SDK list helpers now send an empty params object when filters are omitted while preserving explicit invalid params for Gateway validation.\n\nVerification:\n- git diff --check origin/main...HEAD\n- node --check packages/sdk/src/client.ts\n- codex review --base origin/main\n- GitHub Actions CI release gate 27855603923 succeeded on 353f13c0d1
Summary:
- The branch changes config write preparation and doctor regression coverage so `doctor --fix` persists repair ... rams under canonical `openai/*` with Codex runtime policy, plus a prerelease lane timeout assertion update.
- PR surface: Source +9, Tests +107. Total +116 across 4 files.
- Reproducibility: yes. at source level: current main can re-preserve stale source-authored `openai-codex/*` m ... the candidate config, while the PR body supplies after-fix command proof for the narrowed persistence path.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head 7b5bc00f31.
- Required merge gates passed before the squash merge.
Prepared head SHA: 7b5bc00f31
Review: https://github.com/openclaw/openclaw/pull/94478#issuecomment-4739605890
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
Bound gateway model pricing catalog reads through the shared streaming byte-limit helper so no-content-length LiteLLM/OpenRouter responses cannot be fully buffered past the 5 MiB cap before rejection. Adds a regression for streamed LiteLLM overflow while preserving OpenRouter fallback pricing.
Keep the OpenAI Realtime WebRTC smoke's SDP offer request in the browser fetch path while moving the browser-side SDP answer reader into a testable helper. Reject unsafe decimal Content-Length values before acquiring a body reader and preserve streamed byte limiting for responses without a safe declared length.
Proof: direct bounded-reader repro rejects unsafe content-length before getReader and cancels the body; node --check --experimental-strip-types scripts/dev/realtime-talk-live-smoke.ts; node --check --experimental-strip-types test/scripts/dev-tooling-safety.test.ts; git diff --check origin/main...HEAD; autoreview clean overall 0.84; exact-head release gate succeeded at https://github.com/openclaw/openclaw/actions/runs/27848673438.
Reject unsafe decimal Content-Length values in the E2E bounded response text helper before streaming response bodies. Keep non-decimal values on the streaming byte-limit path and add regression coverage proving unsafe declared lengths cancel without starting a read.
Proof: direct patched repro rejects before reading with code ETOOBIG; origin/main comparison entered the reader first; node --check scripts/e2e/lib/bounded-response-text.mjs; git diff --check origin/main...HEAD; autoreview clean overall 0.86; exact-head release gate succeeded at https://github.com/openclaw/openclaw/actions/runs/27846197115.
* feat(cli): add `sessions compact` command and fail loudly on CLI `/compact`
`sessions.compact` was reachable only as an internal Gateway RPC — no CLI
command, no docs — and `openclaw agent --message '/compact'` silently no-opped
with exit 0 because the slash-command handler rejects CLI-originated senders,
so the message fell through to an ordinary agent turn that compacted nothing.
- Add `openclaw sessions compact <key>` wrapping the existing `sessions.compact`
RPC; exit non-zero on a transport error or an `ok:false` payload so automation
never mistakes a silent no-op for success.
- Reject `openclaw agent --message '/compact'` with a redirect to the new
command and exit 1 instead of a silent exit 0. The shared chat-side `/compact`
handler is left untouched (no compatibility / message-delivery blast radius).
- Strictly validate `--max-lines` and `--timeout` (positive integers only).
- Document the command and the `sessions.compact` RPC in docs/cli/sessions.md.
Fixes#90640.
* fix(cli): inherit parent `sessions` options for `compact`
`openclaw sessions compact <key>` did not merge the parent `sessions`
command options the way its sibling subcommands (list/cleanup/info/…) do,
so a parent-level `--agent`/`--json` was silently dropped. In particular
`openclaw sessions --agent work compact <key>` compacted the default
agent's session instead of the work agent's — a wrong-target session-state
mutation.
Merge the parent options in the compact action (parent `--agent`/`--json`,
with the compact-level option taking precedence) and add regression
coverage for parent `--agent`, parent `--json`, and the compact-level
override.
Refs #90640.
* fix(cli): report pending Codex compaction and reject unsupported parent options
Address two ClawSweeper review findings on the `sessions compact` command:
- `sessions-compact.ts`: the Codex app-server `thread/compact/start` path
returns `ok:true / compacted:false` with a pending marker, meaning the
compaction was *started* asynchronously. The formatter collapsed every
non-compacted success into "No compaction needed", so Codex users were told
nothing happened. Report it as a started/pending compaction instead.
- `register.status-health-sessions.ts`: the parent `sessions` command defines
list-only options (`--store`/`--all-agents`/`--active`/`--limit`) that the
compact action previously ignored. Silently dropping a parent `--store` is
dangerous — the gateway resolves the target store itself, so a user could
believe they targeted one store while another is mutated. Reject any
unsupported inherited parent option with a clear error and a non-zero exit.
Add regression tests for the pending-compaction message and the rejected
parent options.
Refs #90640.
* fix(gateway): guard sessions.compact maxLines truncation against active runs
The non-maxLines (LLM) compact branch interrupts an active session run before
compacting, but the maxLines truncate branch read the tail, archived, and
overwrote the transcript in place without that guard. Exposing `--max-lines`
as a documented CLI command (this PR) would make the active-run data-loss mode
tracked by #72765 easy to trigger from ordinary CLI usage.
Run the same interruptSessionRunIfActive guard in the maxLines branch before
reading the tail and truncating, matching the LLM compact path. Add gateway
regression coverage over a real in-process Gateway: with no active run, the
maxLines branch truncates the on-disk transcript 500 -> 50 and preserves the
original 500 lines in the .bak archive; with an active embedded run, the
maxLines branch fires the same interrupt (abort + wait-for-end) before
archiving and truncating.
* docs(cli): move sessions compact section above related links
The new "Compact a session" section was inserted between the cleanup
section's inline "Related:" list and the page's final "## Related"
block, splitting related-link content around the command docs. Move the
compact section above the related-links area and merge the orphaned
"Session config" link into the single final "## Related" block.
* fix(gateway): avoid no-op compact aborts
Signed-off-by: sallyom <somalley@redhat.com>
* fix(gateway): satisfy compact preflight lint
Signed-off-by: sallyom <somalley@redhat.com>
* fix(sessions): preserve compacted transcript structure
---------
Signed-off-by: sallyom <somalley@redhat.com>
Co-authored-by: sallyom <somalley@redhat.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Reject unsafe numeric Content-Length values in the OpenAI chat tools E2E client before waiting on the response stream.
Also hardens Docker E2E heartbeat timing coverage after the exact-head release gate exposed a brittle zero-padded heartbeat assertion.
Verification: direct mock gateway repro, docker heartbeat shell proof, autoreview clean, and exact-head CI release gate https://github.com/openclaw/openclaw/actions/runs/27843455246.
Keep plugin tool discovery request-local, preserve active provider/channel registries, and carry the prepared registry through MCP and catalog resolution.
Co-authored-by: 郑苏波 (Super Zheng) <superzheng@tencent.com>
Distinguish validated gateway reachability from pre-open and TLS-validation failures, and sanitize close diagnostics before terminal output.
Fixes#79099.
Co-authored-by: xialonglee <li.xialong@xydigit.com>
Clarify that `networkidle` is supported for managed and raw-CDP browser sessions but rejected for existing-session mode.
Fixes#80587.
Co-authored-by: ZengWen-DT <ceng.wen@xydigit.com>
Show elapsed session duration in the status footer using the canonical session lifecycle timestamps and compact formatter.
Fixes#68226.
Co-authored-by: Alix-007 <li.long15@xydigit.com>
Use the watchOS application API for text input, remove simulator-only Debug architecture restrictions, and document the standard Watch bundle location. Refs #92477.
Co-authored-by: Sash Zats <sash@zats.io>
Summary:
- The PR changes isolated cron delivery resolution to reject keyless implicit delivery inherited from the shar ... targets into delivery context resolution, and cleans up direct cron sessions on unresolved delivery exits.
