ClawSweeper

ClawSweeper is the conservative maintenance bot for OpenClaw repositories. It currently covers openclaw/openclaw, openclaw/clawhub, and self-review for openclaw/clawsweeper.

It has two independent lanes:

• issue/PR sweeper: keeps one markdown report per open issue or PR, publishes one durable Codex automated review comment when useful, and only closes items when the evidence is strong
• commit sweeper: reviews code-bearing commits that land on main, writes one canonical markdown report per commit, and optionally publishes a GitHub Check Run for that commit

Capabilities

• Repository profiles: per-repository rules live in src/repository-profiles.ts, so OpenClaw, ClawHub, and ClawSweeper can share the same engine while keeping different apply limits.
• Issue and PR intake: scheduled runs scan open issues and pull requests, while target repositories can forward exact issue/PR events with repository_dispatch for low-latency one-item reviews.
• Codex review reports: each issue or PR becomes records/<repo-slug>/items/<number>.md with the decision, evidence, proposed maintainer-facing comment, runtime metadata, and GitHub snapshot hash.
• Durable review comments: ClawSweeper syncs one marker-backed public review comment per item and edits it in place instead of posting repeated comments. When a review starts and no ClawSweeper comment exists yet, it posts a short crustacean-friendly status placeholder first, then replaces that same comment with the completed review. Completed comments include a dedicated security review section for supply-chain, permission, secret-handling, and code execution concerns. Pull request comments include hidden verdict markers, and actionable PR follow-up includes a hidden clawsweeper-action:fix-required marker for the trusted ClawSweeper repair loop. See docs/pr-review-comments.md.
• Guarded apply: apply mode re-fetches live GitHub state, checks labels, maintainer authorship, paired issue/PR state, snapshot drift, and repository profile rules before commenting or closing anything.
• Archive and reopen handling: closed or already-closed reports move to records/<repo-slug>/closed/<number>.md; reopened archived items move back to items/ as stale work.
• Dashboard: this README contains the generated fleet dashboard with current run state, cadence health, recent reviews, recent closes, and work candidates.
• Workflow status markers: pnpm run status updates per-repository README status blocks so long-running workflows can publish progress without changing report data.
• Audit: pnpm run audit compares live GitHub state with report storage and can publish Audit Health into this README without mutating issues or PRs.
• Reconcile: pnpm run reconcile repairs report placement drift such as reopened archived records or closed items still sitting in items/.
• Work candidates: valid, narrow items can be marked as queue_fix_pr candidates for manual ClawSweeper repair promotion.
• Commit review: push events on target main branches can dispatch to .github/workflows/commit-review.yml, which expands the commit range, skips non-code-only commits cheaply, starts one Codex worker per code-bearing commit, and writes records/<repo-slug>/commits/<sha>.md.
• Manual reruns and backfills: both lanes support manual workflow dispatch. Commit review supports exact SHAs, historic ranges with before_sha, and an additional_prompt input for one-off review instructions.
• Commit report queries: pnpm commit-reports -- --since 24h, --findings, --non-clean, --repo, and --author make the flat per-SHA commit storage easy to review by time window without date folders.
• Optional commit checks: commit reports are the source of truth; target commit Check Runs are disabled by default and can be enabled per run or repo.
• ClawSweeper repair dispatch: commit reports with result: findings can dispatch to the repair intake, where an audit record is written and a PR is created only when the finding is narrow, non-security, and still relevant on latest main.

Guardrails

ClawSweeper may propose a close only when the item is clearly one of these:

• implemented on current main
• not reproducible on current main
• better suited for ClawHub skill/plugin work than core
• duplicate or superseded by a canonical issue/PR
• concrete but not actionable in this source repo
• incoherent enough that no action can be taken
• stale issue older than 60 days with too little data to verify

Maintainer-authored items are never auto-closed. Everything else stays open. Issues with an open PR that references them using GitHub closing syntax such as Fixes #123 stay open until that PR merges or is closed. Open issue/PR pairs from the same author stay open together unless the paired item is already resolved or a maintainer explicitly asks to close one side.

Repository profiles can further narrow apply. ClawHub and ClawSweeper self-review are intentionally stricter: they review issues and PRs, but apply may close only PRs where current main already implements the proposed change with source-backed evidence.

Maintainer Commands

Maintainers can steer ClawSweeper from target-repo issue and PR comments. The preferred form is @clawsweeper .... The router also accepts @clawsweeper[bot] ..., @openclaw-clawsweeper ..., @openclaw-clawsweeper[bot] ..., and legacy slash aliases such as /clawsweeper ..., /review, /automerge, and /autoclose <reason>.

