" == "0" ]]
}
fail_fast_failed_jobs() {
local failed_jobs_json
if [[ "$workflow" == "openclaw-release-checks.yml" && "$CHILD_WORKFLOW_REF" =~ ^tideclaw/alpha/[0-9]{4}-[0-9]{2}-[0-9]{2}-[0-9]{4}Z$ ]]; then
return 0
fi
failed_jobs_json="$(
fetch_child_jobs |
jq -s '[.[] | select(.status == "completed" and .conclusion != "success" and .conclusion != "skipped")]'
)"
if jq -e 'length > 0' <<< "$failed_jobs_json" >/dev/null; then
echo "::error::${workflow} has failed child jobs before the workflow completed; cancelling the remaining matrix."
jq '.[] | {name, conclusion, url: .html_url}' <<< "$failed_jobs_json"
cancel_child
trap - EXIT INT TERM
exit 1
fi
}
cancel_child() {
if [[ -n "${run_id:-}" ]]; then
echo "Cancelling child workflow ${workflow}: ${run_id}" >&2
@@ -705,6 +716,9 @@ jobs:
break
fi
poll_count=$((poll_count + 1))
if (( poll_count % 2 == 0 )); then
fail_fast_failed_jobs
fi
if (( poll_count % 10 == 0 )); then
echo "Still waiting on ${workflow}: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
fetch_child_jobs | jq 'select(.status != "completed") | {name, status, url: .html_url}' || true
@@ -962,6 +976,21 @@ jobs:
}
trap cancel_child EXIT INT TERM
fail_fast_failed_jobs() {
local failed_jobs_json
failed_jobs_json="$(
gh_with_retry run view "$run_id" --json jobs \
--jq '[.jobs[] | select(.status == "completed" and .conclusion != "success" and .conclusion != "skipped")]'
)"
if jq -e 'length > 0' <<< "$failed_jobs_json" >/dev/null; then
echo "::error::npm-telegram-beta-e2e.yml has failed child jobs before the workflow completed; cancelling the remaining run."
jq '.[] | {name, conclusion, url}' <<< "$failed_jobs_json"
cancel_child
trap - EXIT INT TERM
exit 1
fi
}
poll_count=0
while true; do
status="$(gh_with_retry run view "$run_id" --json status --jq '.status')"
@@ -969,6 +998,9 @@ jobs:
break
fi
poll_count=$((poll_count + 1))
if (( poll_count % 2 == 0 )); then
fail_fast_failed_jobs
fi
if (( poll_count % 10 == 0 )); then
echo "Still waiting on npm-telegram-beta-e2e.yml: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
gh_with_retry run view "$run_id" --json jobs --jq '.jobs[] | select(.status != "completed") | {name, status, url}' || true

View File

@@ -798,7 +798,7 @@ jobs:
- name: Build private QA runtime
env:
NODE_OPTIONS: --max-old-space-size=8192
run: pnpm build
run: node scripts/build-all.mjs qaRuntime
- name: Run parity lane
env:
@@ -876,7 +876,7 @@ jobs:
- name: Build private QA runtime
env:
NODE_OPTIONS: --max-old-space-size=8192
run: pnpm build
run: node scripts/build-all.mjs qaRuntime
- name: Generate parity report
run: |
@@ -934,7 +934,7 @@ jobs:
- name: Build private QA runtime
env:
NODE_OPTIONS: --max-old-space-size=8192
run: pnpm build
run: node scripts/build-all.mjs qaRuntime
- name: Run runtime parity lane
id: runtime_parity_lane
@@ -1101,7 +1101,7 @@ jobs:
- name: Build private QA runtime
env:
NODE_OPTIONS: --max-old-space-size=8192
run: pnpm build
run: node scripts/build-all.mjs qaRuntime
- name: Run Matrix live lane
id: run_lane
@@ -1199,7 +1199,7 @@ jobs:
- name: Build private QA runtime
env:
NODE_OPTIONS: --max-old-space-size=8192
run: pnpm build
run: node scripts/build-all.mjs qaRuntime
- name: Run Telegram live lane
id: run_lane
@@ -1295,7 +1295,7 @@ jobs:
- name: Build private QA runtime
env:
NODE_OPTIONS: --max-old-space-size=8192
run: pnpm build
run: node scripts/build-all.mjs qaRuntime
- name: Run Discord live lane
id: run_lane
@@ -1393,7 +1393,7 @@ jobs:
- name: Build private QA runtime
env:
NODE_OPTIONS: --max-old-space-size=8192
run: pnpm build
run: node scripts/build-all.mjs qaRuntime
- name: Run WhatsApp live lane
id: run_lane
@@ -1488,7 +1488,7 @@ jobs:
- name: Build private QA runtime
env:
NODE_OPTIONS: --max-old-space-size=8192
run: pnpm build
run: node scripts/build-all.mjs qaRuntime
- name: Run Slack live lane
id: run_lane

View File

@@ -46,11 +46,12 @@ on:
default: true
type: boolean
release_profile:
description: Release coverage profile used for release evidence summaries
description: Release coverage profile used for release evidence summaries; default reads it from the validation manifest
required: false
default: beta
default: from-validation
type: choice
options:
- from-validation
- beta
- stable
- full
@@ -135,9 +136,9 @@ jobs:
exit 1
fi
case "$RELEASE_PROFILE" in
beta|stable|full) ;;
from-validation|beta|stable|full) ;;
*)
echo "release_profile must be one of: beta, stable, full" >&2
echo "release_profile must be one of: from-validation, beta, stable, full" >&2
exit 1
;;
esac
@@ -259,6 +260,7 @@ jobs:
echo "sha=$release_sha" >> "$GITHUB_OUTPUT"
- name: Validate full release validation manifest
id: full_manifest
if: ${{ inputs.publish_openclaw_npm }}
env:
GH_TOKEN: ${{ github.token }}
@@ -289,7 +291,7 @@ jobs:
echo "Full release validation target SHA mismatch: expected $EXPECTED_SHA, got $target_sha" >&2
exit 1
fi
if [[ "$release_profile" != "$EXPECTED_RELEASE_PROFILE" ]]; then
if [[ "$EXPECTED_RELEASE_PROFILE" != "from-validation" && "$release_profile" != "$EXPECTED_RELEASE_PROFILE" ]]; then
echo "Full release validation profile mismatch: expected $EXPECTED_RELEASE_PROFILE, got $release_profile" >&2
exit 1
fi
@@ -297,6 +299,7 @@ jobs:
echo "Full release validation must run rerun_group=all before npm publish; got $rerun_group" >&2
exit 1
fi
echo "release_profile=$release_profile" >> "$GITHUB_OUTPUT"
- name: Validate release tag is reachable from a trusted release branch
env:
@@ -332,7 +335,7 @@ jobs:
env:
RELEASE_TAG: ${{ inputs.tag }}
TARGET_SHA: ${{ steps.manifest.outputs.sha || steps.ref.outputs.sha }}
RELEASE_PROFILE: ${{ inputs.release_profile }}
RELEASE_PROFILE: ${{ steps.full_manifest.outputs.release_profile || inputs.release_profile }}
FULL_RELEASE_VALIDATION_RUN_ID: ${{ inputs.full_release_validation_run_id }}
run: |
{
@@ -501,7 +504,7 @@ jobs:
wait_for_run() {
local workflow="$1"
local run_id="$2"
local status conclusion url updated_at created_at duration_seconds duration_label last_state
local status conclusion url updated_at created_at duration_seconds duration_label last_state failed_json
last_state=""
while true; do
@@ -510,6 +513,14 @@ jobs:
if [[ "$status" == "completed" ]]; then
break
fi
failed_json="$(gh run view --repo "$GITHUB_REPOSITORY" "$run_id" --json jobs \
--jq '[.jobs[] | select(.status == "completed" and .conclusion != "success" and .conclusion != "skipped")]' || true)"
if [[ -n "${failed_json}" ]] && jq -e 'length > 0' <<< "$failed_json" >/dev/null; then
echo "${workflow} has failed jobs before the workflow completed: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}" >&2
jq '.[] | {name, conclusion, url}' <<< "$failed_json" >&2 || true
print_failed_run_summary "${run_id}"
return 1
fi
url="$(printf '%s' "$run_json" | jq -r '.url')"
updated_at="$(printf '%s' "$run_json" | jq -r '.updatedAt')"
state="${status}:${updated_at}"

View File

@@ -818,6 +818,7 @@ jobs:
OPENCLAW_QA_CONVEX_SECRET_CI: ${{ secrets.OPENCLAW_QA_CONVEX_SECRET_CI }}
OPENCLAW_QA_REDACT_PUBLIC_METADATA: "1"
OPENCLAW_QA_SLACK_CAPTURE_CONTENT: "1"
OPENCLAW_QA_TRANSPORT_READY_TIMEOUT_MS: "180000"
INPUT_SCENARIO: ${{ github.event_name == 'workflow_dispatch' && inputs.slack_scenario || '' }}
run: |
set -euo pipefail

View File

@@ -2,7 +2,7 @@
Docs: https://docs.openclaw.ai
## 2026.5.31
## 2026.6.2
### Highlights
@@ -13,10 +13,10 @@ Docs: https://docs.openclaw.ai
- 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.
- Workboard, SecretRef plugin manifests, hosted iOS push relay, and external Copilot/Tokenjuice packaging add broader orchestration, integration, and plugin delivery surfaces. (#82326, #87469, #87796, #88107, #88117)
- 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)
- Chat and Control UI startup paths keep sends alive through history loading, stream deltas incrementally, skip markdown work while streaming, keep drafts local while typing, trace first-output latency, and expose calmer composer controls. (#88772, #88825, #88998) Thanks @vincentkoc.
- 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.
- Release, CI, Docker, E2E, plugin install, and diagnostics lanes now cap more logs, response bodies, readiness probes, artifact checks, status polling, and rollback snapshots so failures report bounded proof instead of stalling.
### Changes
@@ -35,7 +35,7 @@ Docs: https://docs.openclaw.ai
- 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)
- Control UI: add calmer chat composer controls, local draft typing state, and first-output latency instrumentation for active chat entry. (#88772, #88998) Thanks @vincentkoc.
- 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)
@@ -45,22 +45,39 @@ Docs: https://docs.openclaw.ai
### Fixes
- Release/CI/E2E: fail early when Crabbox sparse-sync full checkouts do not have enough local disk, with guidance for moving the sync root.
- Build: render independent CLI startup metadata help snapshots concurrently to cut cold build-all metadata time.
- Plugins: stop timed-out package-boundary prep steps by process group so descendant TypeScript/helper processes do not survive local check cleanup.
- Control UI: serve static assets asynchronously after safe-open checks so large UI files do not block Gateway request handling.
- Scripts/UI: forward direct wrapper SIGHUP shutdown to child processes so terminal hangups do not leave wrapped dev commands running.
- Gateway: return the post-expiration pending-work revision from node drains so reconnecting nodes do not observe stale queue revisions after expired items are pruned.
- Release/CI/E2E: keep temporary full-sync checkouts alive while slow Crabbox leases boot, so sparse worktree runs do not lose their sync source before file-list generation.
- Release/CI/E2E: normalize inherited Linux `C.UTF-8` locale settings before raw AWS macOS Crabbox bootstrap commands, avoiding macOS locale warnings during package-manager hydration.
- Release/CI/E2E: keep gateway watch regression checks from copying large static plugin assets inside the measured idle window.
- Update: keep core updates nonblocking when a missing external plugin repair download stalls, while still blocking installed active plugin payload smoke failures.
- Agents/providers: keep streaming tool-call argument parsing record-shaped when providers emit valid non-object JSON such as `null` or arrays.
- Release/CI/E2E: reset incremental log readers when watched log files rotate without shrinking, so same-size replacements do not hide new readiness or RPC lines.
- Talk: preserve explicit `null` payloads on controller-created turn and output-audio lifecycle events.
- Agents/TUI: keep local custom provider runs from loading plugin runtime and auth alias metadata when plugins are disabled.
- Agents/TUI: restore in-flight TUI run switch-back behavior, keep no-policy native hook fallback available, guard vanished workspaces, and keep lightweight isolated subagents lightweight.
- 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.
- Agents/Codex: stream Codex app-server final-answer partials to live reply previews, preserve ACP metadata in SQLite, prefer real tool results over synthetic repair output, prevent aborted app-server turn handles from lingering, migrate legacy OpenAI Codex `lastGood` auth state, and preserve workspace/session metadata through ACP runtime refactors. (#88405, #88724, #88730) Thanks @vincentkoc.
- 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.
- Skill Workshop: render the Control UI tab from filtered navigation state and keep filtered fallback routing stable.
- 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)
- Plugins: preserve npm plugin roots after blocked installs, skip plugin-local `openclaw` peer symlinks during rollback snapshots, relink those peers after restore, 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 SQLite cron migrations compatible with legacy run-log tables, archived job stores, diagnostic cron names, and legacy one-shot delete-after-run behavior. (#88285)
- Cron: keep update delivery validation scoped, harden restart state, and retire MCP runtimes on isolated cron cleanup.
- Memory: serialize QMD update/embed writes per store, preserve phase signals on read errors, harden envelope metadata sanitization, and rewrite generated transcript paths on rollover so memory/search state survives concurrent gateway and CLI activity. (#66339, #85931) Thanks @openperf and @amittell.
- Memory: keep vector-disabled FTS indexes from resolving embedding providers during sync and search.
- 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.
@@ -70,16 +87,18 @@ Docs: https://docs.openclaw.ai
- 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: bound release candidate reads, beta smoke REST calls, plugin npm verification commands, changelog restore, cross-OS process groups, kitchen-sink and bundled plugin readiness probes, secret-provider probes, Telegram credential timeouts, Control UI i18n and CLI startup metadata generation, 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)
- 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, keep drafts local while typing, guard composer rerenders, honor Chromium executable overrides, and detect system Chromium for E2E. (#88998) Thanks @vincentkoc.
- Channels: preserve long Feishu streaming replies, send visible fallbacks when accepted Feishu turns produce no final reply, tolerate iMessage self-chat timestamp skew, preserve colon-prefixed slash commands in mention parsing, 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.
- Gateway/plugins: narrow plugin lookup memoization to the stable plugin/runtime inputs, avoiding repeated lookup work without mixing disabled or filtered plugin state.
- 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.
@@ -654,6 +673,7 @@ Docs: https://docs.openclaw.ai
- Gateway/sessions: allow shared-secret bearer callers to read and stream session history without an explicit scope header. (#81815) Thanks @medns.
- Agents/embedded runner: classify HTML auth provider responses as `auth_html` and return a re-authentication hint instead of the CDN-blocked copy that `upstream_html` 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.
- TUI/streaming watchdog: dismiss the `This response is taking longer than expected` 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.
- Agents/auth profiles: replace the bare `No available auth profile for <provider> (all in cooldown or unavailable)` TUI error with plain-language copy that explains what happened in user terms (sign-in expired, provider asking us to slow down, billing issue on the account, etc.) and suggests the matching `openclaw models auth login --provider <provider>` recovery command for sign-in and billing causes, while falling back to the underlying provider error for cases without a clear recovery path. Thanks @romneyda.
- 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.
## 2026.5.20