- PR surface: Source +57, Tests +496. Total +553 across 8 files.
- Reproducibility: yes. from source inspection: current resolver can inherit the shared agent-main last target ... ls or sends based on that resolved target; I did not run live Matrix reproduction in this read-only review.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(cron): clean up deleteAfterRun session when keyless cron delivery…
- PR branch already contained follow-up commit before automerge: Merge remote-tracking branch 'upstream/main' into fix/91613-isolated-…
- PR branch already contained follow-up commit before automerge: Merge upstream main into fix/91613-isolated-cron-delivery-identity
- PR branch already contained follow-up commit before automerge: chore: retrigger PR CI after upstream base fix
Validation:
- ClawSweeper review passed for head f129375dd7.
- Required merge gates passed before the squash merge.
Prepared head SHA: f129375dd7
Review: https://github.com/openclaw/openclaw/pull/91685#issuecomment-4659309145
Co-authored-by: nxmxbbd <32288+nxmxbbd@users.noreply.github.com>
Summary:
- The PR changes Telegram legacy HTML rendering so raw HTML table tags are converted to `<pre><code>` pipe-tab ... ks before unsupported-tag escaping, while preserving pre/code literals and rich-message table sanitization.
- PR surface: Source +38, Tests +31. Total +69 across 2 files.
- Reproducibility: yes. Source inspection shows current main's legacy HTML renderer sends raw tables directly ... the linked issue describes that same escaped output; I did not run tests because this review was read-only.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head 5944f8e4d2.
- Required merge gates passed before the squash merge.
Prepared head SHA: 5944f8e4d2
Review: https://github.com/openclaw/openclaw/pull/94856#issuecomment-4749452707
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: zhangqueping <3436352+zhangqueping@users.noreply.github.com>
Summary:
- Adds saved CLI startup benchmark report comparison flags to `scripts/bench-cli-startup.ts`, plus JSON output coverage and changed-target routing expectations for the new test-helper importer.
- PR surface: Tests +77, Other +109. Total +186 across 4 files.
- Reproducibility: not applicable. as a feature/tooling PR. The prior PR defects were source-proven in review comments and the current head addresses them; I did not run local tests because this review was read-only.
Automerge notes:
- Ran the ClawSweeper repair loop before final review.
- Included post-review commit in the final squash: test(perf): compare saved CLI startup benchmarks
Validation:
- ClawSweeper review passed for head 1afa110f1b.
- Required merge gates passed before the squash merge.
Prepared head SHA: 1afa110f1b
Review: https://github.com/openclaw/openclaw/pull/94812#issuecomment-4748785428
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: Felix Isaac Lim <38658663+FelixIsaac@users.noreply.github.com>
Summary:
- The PR adds provider-internal/server_error classification in reply failure handling and regression tests for classifier output plus pre-reply external-channel copy.
- PR surface: Source +21, Tests +58. Total +79 across 3 files.
- Reproducibility: yes. source-reproducible. Current main sanitizes generic provider internal errors to a stab ... and conversation-state branches, so pre-reply chat failures can fall through to generic session-reset copy.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head 8265fc71f3.
- Required merge gates passed before the squash merge.
Prepared head SHA: 8265fc71f3
Review: https://github.com/openclaw/openclaw/pull/94737#issuecomment-4747506983
Co-authored-by: snowzlm <snowzlm@noreply.codeberg.org>
Approved-by: vincentkoc
Summary:
- The PR changes Telegram sendChatAction 401 detection to trust structured Telegram `error_code` values before an unauthorized-text fallback and adds regression tests for false 401 suspension cases.
- PR surface: Source +14, Tests +90. Total +104 across 2 files.
- Reproducibility: yes. Source inspection shows current main and the latest release classify any rendered erro ... before transient handling, matching the linked issue's structured 429 `retry_after=401` reproduction path.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head 0ffee85d17.
- Required merge gates passed before the squash merge.
Prepared head SHA: 0ffee85d17
Review: https://github.com/openclaw/openclaw/pull/94810#issuecomment-4748778567
Co-authored-by: 徐闻涵0668001344 <xu.wenhan1@xydigit.com>
Approved-by: vincentkoc
Summary:
- The PR expands `src/cron/parse.test.ts` with grouped `parseAbsoluteTimeMs` coverage for epoch, ISO timezone/offset, precision, whitespace, invalid-format, and cron example cases.
- PR surface: Tests +233. Total +233 across 1 file.
- Reproducibility: not applicable. this is a test coverage PR, not a runtime bug report with user steps. Source inspection confirms the requested parser coverage is still added only by this open PR path.
Automerge notes:
- Ran the ClawSweeper repair loop before final review.
- Included post-review commit in the final squash: test(cron): expand parseAbsoluteTimeMs test coverage to 39 cases
Validation:
- ClawSweeper review passed for head 69a49d9512.
- Required merge gates passed before the squash merge.
Prepared head SHA: 69a49d9512
Review: https://github.com/openclaw/openclaw/pull/91656#issuecomment-4657254372
Co-authored-by: 刘江0668001123 <liu.jiang2@xydigit.com>
Co-authored-by: openclaw-clownfish[bot] <280122609+openclaw-clownfish[bot]@users.noreply.github.com>
Summary:
- The branch adds a bounded task-registry predicate and tests so successful delegated ACP parent-review comple ... with a Discord channel target and threadId send the parent-review terminal message directly to that thread.
- PR surface: Source +24, Tests +142. Total +166 across 2 files.
- Reproducibility: yes. at source level. Current main queues successful ACP parent-review completions through ... annel/group owner keys, and the linked canonical issue includes matching Discord thread-bound ACP evidence.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head 04ad66b23d.
- Required merge gates passed before the squash merge.
Prepared head SHA: 04ad66b23d
Review: https://github.com/openclaw/openclaw/pull/89279#issuecomment-4597994374
Co-authored-by: anyech <anyech@gmail.com>
Summary:
- The branch stamps Gateway chat run registrations and abort markers with ordering metadata, uses freshness checks for chat projection suppression, and updates abort/restart/maintenance tests and related types.
- PR surface: Source +79, Tests +103. Total +182 across 13 files.
- Reproducibility: yes. source-level: on current main, seed abortedRuns for a client run id, register a same-k ... end; the presence-only checks suppress both projections. I did not execute tests in this read-only review.
Automerge notes:
- PR branch already contained follow-up commit before automerge: ci: re-trigger checks against current main
- PR branch already contained follow-up commit before automerge: Merge upstream/main into stale-abort marker fix
- PR branch already contained follow-up commit before automerge: Merge remote-tracking branch 'upstream/main' into nex/91013-conflict-…
Validation:
- ClawSweeper review passed for head 6f13d6f7c2.
- Required merge gates passed before the squash merge.
Prepared head SHA: 6f13d6f7c2
Review: https://github.com/openclaw/openclaw/pull/91013#issuecomment-4640475472
Co-authored-by: nxmxbbd <32288+nxmxbbd@users.noreply.github.com>
Adds stdout and both-mode diagnostics OTEL log export, with focused QA Lab smoke coverage and docs/config updates.
Prepared head SHA: efa2ef07ab
Verification: CI 27808480969 passed for the prepared head.
Reviewed-by: @jesse-merhi
Summary:
- The PR adds descriptor-backed CLI command suggestions for unknown root commands, wires them into Commander parse errors and early unowned-root diagnostics, and covers both paths with focused CLI tests.
- PR surface: Source +104, Tests +71. Total +175 across 5 files.
- Reproducibility: yes. for the behavior gap: current main's formatter and early unowned-root path emit generic diagnostics without closest-command hints, and the PR proof shows the after-fix CLI output.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix: suppress suggestions for plugin policy diagnostics
- PR branch already contained follow-up commit before automerge: Merge remote-tracking branch 'origin/main' into fix/83999-cli-command…
- PR branch already contained follow-up commit before automerge: test: align agent model expectations
- PR branch already contained follow-up commit before automerge: test: restore unrelated agent test fixture
Validation:
- ClawSweeper review passed for head b98f5b59e6.