Common commands:

@clawsweeper status
@clawsweeper re-review
@clawsweeper review
@clawsweeper fix ci
@clawsweeper address review
@clawsweeper rebase
@clawsweeper autofix
@clawsweeper automerge
@clawsweeper approve
@clawsweeper explain
@clawsweeper stop
@clawsweeper why did automerge stop here?

• status and explain post a short target summary.
• review and re-review dispatch a fresh ClawSweeper issue/PR review without starting repair.
• Command status replies are marker-backed and edited in place per issue/PR, intent, and head SHA, so repeated review nudges do not leave a trail of duplicate lobster notes.
• Freeform @clawsweeper ... mentions dispatch a read-only assist review that answers the maintainer request in the next ClawSweeper comment. Action-looking prose still maps through existing safe markers and deterministic gates.
• fix ci, address review, and rebase dispatch the repair worker only for ClawSweeper PRs or PRs already opted into clawsweeper:autofix or clawsweeper:automerge.
• autofix labels an open PR, creates or reuses the adopted job, dispatches review, and enters the bounded review/fix loop without merging.
• automerge labels an open PR, creates or reuses the adopted job, dispatches review, and enters the bounded review/fix/merge loop. Draft PRs are fix-only until GitHub marks them ready for review.
• User-facing OpenClaw fix, feat, and perf automerge PRs must include a CHANGELOG.md entry before ClawSweeper will merge them.
• Security-sensitive findings can be repaired only after explicit autofix/automerge opt-in; ClawSweeper still will not merge until a later exact-head review is clean.
• approve lets a maintainer clear a ClawSweeper human-review pause and merge only after the normal exact-head, checks, mergeability, and gate checks pass.
• stop adds clawsweeper:human-review; /autoclose <reason> closes the item and bounded linked same-repo targets with an explicit maintainer reason.

Only maintainers are accepted. The router checks repository collaborator permission (admin, maintain, or write) and falls back to trusted author_association values when permission lookup is unavailable. Contributor commands are ignored without a reply. Scheduled comment routing is dry unless CLAWSWEEPER_COMMENT_ROUTER_EXECUTE=1; workflow dispatch with execute=true can be used for one-off live routing.

Dashboard

Last dashboard update: May 1, 2026, 03:12 UTC

Fleet

Metric	Count
Covered repositories	3
Open issues	3658
Open PRs	3357
Open items total	7015
Reviewed files	7643
Unreviewed open items	54
Due now by cadence	1551
Proposed closes awaiting apply	1
Work candidates awaiting promotion	2255
Closed by Codex apply	11402
Failed or stale reviews	24
Archived closed files	15436

Repositories

Repository	Open	Reviewed	Unreviewed	Due	Proposed closes	Work candidates	Closed	Latest review	Latest close	Comments synced, 1h
OpenClaw	6768	6714	54	1294	1	2209	11394	May 1, 2026, 03:12 UTC	May 1, 2026, 02:58 UTC	260
ClawHub	247	924	0	252	0	45	8	Apr 29, 2026, 22:22 UTC	Apr 29, 2026, 17:17 UTC	0
ClawSweeper	0	5	0	5	0	1	0	May 1, 2026, 02:03 UTC	unknown	0

Current Runs

Repository	State	Updated	Run
OpenClaw	Review comments checked	May 1, 2026, 03:12 UTC	run
ClawHub	Review publish complete	Apr 29, 2026, 22:23 UTC	run
ClawSweeper	Idle	unknown	none

Fleet Activity

Latest review: May 1, 2026, 03:12 UTC. Latest close: May 1, 2026, 02:58 UTC. Latest comment sync: May 1, 2026, 03:12 UTC.

Window	Reviews	Close decisions	Keep-open decisions	Failed/stale reviews	Closed	Comments synced	Apply skips
Last 15 minutes	61	0	61	0	1	13	0
Last hour	353	7	346	0	25	260	0
Last 24 hours	6802	471	6331	11	639	3974	23