View File

@@ -218,6 +218,7 @@ Current OpenClaw Android implication:
- Google Play build excludes SMS send/search, Call Log search, and recent-photo access unless the product is intentionally positioned and approved under the relevant policy exception.
- The repo now ships this split as Android product flavors:
- `play`: removes `READ_SMS`, `SEND_SMS`, `READ_CALL_LOG`, `READ_MEDIA_IMAGES`, `READ_MEDIA_VISUAL_USER_SELECTED`, and `READ_EXTERNAL_STORAGE`; hides SMS, Call Log, and Photos surfaces in onboarding, settings, and advertised node capabilities.
- Installed-app listing is user controlled. `device.apps` is advertised only after the user enables **Settings > Phone Capabilities > Installed Apps**. The command defaults to launcher-visible apps and does not require `QUERY_ALL_PACKAGES`.
- `thirdParty`: keeps the full permission set and the existing SMS / Call Log / Photos functionality.
Policy links:

View File

@@ -65,8 +65,8 @@ android {
applicationId = "ai.openclaw.app"
minSdk = 31
targetSdk = 36
versionCode = 2026053101
versionName = "2026.5.31"
versionCode = 2026060201
versionName = "2026.6.2"
ndk {
// Support all major ABIs — native libs are tiny (~47 KB per ABI)
abiFilters += listOf("armeabi-v7a", "arm64-v8a", "x86", "x86_64")

View File

@@ -148,6 +148,7 @@ class MainViewModel(
val gatewayBootstrapToken: StateFlow<String> = prefs.gatewayBootstrapToken
val onboardingCompleted: StateFlow<Boolean> = prefs.onboardingCompleted
val canvasDebugStatusEnabled: StateFlow<Boolean> = prefs.canvasDebugStatusEnabled
val installedAppsSharingEnabled: StateFlow<Boolean> = prefs.installedAppsSharingEnabled
val speakerEnabled: StateFlow<Boolean> = prefs.speakerEnabled
val voiceCaptureMode: StateFlow<VoiceCaptureMode> = runtimeState(initial = VoiceCaptureMode.Off) { it.voiceCaptureMode }
val micEnabled: StateFlow<Boolean> = runtimeState(initial = false) { it.micEnabled }
@@ -299,6 +300,10 @@ class MainViewModel(
prefs.setCanvasDebugStatusEnabled(value)
}
fun setInstalledAppsSharingEnabled(value: Boolean) {
ensureRuntime().setInstalledAppsSharingEnabled(value)
}
fun setNotificationForwardingEnabled(value: Boolean) {
ensureRuntime().setNotificationForwardingEnabled(value)
}

View File

@@ -207,6 +207,7 @@ class NodeRuntime(
callLogAvailable = { SensitiveFeatureConfig.callLogEnabled },
photosAvailable = { SensitiveFeatureConfig.photosEnabled },
hasRecordAudioPermission = { hasRecordAudioPermission() },
installedAppsSharingEnabled = { installedAppsSharingEnabled.value },
manualTls = { manualTls.value },
)
@@ -245,6 +246,7 @@ class NodeRuntime(
smsTelephonyAvailable = { sms.hasTelephonyFeature() },
callLogAvailable = { SensitiveFeatureConfig.callLogEnabled },
photosAvailable = { SensitiveFeatureConfig.photosEnabled },
installedAppsSharingEnabled = { installedAppsSharingEnabled.value },
debugBuild = { BuildConfig.DEBUG },
onCanvasA2uiPush = {
_canvasA2uiHydrated.value = true
@@ -866,6 +868,7 @@ class NodeRuntime(
val lastDiscoveredStableId: StateFlow<String> = prefs.lastDiscoveredStableId
val canvasDebugStatusEnabled: StateFlow<Boolean> = prefs.canvasDebugStatusEnabled
val installedAppsSharingEnabled: StateFlow<Boolean> = prefs.installedAppsSharingEnabled
val notificationForwardingEnabled: StateFlow<Boolean> = prefs.notificationForwardingEnabled
val notificationForwardingMode: StateFlow<NotificationPackageFilterMode> =
prefs.notificationForwardingMode
@@ -1077,6 +1080,12 @@ class NodeRuntime(
prefs.setCanvasDebugStatusEnabled(value)
}
fun setInstalledAppsSharingEnabled(value: Boolean) {
if (prefs.installedAppsSharingEnabled.value == value) return
prefs.setInstalledAppsSharingEnabled(value)
refreshNodeSurfaceAfterSharingChange()
}
fun setNotificationForwardingEnabled(value: Boolean) {
prefs.setNotificationForwardingEnabled(value)
}
@@ -1414,6 +1423,11 @@ class NodeRuntime(
connectWithAuth(endpoint = endpoint, auth = resolveGatewayConnectAuth(), reconnect = true)
}
private fun refreshNodeSurfaceAfterSharingChange() {
val endpoint = connectedEndpoint ?: return
connectWithAuth(endpoint = endpoint, auth = resolveGatewayConnectAuth(), reconnect = true)
}
private fun connectWithAuth(
endpoint: GatewayEndpoint,
auth: GatewayConnectAuth,

View File

@@ -40,11 +40,13 @@ class SecurePrefs(
private const val notificationsForwardingMaxEventsPerMinuteKey =
"notifications.forwarding.maxEventsPerMinute"
private const val notificationsForwardingSessionKeyKey = "notifications.forwarding.sessionKey"
private const val installedAppsSharingEnabledKey = "device.apps.sharing.enabled"
private const val voiceMicEnabledKey = "voice.micEnabled"
}
private val appContext = context.applicationContext
private val json = Json { ignoreUnknownKeys = true }
// Non-secret UI/runtime preferences stay readable for migration and backup behavior.
private val plainPrefs: SharedPreferences =
appContext.getSharedPreferences(plainPrefsName, Context.MODE_PRIVATE)
@@ -114,6 +116,10 @@ class SecurePrefs(
MutableStateFlow(plainPrefs.getBoolean("canvas.debugStatusEnabled", false))
val canvasDebugStatusEnabled: StateFlow<Boolean> = _canvasDebugStatusEnabled
private val _installedAppsSharingEnabled =
MutableStateFlow(plainPrefs.getBoolean(installedAppsSharingEnabledKey, false))
val installedAppsSharingEnabled: StateFlow<Boolean> = _installedAppsSharingEnabled
private val _notificationForwardingEnabled =
MutableStateFlow(plainPrefs.getBoolean(notificationsForwardingEnabledKey, defaultNotificationForwardingEnabled))
val notificationForwardingEnabled: StateFlow<Boolean> = _notificationForwardingEnabled
@@ -252,6 +258,11 @@ class SecurePrefs(
_canvasDebugStatusEnabled.value = value
}
fun setInstalledAppsSharingEnabled(value: Boolean) {
plainPrefs.edit { putBoolean(installedAppsSharingEnabledKey, value) }
_installedAppsSharingEnabled.value = value
}
internal fun getNotificationForwardingPolicy(appPackageName: String): NotificationForwardingPolicy {
val modeRaw = plainPrefs.getString(notificationsForwardingModeKey, null)
val mode = NotificationPackageFilterMode.fromRawValue(modeRaw)

View File

@@ -28,6 +28,7 @@ class ConnectionManager(
private val callLogAvailable: () -> Boolean,
private val photosAvailable: () -> Boolean,
private val hasRecordAudioPermission: () -> Boolean,
private val installedAppsSharingEnabled: () -> Boolean,
private val manualTls: () -> Boolean,
) {
companion object {
@@ -115,6 +116,7 @@ class ConnectionManager(
voiceWakeEnabled = voiceWakeMode() != VoiceWakeMode.Off && hasRecordAudioPermission(),
motionActivityAvailable = motionActivityAvailable(),
motionPedometerAvailable = motionPedometerAvailable(),
installedAppsSharingEnabled = installedAppsSharingEnabled(),
debugBuild = BuildConfig.DEBUG,
)

View File

@@ -8,6 +8,7 @@ import android.app.ActivityManager
import android.content.Context
import android.content.Intent
import android.content.IntentFilter
import android.content.pm.ApplicationInfo
import android.content.pm.PackageManager
import android.net.ConnectivityManager
import android.net.NetworkCapabilities
@@ -24,16 +25,121 @@ import kotlinx.serialization.json.buildJsonObject
import kotlinx.serialization.json.put
import java.util.Locale
private const val DEFAULT_DEVICE_APPS_LIMIT = 100
private const val MAX_DEVICE_APPS_LIMIT = 200
private const val DEVICE_APPS_SYSTEM_FLAGS =
ApplicationInfo.FLAG_SYSTEM or ApplicationInfo.FLAG_UPDATED_SYSTEM_APP
internal fun isSystemDeviceApp(appInfo: ApplicationInfo): Boolean =
(appInfo.flags and DEVICE_APPS_SYSTEM_FLAGS) != 0
internal data class DeviceAppEntry(
val label: String,
val packageName: String,
val system: Boolean,
val enabled: Boolean,
val launchable: Boolean,
)
internal interface DeviceAppSource {
fun listApps(includeNonLaunchable: Boolean): List<DeviceAppEntry>
}
private class AndroidDeviceAppSource(
private val appContext: Context,
) : DeviceAppSource {
override fun listApps(includeNonLaunchable: Boolean): List<DeviceAppEntry> {
val packageManager = appContext.packageManager
val launcherIntent = Intent(Intent.ACTION_MAIN).apply { addCategory(Intent.CATEGORY_LAUNCHER) }
val launchablePackages =
packageManager
.queryIntentActivities(launcherIntent, PackageManager.MATCH_ALL)
.asSequence()
.mapNotNull {
it.activityInfo
?.packageName
?.trim()
?.takeIf(String::isNotEmpty)
}.toSet()
val appInfos =
if (includeNonLaunchable) {
packageManager.getInstalledApplications(PackageManager.MATCH_ALL)
} else {
launchablePackages.mapNotNull { packageName ->
runCatching { packageManager.getApplicationInfo(packageName, 0) }.getOrNull()
}
}
return appInfos
.asSequence()
.mapNotNull { appInfo ->
appInfo.packageName
?.trim()
?.takeIf(String::isNotEmpty)
?.let { packageName ->
val label = packageManager.getApplicationLabel(appInfo).toString().trim()
DeviceAppEntry(
label = label.ifEmpty { packageName },
packageName = packageName,
system = isSystemDeviceApp(appInfo),
enabled = appInfo.enabled,
launchable = packageName in launchablePackages,
)
}
}.distinctBy { it.packageName }
.sortedWith(compareBy<DeviceAppEntry> { it.label.lowercase() }.thenBy { it.packageName })
.toList()
}
}
private data class DeviceAppsRequest(
val includeSystem: Boolean,
val includeDisabled: Boolean,
val includeNonLaunchable: Boolean,
val query: String?,
val limit: Int,
)
/**
* Gateway device command adapter for Android status, info, permission, and health snapshots.
*/
class DeviceHandler(
class DeviceHandler private constructor(
private val appContext: Context,
private val smsEnabled: Boolean = SensitiveFeatureConfig.smsEnabled,
private val callLogEnabled: Boolean = SensitiveFeatureConfig.callLogEnabled,
private val photosEnabled: Boolean = SensitiveFeatureConfig.photosEnabled,
private val appSource: DeviceAppSource = AndroidDeviceAppSource(appContext),
) {
constructor(
appContext: Context,
smsEnabled: Boolean = SensitiveFeatureConfig.smsEnabled,
callLogEnabled: Boolean = SensitiveFeatureConfig.callLogEnabled,
photosEnabled: Boolean = SensitiveFeatureConfig.photosEnabled,
) : this(
appContext = appContext,
smsEnabled = smsEnabled,
callLogEnabled = callLogEnabled,
photosEnabled = photosEnabled,
appSource = AndroidDeviceAppSource(appContext),
)
companion object {
internal fun forTesting(
appContext: Context,
appSource: DeviceAppSource,
smsEnabled: Boolean = SensitiveFeatureConfig.smsEnabled,
callLogEnabled: Boolean = SensitiveFeatureConfig.callLogEnabled,
photosEnabled: Boolean = SensitiveFeatureConfig.photosEnabled,
): DeviceHandler =
DeviceHandler(
appContext = appContext,
smsEnabled = smsEnabled,
callLogEnabled = callLogEnabled,
photosEnabled = photosEnabled,
appSource = appSource,
)
/**
* SMS is available only when the feature flag, telephony hardware, and at least one SMS permission align.
*/
@@ -74,6 +180,48 @@ class DeviceHandler(
/** Returns coarse device health for memory, power, thermal, battery, and security patch state. */
fun handleDeviceHealth(_paramsJson: String?): GatewaySession.InvokeResult = GatewaySession.InvokeResult.ok(healthPayloadJson())
fun handleDeviceApps(paramsJson: String?): GatewaySession.InvokeResult {
val request = parseDeviceAppsRequest(paramsJson)
val matchingApps =
appSource
.listApps(includeNonLaunchable = request.includeNonLaunchable)
.asSequence()
.filter { request.includeSystem || !it.system }
.filter { request.includeDisabled || it.enabled }
.filter { app ->
val query = request.query ?: return@filter true
app.label.contains(query, ignoreCase = true) || app.packageName.contains(query, ignoreCase = true)
}.toList()
val limitedApps = matchingApps.take(request.limit)
return GatewaySession.InvokeResult.ok(
buildJsonObject {
put("count", JsonPrimitive(limitedApps.size))
put("totalMatched", JsonPrimitive(matchingApps.size))
put("truncated", JsonPrimitive(matchingApps.size > limitedApps.size))
put("visibility", JsonPrimitive(if (request.includeNonLaunchable) "android-visible" else "launcher"))
put("includeSystem", JsonPrimitive(request.includeSystem))
put("includeDisabled", JsonPrimitive(request.includeDisabled))
put(
"apps",
buildJsonArray {
for (app in limitedApps) {
add(
buildJsonObject {
put("label", JsonPrimitive(app.label))
put("packageName", JsonPrimitive(app.packageName))
put("system", JsonPrimitive(app.system))
put("enabled", JsonPrimitive(app.enabled))
put("launchable", JsonPrimitive(app.launchable))
},
)
}
},
)
}.toString(),
)
}
private fun statusPayloadJson(): String {
val battery = readBatterySnapshot()
val powerManager = appContext.getSystemService(PowerManager::class.java)
@@ -365,6 +513,24 @@ class DeviceHandler(
}.toString()
}
private fun parseDeviceAppsRequest(paramsJson: String?): DeviceAppsRequest {
val params = parseJsonParamsObject(paramsJson)
val includeSystem = parseJsonBooleanFlag(params, "includeSystem") ?: false
val includeDisabled = parseJsonBooleanFlag(params, "includeDisabled") ?: false
val includeNonLaunchable = parseJsonBooleanFlag(params, "includeNonLaunchable") ?: false
val query = parseJsonString(params, "query")?.trim()?.takeIf { it.isNotEmpty() }
val limit =
(parseJsonInt(params, "limit") ?: DEFAULT_DEVICE_APPS_LIMIT)
.coerceIn(1, MAX_DEVICE_APPS_LIMIT)
return DeviceAppsRequest(
includeSystem = includeSystem,
includeDisabled = includeDisabled,
includeNonLaunchable = includeNonLaunchable,
query = query,
limit = limit,
)
}
private fun readBatterySnapshot(): BatterySnapshot {
// ACTION_BATTERY_CHANGED is sticky; registerReceiver(null, ...) reads the last system snapshot.
val intent = appContext.registerReceiver(null, IntentFilter(Intent.ACTION_BATTERY_CHANGED))