- Required merge gates passed before the squash merge.
Prepared head SHA: b98f5b59e6
Review: https://github.com/openclaw/openclaw/pull/91345#issuecomment-4646215016
Co-authored-by: Glenn-Agent <glenn_agent@163.com>
Summary:
- The branch replaces iOS notification permission display-string state with a typed SettingsNotificationStatus ... n value, and opens the app notification Settings page with UIApplication.openNotificationSettingsURLString.
- PR surface: Other +51. Total +51 across 5 files.
- Reproducibility: yes. Current main has a source-level reproduction path where the Notifications settings act ... n display strings and opens the general app Settings URL instead of the notification-specific Settings URL.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head 1a2fdeeac5.
- Required merge gates passed before the squash merge.
Prepared head SHA: 1a2fdeeac5
Review: https://github.com/openclaw/openclaw/pull/91923#issuecomment-4669439195
Co-authored-by: Sash Zats <sash@zats.io>
Summary:
- The branch replaces Feishu's module-load Axios `handlers` reset with public request-interceptor registration and adds tests that throw on private handler access.
- PR surface: Source +7, Tests +48. Total +55 across 2 files.
- Reproducibility: yes. for the source/dependency boundary: current main still writes `interceptors.request.ha ... l on that access before the production change. No live authenticated Feishu request failure was reproduced.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head b87083193b.
- Required merge gates passed before the squash merge.
Prepared head SHA: b87083193b
Review: https://github.com/openclaw/openclaw/pull/89806#issuecomment-4611809953
Co-authored-by: Cornna <96944678+ymylive@users.noreply.github.com>
Summary:
- The PR wires the macOS Dashboard and Canvas WKWebViews to WKUIDelegate and presents NSOpenPanel for HTML file inputs.
- PR surface: Other +61. Total +61 across 3 files.
- Reproducibility: yes. at source level: current main renders the affected file inputs while the macOS Dashboa ... fore-fix packaged macOS app in this read-only review, but the after-fix screenshots show the real app path.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head 4f477c4ed0.
- Required merge gates passed before the squash merge.
Prepared head SHA: 4f477c4ed0
Review: https://github.com/openclaw/openclaw/pull/94612#issuecomment-4743165861
Co-authored-by: bbblending <li.mingkang@xydigit.com>
Summary:
- This PR wraps embedded-agent tool-handler onExecutionPhase and per-run onAgentEvent emissions in best-effort warning guards and adds regression tests for throwing and rejecting callbacks.
- PR surface: Source +31, Tests +44. Total +75 across 2 files.
- Reproducibility: yes. Current main directly invokes the relevant callbacks in the tool-start and tool-event ... sync observer can leak unless guarded; I did not run a failing current-main repro in this read-only review.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head 65de17d9e0.
- Required merge gates passed before the squash merge.
Prepared head SHA: 65de17d9e0
Review: https://github.com/openclaw/openclaw/pull/81696#issuecomment-4448200659
Co-authored-by: xuyi1243 <maginaxwhz@gmail.com>
Summary:
- The branch adds a Slack subsystem INFO receipt formatter/logger for accepted non-DM app_mention events before dispatch, plus direct log tests and a test-harness team id.
- PR surface: Source +37, Tests +81. Total +118 across 3 files.
- Reproducibility: yes. from source inspection. Current main and v2026.6.8 route accepted Slack app_mention ev ... andleSlackMessage without a per-inbound INFO receipt, while Telegram emits an inbound line before dispatch.
Automerge notes:
- PR branch already contained follow-up commit before automerge: feat(slack): log INFO receipt for inbound app_mention events
Validation:
- ClawSweeper review passed for head b174201e0a.
- Required merge gates passed before the squash merge.
Prepared head SHA: b174201e0a
Review: https://github.com/openclaw/openclaw/pull/94790#issuecomment-4748509343
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: ZengWen-DT <290981215+ZengWen-DT@users.noreply.github.com>
Summary:
- The PR adds `curl` to the bundled Trello skill's `metadata.openclaw.requires.bins` entry.
- PR surface: Docs 0. Total 0 across 1 file.
- Reproducibility: yes. at source level. Current main and v2026.6.8 declare only `jq` for Trello while the skill body uses `curl`, and the shared requirement evaluator checks only declared bins.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head 83ae5e8bef.
- Required merge gates passed before the squash merge.
Prepared head SHA: 83ae5e8bef
Review: https://github.com/openclaw/openclaw/pull/94729#issuecomment-4747397470
Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
Summary:
- The PR updates Codex context projection fitting so non-positive context budgets still return turn/start text within the app-server input cap while preserving the current user request tail.
- PR surface: Source +23, Tests +87. Total +110 across 2 files.
- Reproducibility: yes. Current main is source-reproducible: when `beforeContext.length + afterContext.length ... ll-over-limit text; the linked diagnostic also shows the real Codex app-server rejects that pre-fix string.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head 1510a3d13a.
- Required merge gates passed before the squash merge.
Prepared head SHA: 1510a3d13a
Review: https://github.com/openclaw/openclaw/pull/94756#issuecomment-4747889774
Co-authored-by: Anas <anaselghoudane@gmail.com>
Summary:
- The branch adds Vitest coverage for browser action-input CLI request bodies across element, navigation/resize, fill/evaluate, and upload paths, plus blank-ref validation.
- PR surface: Tests +278. Total +278 across 4 files.
- Reproducibility: yes. for a source-level coverage gap: current main exposes the browser action-input command ... isting tests still lack broad success-path request-body assertions. This is not a runtime bug reproduction.
Automerge notes:
- PR branch already contained follow-up commit before automerge: test(browser): cover click-coords action body
Validation:
- ClawSweeper review passed for head c070a8d51b.
- Required merge gates passed before the squash merge.
Prepared head SHA: c070a8d51b
Review: https://github.com/openclaw/openclaw/pull/92574#issuecomment-4697124920
Co-authored-by: Stellar鱼 <2182712990@qq.com>
Co-authored-by: yu-xin-c <2182712990@qq.com>
Summary:
- The PR changes gateway chat-history byte-budget fallback behavior to return a small metadata-free unavailable sentinel instead of an empty transcript, with focused budget tests.
- PR surface: Source +20, Tests +73. Total +93 across 2 files.
- Reproducibility: yes. Source inspection shows current main reaches `messages: []` when the full history, las ... d copied oversized placeholder all exceed `maxBytes`; I did not run tests because this review is read-only.
Automerge notes:
- PR branch already contained follow-up commit before automerge: test: access __openclaw via bracket notation for no-underscore-dangle
Validation:
- ClawSweeper review passed for head f2fa246ab7.
- Required merge gates passed before the squash merge.
Prepared head SHA: f2fa246ab7
Review: https://github.com/openclaw/openclaw/pull/92383#issuecomment-4688688923
Co-authored-by: Hidetsugu55 <183473679+Hidetsugu55@users.noreply.github.com>
Summary:
- The PR reorganizes the Android Settings home rows into titled intent sections and adds ShellScreen logic tests for section title mapping and section ordering.
- PR surface: Other +106. Total +106 across 2 files.
- Reproducibility: not applicable. this is a UI organization cleanup rather than a bug report. The relevant ve ... ion path is the before/after Android emulator screenshot proof plus source comparison against current main.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head da9bf5c5b5.
- Required merge gates passed before the squash merge.
Prepared head SHA: da9bf5c5b5
Review: https://github.com/openclaw/openclaw/pull/94539#issuecomment-4741795253
Co-authored-by: Tosko4 <tosko4@gmail.com>
Summary:
- The PR extends TUI session info to carry `totalTokensFresh`, maps fresh missing totals to `0`, and adds a focused regression test for the footer merge path.
- PR surface: Source +15, Tests +38. Total +53 across 4 files.