Recently Closed Across Repos

Repository	Item	Title	Reason	Closed	Report
openclaw/openclaw	#75360	Fix Telegram reply cold-start latency	kept open	May 1, 2026, 02:58 UTC	records/openclaw-openclaw/closed/75360.md
openclaw/openclaw	#75367	fix(auto-reply): move visible reply warnings to doctor	closed externally after review	May 1, 2026, 02:52 UTC	records/openclaw-openclaw/closed/75367.md
openclaw/openclaw	#75361	test: strengthen published upgrade survivor lane	closed externally after review	May 1, 2026, 02:50 UTC	records/openclaw-openclaw/closed/75361.md
openclaw/openclaw	#75335	fix: keep async music delivery agent-mediated	closed externally after review	May 1, 2026, 02:48 UTC	records/openclaw-openclaw/closed/75335.md
openclaw/openclaw	#74234	[Bug]: Possibly incorrect gpg key fingerprint validation in Dockerfile	closed externally after review	May 1, 2026, 02:47 UTC	records/openclaw-openclaw/closed/74234.md
openclaw/openclaw	#74254	fix(docker): require single primary key before Docker apt GPG pin	closed externally after review	May 1, 2026, 02:47 UTC	records/openclaw-openclaw/closed/74254.md
openclaw/openclaw	#74597	Bug: update dev-channel switch can leave npm-global openclaw as source checkout symlink	closed externally after review	May 1, 2026, 02:47 UTC	records/openclaw-openclaw/closed/74597.md
openclaw/openclaw	#62557	openclaw update does not restart system-wide systemd services	closed externally after review	May 1, 2026, 02:47 UTC	records/openclaw-openclaw/closed/62557.md
openclaw/openclaw	#73448	Bug: message tool asVoice parameter defined in schema but never read in handleSendAction	closed externally after review	May 1, 2026, 02:47 UTC	records/openclaw-openclaw/closed/73448.md
openclaw/openclaw	#73483	fix(message): preserve asVoice on shared sends	closed externally after review	May 1, 2026, 02:47 UTC	records/openclaw-openclaw/closed/73483.md

Work Candidates Across Repos

Repository	Item	Title	Priority	Status	Reviewed	Report
openclaw/openclaw	#75284	fix(agents): trim trailing assistant turns during session file repair (#75271)	high	candidate	May 1, 2026, 03:08 UTC	records/openclaw-openclaw/items/75284.md
openclaw/openclaw	#73121	Zombie running tasks: CLI runtime tasks that terminate are never auto-transitioned to failed/timed_out	high	candidate	May 1, 2026, 03:08 UTC	records/openclaw-openclaw/items/73121.md
openclaw/openclaw	#73427	Control UI Realtime Talk: CSP blocks OpenAI WebRTC and UI hides realtime audio errors	high	candidate	May 1, 2026, 03:07 UTC	records/openclaw-openclaw/items/73427.md
openclaw/openclaw	#73478	[Bug]: openclaw gateway 没有输出图片信息	high	candidate	May 1, 2026, 03:07 UTC	records/openclaw-openclaw/items/73478.md
openclaw/openclaw	#75180	fix(reply): delivery-aware media tracking in block reply pipeline (#75156)	high	candidate	May 1, 2026, 03:02 UTC	records/openclaw-openclaw/items/75180.md
openclaw/openclaw	#73391	fix(cli): preserve parent options + await eager registration in lazy CLI runtime	high	candidate	May 1, 2026, 02:55 UTC	records/openclaw-openclaw/items/73391.md
openclaw/openclaw	#73839	fix: disable Pi auto-compaction when safeguard mode is active	high	candidate	May 1, 2026, 02:54 UTC	records/openclaw-openclaw/items/73839.md
openclaw/openclaw	#73624	Bug: subagent spawns drop task instructions when systemPromptOverride is set	high	candidate	May 1, 2026, 02:54 UTC	records/openclaw-openclaw/items/73624.md
openclaw/openclaw	#73855	ci: add workflow to detect hosted installer drift	high	candidate	May 1, 2026, 02:53 UTC	records/openclaw-openclaw/items/73855.md
openclaw/openclaw	#75375	boot-md startup hook blocks gateway event loop, causing apparent outage on every restart	high	candidate	May 1, 2026, 02:48 UTC	records/openclaw-openclaw/items/75375.md
openclaw/openclaw	#72370	Workspace hooks rejected as "cannot override openclaw-managed hook code" and replaced with empty managed versions (2026.4.23+)	high	candidate	May 1, 2026, 02:48 UTC	records/openclaw-openclaw/items/72370.md
openclaw/openclaw	#75339	fix(agents): normalize structured delta.content blocks to prevent [object Object] in chat replies	high	candidate	May 1, 2026, 02:48 UTC	records/openclaw-openclaw/items/75339.md
openclaw/openclaw	#70903	Persistent file-based provider cooldown blocks user for hours after billing recovery	high	candidate	May 1, 2026, 02:47 UTC	records/openclaw-openclaw/items/70903.md
openclaw/openclaw	#70928	[Bug]: message_sent / before_message_write hooks never fire for webchat and openclaw-tui outbound paths	high	candidate	May 1, 2026, 02:47 UTC	records/openclaw-openclaw/items/70928.md
openclaw/openclaw	#75374	service-env regenerator lists OPENCLAW_SERVICE_MANAGED_ENV_KEYS but does not export the actual values (gateway boots without auth token)	high	candidate	May 1, 2026, 02:47 UTC	records/openclaw-openclaw/items/75374.md