View File

@@ -28,6 +28,7 @@ data class NodeRuntimeFlags(
val voiceWakeEnabled: Boolean,
val motionActivityAvailable: Boolean,
val motionPedometerAvailable: Boolean,
val installedAppsSharingEnabled: Boolean,
val debugBuild: Boolean,
)
@@ -43,6 +44,7 @@ enum class InvokeCommandAvailability {
PhotosAvailable,
MotionActivityAvailable,
MotionPedometerAvailable,
InstalledAppsSharingEnabled,
DebugBuild,
}
@@ -193,6 +195,10 @@ object InvokeCommandRegistry {
InvokeCommandSpec(
name = OpenClawDeviceCommand.Health.rawValue,
),
InvokeCommandSpec(
name = OpenClawDeviceCommand.Apps.rawValue,
availability = InvokeCommandAvailability.InstalledAppsSharingEnabled,
),
InvokeCommandSpec(
name = OpenClawNotificationsCommand.List.rawValue,
),
@@ -281,6 +287,7 @@ object InvokeCommandRegistry {
InvokeCommandAvailability.PhotosAvailable -> flags.photosAvailable
InvokeCommandAvailability.MotionActivityAvailable -> flags.motionActivityAvailable
InvokeCommandAvailability.MotionPedometerAvailable -> flags.motionPedometerAvailable
InvokeCommandAvailability.InstalledAppsSharingEnabled -> flags.installedAppsSharingEnabled
InvokeCommandAvailability.DebugBuild -> flags.debugBuild
}
}.map { it.name }

View File

@@ -85,6 +85,7 @@ class InvokeDispatcher(
private val smsTelephonyAvailable: () -> Boolean,
private val callLogAvailable: () -> Boolean,
private val photosAvailable: () -> Boolean,
private val installedAppsSharingEnabled: () -> Boolean,
private val debugBuild: () -> Boolean,
private val onCanvasA2uiPush: () -> Unit,
private val onCanvasA2uiReset: () -> Unit,
@@ -193,6 +194,7 @@ class InvokeDispatcher(
OpenClawDeviceCommand.Info.rawValue -> deviceHandler.handleDeviceInfo(paramsJson)
OpenClawDeviceCommand.Permissions.rawValue -> deviceHandler.handleDevicePermissions(paramsJson)
OpenClawDeviceCommand.Health.rawValue -> deviceHandler.handleDeviceHealth(paramsJson)
OpenClawDeviceCommand.Apps.rawValue -> deviceHandler.handleDeviceApps(paramsJson)
// Notifications command
OpenClawNotificationsCommand.List.rawValue -> notificationsHandler.handleNotificationsList(paramsJson)
@@ -348,6 +350,15 @@ class InvokeDispatcher(
message = "PHOTOS_UNAVAILABLE: photos not available on this build",
)
}
InvokeCommandAvailability.InstalledAppsSharingEnabled ->
if (installedAppsSharingEnabled()) {
null
} else {
GatewaySession.InvokeResult.error(
code = "INSTALLED_APPS_SHARING_DISABLED",
message = "INSTALLED_APPS_SHARING_DISABLED: enable Installed Apps in Settings",
)
}
InvokeCommandAvailability.DebugBuild ->
if (debugBuild()) {
null

View File

@@ -112,6 +112,7 @@ enum class OpenClawDeviceCommand(
Info("device.info"),
Permissions("device.permissions"),
Health("device.health"),
Apps("device.apps"),
;
companion object {

View File

@@ -0,0 +1,82 @@
package ai.openclaw.app.ui
import ai.openclaw.app.node.DeviceNotificationListenerService
import android.content.Context
import android.content.Intent
import android.content.pm.PackageManager
/** App entry shown in the notification-forwarding package picker. */
data class InstalledApp(
val label: String,
val packageName: String,
val isSystemApp: Boolean,
)
/** Reads launcher, recent-notification, and configured packages for the picker. */
internal fun queryInstalledApps(
context: Context,
configuredPackages: Set<String>,
): List<InstalledApp> {
val packageManager = context.packageManager
val launcherIntent = Intent(Intent.ACTION_MAIN).apply { addCategory(Intent.CATEGORY_LAUNCHER) }
val launcherPackages =
packageManager
.queryIntentActivities(launcherIntent, PackageManager.MATCH_ALL)
.asSequence()
.mapNotNull {
it.activityInfo
?.packageName
?.trim()
?.takeIf(String::isNotEmpty)
}.toMutableSet()
val recentNotificationPackages =
DeviceNotificationListenerService
.recentPackages(context)
.asSequence()
.map { it.trim() }
.filter { it.isNotEmpty() }
.toList()
val candidatePackages =
resolveNotificationCandidatePackages(
launcherPackages = launcherPackages,
recentPackages = recentNotificationPackages,
configuredPackages = configuredPackages,
appPackageName = context.packageName,
)
return candidatePackages
.asSequence()
.mapNotNull { packageName ->
runCatching {
val appInfo = packageManager.getApplicationInfo(packageName, 0)
val label = packageManager.getApplicationLabel(appInfo).toString().trim()
InstalledApp(
label = if (label.isEmpty()) packageName else label,
packageName = packageName,
isSystemApp = (appInfo.flags and android.content.pm.ApplicationInfo.FLAG_SYSTEM) != 0,
)
}.getOrNull()
}.sortedWith(compareBy<InstalledApp> { it.label.lowercase() }.thenBy { it.packageName })
.toList()
}
/** Merges package sources while excluding OpenClaw from its own forwarding filter. */
internal fun resolveNotificationCandidatePackages(
launcherPackages: Set<String>,
recentPackages: List<String>,
configuredPackages: Set<String>,
appPackageName: String,
): Set<String> {
val blockedPackage = appPackageName.trim()
return sequenceOf(
configuredPackages.asSequence(),
launcherPackages.asSequence(),
recentPackages.asSequence(),
).flatten()
.map { it.trim() }
.filter { it.isNotEmpty() && it != blockedPackage }
.toSet()
}

View File

@@ -493,6 +493,8 @@ private fun playVoiceSetupTone() {
Handler(Looper.getMainLooper()).postDelayed({ tone.release() }, 300L)
}
private const val NOTIFICATION_PICKER_RESULT_LIMIT = 40
@Composable
private fun NotificationSettingsScreen(
viewModel: MainViewModel,
@@ -507,6 +509,19 @@ private fun NotificationSettingsScreen(
val quietEnd by viewModel.notificationForwardingQuietEnd.collectAsState()
val maxEventsPerMinute by viewModel.notificationForwardingMaxEventsPerMinute.collectAsState()
val modeLabel = if (mode == NotificationPackageFilterMode.Blocklist) "Blocklist" else "Allowlist"
val installedApps = remember(context, packages) { queryInstalledApps(context, packages) }
var notificationPickerExpanded by remember { mutableStateOf(false) }
var notificationAppSearch by remember { mutableStateOf("") }
var notificationShowSystemApps by remember { mutableStateOf(false) }
val filteredApps =
remember(installedApps, packages, notificationAppSearch, notificationShowSystemApps) {
filterNotificationAppsForPicker(
apps = installedApps,
selectedPackages = packages,
query = notificationAppSearch,
showSystemApps = notificationShowSystemApps,
)
}
var listenerEnabled by remember { mutableStateOf(DeviceNotificationListenerService.isAccessEnabled(context)) }
val notificationPermissionLauncher =
rememberLauncherForActivityResult(ActivityResultContracts.RequestPermission()) { granted ->
@@ -567,6 +582,124 @@ private fun NotificationSettingsScreen(
)
}
}
NotificationPackagePickerPanel(
mode = mode,
selectedPackages = packages,
apps = filteredApps,
search = notificationAppSearch,
showSystemApps = notificationShowSystemApps,
expanded = notificationPickerExpanded,
onSearchChange = { notificationAppSearch = it },
onShowSystemAppsChange = { notificationShowSystemApps = it },
onExpandedChange = { notificationPickerExpanded = it },
onPackageSelectionChange = { packageName, selected ->
val next = packages.toMutableSet()
if (selected) {
next.add(packageName)
} else {
next.remove(packageName)
}
viewModel.setNotificationForwardingPackagesCsv(next.sorted().joinToString(","))
},
)
}
}
@Composable
private fun NotificationPackagePickerPanel(
mode: NotificationPackageFilterMode,
selectedPackages: Set<String>,
apps: List<InstalledApp>,
search: String,
showSystemApps: Boolean,
expanded: Boolean,
onSearchChange: (String) -> Unit,
onShowSystemAppsChange: (Boolean) -> Unit,
onExpandedChange: (Boolean) -> Unit,
onPackageSelectionChange: (String, Boolean) -> Unit,
) {
val visibleApps = apps.take(NOTIFICATION_PICKER_RESULT_LIMIT)
ClawPanel {
Column(verticalArrangement = Arrangement.spacedBy(10.dp)) {
Text(text = "App Filter", style = ClawTheme.type.section, color = ClawTheme.colors.text)
Text(
text = notificationPackageSelectionSummary(mode = mode, selectedCount = selectedPackages.size),
style = ClawTheme.type.body,
color = ClawTheme.colors.textMuted,
)
ClawSecondaryButton(
text = if (expanded) "Close App Picker" else "Open App Picker",
onClick = { onExpandedChange(!expanded) },
modifier = Modifier.fillMaxWidth(),
)
if (expanded) {
ClawTextField(value = search, onValueChange = onSearchChange, placeholder = "Search apps")
SettingsToggleListRow(
SettingsToggleRow(
title = "Show System Apps",
subtitle = "Include Android and background packages.",
icon = Icons.Default.Storage,
checked = showSystemApps,
onCheckedChange = onShowSystemAppsChange,
),
)
if (visibleApps.isEmpty()) {
Text(text = "No matching apps.", style = ClawTheme.type.body, color = ClawTheme.colors.textMuted)
} else {
ClawSeparatedColumn(items = visibleApps) { app ->
NotificationPackageAppRow(
app = app,
selected = selectedPackages.contains(app.packageName),
onSelectedChange = { selected -> onPackageSelectionChange(app.packageName, selected) },
)
}
if (apps.size > visibleApps.size) {
Text(
text = "Showing ${visibleApps.size} of ${apps.size}. Refine search for more.",
style = ClawTheme.type.caption,
color = ClawTheme.colors.textMuted,
)
}
}
}
}
}
}
@Composable
private fun NotificationPackageAppRow(
app: InstalledApp,
selected: Boolean,
onSelectedChange: (Boolean) -> Unit,
) {
Row(
modifier =
Modifier
.fillMaxWidth()
.heightIn(min = 58.dp)
.clickable { onSelectedChange(!selected) }
.padding(vertical = 7.dp),
verticalAlignment = Alignment.CenterVertically,
horizontalArrangement = Arrangement.spacedBy(9.dp),
) {
ClawTextBadge(text = notificationAppBadge(app.label))
Column(modifier = Modifier.weight(1f), verticalArrangement = Arrangement.spacedBy(1.dp)) {
Text(
text = app.label,
style = ClawTheme.type.body,
color = ClawTheme.colors.text,
maxLines = 1,
overflow = TextOverflow.Ellipsis,
)
Text(
text = app.packageName,
style = ClawTheme.type.caption,
color = ClawTheme.colors.textMuted,
maxLines = 1,
overflow = TextOverflow.Ellipsis,
)
}
Switch(checked = selected, onCheckedChange = onSelectedChange)
}
}
@@ -581,6 +714,7 @@ private fun PhoneCapabilitiesScreen(
val locationPreciseEnabled by viewModel.locationPreciseEnabled.collectAsState()
val preventSleep by viewModel.preventSleep.collectAsState()
val canvasDebugStatusEnabled by viewModel.canvasDebugStatusEnabled.collectAsState()
val installedAppsSharingEnabled by viewModel.installedAppsSharingEnabled.collectAsState()
val cameraPermissionLauncher =
rememberLauncherForActivityResult(ActivityResultContracts.RequestPermission()) { granted ->
viewModel.setCameraEnabled(granted)
@@ -635,6 +769,13 @@ private fun PhoneCapabilitiesScreen(
listOf(
SettingsToggleRow("Camera", "Allow camera tools when requested.", Icons.Default.CameraAlt, cameraEnabled, ::setCameraAccess),
SettingsToggleRow("Precise Location", "Share precise location while location is enabled.", Icons.Default.LocationOn, locationPreciseEnabled, ::setPreciseLocation),
SettingsToggleRow(
"Installed Apps",
if (installedAppsSharingEnabled) "OpenClaw can list launcher-visible apps." else "App list stays on this phone.",
Icons.Default.Storage,
installedAppsSharingEnabled,
viewModel::setInstalledAppsSharingEnabled,
),
SettingsToggleRow("Keep Awake", "Keep the node available during active work.", Icons.Default.Bolt, preventSleep, viewModel::setPreventSleep),
SettingsToggleRow("Canvas Status", "Show screen-sharing debug state.", Icons.AutoMirrored.Filled.ScreenShare, canvasDebugStatusEnabled, viewModel::setCanvasDebugStatusEnabled),
),
@@ -1112,6 +1253,58 @@ private fun cronJobStatus(job: GatewayCronJobSummary): ClawStatus {
}
}
/** Applies query/system visibility rules while always preserving selected packages. */
internal fun filterNotificationAppsForPicker(
apps: List<InstalledApp>,
selectedPackages: Set<String>,
query: String,
showSystemApps: Boolean,
): List<InstalledApp> {
val normalizedQuery = query.trim().lowercase()
return apps.filter { app ->
val selected = app.packageName in selectedPackages
val visibleByType = showSystemApps || !app.isSystemApp || selected
val visibleBySearch =
normalizedQuery.isEmpty() ||
app.label.lowercase().contains(normalizedQuery) ||
app.packageName.lowercase().contains(normalizedQuery)
visibleByType && visibleBySearch
}
}
/** Summarizes allowlist/blocklist mode with an empty-state warning when needed. */
private fun notificationPackageSelectionSummary(
mode: NotificationPackageFilterMode,
selectedCount: Int,
): String =
when (mode) {
NotificationPackageFilterMode.Allowlist ->
if (selectedCount == 0) {
"No apps selected. Nothing forwards until you add apps."
} else {
"$selectedCount ${if (selectedCount == 1) "app" else "apps"} allowed to forward."
}
NotificationPackageFilterMode.Blocklist ->
if (selectedCount == 0) {
"No apps blocked. Apps can forward unless you add blocks."
} else {
"$selectedCount ${if (selectedCount == 1) "app" else "apps"} blocked from forwarding."
}
}
/** Builds compact two-letter app badges from package-picker labels. */
private fun notificationAppBadge(label: String): String {
val initials =
label
.split(' ', '-', '_', '.')
.asSequence()
.filter { it.isNotBlank() }
.take(2)
.mapNotNull { it.firstOrNull()?.uppercaseChar()?.toString() }
.joinToString("")
return initials.ifBlank { "A" }
}
/**
* Converts cron wake times into short relative labels for scheduled-work rows.
*/