- Reproducibility: yes. at source level: `chat.history` returns session info with `totalTokensFresh`, but curr ... `null` before footer formatting. I did not run local tests or a live TUI session in this read-only review.
Automerge notes:
- PR branch already contained follow-up commit before automerge: Merge branch 'main' into fix/followup-93798
Validation:
- ClawSweeper review passed for head 43657b52c8.
- Required merge gates passed before the squash merge.
Prepared head SHA: 43657b52c8
Review: https://github.com/openclaw/openclaw/pull/94337#issuecomment-4737123127
Co-authored-by: 杨浩宇0668001029 <yang.haoyu@xydigit.com>
Co-authored-by: mushuiyu_xydt <yang.haoyu@xydigit.com>
Summary:
- The PR retargets stale generated plugin-skill symlinks when their old target disappeared and adds regression coverage for that case.
- PR surface: Source +11, Tests +17. Total +28 across 2 files.
- Reproducibility: no. high-confidence current-main failure was run in this read-only review. The linked issue ... ased-build filesystem state and source inspection confirms the runtime publisher path that this PR changes.
Automerge notes:
- PR branch already contained follow-up commit before automerge: Merge remote-tracking branch 'upstream/main' into fix/plugin-skill-st…
- PR branch already contained follow-up commit before automerge: fix(skills): unlink generated plugin skill symlinks
Validation:
- ClawSweeper review passed for head 94a9765735.
- Required merge gates passed before the squash merge.
Prepared head SHA: 94a9765735
Review: https://github.com/openclaw/openclaw/pull/86719#issuecomment-4539047343
Co-authored-by: Steven Palmer <palmer.e.steven@gmail.com>
Summary:
- The PR widens the virtual Clack output columns for wrapped terminal notes and adds a rendered-output regression test for copy-sensitive session-lock paths.
- PR surface: Source +8, Tests +28. Total +36 across 2 files.
- Reproducibility: yes. Current source routes session lock paths through `note()`, and the pinned Clack note renderer hard-wraps final content from `getColumns(output) - 6` after OpenClaw's first wrapping pass.
Automerge notes:
- PR branch already contained follow-up commit before automerge: test(note): add rendered-output regression test for copy-sensitive to…
Validation:
- ClawSweeper review passed for head b17a4ff571.
- Required merge gates passed before the squash merge.
Prepared head SHA: b17a4ff571
Review: https://github.com/openclaw/openclaw/pull/94746#issuecomment-4747714518
Co-authored-by: Dirk <0668000837@xydigit.com>
* fix: default cron runMode to 'due' instead of 'force'
When the runMode parameter is omitted from a cron 'run' action,
the default value now respects schedule guards ('due') instead
of bypassing them ('force'). This prevents unintended execution
of scheduled jobs outside their configured time windows.
Fixes#94270
Co-Authored-By: Claude <noreply@anthropic.com>
* test: update runMode expectations for default 'due' (#94270)
* ci: trigger re-evaluation of real behavior proof
* fix(cron): document due-by-default agent runs
Signed-off-by: sallyom <somalley@redhat.com>
---------
Signed-off-by: sallyom <somalley@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: sallyom <somalley@redhat.com>
Summary:
- The PR changes the WhatsApp auto-reply first-media failure fallback to resend the saved leading caption chunk and adds a multi-chunk regression test for that failure path.
- PR surface: Source 0, Tests +26. Total +26 across 2 files.
- Reproducibility: yes. Source inspection of current main gives a deterministic path: the first chunk is shift ... fallback shifts `remainingText` again before checking `caption`; this read-only review did not rerun tests.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head b609e44654.
- Required merge gates passed before the squash merge.
Prepared head SHA: b609e44654
Review: https://github.com/openclaw/openclaw/pull/93823#issuecomment-4724923171
Co-authored-by: yetval <yetvald@gmail.com>
Summary:
- The branch changes `formatMessageCliText` to render dry-run message output from `result.dryRun` instead of only `handledBy === "dry-run"`.
- PR surface: Source 0. Total 0 across 1 file.
- Reproducibility: yes. source-reproducible. The linked issue has captured CLI output, and current main shows ... e the formatter still checks `handledBy === "dry-run"`; I did not execute the CLI in this read-only review.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head dce6d6a0d3.
- Required merge gates passed before the squash merge.
Prepared head SHA: dce6d6a0d3
Review: https://github.com/openclaw/openclaw/pull/94684#issuecomment-4746101038
Co-authored-by: lizeyu-xydt <li.zeyu@xydigit.com>
Summary:
- This PR replaces the generated Documentation prompt wording with self-knowledge docs-authority guidance and updates prompt tests plus the system-prompt docs.
- PR surface: Source 0, Tests +27, Docs +6. Total +33 across 4 files.
- Reproducibility: yes. from source for the prompt gap: current main and v2026.6.8 have only broad docs-first ... ledge failure example. I did not run a fresh current-main live model conversation in this read-only review.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix: strengthen self-knowledge docs prompt
- PR branch already contained follow-up commit before automerge: test: narrow cli prompt tool assertion
- PR branch already contained follow-up commit before automerge: fix: condense self-knowledge docs prompt
- PR branch already contained follow-up commit before automerge: fix: clarify self-knowledge docs authority
- PR branch already contained follow-up commit before automerge: Merge branch 'main' into sutrah/self-knowledge-docs-prompt
Validation:
- ClawSweeper review passed for head 88a7db5d2a.
- Required merge gates passed before the squash merge.
Prepared head SHA: 88a7db5d2a
Review: https://github.com/openclaw/openclaw/pull/90882#issuecomment-4637990339
Co-authored-by: Sutra Hsing <sutrahsing@163.com>
Co-authored-by: sutra <sutrahsing@163.com>
* Add /name chat command to rename the current session
Adds a `/name <title>` slash command so users can name or rename the
current session directly from any chat channel, instead of only through
the web/admin session manager. This keeps parallel sessions easy to tell
apart from within the chat flow.
Behaviour:
- `/name <title>` sets the session label, reusing the canonical
`parseSessionLabel` validation (trim, non-empty, max 512 chars) and the
same cross-store uniqueness rule enforced by the web `sessions.patch`
path, so chat naming behaves identically to the session manager.
- `/name` with no argument shows the current name plus a locally derived
`deriveSessionTitle` suggestion without mutating anything (no LLM).
- Only authorized senders can rename (rejectUnauthorizedCommand), matching
/goal. The label surfaces everywhere sessions.list is shown (TUI, web,
CLI, MCP).
The handler resolves the session via resolveSessionStoreEntry so renames
land on the canonical entry even when the store still holds a legacy or
case-folded key alias, and excludes those aliases from the uniqueness scan
to avoid false conflicts. Failed renames skip the store write.
Registers the command in commands-registry.shared.ts and the handler in
loadCommandHandlers, documents it in docs/tools/slash-commands.md, and adds
unit tests covering rename, no-arg suggestion, duplicate-label rejection,
unauthorized senders, disabled text commands, and persisted-name re-read.
Part of the chat-native session naming feature (follows the web in-chat
rename PR). Relates to openclaw#85502 and openclaw#54397.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix(name): seed native sessions and persist renames via canonical key
Address Codex review on PR #88581:
- Fall back to the in-memory params.sessionEntry when the store has no row
yet, so a brand-new native slash session can be named from its first
/name command instead of failing with 'no active session to name'.
- Persist the rename through resolved.normalizedKey and drop legacy/
case-folded alias keys (mirroring persistResolvedSessionEntry) so the
canonical entry is updated and sessions.list stops surfacing the stale
alias row.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix(name): emit session metadata changes
Route successful /name renames through the shared command session metadata seam so subscribed session lists receive sessions.changed like /goal.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* feat(commands): add /name to rename the current session from chat
* fix(docs): document the /name slash command
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Agent <agent@example.com>
Co-authored-by: openclaw-clownfish[bot] <280122609+openclaw-clownfish[bot]@users.noreply.github.com>
* fix(skills/1password): stop forcing tmux for desktop app auth (#52540)
The bundled skill currently mandates that every `op` invocation run inside
a fresh tmux session. That guidance is wrong on every desktop-app-integration
setup (macOS/Windows/Linux) because the 1Password app exposes the CLI over
a per-user Unix domain socket the gateway exec env can reach but tmux
subshells generally cannot — wrapping in tmux produces "1Password CLI
couldn't connect to the 1Password desktop app" failures.