Recently Reviewed Across Repos

Repository	Item	Title	Outcome	Status	Reviewed
openclaw/openclaw	#73817	fix(media): allow private openai compatible audio transcription endpoints	keep_open / kept_open	complete	May 1, 2026, 03:12 UTC
openclaw/openclaw	#75381	Fix TUI exit after gateway disconnect	keep_open / kept_open	complete	May 1, 2026, 03:11 UTC
openclaw/openclaw	#75380	provider-payload.jsonl and cache-trace.jsonl grow unbounded — no rotation/max-size policy	keep_open / kept_open	complete	May 1, 2026, 03:10 UTC
openclaw/openclaw	#74873	feat(gateway): write drain manifest on shutdown for session recovery	keep_open / kept_open	complete	May 1, 2026, 03:10 UTC
openclaw/openclaw	#44695	feat(onboarding): complete zh-CN locale onboarding bundle + review fixes	keep_open / kept_open	complete	May 1, 2026, 03:09 UTC
openclaw/openclaw	#75284	fix(agents): trim trailing assistant turns during session file repair (#75271)	keep_open / kept_open	complete	May 1, 2026, 03:08 UTC
openclaw/openclaw	#75183	fix: simplify bundled runtime dependency repair	keep_open / kept_open	complete	May 1, 2026, 03:08 UTC
openclaw/openclaw	#71820	feat(bluebubbles): add reply-context API fallback for cache misses	keep_open / kept_open	complete	May 1, 2026, 03:08 UTC
openclaw/openclaw	#73210	Auto-TTS: add voice-only delivery mode + improve system prompt for natural speech output	keep_open / kept_open	complete	May 1, 2026, 03:08 UTC
openclaw/openclaw	#73303	v2026.4.26: gateway restart can hang ~3-4 min before new process starts	keep_open / kept_open	complete	May 1, 2026, 03:08 UTC

Repository Details

OpenClaw (openclaw/openclaw)

Current Run

Workflow status

Repository: openclaw/openclaw

Updated: May 1, 2026, 03:12 UTC

State: Review comments checked

Checked selected durable Codex review comments and synced missing or stale comments. Synced: 1. Item numbers: 73638. Run: https://github.com/openclaw/clawsweeper/actions/runs/25200240804

Queue

Metric	Count
Target repository	openclaw/openclaw
Open issues	3428
Open PRs	3340
Open items total	6768
Reviewed files	6714
Unreviewed open items	54
Archived closed files	15410

Review Outcomes

Metric	Count
Fresh reviewed issues in the last 7 days	3385
Proposed issue closes	1 (0% of reviewed issues)
Fresh reviewed PRs in the last 7 days	3282
Proposed PR closes	0 (0% of reviewed PRs)
Fresh verified reviews in the last 7 days	6667
Proposed closes awaiting apply	1 (0% of fresh reviews)
Work candidates awaiting promotion	2209
Closed by Codex apply	11394
Failed or stale reviews	11

Cadence

Metric	Coverage
Hourly cadence coverage	306/1456 current (1150 due, 21%)
Hourly hot item cadence (<7d)	306/1456 current (1150 due, 21%)
Daily cadence coverage	3417/3476 current (59 due, 98.3%)
Daily PR cadence	2390/2444 current (54 due, 97.8%)
Daily new issue cadence (<30d)	1027/1032 current (5 due, 99.5%)
Weekly older issue cadence	1751/1782 current (31 due, 98.3%)
Due now by cadence	1294

Audit Health

Repository: openclaw/openclaw

Last audit: May 1, 2026, 01:13 UTC

Status: Action needed

Targeted review input: 51947,61960,62112,73342

Metric	Count
Scan complete	yes
Open items seen	6780
Missing eligible open records	0
Missing maintainer-authored open records	33
Missing protected open records	21
Missing recently-created open records	1
Archived records that are open again	0
Stale item records	2
Duplicate records	0
Protected proposed closes	0
Stale reviews	4