View File

@@ -1222,82 +1222,6 @@ fun SettingsSheet(viewModel: MainViewModel) {
}
}
/** App entry shown in the notification-forwarding package picker. */
data class InstalledApp(
val label: String,
val packageName: String,
val isSystemApp: Boolean,
)
/** Reads launcher, recent-notification, and configured packages for the picker. */
private fun queryInstalledApps(
context: Context,
configuredPackages: Set<String>,
): List<InstalledApp> {
val packageManager = context.packageManager
val launcherIntent = Intent(Intent.ACTION_MAIN).apply { addCategory(Intent.CATEGORY_LAUNCHER) }
val launcherPackages =
packageManager
.queryIntentActivities(launcherIntent, PackageManager.MATCH_ALL)
.asSequence()
.mapNotNull {
it.activityInfo
?.packageName
?.trim()
?.takeIf(String::isNotEmpty)
}.toMutableSet()
val recentNotificationPackages =
DeviceNotificationListenerService
.recentPackages(context)
.asSequence()
.map { it.trim() }
.filter { it.isNotEmpty() }
.toList()
val candidatePackages =
resolveNotificationCandidatePackages(
launcherPackages = launcherPackages,
recentPackages = recentNotificationPackages,
configuredPackages = configuredPackages,
appPackageName = context.packageName,
)
return candidatePackages
.asSequence()
.mapNotNull { packageName ->
runCatching {
val appInfo = packageManager.getApplicationInfo(packageName, 0)
val label = packageManager.getApplicationLabel(appInfo).toString().trim()
InstalledApp(
label = if (label.isEmpty()) packageName else label,
packageName = packageName,
isSystemApp = (appInfo.flags and android.content.pm.ApplicationInfo.FLAG_SYSTEM) != 0,
)
}.getOrNull()
}.sortedWith(compareBy<InstalledApp> { it.label.lowercase() }.thenBy { it.packageName })
.toList()
}
/** Merges package sources while excluding OpenClaw from its own forwarding filter. */
internal fun resolveNotificationCandidatePackages(
launcherPackages: Set<String>,
recentPackages: List<String>,
configuredPackages: Set<String>,
appPackageName: String,
): Set<String> {
val blockedPackage = appPackageName.trim()
return sequenceOf(
configuredPackages.asSequence(),
launcherPackages.asSequence(),
recentPackages.asSequence(),
).flatten()
.map { it.trim() }
.filter { it.isNotEmpty() && it != blockedPackage }
.toSet()
}
/** Shared Material text-field colors for the legacy mobile settings sheet. */
@Composable
private fun settingsTextFieldColors() =

View File

@@ -62,6 +62,21 @@ class SecurePrefsTest {
assertFalse(plainPrefs.getBoolean("talk.enabled", false))
}
@Test
fun installedAppsSharing_defaultsOffAndPersistsOptIn() {
val context = RuntimeEnvironment.getApplication()
val plainPrefs = context.getSharedPreferences("openclaw.node", Context.MODE_PRIVATE)
plainPrefs.edit().clear().commit()
val prefs = SecurePrefs(context)
assertFalse(prefs.installedAppsSharingEnabled.value)
prefs.setInstalledAppsSharingEnabled(true)
assertTrue(prefs.installedAppsSharingEnabled.value)
assertTrue(plainPrefs.getBoolean("device.apps.sharing.enabled", false))
}
@Test
fun saveGatewayBootstrapToken_persistsSeparatelyFromSharedToken() {
val context = RuntimeEnvironment.getApplication()

View File

@@ -9,6 +9,7 @@ import ai.openclaw.app.gateway.isLoopbackGatewayHost
import ai.openclaw.app.protocol.OpenClawCallLogCommand
import ai.openclaw.app.protocol.OpenClawCameraCommand
import ai.openclaw.app.protocol.OpenClawCapability
import ai.openclaw.app.protocol.OpenClawDeviceCommand
import ai.openclaw.app.protocol.OpenClawLocationCommand
import ai.openclaw.app.protocol.OpenClawMotionCommand
import ai.openclaw.app.protocol.OpenClawPhotosCommand
@@ -475,6 +476,15 @@ class ConnectionManagerTest {
assertTrue(options.caps.contains(OpenClawCapability.VoiceWake.rawValue))
}
@Test
fun buildNodeConnectOptions_advertisesDeviceAppsOnlyWhenUserOptedIn() {
val disabled = newManager(installedAppsSharingEnabled = false).buildNodeConnectOptions()
val enabled = newManager(installedAppsSharingEnabled = true).buildNodeConnectOptions()
assertFalse(disabled.commands.contains(OpenClawDeviceCommand.Apps.rawValue))
assertTrue(enabled.commands.contains(OpenClawDeviceCommand.Apps.rawValue))
}
@Test
fun buildNodeConnectOptions_omitsVoiceWakeWithoutMicrophonePermission() {
val options =
@@ -546,6 +556,7 @@ class ConnectionManagerTest {
callLogAvailable: Boolean = false,
photosAvailable: Boolean = false,
hasRecordAudioPermission: Boolean = false,
installedAppsSharingEnabled: Boolean = false,
): ConnectionManager {
val context = RuntimeEnvironment.getApplication()
val prefs =
@@ -567,6 +578,7 @@ class ConnectionManagerTest {
callLogAvailable = { callLogAvailable },
photosAvailable = { photosAvailable },
hasRecordAudioPermission = { hasRecordAudioPermission },
installedAppsSharingEnabled = { installedAppsSharingEnabled },
manualTls = { false },
)
}

View File

@@ -1,6 +1,7 @@
package ai.openclaw.app.node
import android.content.Context
import android.content.pm.ApplicationInfo
import kotlinx.serialization.json.Json
import kotlinx.serialization.json.JsonObject
import kotlinx.serialization.json.boolean
@@ -320,6 +321,108 @@ class DeviceHandlerTest {
system["securityPatchLevel"]?.jsonPrimitive?.content
}
@Test
fun handleDeviceApps_filtersAndLimitsVisibleApps() {
val handler =
DeviceHandler.forTesting(
appContext = appContext(),
appSource =
FakeDeviceAppSource(
listOf(
DeviceAppEntry(
label = "Calendar",
packageName = "com.google.android.calendar",
system = false,
enabled = true,
launchable = true,
),
DeviceAppEntry(
label = "Android System",
packageName = "android",
system = true,
enabled = true,
launchable = false,
),
DeviceAppEntry(
label = "Disabled App",
packageName = "com.example.disabled",
system = false,
enabled = false,
launchable = true,
),
DeviceAppEntry(
label = "Gmail",
packageName = "com.google.android.gm",
system = false,
enabled = true,
launchable = true,
),
),
),
)
val result = handler.handleDeviceApps("""{"query":"google","limit":1}""")
assertTrue(result.ok)
val payload = parsePayload(result.payloadJson)
assertEquals("1", payload.getValue("count").jsonPrimitive.content)
assertEquals("2", payload.getValue("totalMatched").jsonPrimitive.content)
assertTrue(payload.getValue("truncated").jsonPrimitive.boolean)
assertEquals("launcher", payload.getValue("visibility").jsonPrimitive.content)
val apps = payload.getValue("apps").jsonArray
assertEquals(1, apps.size)
val app = apps.first().jsonObject
assertEquals("Calendar", app.getValue("label").jsonPrimitive.content)
assertEquals("com.google.android.calendar", app.getValue("packageName").jsonPrimitive.content)
assertTrue(!app.getValue("system").jsonPrimitive.boolean)
assertTrue(app.getValue("enabled").jsonPrimitive.boolean)
assertTrue(app.getValue("launchable").jsonPrimitive.boolean)
}
@Test
fun handleDeviceApps_canIncludeSystemAndNonLaunchableApps() {
val source =
FakeDeviceAppSource(
listOf(
DeviceAppEntry(
label = "Android System",
packageName = "android",
system = true,
enabled = true,
launchable = false,
),
),
)
val handler = DeviceHandler.forTesting(appContext = appContext(), appSource = source)
val result = handler.handleDeviceApps("""{"includeSystem":true,"includeNonLaunchable":true}""")
assertTrue(result.ok)
val payload = parsePayload(result.payloadJson)
assertEquals("android-visible", payload.getValue("visibility").jsonPrimitive.content)
assertTrue(payload.getValue("includeSystem").jsonPrimitive.boolean)
val app =
payload
.getValue("apps")
.jsonArray
.first()
.jsonObject
assertEquals("android", app.getValue("packageName").jsonPrimitive.content)
assertTrue(app.getValue("system").jsonPrimitive.boolean)
assertTrue(!app.getValue("launchable").jsonPrimitive.boolean)
assertTrue(source.includeNonLaunchableRequests.single())
}
@Test
fun isSystemDeviceApp_treatsUpdatedBuiltInsAsSystemApps() {
val appInfo =
ApplicationInfo().apply {
flags = ApplicationInfo.FLAG_UPDATED_SYSTEM_APP
}
assertTrue(isSystemDeviceApp(appInfo))
}
private fun appContext(): Context = RuntimeEnvironment.getApplication()
private fun parsePayload(payloadJson: String?): JsonObject {
@@ -327,3 +430,14 @@ class DeviceHandlerTest {
return Json.parseToJsonElement(jsonString).jsonObject
}
}
private class FakeDeviceAppSource(
private val apps: List<DeviceAppEntry>,
) : DeviceAppSource {
val includeNonLaunchableRequests = mutableListOf<Boolean>()
override fun listApps(includeNonLaunchable: Boolean): List<DeviceAppEntry> {
includeNonLaunchableRequests += includeNonLaunchable
return apps
}
}

View File

@@ -115,6 +115,15 @@ class InvokeCommandRegistryTest {
assertMissingAll(commands, optionalCommands + debugCommands)
}
@Test
fun advertisedCommands_includesDeviceAppsOnlyWhenUserOptedIn() {
val disabled = InvokeCommandRegistry.advertisedCommands(defaultFlags(installedAppsSharingEnabled = false))
val enabled = InvokeCommandRegistry.advertisedCommands(defaultFlags(installedAppsSharingEnabled = true))
assertFalse(disabled.contains(OpenClawDeviceCommand.Apps.rawValue))
assertTrue(enabled.contains(OpenClawDeviceCommand.Apps.rawValue))
}
@Test
fun advertisedCommands_includesFeatureCommandsWhenEnabled() {
val commands =
@@ -151,6 +160,7 @@ class InvokeCommandRegistryTest {
voiceWakeEnabled = false,
motionActivityAvailable = true,
motionPedometerAvailable = false,
installedAppsSharingEnabled = false,
debugBuild = false,
),
)
@@ -262,6 +272,7 @@ class InvokeCommandRegistryTest {
voiceWakeEnabled: Boolean = false,
motionActivityAvailable: Boolean = false,
motionPedometerAvailable: Boolean = false,
installedAppsSharingEnabled: Boolean = false,
debugBuild: Boolean = false,
): NodeRuntimeFlags =
NodeRuntimeFlags(
@@ -275,6 +286,7 @@ class InvokeCommandRegistryTest {
voiceWakeEnabled = voiceWakeEnabled,
motionActivityAvailable = motionActivityAvailable,
motionPedometerAvailable = motionPedometerAvailable,
installedAppsSharingEnabled = installedAppsSharingEnabled,
debugBuild = debugBuild,
)

View File

@@ -4,6 +4,7 @@ import ai.openclaw.app.gateway.DeviceIdentityStore
import ai.openclaw.app.gateway.GatewaySession
import ai.openclaw.app.protocol.OpenClawCallLogCommand
import ai.openclaw.app.protocol.OpenClawCameraCommand
import ai.openclaw.app.protocol.OpenClawDeviceCommand
import ai.openclaw.app.protocol.OpenClawLocationCommand
import ai.openclaw.app.protocol.OpenClawMotionCommand
import ai.openclaw.app.protocol.OpenClawPhotosCommand
@@ -170,6 +171,20 @@ class InvokeDispatcherTest {
assertEquals("LOCATION_DISABLED: enable Location in Settings", result.error?.message)
}
@Test
fun handleInvoke_blocksDeviceAppsWhenSharingDisabled() =
runTest {
val result =
newDispatcher(installedAppsSharingEnabled = false)
.handleInvoke(OpenClawDeviceCommand.Apps.rawValue, """{"limit":1}""")
assertEquals("INSTALLED_APPS_SHARING_DISABLED", result.error?.code)
assertEquals(
"INSTALLED_APPS_SHARING_DISABLED: enable Installed Apps in Settings",
result.error?.message,
)
}
@Test
fun handleInvoke_blocksMotionActivityWhenUnavailable() =
runTest {
@@ -250,6 +265,7 @@ class InvokeDispatcherTest {
smsTelephonyAvailable: Boolean = true,
callLogAvailable: Boolean = false,
photosAvailable: Boolean = true,
installedAppsSharingEnabled: Boolean = true,
debugBuild: Boolean = false,
motionActivityAvailable: Boolean = false,
motionPedometerAvailable: Boolean = false,
@@ -297,6 +313,7 @@ class InvokeDispatcherTest {
smsTelephonyAvailable = { smsTelephonyAvailable },
callLogAvailable = { callLogAvailable },
photosAvailable = { photosAvailable },
installedAppsSharingEnabled = { installedAppsSharingEnabled },
debugBuild = { debugBuild },
onCanvasA2uiPush = {},
onCanvasA2uiReset = {},

View File

@@ -57,6 +57,7 @@ class OpenClawProtocolConstantsTest {
assertEquals("device.info", OpenClawDeviceCommand.Info.rawValue)
assertEquals("device.permissions", OpenClawDeviceCommand.Permissions.rawValue)
assertEquals("device.health", OpenClawDeviceCommand.Health.rawValue)
assertEquals("device.apps", OpenClawDeviceCommand.Apps.rawValue)
}
@Test

View File

@@ -32,4 +32,46 @@ class SettingsSheetNotificationAppsTest {
assertEquals(setOf("com.example.recent", "com.example.configured"), packages)
}
@Test
fun filterNotificationAppsForPicker_keepsSelectedSystemPackagesVisible() {
val apps =
listOf(
InstalledApp(label = "Android System", packageName = "android", isSystemApp = true),
InstalledApp(label = "Phone Services", packageName = "com.android.phone", isSystemApp = true),
InstalledApp(label = "Gmail", packageName = "com.google.android.gm", isSystemApp = false),
)
val filtered =
filterNotificationAppsForPicker(
apps = apps,
selectedPackages = setOf("com.android.phone"),
query = "",
showSystemApps = false,
)
assertEquals(
listOf("com.android.phone", "com.google.android.gm"),
filtered.map { it.packageName },
)
}
@Test
fun filterNotificationAppsForPicker_matchesLabelsAndPackageNames() {
val apps =
listOf(
InstalledApp(label = "Gmail", packageName = "com.google.android.gm", isSystemApp = false),
InstalledApp(label = "Calendar", packageName = "com.google.android.calendar", isSystemApp = false),
)
val filtered =
filterNotificationAppsForPicker(
apps = apps,
selectedPackages = emptySet(),
query = "gm",
showSystemApps = false,
)
assertEquals(listOf("com.google.android.gm"), filtered.map { it.packageName })
}
}

View File

@@ -1,6 +1,10 @@
# OpenClaw iOS Changelog
## 2026.5.31 - 2026-05-31
## 2026.6.2 - 2026-06-02
Maintenance update for the current OpenClaw release.
## 2026.6.1 - 2026-06-01
Maintenance update for the current OpenClaw release.