Rewrite the skill to detect auth mode first and only use tmux for the one
case where it actually helps:
- Service account (`OP_SERVICE_ACCOUNT_TOKEN`): direct exec, no signin.
- Desktop app integration: direct exec, never tmux. Note the macOS socket
location (`~/Library/Group Containers/2BUA8C4S2C.com.1password/t/`) so
agents can recognize the failure mode.
- Standalone interactive signin: tmux is the right tool because it
preserves the per-shell session token written by `op signin`.
Update Guardrails and the get-started reference accordingly. Drop the
blanket 'do not run op outside tmux' rule.
Fixes#52540
* fix(skills/1password): correct desktop-app IPC wording and signin example
Address PR #75090 review:
- Replace the blanket 'per-user Unix domain socket' description with
per-platform wording: XPC via the 1Password Browser Helper on macOS,
a Unix domain socket on Linux, a named pipe on Windows. Keep the macOS
group-container path as a symptom indicator only, not as a transport
claim. Mirror the same correction in the get-started reference and the
changelog entry.
- Fix the standalone-signin tmux example: `op signin` was being sent as
a plain command, so its eval-style export was printed but never applied.
Subsequent `op whoami` and `op vault list` calls would fail because
the OP_SESSION_* env var was never set. Wrap the call in
`eval "$(op signin ...)"` so the session token is exported into the
tmux pane environment as the surrounding text describes.
Same direct-exec direction; tighter and more accurate.
* docs(1password): clarify Windows standalone signin
* Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* fix(skills/1password): repair auth-mode guidance
---------
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: openclaw-clownfish[bot] <280122609+openclaw-clownfish[bot]@users.noreply.github.com>
* fix(scripts): render auth monitor unit before install
Render the auth monitor service into temporary files instead of editing the tracked template. Quote the generated ExecStart safely, including spaces and literal dollars, then atomically install the rendered unit.
* fix(scripts): avoid mutating tracked auth-monitor template during setup
* fix(scripts): avoid mutating tracked auth-monitor template during setup
* fix(scripts): avoid mutating tracked auth-monitor template during setup
---------
Co-authored-by: JackWuGlobal <JackWuGlobal@users.noreply.github.com>
Co-authored-by: openclaw-clownfish[bot] <280122609+openclaw-clownfish[bot]@users.noreply.github.com>
* fix(slack): stop leaking bot token into /api/auth.test request body
The bot token is already passed as an `Authorization` header,
so we don't need to send it in the request body when calling `/api/auth.test`.
See [Slack API documentation](https://api.slack.com/methods/auth.test).
Also, showing with `curl` that the bot token is not needed in the request body when passed as an `Authorization` header when calling `/api/auth.test`:
```
curl -X POST https://slack.com:443/api/auth.test -H "Authorization: Bearer xoxb-..."
{"ok":true,"url":"https://xcoulonworkspace.slack.com/","team":"xcoulon",...}
```
Signed-off-by: Xavier Coulon <xcoulon@redhat.com>
* add test for slack auth.test token handling
verify that the bot token is not passed in the request body when calling `/api/auth.test`.
Signed-off-by: Xavier Coulon <xcoulon@redhat.com>
---------
Signed-off-by: Xavier Coulon <xcoulon@redhat.com>
* fix(exec): resume agent turn for native chat exec approvals (issue #93918)
Extend the inline approval-pending path that PR #85239 added for webchat to
every bundled chat channel that ships an `approval-handler.runtime`
adapter (Telegram, Discord, Slack, Signal, WhatsApp, iMessage, Matrix,
Google Chat, QQ Bot, plus webchat). When the originating turn can be
approved in the same chat, the gateway resolves the approval in place and
the agent waits inline for the command output instead of terminating the
run on the "approval-pending" tool result.
Before this fix, native chat approvals landed in the fire-and-forget
`sendExecApprovalFollowup` path. The followup either failed silently
against the agent dispatch and fell through to a direct delivery to the
operator, or never reached the agent at all; either way the model never
saw an "Exec running / Exec finished / Exec denied" event. The operator
had to send a follow-up message to recover the turn, and a new approval
was minted because the original run had already ended.
The change:
- Introduces `NATIVE_APPROVAL_CHANNELS` and `isNativeApprovalChannel`
in `src/utils/message-channel-constants.ts`, listing the channels that
ship a native chat approval client. `webchat` is included so the
single-channel check inside `shouldAwaitGatewayApprovalInline` can
move from "this one id" to "any native approval client".
- Replaces the `INTERNAL_MESSAGE_CHANNEL` equality check in
`shouldAwaitGatewayApprovalInline` with `isNativeApprovalChannel`,
preserving the `approvalFollowupMode` opt-out and the existing
`unavailableReason === null` gate.
- Adds unit tests asserting inline resolution and inline denial for
every native approval channel, plus a regression test that
non-native channels (e.g. feishu) and explicit `approvalFollowupMode`
settings still take the fire-and-forget path.
- Adds a `NATIVE_APPROVAL_CHANNELS` test in
`src/utils/message-channel.test.ts` to lock the membership and the
negative cases.
Refs https://github.com/openclaw/openclaw/issues/93918
* fix(lint): restore InternalMessageChannel type export lost during rebase
Rebase on upstream/main dropped the InternalMessageChannel type alias
from message-channel-constants.ts, breaking the plugin-sdk boundary
.dts check ('has no exported member named InternalMessageChannel').
message-channel.ts was also re-importing the type only to re-export
it, triggering the oxlint no-unused-vars rule.
- Re-add 'export type InternalMessageChannel = typeof INTERNAL_MESSAGE_CHANNEL'
in message-channel-constants.ts so the public re-export is valid.
- Drop the redundant 'type InternalMessageChannel' from the local
import in message-channel.ts; the value-side import is what the
file body actually needs.
* test(exec): align native approval routing expectations
* fix(openai-embedding): preserve openai/ prefix for non-native base URLs
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(openai-embedding): normalize model before maxInputTokens lookup so qualified models retain token cap
* fix(openai-embedding): use semantic hostname check for native OpenAI URL detection
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Stabilize timeout-sensitive hosted QA by removing wedged synthetic Codex run-attempt integrations while keeping narrower dynamic-tool and thread-start coverage. Refresh root and Discord shrinkwraps after the current undici security floor landed on main.\n\nProof: git diff --check origin/main...HEAD; node scripts/pre-commit/pnpm-audit-prod.mjs --audit-level=high; node scripts/generate-npm-shrinkwrap.mjs --all --check; CI run 27774571070; Plugin Prerelease run 27774571273.
The lane timeout sliding window expires during long-running tool
execution (e.g. exec commands >5min) because noteLaneTaskProgress()
is never called during tool execution. Add a periodic 30s interval
that calls noteLaneTaskProgress() while the embedded attempt runs,
keeping the lane alive until the attempt completes.
Closes: openclaw/openclaw#94033
Co-Authored-By: Claude <noreply@anthropic.com>
Address ClawSweeper P1 (Carry the effective git channel into finalize):
an unconfigured git/source update runs the core update on the git/dev channel
(runGatewayUpdate: opts.channel ?? "dev"), but the finalizer received no channel
and fell back to the stable package channel, so plugin convergence could resolve
official plugins on the wrong channel.
Mirror the CLI post-core resume's effective/requested channel split: the RPC
finalize path now passes the effective channel (configChannel ?? DEFAULT_GIT_CHANNEL)
to update finalize via OPENCLAW_UPDATE_EFFECTIVE_CHANNEL (convergence-only), never
as --channel. update finalize uses it as a convergence fallback but never persists
update.channel unless the user actually requested one.
Codex follow-up: defaulting the channel to dev and passing --channel made
update finalize persist update.channel into openclaw.json (persistRequestedUpdateChannel
treats any --channel as an explicit request). Only forward --channel when the
caller has a configured channel so the finalizer never writes a channel the user
did not request; when omitted it converges on the stored/default channel and the
reconcile still resolves a host-compatible version. Keeps the per-step vs
whole-process timeout decoupling.
Address codex PR-review findings:
- Default the post-core finalize channel to the git/dev channel (matching
runGatewayUpdate's git default) instead of letting update finalize fall back to
the stable package channel, so official plugins converge on the same channel as
the core update for default source updates.
- Decouple the finalizer's whole-process spawn timeout from the per-step
--timeout so a valid multi-step finalize is not killed prematurely and falsely
reported as post-core-plugin-finalize-failed.
- Strip gateway service identity (OPENCLAW_SERVICE_MARKER/KIND/PID) from the
finalizer child so it is not mistaken for the managed service, matching the
CLI post-core spawn.
- Skip finalize for no-op git updates (unchanged SHA and version), mirroring the
CLI resume gate, to avoid an unnecessary doctor/convergence run.
The gateway update.run RPC updated git/source installs via runGatewayUpdate
but, unlike the openclaw update CLI, never resumed the post-core plugin
convergence that runGatewayUpdate's doctor pass defers. As a result a
git/source core update would restart on the new core with official managed
plugins still pinned to versions built against removed core APIs.
Spawn the rebuilt binary's update finalize entrypoint after a successful
git update so official plugins reconcile to a host-compatible version, and
block the restart if convergence fails (mirroring the CLI).
description: "Use when previewing local channel message flow fixtures."
description: "Use when running QA Lab channel message flow evidence."
---
# Channel Message Flows
Use this from the OpenClaw repo root to send canned channel preview flows while iterating on message UX. These are real sends/edits/deletes against the configured channel target.
Use this from the OpenClaw repo root to run the QA Lab evidence for Telegram
draft/final delivery sequencing. This skill no longer launches a standalone
script; the behavior is owned by the QA scenario and its Vitest-backed e2e test.
## Telegram
## QA Scenario
Native Telegram `sendMessageDraft` tool progress, then a final answer:
Add a visible `Closes #<issue-number>` or `Related: #<issue-number>` line
below this comment.
What problem does this PR solve?
Required PR title:
type: user-facing description
Use a parenthesized scope only when it adds clarity:
fix(auth): login redirect loops when session cookie is expired
Why does this matter now?
Types: feat, fix, improve, refactor, docs, chore.
For fixes, describe the user-visible symptom and trigger:
fix: task list fails to load when user has no environments
Avoid implementation details such as:
fix: add null check to task query
-->
What is the intended outcome?
## What Problem This Solves
What is intentionally out of scope?
<!--
Describe the concrete user, product, or operational problem.
For fixes, begin with:
"Fixes an issue where users <do X> would <experience Y> when <condition>."
or:
"Resolves a problem where..."
What does success look like?
Name the affected UI surface or workflow. Do not describe the code-level cause here.
-->
What should reviewers focus on?
## Why This Change Was Made
<details>
<summary>Summary guidance</summary>
<!--
In one or two sentences, explain the complete shipped solution, key design
decisions, and relevant boundaries or non-goals. Include implementation detail
only when it helps reviewers understand user-visible behavior or risk.
Avoid file-by-file narration.
-->
This PR description is the contributor's durable explanation of the change. Write it for human maintainers first; ClawSweeper and Barnacle use the same text to understand intent, proof, risk, and current review state.
## User Impact
Describe the intent and outcome in 2-5 bullets. Avoid restating the diff; reviewers and bots can read the changed files.
<!--
State what users, operators, or developers can now do or expect. Lead with the
concrete benefit and use user-facing language. If there is no user-visible
impact, say so plainly.
-->
If this PR fixes a plugin beta-release blocker, title it `fix(<plugin-id>): beta blocker - <summary>` and link the matching `Beta blocker: <plugin-name> - <summary>` issue labeled `beta-blocker`. Contributors cannot label PRs, so the title is the PR-side signal for maintainers and automation.
## Evidence
</details>
<!--
Show the most useful proof that this change works. Screenshots, screencasts,
terminal output, focused tests, CI results, live observations, redacted logs,
and artifact links are all useful. Include before/after evidence for visual
changes when it clarifies the result.
## Linked context
Which issue does this close?
Closes #
Which issues, PRs, or discussions are related?
Related #
Was this requested by a maintainer or owner?
<details>
<summary>Linked context guidance</summary>
Link the issue, PR, discussion, maintainer request, or owner request that explains why this PR should exist. Maintainer context helps reviewers and automation distinguish intended work from drive-by churn.
</details>
## Real behavior proof (required for external PRs)
- Behavior or issue addressed:
- Real environment tested:
- Exact steps or command run after this patch:
- Evidence after fix (screenshot, recording, terminal capture, console output, redacted runtime log, linked artifact, or copied live output):
- Observed result after fix:
- What was not tested:
- Proof limitations or environment constraints:
- Before evidence (optional but encouraged):
<details>
<summary>Real behavior proof guidance</summary>
External contributors must show after-fix evidence from a real OpenClaw setup. Unit tests, mocks, lint, typechecks, snapshots, and CI are supplemental only.
Screenshots are encouraged even for CLI, console, text, or log changes. Terminal screenshots, copied live output, redacted runtime logs, recordings, and linked artifacts count.
If your environment cannot produce the ideal proof, explain that under `Proof limitations or environment constraints` so reviewers and ClawSweeper can direct the next step properly.
Be mindful of private information like IP addresses, API keys, phone numbers, non-public endpoints, or other private details when providing evidence.
</details>
## Tests and validation
Which commands did you run?
What regression coverage was added or updated?
What failed before this fix, if known?
If no test was added, why not?
<details>
<summary>Testing guidance</summary>
List focused commands, not every incidental check. CI is useful support, but external PRs still need real behavior proof above when behavior changes.
</details>
## Risk checklist
Did user-visible behavior change? (`Yes/No`)
Did config, environment, or migration behavior change? (`Yes/No`)
Did security, auth, secrets, network, or tool execution behavior change? (`Yes/No`)
What is the highest-risk area?
How is that risk mitigated?
<details>
<summary>Risk guidance</summary>
Use this for author judgment that is not obvious from the diff. ClawSweeper can see touched files, but it cannot know which behavior you think is risky, why the risk is acceptable, or what mitigation reviewers should verify.
</details>
## Current review state
What is the next action?
What is still waiting on author, maintainer, CI, or external proof?
Which bot or reviewer comments were addressed?
<details>
<summary>Review state guidance</summary>
Keep this as the durable state for review progress. If useful information appears in comments, fold the current next action or blocker back here so maintainers and ClawSweeper do not need to reconstruct state from comment history.
</details>
Reviewers will inspect the code, tests, and CI. Use this section to make the
validation easy to understand, not to restate the diff.
if ! grep -Eiq '(^|[[:space:]])@(clawsweeper|openclaw-clawsweeper)\b(\[bot\])?|(^|[[:space:]])/(clawsweeper|review|automerge|autoclose)\b' "$body_file"; then
@@ -206,7 +238,7 @@ jobs:
fi
if [ -n "$TARGET_TOKEN" ]; then
err="$(mktemp)"
if GH_TOKEN="$TARGET_TOKEN" ghapi -X POST \
if GH_TOKEN="$TARGET_TOKEN" gh_api_with_retry -X POST \
@@ -35,7 +35,7 @@ Skills own workflows; root owns hard policy and routing.
- One-sided fixes need sibling-surface proof, an explanation for why siblings are unaffected, or explicit follow-up work.