View File

@@ -2,8 +2,8 @@
// Source of truth: apps/ios/version.json
// Generated by scripts/ios-sync-versioning.ts.
OPENCLAW_IOS_VERSION = 2026.5.31
OPENCLAW_MARKETING_VERSION = 2026.5.31
OPENCLAW_IOS_VERSION = 2026.6.2
OPENCLAW_MARKETING_VERSION = 2026.6.2
OPENCLAW_BUILD_VERSION = 1
#include? "../build/Version.xcconfig"

View File

@@ -1,5 +1 @@
Maintenance update for the current OpenClaw release.
- Added hosted push relay defaults, realtime Talk playback, and safer WebSocket ping handling for mobile sessions.
- Updated App Store screenshots to cover Gateway pairing, Command, Chat, Talk, Agent, and Settings flows.
- Highlighted realtime Talk relay, Gateway connection status, node capabilities, push wake, and privacy controls.

View File

@@ -1,3 +1,3 @@
{
"version": "2026.5.31"
"version": "2026.6.2"
}

View File

@@ -514,12 +514,16 @@ extension GatewayConnection {
var params: [String: AnyCodable] = [
"message": AnyCodable(trimmed),
"sessionKey": AnyCodable(sessionKey),
"thinking": AnyCodable(invocation.thinking ?? "default"),
"deliver": AnyCodable(invocation.deliver),
"to": AnyCodable(invocation.to ?? ""),
"channel": AnyCodable(invocation.channel.rawValue),
"idempotencyKey": AnyCodable(invocation.idempotencyKey),
]
if let thinking = invocation.thinking?.trimmingCharacters(in: .whitespacesAndNewlines),
!thinking.isEmpty
{
params["thinking"] = AnyCodable(thinking)
}
if let timeout = invocation.timeoutSeconds {
params["timeout"] = AnyCodable(timeout)
}
@@ -664,7 +668,7 @@ extension GatewayConnection {
func chatSend(
sessionKey: String,
message: String,
thinking: String,
thinking: String?,
idempotencyKey: String,
attachments: [OpenClawChatAttachmentPayload],
timeoutMs: Int = 30000) async throws -> OpenClawChatSendResponse
@@ -673,10 +677,14 @@ extension GatewayConnection {
var params: [String: AnyCodable] = [
"sessionKey": AnyCodable(resolvedKey),
"message": AnyCodable(message),
"thinking": AnyCodable(thinking),
"idempotencyKey": AnyCodable(idempotencyKey),
"timeoutMs": AnyCodable(timeoutMs),
]
if let thinking = thinking?.trimmingCharacters(in: .whitespacesAndNewlines),
!thinking.isEmpty
{
params["thinking"] = AnyCodable(thinking)
}
if !attachments.isEmpty {
let encoded = attachments.map { att in

View File

@@ -15,9 +15,9 @@
<key>CFBundlePackageType</key>
<string>APPL</string>
<key>CFBundleShortVersionString</key>
<string>2026.5.31</string>
<string>2026.6.2</string>
<key>CFBundleVersion</key>
<string>2026053100</string>
<string>2026060200</string>
<key>CFBundleIconFile</key>
<string>OpenClaw</string>
<key>CFBundleURLTypes</key>

View File

@@ -387,7 +387,7 @@ actor TalkModeRuntime {
let response = try await GatewayConnection.shared.chatSend(
sessionKey: sessionKey,
message: prompt,
thinking: "low",
thinking: nil,
idempotencyKey: runId,
attachments: [])
guard self.isCurrent(gen) else { return }

View File

@@ -34,7 +34,7 @@ enum VoiceWakeForwarder {
struct ForwardOptions {
var sessionKey: String = "main"
var thinking: String = "low"
var thinking: String?
var deliver: Bool = true
var to: String?
var channel: GatewayAgentChannel = .webchat
@@ -97,7 +97,6 @@ enum VoiceWakeForwarder {
return ForwardOptions(
sessionKey: sessionKey,
thinking: "low",
deliver: true,
to: to,
channel: channel,

View File

@@ -173,9 +173,57 @@ private func makeTestGatewayConnection() -> (GatewayConnection, FakeWebSocketSes
let json = try JSONSerialization.jsonObject(with: payloadData) as? [String: Any]
let params = json?["params"] as? [String: Any]
#expect(params?["thinking"] == nil)
#expect(params?["voiceWakeTrigger"] as? String == "")
}
@Test func `chat send omits thinking when inheriting session default`() async throws {
let recorder = WebSocketMessageRecorder()
let session = GatewayTestWebSocketSession(taskFactory: {
GatewayTestWebSocketTask(sendHook: { task, message, sendIndex in
recorder.append(message)
guard sendIndex > 0,
let data = Self.messageData(message),
let json = try? JSONSerialization.jsonObject(with: data) as? [String: Any],
let id = json["id"] as? String
else { return }
task.emitReceiveSuccess(.data(Self.chatSendOkResponseData(id: id)))
})
})
let connection = GatewayConnection(
configProvider: {
(url: URL(string: "ws://127.0.0.1:1")!, token: nil, password: nil)
},
sessionBox: WebSocketSessionBox(session: session))
_ = try await connection.chatSend(
sessionKey: "main",
message: "hello",
thinking: nil,
idempotencyKey: "chat-1",
attachments: [])
await connection.shutdown()
guard let chatMessage = recorder.snapshot().reversed().first(where: { message in
guard let data = Self.messageData(message),
let json = try? JSONSerialization.jsonObject(with: data) as? [String: Any]
else { return false }
return json["method"] as? String == "chat.send"
}) else {
Issue.record("expected chat.send websocket payload")
return
}
guard let payloadData = Self.messageData(chatMessage) else {
Issue.record("unexpected chat.send websocket message type")
return
}
let json = try JSONSerialization.jsonObject(with: payloadData) as? [String: Any]
let params = json?["params"] as? [String: Any]
#expect(params?["thinking"] == nil)
}
private static func messageData(_ message: URLSessionWebSocketTask.Message) -> Data? {
switch message {
case let .string(text):
@@ -186,4 +234,15 @@ private func makeTestGatewayConnection() -> (GatewayConnection, FakeWebSocketSes
nil
}
}
private static func chatSendOkResponseData(id: String) -> Data {
Data("""
{
"type": "res",
"id": "\(id)",
"ok": true,
"payload": { "runId": "chat-1", "status": "ok" }
}
""".utf8)
}
}

View File

@@ -14,7 +14,7 @@ import Testing
@Test func `forward options defaults`() {
let opts = VoiceWakeForwarder.ForwardOptions()
#expect(opts.sessionKey == "main")
#expect(opts.thinking == "low")
#expect(opts.thinking == nil)
#expect(opts.deliver == true)
#expect(opts.to == nil)
#expect(opts.channel == .webchat)
@@ -38,6 +38,7 @@ import Testing
#expect(opts.channel == .telegram)
#expect(opts.to == "telegram:6812765697")
#expect(opts.voiceWakeTrigger == "open claw")
#expect(opts.thinking == nil)
#expect(opts.channel.shouldDeliver(opts.deliver) == true)
}

View File

@@ -1,2 +1,2 @@
47d4365c4133f57769758907b7cf1a43d17e040db0570a1433e2f03e4fb0bd02 plugin-sdk-api-baseline.json
161027bba89497f5e30127dd0f57b4da623270cfc771b989e29262da5760e723 plugin-sdk-api-baseline.jsonl
f3e0379cbe0e584a8c9658253d4a808356fe80fb5ec775bbee9e968e8d815380 plugin-sdk-api-baseline.json
601b55acafbd1e00b850c9b0c15d587029050906960071d448d37538b223e226 plugin-sdk-api-baseline.jsonl

Binary file not shown.

Before

Width:  |  Height:  |  Size: 146 KiB

After

Width:  |  Height:  |  Size: 251 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 250 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 135 KiB

After

Width:  |  Height:  |  Size: 251 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 219 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 257 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 262 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 134 KiB

After

Width:  |  Height:  |  Size: 244 KiB

82
docs/clawhub/cli.md Normal file
View File

@@ -0,0 +1,82 @@
---
summary: "ClawHub CLI entry points for discovering, installing, publishing, and verifying OpenClaw skills and plugins."
read_when:
- You want to use ClawHub from the command line
- You want to install ClawHub skills or plugins through OpenClaw
- You want to publish ClawHub packages
title: "ClawHub CLI"
---
# ClawHub CLI
OpenClaw has two command-line entry points for ClawHub:
- `openclaw skills` and `openclaw plugins` install and manage ClawHub packages
inside OpenClaw.
- The standalone `clawhub` CLI handles publisher workflows such as login,
publish, transfer, and sync.
## Discover and install
Use OpenClaw commands when you want to install or update packages for a local
OpenClaw agent or Gateway.
```bash
openclaw skills search "calendar"
openclaw skills install <slug>
openclaw skills update <slug>
openclaw skills verify <slug>
openclaw plugins search "calendar"
openclaw plugins install clawhub:<package>
openclaw plugins update <id-or-npm-spec>
```
Skill installs target the active workspace `skills/` directory by default. Add
`--global` to install into the shared managed skills directory.
Plugin installs use the `clawhub:` prefix when you want ClawHub resolution
instead of npm or another install source.
## Publish and maintain
Install the standalone ClawHub CLI for publisher workflows:
```bash
npm i -g clawhub
clawhub login
```
Publish plugin packages with `clawhub package publish`:
```bash
clawhub package publish your-org/your-plugin --dry-run
clawhub package publish your-org/your-plugin
clawhub package publish your-org/your-plugin@v1.0.0
```
Publish skill folders with `clawhub skill publish`:
```bash
clawhub skill publish ./skills/review-helper
clawhub skill publish ./skills/review-helper --version 1.0.0
```
When local skill scan state or package ownership needs maintenance, use the
relevant standalone command:
```bash
clawhub sync --all
clawhub package transfer @old-owner/package --to new-owner
```
## Related
- [`openclaw skills`](/cli/skills) - local skill search, install, update, and
verification
- [`openclaw plugins`](/cli/plugins) - plugin search, install, update, and
inspection
- [ClawHub publishing](/clawhub/publishing) - owner scope, release validation,
and review flow
- [Creating skills](/tools/creating-skills) - skill authoring and publish flow
- [Building plugins](/plugins/building-plugins) - plugin package authoring

View File

@@ -93,6 +93,7 @@ openclaw onboard --non-interactive \
`--custom-api-key` is optional in non-interactive mode. If omitted, onboarding checks `CUSTOM_API_KEY`.
OpenClaw marks common vision model IDs as image-capable automatically. Pass `--custom-image-input` for unknown custom vision IDs, or `--custom-text-input` to force text-only metadata.
Use `--custom-compatibility openai-responses` for OpenAI-compatible endpoints that support `/v1/responses` but not `/v1/chat/completions`.
LM Studio also supports a provider-specific key flag in non-interactive mode:

View File

@@ -329,6 +329,19 @@ openclaw plugins install -l ./my-plugin
Standalone plugin files must be listed in `plugins.load.paths` rather than placed directly in `~/.openclaw/extensions` or `<workspace>/.openclaw/extensions`. Those auto-discovered roots load plugin package or bundle directories, while top-level script files are treated as local helpers and skipped.
<Note>
Workspace-origin plugins discovered from a workspace extensions root are not
imported or executed until they are explicitly enabled. For local development,
run `openclaw plugins enable <plugin-id>` or set
`plugins.entries.<plugin-id>.enabled: true`; if your config uses
`plugins.allow`, include the same plugin id there too. This fail-closed rule
also applies when channel setup explicitly targets a workspace-origin plugin for
setup-only loading, so local channel plugin setup code will not run while that
workspace plugin remains disabled or excluded from the allowlist. Linked installs
and explicit `plugins.load.paths` entries follow the normal policy for their
resolved plugin origin. See
[Configure plugin policy](/tools/plugin#configure-plugin-policy)
and [Configuration reference](/gateway/configuration-reference#plugins).
`--force` is not supported with `--link` because linked installs reuse the source path instead of copying over a managed install target.
Use `--pin` on npm installs to save the resolved exact spec (`name@version`) in the managed plugin index while keeping the default behavior unpinned.