- Changelog findings: see Docs / Changelog.
- Public ClawSweeper comments prefer `https://docs.openclaw.ai/...` when a public docs page exists; structured evidence still cites repo files, lines, SHAs.
- Findings need current source, shipped/current behavior, tests/CI evidence, and dependency contract proof when dependency-backed behavior is involved. Validation is judged against touched and sibling surfaces plus this file's commands; real behavior proof matters for user-visible changes, with Telegram/Desktop proof for Telegram-visible behavior when feasible.
- Findings need current source, shipped/current behavior, tests/CI evidence, and dependency contract proof when dependency-backed behavior is involved. Validation is judged against touched and sibling surfaces plus this file's commands; clear evidence matters for user-visible changes, with Telegram/Desktop proof for Telegram-visible behavior when feasible.
- Prefer findings for concrete behavior regressions, missing changed-surface proof, owner-boundary violations, security/API contract issues, or docs/config mismatches.
- Do not file findings for repo policy preference when changed code follows the relevant scoped guide and no user-visible, runtime, security, or maintainer-risk impact is shown.
@@ -165,13 +165,12 @@ Skills own workflows; root owns hard policy and routing.
- Representing user: if user already has a comment/thread for the point, update/reply there when possible; avoid duplicate PR/issue comments.
- No surprise GH writes: chat must mention every posted/updated public comment with URL.
- GH comments with backticks, `$`, or shell snippets: use heredoc/body file, not inline double-quoted `--body`.
- PR create: real body required. Include Summary + Verification; mention refs, behavior, and proof.
- PR create: real body required. Use the current template: `What Problem This Solves`, `Why This Change Was Made`, `User Impact`, and `Evidence`; include visible refs, behavior, and validation.
- PR create/refresh: keep PR branches takeover-ready. Use a branch maintainers can push to, or for fork PRs ensure `maintainer_can_modify` / GitHub's `Allow edits by maintainers` is enabled unless explicitly told otherwise or GitHub's Actions/secrets warning makes that unsafe.
- GitHub issue/PR create: read `$agent-transcript`; ask about sanitized transcript logs when available.
- Contributor PRs: parsed `Real behavior proof` uses exact `field: value` labels: `Behavior addressed`, `Real environment tested`, `Exact steps or command run after this patch`, `Evidence after fix`, `Observed result after fix`, `What was not tested`.
- Contributor PRs: parsed context requires authored `What Problem This Solves` and `Evidence` sections. Do not require field-level proof forms; reviewers inspect code, tests, and CI for correctness.
- PR artifacts/screenshots: attach to PR/comment/external artifact store. Never push screenshots, videos, proof images, or proof assets to OpenClaw or any product repo branch, including temp artifact branches. Use Crabbox artifact publishing plus the manifest URL. Do not commit `.github/pr-assets`.
- CI polling: exact SHA, relevant checks only, minimal fields. Skip routine noise (`Auto response`, `Labeler`, docs agents, performance/stale). Logs only after failure/completion or concrete need.
- OpenClaw write-access maintainers may skip `Real behavior proof` when local tests or Crabbox verified behavior; record proof in PR verification.
- Agent PR landing to `main`: use only the repo-native `scripts/pr` wrapper: run `scripts/pr review-init <PR>`, follow its emitted checkout/guard guidance, initialize and complete review artifacts with `scripts/pr review-artifacts-init <PR>`, validate them with `scripts/pr review-validate-artifacts <PR>`, then run `scripts/pr prepare-run <PR>` and `scripts/pr merge-run <PR>`; do not idle on `auto-response` or `check-docs`.
@@ -106,7 +106,8 @@ For coordinated change sets that genuinely need more than 20 PRs, join the **#cl
## Before You PR
- Test locally with your OpenClaw instance
- External PRs must include a filled **Real behavior proof** section in the PR body. Show the real setup you tested, the exact command or steps you ran after the patch, after-fix evidence, the observed result, and anything you did not test. Screenshots, recordings, terminal screenshots, console output, copied live output, linked artifacts, and redacted runtime logs all count. Unit tests, mocks, snapshots, lint, typechecks, and CI are useful but do not satisfy this requirement by themselves. Maintainers may apply `proof: override` only when the proof gate should not apply.
- External PRs must describe the user, product, or operational problem in **What Problem This Solves** and include useful validation in **Evidence**. Focused tests, CI results, screenshots, recordings, terminal output, live observations, redacted logs, and artifact links all count. Reviewers will inspect the code, tests, and CI; use the PR body to explain intent and make validation easy to understand.
- When ClawSweeper, Codex, Barnacle, or a maintainer asks for more context or evidence, edit the PR description instead of only replying in a new comment. Keep **What Problem This Solves**, **Why This Change Was Made**, **User Impact**, and **Evidence** current; a short comment can point reviewers to the update, but the PR body should remain the durable explanation for maintainers and bots.
- Keep PRs takeover-ready: open them from a branch maintainers can push to. For fork PRs, leave GitHub's **Allow edits by maintainers** option enabled so maintainers can finish urgent fixes, changelog entries, or merge prep when needed. If GitHub shows **Allow edits and access to secrets by maintainers**, enable it only when that workflow/secrets access is acceptable and say so in the PR.
- Do not edit `CHANGELOG.md` in contributor PRs. Maintainers or ClawSweeper add the changelog entry when landing user-facing changes.
@@ -169,7 +170,7 @@ Built with Codex, Claude, or other AI tools? **Awesome - just mark it!**
Please include in your PR:
- [ ] Mark as AI-assisted in the PR title or description
- [ ] Include human-run real behavior proof from your own setup. AI-generated tests, mocks, lint, typechecks, and CI output are supplemental only; they do not prove the fix works for users.
- [ ] Include a concise **Evidence** section with the most useful validation. Reviewers will inspect the code, tests, and CI rather than relying on the PR body alone.
- [ ] Include prompts or session logs if possible (super helpful!)
- [ ] Confirm you understand what the code does
- [ ] If you have access to Codex, run `codex review --base origin/main` locally and address the findings before asking for review
3. Update `apps/android/CHANGELOG.md`, then run `pnpm android:version:sync` again if needed.
4. Run `MATCH_PASSWORD=<signing repo password> pnpm android:release:signing:sync:pull` to materialize encrypted Android signing assets from `apps-signing`.
5. Run `pnpm android:release:preflight` to validate Play auth, signing, synced versioning, and release notes.
6. Run `pnpm android:screenshots` to refresh raw Google Play screenshots.
6. Run `ANDROID_SCREENSHOT_AVD=<avd-name> pnpm android:screenshots` to refresh raw Google Play screenshots with a script-managed emulator, or run `pnpm android:screenshots` when exactly one ADB device is already connected.
7. Run `pnpm android:release:archive` to produce the signed Play AAB and third-party APK.
8. Run `pnpm android:release:upload` to upload metadata, screenshots, and the Play AAB to Google Play internal testing.
9. Promote to production manually in Google Play Console.
SettingsRow("Agents",if(agents.isEmpty())"Load from gateway"else"${agents.size} available",Icons.Default.Person,status=agents.isNotEmpty(),route=SettingsRoute.Agents),
SettingsRow("Agents",if(agents.isEmpty())"Load from gateway"else"${agents.size} available",Icons.Default.Person,status=agents.isNotEmpty(),route=SettingsRoute.Agents),
- App Store Connect API auth uses Keychain for private key material plus non-secret `apps/ios/fastlane/.env` variables.
- The encrypted signing repo password lives outside this repo in the release-owner vault and is exposed locally as `MATCH_PASSWORD`.
- The share sheet requires the Apple Developer App Group in `apps/ios/Config/AppStoreSigning.json` to be associated with both the app and share-extension bundle IDs before App Store profiles are regenerated.
- Apple Distribution private keys, certificates, provisioning profiles, and decrypted signing sync output stay under `apps/ios/build/` or Keychain and are gitignored.
- Rotating release signing means refreshing Fastlane `match` assets and pushing a fresh encrypted sync state.