View File

@@ -32,9 +32,8 @@ This is for cooperative/shared inbox hardening. A single Gateway shared by mutua
It also emits `security.trust_model.multi_user_heuristic` when config suggests likely shared-user ingress (for example open DM/group policy, configured group targets, or wildcard sender rules), and reminds you that OpenClaw is a personal-assistant trust model by default.
For intentional shared-user setups, the audit guidance is to sandbox all sessions, keep filesystem access workspace-scoped, and keep personal/private identities or credentials off that runtime.
It also warns when small models (`<=300B`) are used without sandboxing and with web/browser tools enabled.
For webhook ingress, it warns when:
For webhook ingress, startup logs a non-fatal security warning and audit flags `hooks.token` reuse of active Gateway shared-secret auth values, including `gateway.auth.token` / `OPENCLAW_GATEWAY_TOKEN` and `gateway.auth.password` / `OPENCLAW_GATEWAY_PASSWORD`. It also warns when:
- `hooks.token` reuses an active Gateway shared-secret auth value (`gateway.auth.token` / `OPENCLAW_GATEWAY_TOKEN` or `gateway.auth.password` / `OPENCLAW_GATEWAY_PASSWORD`)
- `hooks.token` is short
- `hooks.path="/"`
- `hooks.defaultSessionKey` is unset
@@ -43,7 +42,7 @@ For webhook ingress, it warns when:
- overrides are enabled without `hooks.allowedSessionKeyPrefixes`
If Gateway password auth is supplied only at startup, pass the same value to `openclaw security audit --auth password --password <password>` so the audit can check it against `hooks.token`.
Password-mode reuse is an audit finding for compatibility; rotate one of the secrets instead of expecting Gateway startup to reject that configuration.
Run `openclaw doctor --fix` to rotate a persisted reused `hooks.token`, then update external hook senders to use the new hook token.
It also warns when sandbox Docker settings are configured while sandbox mode is off, when `gateway.nodes.denyCommands` uses ineffective pattern-like/unknown entries (exact node command-name matching only, not shell-text filtering), when `gateway.nodes.allowCommands` explicitly enables dangerous node commands, when global `tools.profile="minimal"` is overridden by agent tool profiles, when write/edit tools are disabled but `exec` is still available without a constraining sandbox filesystem boundary, when open groups expose runtime/filesystem tools without sandbox/workspace guards, and when installed plugin tools may be reachable under permissive tool policy.
It also flags `gateway.allowRealIpFallback=true` (header-spoofing risk if proxies are misconfigured) and `discovery.mdns.mode="full"` (metadata leakage via mDNS TXT records).

View File

@@ -372,6 +372,30 @@ its own control markers and channel delivery.
For CLIs that emit Claude Code stream-json compatible JSONL, set
`jsonlDialect: "claude-stream-json"` on that backend's config.
## Native compaction ownership
Some CLI backends run an agent that compacts its **own** transcript, so OpenClaw must
not run its safeguard summarizer against them - doing so fights the backend's own
compaction and can hard-fail the turn.
`claude-cli` has no harness endpoint - Claude Code compacts internally - so it declares
`ownsNativeCompaction: true`, and OpenClaw returns a no-op from the compaction path.
Native-harness sessions such as Codex keep routing to their harness compaction endpoint
instead.
Because the backend owns compaction, the old stopgap of setting
`contextTokens: 1_000_000` purely to keep OpenClaw's safeguard from firing on a
claude-cli session is **no longer needed** - the opt-out replaces it.
```typescript
api.registerCliBackend({ id: "my-cli", ownsNativeCompaction: true /* ... */ });
```
Only declare `ownsNativeCompaction` for a backend that genuinely owns its compaction: it
must reliably bound its own transcript as it nears its context window and persist a
resumable session (e.g. `--resume` / `--session-id`); otherwise a deferred session can
stay over budget. Matching `agentHarnessId` sessions still route to the harness endpoint.
## Bundle MCP overlays
CLI backends do **not** receive OpenClaw tool calls directly, but a backend can

View File

@@ -469,7 +469,7 @@ Experimental built-in tool flags. Default off unless a strict-agentic GPT-5 auto
- `model`: default model for spawned sub-agents. If omitted, sub-agents inherit the caller's model.
- `allowAgents`: default allowlist of configured target agent ids for `sessions_spawn` when the requester agent does not set its own `subagents.allowAgents` (`["*"]` = any configured target; default: same agent only). Stale entries whose agent config was deleted are rejected by `sessions_spawn` and omitted from `agents_list`; run `openclaw doctor --fix` to clean them up.
- `runTimeoutSeconds`: default timeout (seconds) for `sessions_spawn` when the tool call omits `runTimeoutSeconds`. `0` means no timeout.
- `runTimeoutSeconds`: default timeout (seconds) for `sessions_spawn`. `0` means no timeout.
- `announceTimeoutMs`: per-call timeout (milliseconds) for gateway `agent` announce delivery attempts. Default: `120000`. Transient retries can make the total announce wait longer than one configured timeout.
- Per-subagent tool policy: `tools.subagents.tools.allow` / `tools.subagents.tools.deny`.

View File

@@ -730,8 +730,8 @@ Query-string hook tokens are rejected.
Validation and safety notes:
- `hooks.enabled=true` requires a non-empty `hooks.token`.
- `hooks.token` must be distinct from `gateway.auth.token` / `OPENCLAW_GATEWAY_TOKEN`; reusing the Gateway token fails startup validation.
- `openclaw security audit` also flags `hooks.token` reuse of active Gateway password auth (`gateway.auth.password` / `OPENCLAW_GATEWAY_PASSWORD`, or `--auth password --password <password>`) as a critical finding; password-mode reuse stays startup-compatible and should be repaired by rotating one of the secrets.
- `hooks.token` should be distinct from active Gateway shared-secret auth (`gateway.auth.token` / `OPENCLAW_GATEWAY_TOKEN` or `gateway.auth.password` / `OPENCLAW_GATEWAY_PASSWORD`); startup logs a non-fatal security warning when it detects reuse.
- `openclaw security audit` flags hook/Gateway auth reuse as a critical finding, including Gateway password auth supplied only at audit time (`--auth password --password <password>`). Run `openclaw doctor --fix` to rotate a persisted reused `hooks.token`, then update external hook senders to use the new hook token.
- `hooks.path` cannot be `/`; use a dedicated subpath such as `/hooks`.
- If `hooks.allowRequestSessionKey=true`, constrain `hooks.allowedSessionKeyPrefixes` (for example `["hook:"]`).
- If a mapping or preset uses a templated `sessionKey`, set `hooks.allowedSessionKeyPrefixes` and `hooks.allowRequestSessionKey=true`. Static mapping keys do not require that opt-in.

View File

@@ -329,6 +329,7 @@ Android nodes can advertise additional command families when the corresponding c
Available families:
- `device.status`, `device.info`, `device.permissions`, `device.health`
- `device.apps` when Installed Apps sharing is enabled in Android Settings
- `notifications.list`, `notifications.actions`
- `photos.latest`
- `contacts.search`, `contacts.add`
@@ -341,12 +342,14 @@ Example invokes:
```bash
openclaw nodes invoke --node <idOrNameOrIp> --command device.status --params '{}'
openclaw nodes invoke --node <idOrNameOrIp> --command device.apps --params '{"limit":10}'
openclaw nodes invoke --node <idOrNameOrIp> --command notifications.list --params '{}'
openclaw nodes invoke --node <idOrNameOrIp> --command photos.latest --params '{"limit":1}'
```
Notes:
- `device.apps` is opt-in and returns launcher-visible apps by default.
- Motion commands are capability-gated by available sensors.
## System commands (node host / mac node)

View File

@@ -219,8 +219,9 @@ See [Camera node](/nodes/camera) for parameters and CLI helpers.
- By default, Android Talk uses native speech recognition, Gateway chat, and `talk.speak` through the configured gateway Talk provider. Local system TTS is used only when `talk.speak` is unavailable.
- Android Talk uses realtime Gateway relay only when `talk.realtime.mode` is `realtime` and `talk.realtime.transport` is `gateway-relay`.
- Voice wake remains disabled in the Android UX/runtime.
- Additional Android command families (availability depends on device + permissions):
- Additional Android command families (availability depends on device, permissions, and user settings):
- `device.status`, `device.info`, `device.permissions`, `device.health`
- `device.apps` only when **Settings > Phone Capabilities > Installed Apps** is enabled; it lists launcher-visible apps by default.
- `notifications.list`, `notifications.actions` (see [Notification forwarding](#notification-forwarding) below)
- `photos.latest`
- `contacts.search`, `contacts.add`

View File

@@ -208,10 +208,28 @@ only for behavior that really belongs to the backend.
| `authEpochMode` | Decide how auth changes invalidate stored CLI sessions |
| `nativeToolMode` | Declare whether the CLI has always-on native tools |
| `bundleMcp` / `bundleMcpMode` | Opt into OpenClaw's loopback MCP tool bridge |
| `ownsNativeCompaction` | Backend owns its own compaction - OpenClaw defers |
Keep these hooks provider-owned. Do not add CLI-specific branches to core when a
backend hook can express the behavior.
### `ownsNativeCompaction`: opting out of OpenClaw compaction
If your backend runs an agent that compacts its **own** transcript, set
`ownsNativeCompaction: true` so OpenClaw's safeguard summarizer never runs against its
sessions - the CLI compaction lifecycle returns a no-op and the turn proceeds. `claude-cli`
declares it because Claude Code compacts internally with no harness endpoint. Native-harness
sessions such as Codex keep routing to their harness compaction endpoint instead.
**Only declare it when all of the following hold**, or a deferred over-budget session can
stay over budget / go stale (OpenClaw no longer rescues it):
- the backend reliably compacts or bounds its own transcript as it nears its window;
- it persists a resumable session so the compacted state survives turns
(e.g. `--resume` / `--session-id`);
- it is not a native-harness compaction session - matching `agentHarnessId` sessions
route to the harness endpoint instead.
## MCP tool bridge
CLI backends do not receive OpenClaw tools by default. If the CLI can consume an

View File

@@ -368,7 +368,7 @@ If discovery fails or times out, OpenClaw uses a bundled fallback catalog for:
- GPT-5.4 mini
- GPT-5.2
The current bundled harness is `@openai/codex` `0.134.0`. A `model/list` probe
The current bundled harness is `@openai/codex` `0.135.0`. A `model/list` probe
against that bundled app-server returned:
| Model id | Default | Hidden | Input modalities | Reasoning efforts |

View File

@@ -190,11 +190,10 @@ plugins, channels, and core code only see the standard
When `harness.compact` runs, the Copilot SDK harness:
1. Enables `infiniteSessions` on the SDK session.
2. Lets the SDK perform its native compaction.
3. Writes an OpenClaw-shaped marker at
`workspacePath/files/openclaw-compaction-<ts>.json` so existing OpenClaw
transcript readers still see a familiar artifact.
1. Resumes the tracked SDK session without continuing pending work.
2. Calls the SDK's session-scoped history compaction RPC.
3. Returns the SDK compaction outcome without writing compatibility marker
files under the workspace.
The OpenClaw side transcript mirror (see below) continues to receive the
post-compaction messages, so user-facing chat history stays consistent.

View File

@@ -120,6 +120,7 @@ observation-only.
- **`before_tool_call`** - rewrite tool params, block execution, or require approval
- `after_tool_call` - observe tool results, errors, and duration
- `resolve_exec_env` - contribute plugin-owned environment variables to `exec`
- **`tool_result_persist`** - rewrite the assistant message produced from a tool result
- **`before_message_write`** - inspect or block an in-progress message write (rare)
@@ -233,6 +234,28 @@ for host-trusted gates such as workspace policy, budget enforcement, or
reserved workflow safety. External plugins should use normal `before_tool_call`
hooks.
### Exec environment hook
`resolve_exec_env` lets plugins contribute environment variables to `exec`
tool invocations after the base exec environment is built and before the
command runs. It receives:
- `event.sessionKey`
- `event.toolName`, currently always `"exec"`
- `event.host`, one of `"gateway"`, `"sandbox"`, or `"node"`
- context fields such as `ctx.agentId`, `ctx.sessionKey`,
`ctx.messageProvider`, and `ctx.channelId`
Return a `Record<string, string>` to merge into the exec environment. Handlers
run in priority order, and later hook results override earlier hook results for
the same key.
Hook output is filtered through the host exec environment key policy before it
is merged. Invalid keys, `PATH`, and dangerous host override keys such as
`LD_*`, `DYLD_*`, `NODE_OPTIONS`, proxy variables, and TLS override variables
are dropped. The filtered plugin env is included in gateway approval/audit
metadata and forwarded to node-host execution requests.
### Tool result persistence
Tool results can include structured `details` for UI rendering, diagnostics,

View File

@@ -107,7 +107,7 @@ commands.
| [oc-path](/plugins/reference/oc-path) | Adds the openclaw path CLI for oc:// workspace file addressing. | `@openclaw/oc-path`<br />included in OpenClaw | plugin |
| [ollama](/plugins/reference/ollama) | Adds Ollama, Ollama Cloud model provider support to OpenClaw. | `@openclaw/ollama-provider`<br />included in OpenClaw | providers: ollama, ollama-cloud; contracts: memoryEmbeddingProviders, webSearchProviders |
| [open-prose](/plugins/reference/open-prose) | OpenProse VM skill pack with a /prose slash command. | `@openclaw/open-prose`<br />included in OpenClaw | skills |
| [openai](/plugins/reference/openai) | Adds OpenAI model provider support to OpenClaw, including ChatGPT/Codex OAuth. | `@openclaw/openai-provider`<br />included in OpenClaw | providers: openai; contracts: imageGenerationProviders, mediaUnderstandingProviders, memoryEmbeddingProviders, realtimeTranscriptionProviders, realtimeVoiceProviders, speechProviders, videoGenerationProviders |
| [openai](/plugins/reference/openai) | Adds OpenAI model provider support to OpenClaw. | `@openclaw/openai-provider`<br />included in OpenClaw | providers: openai; contracts: imageGenerationProviders, mediaUnderstandingProviders, memoryEmbeddingProviders, realtimeTranscriptionProviders, realtimeVoiceProviders, speechProviders, videoGenerationProviders |
| [opencode](/plugins/reference/opencode) | Adds OpenCode model provider support to OpenClaw. | `@openclaw/opencode-provider`<br />included in OpenClaw | providers: opencode; contracts: mediaUnderstandingProviders |
| [opencode-go](/plugins/reference/opencode-go) | Adds OpenCode Go model provider support to OpenClaw. | `@openclaw/opencode-go-provider`<br />included in OpenClaw | providers: opencode-go; contracts: mediaUnderstandingProviders |
| [openrouter](/plugins/reference/openrouter) | Adds OpenRouter model provider support to OpenClaw. | `@openclaw/openrouter-provider`<br />included in OpenClaw | providers: openrouter; contracts: imageGenerationProviders, mediaUnderstandingProviders, musicGenerationProviders, speechProviders, videoGenerationProviders |

View File

@@ -95,7 +95,7 @@ pnpm plugins:inventory:gen
| [oc-path](/plugins/reference/oc-path) | Adds the openclaw path CLI for oc:// workspace file addressing. | `@openclaw/oc-path`<br />included in OpenClaw | plugin |
| [ollama](/plugins/reference/ollama) | Adds Ollama, Ollama Cloud model provider support to OpenClaw. | `@openclaw/ollama-provider`<br />included in OpenClaw | providers: ollama, ollama-cloud; contracts: memoryEmbeddingProviders, webSearchProviders |
| [open-prose](/plugins/reference/open-prose) | OpenProse VM skill pack with a /prose slash command. | `@openclaw/open-prose`<br />included in OpenClaw | skills |
| [openai](/plugins/reference/openai) | Adds OpenAI model provider support to OpenClaw, including ChatGPT/Codex OAuth. | `@openclaw/openai-provider`<br />included in OpenClaw | providers: openai; contracts: imageGenerationProviders, mediaUnderstandingProviders, memoryEmbeddingProviders, realtimeTranscriptionProviders, realtimeVoiceProviders, speechProviders, videoGenerationProviders |
| [openai](/plugins/reference/openai) | Adds OpenAI model provider support to OpenClaw. | `@openclaw/openai-provider`<br />included in OpenClaw | providers: openai; contracts: imageGenerationProviders, mediaUnderstandingProviders, memoryEmbeddingProviders, realtimeTranscriptionProviders, realtimeVoiceProviders, speechProviders, videoGenerationProviders |
| [opencode](/plugins/reference/opencode) | Adds OpenCode model provider support to OpenClaw. | `@openclaw/opencode-provider`<br />included in OpenClaw | providers: opencode; contracts: mediaUnderstandingProviders |
| [opencode-go](/plugins/reference/opencode-go) | Adds OpenCode Go model provider support to OpenClaw. | `@openclaw/opencode-go-provider`<br />included in OpenClaw | providers: opencode-go; contracts: mediaUnderstandingProviders |
| [openrouter](/plugins/reference/openrouter) | Adds OpenRouter model provider support to OpenClaw. | `@openclaw/openrouter-provider`<br />included in OpenClaw | providers: openrouter; contracts: imageGenerationProviders, mediaUnderstandingProviders, musicGenerationProviders, speechProviders, videoGenerationProviders |

View File

@@ -1,5 +1,5 @@
---
summary: "Adds OpenAI model provider support to OpenClaw, including ChatGPT/Codex OAuth."
summary: "Adds OpenAI model provider support to OpenClaw."
read_when:
- You are installing, configuring, or auditing the openai plugin
title: "OpenAI plugin"
@@ -7,7 +7,7 @@ title: "OpenAI plugin"
# OpenAI plugin
Adds OpenAI model provider support to OpenClaw, including ChatGPT/Codex OAuth.
Adds OpenAI model provider support to OpenClaw.
## Distribution

View File

@@ -353,7 +353,7 @@ API key auth, and dynamic model resolution.
| --- | --- | --- |
| `openai-compatible` | Shared OpenAI-style replay policy for OpenAI-compatible transports, including tool-call-id sanitation, assistant-first ordering fixes, and generic Gemini-turn validation where the transport needs it | `moonshot`, `ollama`, `xai`, `zai` |
| `anthropic-by-model` | Claude-aware replay policy chosen by `modelId`, so Anthropic-message transports only get Claude-specific thinking-block cleanup when the resolved model is actually a Claude id | `amazon-bedrock`, `anthropic-vertex` |
| `google-gemini` | Native Gemini replay policy plus bootstrap replay sanitation and tagged reasoning-output mode | `google`, `google-gemini-cli` |
| `google-gemini` | Native Gemini replay policy plus bootstrap replay sanitation. The shared family keeps the text-output Gemini CLI on tagged reasoning; the direct `google` provider overrides `resolveReasoningOutputMode` to `native` because Gemini API thinking arrives as native thought parts. | `google`, `google-gemini-cli` |
| `passthrough-gemini` | Gemini thought-signature sanitation for Gemini models running through OpenAI-compatible proxy transports; does not enable native Gemini replay validation or bootstrap rewrites | `openrouter`, `kilocode`, `opencode`, `opencode-go` |
| `hybrid-anthropic-openai` | Hybrid policy for providers that mix Anthropic-message and OpenAI-compatible model surfaces in one plugin; optional Claude-only thinking-block dropping stays scoped to the Anthropic side | `minimax` |
@@ -376,6 +376,13 @@ API key auth, and dynamic model resolution.
- `openclaw/plugin-sdk/provider-stream` - `ProviderStreamFamily`, `buildProviderStreamFamilyHooks(...)`, `composeProviderStreamWrappers(...)`, plus the shared OpenAI/Codex wrappers (`createOpenAIAttributionHeadersWrapper`, `createOpenAIFastModeWrapper`, `createOpenAIServiceTierWrapper`, `createOpenAIResponsesContextManagementWrapper`, `createCodexNativeWebSearchWrapper`), DeepSeek V4 OpenAI-compatible wrapper (`createDeepSeekV4OpenAICompatibleThinkingWrapper`), Anthropic Messages thinking prefill cleanup (`createAnthropicThinkingPrefillPayloadWrapper`), plain-text tool-call compat (`createPlainTextToolCallCompatWrapper`), and shared proxy/provider wrappers (`createOpenRouterWrapper`, `createToolStreamWrapper`, `createMinimaxFastModeWrapper`).
- `openclaw/plugin-sdk/provider-tools` - `ProviderToolCompatFamily`, `buildProviderToolCompatFamilyHooks("deepseek" | "gemini" | "openai")`, and underlying provider schema helpers.
For Gemini-family providers, keep the reasoning-output mode aligned with
the transport. Direct Google Gemini API providers should use `native`
reasoning output so OpenClaw consumes native thought parts without adding
`<think>` / `<final>` prompt directives. Text-only Gemini CLI-style
backends that parse a final JSON/text response can keep the shared
`google-gemini` tagged contract.
Some stream helpers stay provider-local on purpose. `@openclaw/anthropic-provider` keeps `wrapAnthropicProviderStream`, `resolveAnthropicBetas`, `resolveAnthropicFastMode`, `resolveAnthropicServiceTier`, and the lower-level Anthropic wrapper builders in its own public `api.ts` / `contract-api.ts` seam because they encode Claude OAuth beta handling and `context1m` gating. The xAI plugin similarly keeps native xAI Responses shaping in its own `wrapStreamFn` (`/fast` aliases, default `tool_stream`, unsupported strict-tool cleanup, xAI-specific reasoning-payload removal).
The same package-root pattern also backs `@openclaw/openai-provider` (provider builders, default-model helpers, realtime provider builders) and `@openclaw/openrouter-provider` (provider builder plus onboarding/config helpers).

View File

@@ -76,6 +76,7 @@ by package contract guardrails.
| `plugin-sdk/channel-config-helpers` | `createHybridChannelConfigAdapter`, `resolveChannelDmAccess`, `resolveChannelDmAllowFrom`, `resolveChannelDmPolicy`, `normalizeChannelDmPolicy`, `normalizeLegacyDmAliases` |
| `plugin-sdk/channel-config-schema` | Shared channel config schema primitives plus Zod and direct JSON/TypeBox builders |
| `plugin-sdk/bundled-channel-config-schema` | Bundled OpenClaw channel config schemas for maintained bundled plugins only |
| `plugin-sdk/chat-channel-ids` | `BUNDLED_CHAT_CHANNEL_IDS`, `BUNDLED_CHAT_CHANNEL_ENVELOPE_PREFIXES`, `ChatChannelId`. Canonical bundled/official chat channel ids plus formatter labels/aliases for plugins that need to recognize envelope-prefixed text without hardcoding their own table. |
| `plugin-sdk/channel-config-schema-legacy` | Deprecated compatibility alias for bundled-channel config schemas |
| `plugin-sdk/telegram-command-config` | Telegram custom-command normalization/validation helpers with bundled-contract fallback |
| `plugin-sdk/command-gating` | Narrow command authorization gate helpers |

View File

@@ -457,6 +457,10 @@ The branch already has a real shared SQLite base:
- GitHub Copilot token exchange cache uses the shared SQLite plugin-state table
under `github-copilot/token-cache/default`. It is provider-owned cache state,
so it intentionally does not add a host schema table.
- GitHub Copilot compaction no longer writes `openclaw-compaction-*.json`
workspace sidecars. The harness calls the SDK history compaction RPC for the
tracked SDK session, and OpenClaw keeps durable session/transcript state in
SQLite instead of compatibility marker files.
- The shared Swift runtime (`OpenClawKit`) uses the same
`state/openclaw.sqlite` rows for device identity and device auth. macOS app
helpers import the shared SQLite helpers instead of owning a second JSON or

View File

@@ -58,6 +58,15 @@ explicitly to use Gemini, Voyage, Mistral, DeepInfra, Bedrock, GitHub Copilot,
Ollama, a local GGUF model, or an OpenAI-compatible `/v1/embeddings` endpoint.
Legacy configs that still say `provider: "auto"` resolve to `openai`.
<Warning>
Changing the embedding provider, model, provider settings, sources, scope,
chunking, or tokenizer can make the existing SQLite vector index incompatible.
OpenClaw pauses vector search and reports an index identity warning instead of
automatically re-embedding everything. Rebuild when you are ready with
`openclaw memory status --index --agent <id>` or
`openclaw memory index --force --agent <id>`.
</Warning>
If OpenAI embeddings are unreachable from your network, memory recall fails open
instead of blocking the turn. Set the existing `memorySearch.provider` field to a
reachable local, Ollama, regional, or OpenAI-compatible provider to restore
@@ -155,7 +164,8 @@ Use `provider: "openai-compatible"` for a generic OpenAI-compatible
| `outputDimensionality` | `number` | `3072` | For Embedding 2: 768, 1536, or 3072 |
<Warning>
Changing model or `outputDimensionality` triggers an automatic full reindex.
Changing model or `outputDimensionality` changes the index identity. OpenClaw
pauses vector search until you explicitly rebuild the memory index.
</Warning>
</Accordion>

View File

@@ -105,7 +105,7 @@ Per-agent heartbeat is supported at `agents.list[].heartbeat`.
- Prompt caching is automatic on supported recent models. OpenClaw does not need to inject block-level cache markers.
- OpenClaw uses `prompt_cache_key` to keep cache routing stable across turns. Direct OpenAI hosts use `prompt_cache_retention: "24h"` when `cacheRetention: "long"` is selected.
- OpenAI-compatible Completions providers receive `prompt_cache_key` only when their model config explicitly sets `compat.supportsPromptCacheKey: true`; with that same opt-in, explicit `cacheRetention: "long"` also forwards `prompt_cache_retention: "24h"`, and `cacheRetention: "none"` suppresses both fields.
- OpenAI-compatible Completions providers receive `prompt_cache_key` only when their model config explicitly sets `compat.supportsPromptCacheKey: true`. Long-retention forwarding is a separate capability: explicit `cacheRetention: "long"` sends `prompt_cache_retention: "24h"` only when that compat entry also supports long cache retention. Providers such as Mistral can opt into cache keys while setting `compat.supportsLongCacheRetention: false` to suppress the long-retention field. `cacheRetention: "none"` suppresses both fields.
- OpenAI responses expose cached prompt tokens via `usage.prompt_tokens_details.cached_tokens` (or `input_tokens_details.cached_tokens` on Responses API events). OpenClaw maps that to `cacheRead`.
- OpenAI does not expose a separate cache-write token counter, so `cacheWrite` stays `0` on OpenAI paths even when the provider is warming a cache.
- OpenAI returns useful tracing and rate-limit headers such as `x-request-id`, `openai-processing-ms`, and `x-ratelimit-*`, but cache-hit accounting should come from the usage payload, not from headers.

View File

@@ -101,6 +101,8 @@ Automated UK school meal booking via ParentPay. Uses mouse coordinates for relia
**@julianengel** • `files` `r2` `presigned-urls`
Upload to Cloudflare R2/S3 and generate secure presigned download links. Useful for remote OpenClaw instances.
<img src="/assets/showcase/r2-upload.png" alt="R2 upload skill on ClawHub" />
</Card>
<Card title="iOS app via Telegram" icon="mobile">
@@ -269,6 +271,8 @@ Vapi voice assistant to OpenClaw HTTP bridge. Near real-time phone calls with yo
**@obviyus** • `transcription` `multilingual` `skill`
Multi-lingual audio transcription via OpenRouter (Gemini, and more). Available on ClawHub.
<img src="/assets/showcase/openrouter-transcribe.png" alt="OpenRouter transcription skill on ClawHub" />
</Card>
</CardGroup>
@@ -289,6 +293,8 @@ OpenClaw gateway running on Home Assistant OS with SSH tunnel support and persis
**ClawHub**`homeassistant` `skill` `automation`
Control and automate Home Assistant devices via natural language.
<img src="/assets/showcase/homeassistant.png" alt="Home Assistant skill on ClawHub" />
</Card>
<Card title="Nix packaging" icon="snowflake" href="https://github.com/openclaw/nix-openclaw">
@@ -301,6 +307,8 @@ Batteries-included nixified OpenClaw configuration for reproducible deployments.
**ClawHub**`calendar` `caldav` `skill`
Calendar skill using khal and vdirsyncer. Self-hosted calendar integration.
<img src="/assets/showcase/caldav-calendar.png" alt="CalDAV calendar skill on ClawHub" />
</Card>
</CardGroup>

View File

@@ -219,7 +219,7 @@ What you set:
- `--custom-model-id`
- `--custom-api-key` (optional; falls back to `CUSTOM_API_KEY`)
- `--custom-provider-id` (optional)
- `--custom-compatibility <openai|anthropic>` (optional; default `openai`)
- `--custom-compatibility <openai|openai-responses|anthropic>` (optional; default `openai`)
- `--custom-image-input` / `--custom-text-input` (optional; override inferred model input capability)
</Accordion>