@@ -155,7 +156,8 @@ This should create `apps/ios/fastlane/.env` with non-secret App Store Connect va
The main app and share extension must both be associated with the App Group pinned in `apps/ios/Config/AppStoreSigning.json`.
Use `pnpm ios:release:signing:setup` for the initial portal setup, then `MATCH_PASSWORD=... pnpm ios:release:signing:sync:push` to publish encrypted Fastlane match assets to the shared private repo.
"Provisioning profile #{target.fetch("profileName")} for #{target.fetch("bundleId")} is missing App Groups #{missing.join(", ")}; actual groups: #{actual_app_groups.empty? ? "missing" : actual_app_groups.join(", ")}."
`signing:setup` uses Fastlane `produce` and `modify_services` to create Developer Portal bundle IDs and enable required services before running `match`. If Fastlane does not already have a valid Apple Developer Portal session, run `fastlane spaceauth` for a release-owner Apple ID and export the resulting `FASTLANE_SESSION`.
`signing:setup` uses Fastlane `produce` and `modify_services` to create Developer Portal bundle IDs and enable required services before running `match`. The main app and share extension also require the shared App Group from `apps/ios/Config/AppStoreSigning.json`; associate that group with both bundle IDs in the Apple Developer Portal before regenerating profiles. If Fastlane does not already have a valid Apple Developer Portal session, run `fastlane spaceauth` for a release-owner Apple ID and export the resulting `FASTLANE_SESSION`.
- `socketMode` is ignored in HTTP Request URL mode.
- Base `channels.slack.socketMode` settings apply to all Slack accounts unless overridden. Per-account overrides use `channels.slack.accounts.<accountId>.socketMode`; because this is an object override, include every socket tuning field you want for that account.
- Only `clientPingTimeout` has an OpenClaw default (`15000`). `serverPingTimeout` and `pingPongLoggingEnabled` are passed to the Slack SDK only when configured.
- Socket Mode restart backoff starts around 2 seconds and caps around 30 seconds. Consecutive recoverable start/start-wait failures stop after 12 attempts; after a successful connection, later recoverable disconnects start a fresh retry cycle. Non-recoverable Slack auth errors such as `invalid_auth`, revoked tokens, or missing scopes fail fast instead of retrying forever.
- Socket Mode restart backoff starts around 2 seconds and caps around 30 seconds. Recoverable start, start-wait, and disconnect failures retry until the channel stops. Permanent account and credential errors such as invalidauth, revoked tokens, or missing scopes fail fast instead of retrying forever.
## Manifest and scope checklist
@@ -1409,10 +1409,14 @@ Same-chat `/approve` also works in Slack channels and DMs that already support c
- `channel_id_changed` can migrate channel config keys when `configWrites` is enabled.
- Channel topic/purpose metadata is treated as untrusted context and can be injected into routing context.
- Thread starter and initial thread-history context seeding are filtered by configured sender allowlists when applicable.
- Block actions and modal interactions emit structured `Slack interaction: ...` system events with rich payload fields:
- Block actions, shortcuts, and modal interactions emit structured `Slack interaction: ...` system events with rich payload fields:
- global shortcuts: callback and actor metadata, routed to the actor's direct session
- message shortcuts: callback, actor, channel, thread, and selected-message context
- modal `view_submission` and `view_closed` events with routed channel metadata and form inputs
Define global or message shortcuts in your Slack app configuration and use any non-empty callback ID. OpenClaw acknowledges matching shortcut payloads, applies the same DM/channel sender policy as other Slack interactions, and queues the sanitized event for the routed agent session. Trigger IDs and response URLs are redacted from agent context.
- [OpenClaw](https://docs.openclaw.ai/install) must be installed (`openclaw` CLI available).
- A Zalo account on a mobile device to scan the login QR code.
## Install with onboard (recommended)
Run the OpenClaw onboarding wizard and pick **Zalo ClawBot** from the channel menu:
```bash
openclaw onboard
```
The wizard installs the plugin from the official catalog (integrity-verified), renders the login QR right in the terminal, and finishes the channel once you scan it with the Zalo app. No extra commands are needed.
## Manual Installation
To add the channel to an already-onboarded gateway, follow these steps:
Use the exact pinned version shown above (it matches the official catalog entry), so OpenClaw verifies the package against the catalog integrity hash during install.
### 2. Enable the plugin in config
```bash
openclaw config set plugins.entries.openclaw-zaloclawbot.enabled true
Scan the terminal-rendered QR code using the Zalo mobile app, accept the Terms of Use inside the Zalo Mini App, and authorize the session.
### 4. Restart the gateway
```bash
openclaw gateway restart
```
---
## How It Works
Unlike the standard developer Zalo channel which requires you to register your own Zalo Official Account (OA) and paste static developer credentials, Zalo ClawBot operates as an **owner-bound personal assistant** using a shared, official infrastructure:
1.**Secure Onboarding:** The QR code resolves to a secure Zalo Mini App that binds a newly-provisioned, private bot under a shared official OA directly to your Zalo User ID.
2.**Owner-Bound Privacy:** By design, the bot is restricted to communicating _only_ with its owner. Messages from other users are dropped at the platform level, making the connection private and secure.
3.**Official API path:** The plugin uses Zalo Bot Platform APIs instead of
browser or web-session automation.
## Under the Hood
The Zalo ClawBot plugin communicates with Zalo APIs via a persistent long-polling message loop. To maintain a clean and lightweight runtime:
- Long-poll connections utilize the `getUpdates` endpoint.
- Webhooks are disabled by default for local desktop/terminal gateway runs.
- Messages are processed client-side and mapped directly to your local agent runtime.
The external plugin manages bot credentials under the OpenClaw state directory.
Treat that directory as sensitive and include it in the same access-control and
backup policy as the rest of your OpenClaw state.
---
## Troubleshooting
- **QR Login Timeout:** The login token (`zbsk`) expires after 5 minutes for security reasons. If the QR code expires before you scan it, simply rerun the login command to generate a new one.
- **Gateway Fails to Load:** Ensure your OpenClaw host version is `2026.4.10` or higher. Older versions do not support the external npm-plugin installation ledger.
@@ -47,33 +47,21 @@ Use `pnpm ci:timings`, `pnpm ci:timings:recent`, or `node scripts/ci-run-timings
For pull request runs, the terminal timing-summary job runs the helper from the trusted base revision before passing `GH_TOKEN` to `gh run view`. That keeps the tokened query out of branch-controlled code while still summarizing the pull request's current CI run.
## Real behavior proof
## PR context and evidence
External contributor PRs run a `Real behavior proof` gate from
External contributor PRs run a PR context and evidence gate from
`.github/workflows/real-behavior-proof.yml`. The workflow checks out the trusted
base commit and evaluates the PR body only; it does not execute code from the
contributor branch.
The gate applies to PR authors who are not repository owners, members,
collaborators, or bots. It passes when the PR body contains a
`Real behavior proof` section with filled values for:
-`Behavior or issue addressed`
-`Real environment tested`
-`Exact steps or command run after this patch`
-`Evidence after fix`
-`Observed result after fix`
-`What was not tested`
The evidence must show the changed behavior after the patch in a real OpenClaw
setup. Screenshots, recordings, terminal captures, console output, copied live
output, redacted runtime logs, and linked artifacts all count. Unit tests, mocks,
snapshots, lint, typechecks, and CI results are useful supporting verification,
but they do not satisfy this gate by themselves.
collaborators, or bots. It passes when the PR body contains authored
`What Problem This Solves` and `Evidence` sections. Evidence can be a focused
test, CI result, screenshot, recording, terminal output, live observation,
redacted log, or artifact link. The body provides intent and useful validation;
reviewers inspect the code, tests, and CI to assess correctness.
When the check fails, update the PR body instead of pushing another code commit.
Maintainers can apply `proof: override` only when the proof gate should not
apply to that PR.
## Scope and routing
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.