View File

@@ -286,8 +286,9 @@ different operation limit:
openclaw config set plugins.entries.acpx.config.timeoutSeconds 180
```
Runtime turns use OpenClaw agent/run timeouts, including `/acp timeout` and
`sessions_spawn.timeoutSeconds`. Restart the gateway after changing this value.
Runtime turns use OpenClaw agent/run timeouts, including `/acp timeout`.
`sessions_spawn` does not accept per-call timeout overrides. Restart the
gateway after changing this value.
### Health probe agent configuration

View File

@@ -549,12 +549,11 @@ Two ways to start an ACP session:
`streamLogPath` pointing to a session-scoped JSONL log
(`<sessionId>.acp-stream.jsonl`) you can tail for full relay history.
</ParamField>
<ParamField path="runTimeoutSeconds" type="number">
Aborts the ACP child turn after N seconds. `0` keeps the turn on the
gateway's no-timeout path. The same value is applied to the Gateway
run and ACP runtime so stalled/quota-exhausted harnesses do not
occupy the parent agent lane indefinitely.
</ParamField>
ACP `sessions_spawn` runs use `agents.defaults.subagents.runTimeoutSeconds` for
their default child turn limit. The tool does not accept per-call timeout
overrides.
<ParamField path="model" type="string">
Explicit model override for the ACP child session. Codex ACP spawns
normalize OpenAI refs such as `openai/gpt-5.4` to Codex ACP startup

View File

@@ -141,7 +141,7 @@ session to confirm the effective tool list.
- **Model:** native sub-agents inherit the caller unless you set `agents.defaults.subagents.model` (or per-agent `agents.list[].subagents.model`). ACP runtime spawns use the same configured subagent model when present; otherwise the ACP harness keeps its own default. An explicit `sessions_spawn.model` still wins.
- **Thinking:** native sub-agents inherit the caller unless you set `agents.defaults.subagents.thinking` (or per-agent `agents.list[].subagents.thinking`). ACP runtime spawns also apply `agents.defaults.models["provider/model"].params.thinking` for the selected model. An explicit `sessions_spawn.thinking` still wins.
- **Run timeout:** if `sessions_spawn.runTimeoutSeconds` is omitted, OpenClaw uses `agents.defaults.subagents.runTimeoutSeconds` when set; otherwise it falls back to `0` (no timeout).
- **Run timeout:** OpenClaw uses `agents.defaults.subagents.runTimeoutSeconds` when set; otherwise it falls back to `0` (no timeout). `sessions_spawn` does not accept per-call timeout overrides.
- **Task delivery:** native sub-agents receive the delegated task in their first visible `[Subagent Task]` message. The sub-agent system prompt carries runtime rules and routing context, not a hidden duplicate of the task.
Accepted native sub-agent spawns include the resolved child model metadata in
@@ -208,9 +208,6 @@ Per-agent overrides use `agents.list[].subagents.delegationMode`.
<ParamField path="thinking" type="string">
Override thinking level for the sub-agent run.
</ParamField>
<ParamField path="runTimeoutSeconds" type="number">
Defaults to `agents.defaults.subagents.runTimeoutSeconds` when set, otherwise `0`. When set, the sub-agent run is aborted after N seconds.
</ParamField>
<ParamField path="thread" type="boolean" default="false">
When `true`, requests channel thread binding for this sub-agent session.
</ParamField>
@@ -375,7 +372,7 @@ remain spawnable while inheriting defaults.
- Archive uses `sessions.delete` and renames the transcript to `*.deleted.<timestamp>` (same folder).
- `cleanup: "delete"` archives immediately after announce (still keeps the transcript via rename).
- Auto-archive is best-effort; pending timers are lost if the gateway restarts.
- `runTimeoutSeconds` does **not** auto-archive; it only stops the run. The session remains until auto-archive.
- Configured run timeouts do **not** auto-archive; they only stop the run. The session remains until auto-archive.
- Auto-archive applies equally to depth-1 and depth-2 sessions.
- Browser cleanup is separate from archive cleanup: tracked browser tabs/processes are best-effort closed when the run finishes, even if the transcript/session record is kept.
@@ -394,7 +391,7 @@ worker sub-sub-agents.
maxSpawnDepth: 2, // allow sub-agents to spawn children (default: 1)
maxChildrenPerAgent: 5, // max active children per agent session (default: 5)
maxConcurrent: 8, // global concurrency lane cap (default: 8)
runTimeoutSeconds: 900, // default timeout for sessions_spawn when omitted (0 = no timeout)
runTimeoutSeconds: 900, // default timeout for sessions_spawn (0 = no timeout)
announceTimeoutMs: 120000, // per-call gateway announce timeout
},
},

View File

@@ -1,12 +1,12 @@
{
"name": "@openclaw/acpx",
"version": "2026.5.31",
"version": "2026.6.2",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@openclaw/acpx",
"version": "2026.5.31",
"version": "2026.6.2",
"dependencies": {
"@agentclientprotocol/claude-agent-acp": "0.39.0",
"@zed-industries/codex-acp": "0.15.0",

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/acpx",
"version": "2026.5.31",
"version": "2026.6.2",
"description": "OpenClaw ACP runtime backend with plugin-owned session and transport management.",
"repository": {
"type": "git",
@@ -26,10 +26,10 @@
"minHostVersion": ">=2026.4.25"
},
"compat": {
"pluginApi": ">=2026.5.31"
"pluginApi": ">=2026.6.2"
},
"build": {
"openclawVersion": "2026.5.31",
"openclawVersion": "2026.6.2",
"staticAssets": [
{
"source": "./src/runtime-internals/mcp-proxy.mjs",

View File

@@ -215,6 +215,7 @@ describe("AcpxRuntime fresh reset wrapper", () => {
agent: "codex",
mode: "persistent",
model: "gpt-5.4",
sessionOptions: { model: "gpt-5.4" },
});
});
@@ -619,7 +620,7 @@ describe("AcpxRuntime fresh reset wrapper", () => {
);
});
it("does not normalize model startup for non-Codex ACP agents", async () => {
it("passes model startup through sessionOptions for non-Codex ACP agents", async () => {
const baseStore: TestSessionStore = {
load: vi.fn(async () => undefined),
save: vi.fn(async () => {}),
@@ -648,6 +649,7 @@ describe("AcpxRuntime fresh reset wrapper", () => {
agent: "main",
mode: "persistent",
model: "openai/gpt-5.5",
sessionOptions: { model: "openai/gpt-5.5" },
});
});
@@ -694,6 +696,7 @@ describe("AcpxRuntime fresh reset wrapper", () => {
agent: "codex",
mode: "persistent",
model: "gpt-5.5",
sessionOptions: { model: "gpt-5.5" },
});
});
@@ -728,6 +731,7 @@ describe("AcpxRuntime fresh reset wrapper", () => {
mode: "persistent",
model: "gpt-5.4/xhigh",
thinking: "x-high",
sessionOptions: { model: "gpt-5.4/xhigh" },
});
});

View File

@@ -17,6 +17,7 @@ import {
type AcpRuntimeStatus,
type AcpRuntimeTurn,
type AcpRuntimeTurnResult,
type SessionAgentOptions,
} from "acpx/runtime";
import { parseStrictPositiveInteger } from "openclaw/plugin-sdk/number-runtime";
import { redactSensitiveText } from "openclaw/plugin-sdk/security-runtime";
@@ -49,6 +50,8 @@ type AcpxRuntimeTestOptions = Record<string, unknown> & {
openclawProcessCleanup?: AcpxProcessCleanupDeps;
};
type OpenClawRuntimeTurnInput = Parameters<NonNullable<AcpRuntime["startTurn"]>>[0];
type OpenClawRuntimeEnsureInput = Parameters<AcpRuntime["ensureSession"]>[0];
type AcpxDelegateEnsureInput = Parameters<BaseAcpxRuntime["ensureSession"]>[0];
type ResetAwareSessionStore = AcpSessionStore & {
markFresh: (sessionKey: string) => void;
@@ -547,6 +550,16 @@ function codexAcpSessionModelId(override: CodexAcpModelOverride): string {
: override.model;
}
function withAcpxSessionOptions(input: OpenClawRuntimeEnsureInput): AcpxDelegateEnsureInput {
const existingOptions = (input as { sessionOptions?: SessionAgentOptions }).sessionOptions;
const model = input.model?.trim() || existingOptions?.model;
const sessionOptions = model ? { ...existingOptions, model } : existingOptions;
return {
...input,
...(sessionOptions ? { sessionOptions } : {}),
} as AcpxDelegateEnsureInput;
}
function quoteShellArg(value: string): string {
if (/^[A-Za-z0-9_./:=@+-]+$/.test(value)) {
return value;
@@ -942,7 +955,7 @@ export class AcpxRuntime implements AcpRuntime {
this.withCodexWrapperDiagnostics({
command: stableLaunchCommand,
fallbackCode: "ACP_SESSION_INIT_FAILED",
run: () => delegate.ensureSession(input),
run: () => delegate.ensureSession(withAcpxSessionOptions(input)),
}),
});
}
@@ -962,7 +975,7 @@ export class AcpxRuntime implements AcpRuntime {
this.withCodexWrapperDiagnostics({
command: stableLaunchCommand,
fallbackCode: "ACP_SESSION_INIT_FAILED",
run: () => delegate.ensureSession(normalizedInput),
run: () => delegate.ensureSession(withAcpxSessionOptions(normalizedInput)),
}),
),
});

View File

@@ -3218,7 +3218,7 @@ describe("active-memory plugin", () => {
testing.setSetupGraceTimeoutMsForTests(0);
api.pluginConfig = {
agents: ["main"],
timeoutMs: 100,
timeoutMs: 1_000,
};
plugin.register(api as unknown as OpenClawPluginApi);
hoisted.sessionStore["agent:main:memory-get-miss"] = {

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/admin-http-rpc",
"version": "2026.5.31",
"version": "2026.6.2",
"private": true,
"description": "OpenClaw admin HTTP RPC endpoint",
"type": "module",

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/alibaba-provider",
"version": "2026.5.31",
"version": "2026.6.2",
"private": true,
"description": "OpenClaw Alibaba Model Studio video provider plugin",
"type": "module",

View File

@@ -1,12 +1,12 @@
{
"name": "@openclaw/amazon-bedrock-mantle-provider",
"version": "2026.5.31",
"version": "2026.6.2",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@openclaw/amazon-bedrock-mantle-provider",
"version": "2026.5.31",
"version": "2026.6.2",
"dependencies": {
"@anthropic-ai/sdk": "0.100.1",
"@aws/bedrock-token-generator": "1.1.0"

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/amazon-bedrock-mantle-provider",
"version": "2026.5.31",
"version": "2026.6.2",
"description": "OpenClaw Amazon Bedrock Mantle provider plugin for OpenAI-compatible model routing.",
"repository": {
"type": "git",
@@ -24,10 +24,10 @@
"minHostVersion": ">=2026.5.12-beta.1"
},
"compat": {
"pluginApi": ">=2026.5.31"
"pluginApi": ">=2026.6.2"
},
"build": {
"openclawVersion": "2026.5.31",
"openclawVersion": "2026.6.2",
"bundledDist": false
},
"release": {

View File

@@ -1,12 +1,12 @@
{
"name": "@openclaw/amazon-bedrock-provider",
"version": "2026.5.31",
"version": "2026.6.2",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@openclaw/amazon-bedrock-provider",
"version": "2026.5.31",
"version": "2026.6.2",
"dependencies": {
"@aws-sdk/client-bedrock": "3.1056.0",
"@aws-sdk/client-bedrock-runtime": "3.1056.0",

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/amazon-bedrock-provider",
"version": "2026.5.31",
"version": "2026.6.2",
"description": "OpenClaw Amazon Bedrock provider plugin with model discovery, embeddings, and guardrail support.",
"repository": {
"type": "git",
@@ -28,10 +28,10 @@
"minHostVersion": ">=2026.5.12-beta.1"
},
"compat": {
"pluginApi": ">=2026.5.31"
"pluginApi": ">=2026.6.2"
},
"build": {
"openclawVersion": "2026.5.31",
"openclawVersion": "2026.6.2",
"bundledDist": false
},
"release": {

View File

@@ -1,12 +1,12 @@
{
"name": "@openclaw/anthropic-vertex-provider",
"version": "2026.5.31",
"version": "2026.6.2",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@openclaw/anthropic-vertex-provider",
"version": "2026.5.31",
"version": "2026.6.2",
"dependencies": {
"@anthropic-ai/vertex-sdk": "0.16.1"
}

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/anthropic-vertex-provider",
"version": "2026.5.31",
"version": "2026.6.2",
"description": "OpenClaw Anthropic Vertex provider plugin for Claude models on Google Vertex AI.",
"repository": {
"type": "git",
@@ -23,10 +23,10 @@
"minHostVersion": ">=2026.5.12-beta.1"
},
"compat": {
"pluginApi": ">=2026.5.31"
"pluginApi": ">=2026.6.2"
},
"build": {
"openclawVersion": "2026.5.31",
"openclawVersion": "2026.6.2",
"bundledDist": false
},
"release": {

View File

@@ -29,6 +29,7 @@ export function buildAnthropicCliBackend(): CliBackendPlugin {
bundleMcp: true,
bundleMcpMode: "claude-config-file",
nativeToolMode: "always-on",
ownsNativeCompaction: true,
config: {
command: "claude",
args: [

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/anthropic-provider",
"version": "2026.5.31",
"version": "2026.6.2",
"private": true,
"description": "OpenClaw Anthropic provider plugin",
"type": "module",

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/arcee-provider",
"version": "2026.5.31",
"version": "2026.6.2",
"private": true,
"description": "OpenClaw Arcee provider plugin",
"type": "module",

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/azure-speech",
"version": "2026.5.31",
"version": "2026.6.2",
"private": true,
"description": "OpenClaw Azure Speech plugin",
"type": "module",

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/bonjour",
"version": "2026.5.31",
"version": "2026.6.2",
"description": "OpenClaw Bonjour/mDNS gateway discovery",
"type": "module",
"dependencies": {

View File

@@ -1,12 +1,12 @@
{
"name": "@openclaw/brave-plugin",
"version": "2026.5.31",
"version": "2026.6.2",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@openclaw/brave-plugin",
"version": "2026.5.31"
"version": "2026.6.2"
}
}
}

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/brave-plugin",
"version": "2026.5.31",
"version": "2026.6.2",
"description": "OpenClaw Brave Search provider plugin for web search.",
"repository": {
"type": "git",
@@ -21,10 +21,10 @@
"allowInvalidConfigRecovery": true
},
"compat": {
"pluginApi": ">=2026.5.31"
"pluginApi": ">=2026.6.2"
},
"build": {
"openclawVersion": "2026.5.31"
"openclawVersion": "2026.6.2"
},
"release": {
"publishToClawHub": true,

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/browser-plugin",
"version": "2026.5.31",
"version": "2026.6.2",
"private": true,
"description": "OpenClaw browser tool plugin",
"type": "module",

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/byteplus-provider",
"version": "2026.5.31",
"version": "2026.6.2",
"private": true,
"description": "OpenClaw BytePlus provider plugin",
"type": "module",

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/canvas-plugin",
"version": "2026.5.31",
"version": "2026.6.2",
"private": true,
"description": "OpenClaw Canvas plugin",
"type": "module",

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/cerebras-provider",
"version": "2026.5.31",
"version": "2026.6.2",
"private": true,
"description": "OpenClaw Cerebras provider plugin",
"type": "module",

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/chutes-provider",
"version": "2026.5.31",
"version": "2026.6.2",
"private": true,
"description": "OpenClaw Chutes.ai provider plugin",
"type": "module",

View File

@@ -1,6 +1,6 @@
{
"name": "@openclaw/clickclack",
"version": "2026.5.31",
"version": "2026.6.2",
"private": true,
"description": "OpenClaw ClickClack channel plugin",
"type": "module",
@@ -18,7 +18,7 @@
"openclaw": "2026.5.28"
},
"peerDependencies": {
"openclaw": ">=2026.5.31"
"openclaw": ">=2026.6.2"
},
"peerDependenciesMeta": {
"openclaw": {

Some files were not shown because too many files have changed in this diff Show More