Item	Category	Title	Detail
#51947	Stale review	proactive send from DM may route to wrong conversation when user has multiple conversations	records/openclaw-openclaw/items/51947.md
#61960	Stale review	docs: require i18n postprocess before skip	records/openclaw-openclaw/items/61960.md
#62112	Stale review	fix(agents): preserve Anthropic refusal handling	records/openclaw-openclaw/items/62112.md

Latest Run Activity

Latest review: May 1, 2026, 03:12 UTC. Latest close: May 1, 2026, 02:58 UTC. Latest comment sync: May 1, 2026, 03:12 UTC.

Window	Reviews	Close decisions	Keep-open decisions	Failed/stale reviews	Closed	Comments synced	Apply skips
Last 15 minutes	61	0	61	0	1	13	0
Last hour	353	7	346	0	25	260	0
Last 24 hours	6800	471	6329	11	639	3972	23

Recently Closed

Item	Title	Reason	Closed	Report
#75360	Fix Telegram reply cold-start latency	kept open	May 1, 2026, 02:58 UTC	records/openclaw-openclaw/closed/75360.md
#75367	fix(auto-reply): move visible reply warnings to doctor	closed externally after review	May 1, 2026, 02:52 UTC	records/openclaw-openclaw/closed/75367.md
#75361	test: strengthen published upgrade survivor lane	closed externally after review	May 1, 2026, 02:50 UTC	records/openclaw-openclaw/closed/75361.md
#75335	fix: keep async music delivery agent-mediated	closed externally after review	May 1, 2026, 02:48 UTC	records/openclaw-openclaw/closed/75335.md
#74234	[Bug]: Possibly incorrect gpg key fingerprint validation in Dockerfile	closed externally after review	May 1, 2026, 02:47 UTC	records/openclaw-openclaw/closed/74234.md
#74254	fix(docker): require single primary key before Docker apt GPG pin	closed externally after review	May 1, 2026, 02:47 UTC	records/openclaw-openclaw/closed/74254.md
#74597	Bug: update dev-channel switch can leave npm-global openclaw as source checkout symlink	closed externally after review	May 1, 2026, 02:47 UTC	records/openclaw-openclaw/closed/74597.md
#62557	openclaw update does not restart system-wide systemd services	closed externally after review	May 1, 2026, 02:47 UTC	records/openclaw-openclaw/closed/62557.md
#73448	Bug: message tool asVoice parameter defined in schema but never read in handleSendAction	closed externally after review	May 1, 2026, 02:47 UTC	records/openclaw-openclaw/closed/73448.md
#73483	fix(message): preserve asVoice on shared sends	closed externally after review	May 1, 2026, 02:47 UTC	records/openclaw-openclaw/closed/73483.md

Work Candidates

Item	Title	Priority	Status	Reviewed	Report
#75284	fix(agents): trim trailing assistant turns during session file repair (#75271)	high	candidate	May 1, 2026, 03:08 UTC	records/openclaw-openclaw/items/75284.md
#73121	Zombie running tasks: CLI runtime tasks that terminate are never auto-transitioned to failed/timed_out	high	candidate	May 1, 2026, 03:08 UTC	records/openclaw-openclaw/items/73121.md
#73427	Control UI Realtime Talk: CSP blocks OpenAI WebRTC and UI hides realtime audio errors	high	candidate	May 1, 2026, 03:07 UTC	records/openclaw-openclaw/items/73427.md
#73478	[Bug]: openclaw gateway 没有输出图片信息	high	candidate	May 1, 2026, 03:07 UTC	records/openclaw-openclaw/items/73478.md
#75180	fix(reply): delivery-aware media tracking in block reply pipeline (#75156)	high	candidate	May 1, 2026, 03:02 UTC	records/openclaw-openclaw/items/75180.md
#73391	fix(cli): preserve parent options + await eager registration in lazy CLI runtime	high	candidate	May 1, 2026, 02:55 UTC	records/openclaw-openclaw/items/73391.md
#73839	fix: disable Pi auto-compaction when safeguard mode is active	high	candidate	May 1, 2026, 02:54 UTC	records/openclaw-openclaw/items/73839.md
#73624	Bug: subagent spawns drop task instructions when systemPromptOverride is set	high	candidate	May 1, 2026, 02:54 UTC	records/openclaw-openclaw/items/73624.md
#73855	ci: add workflow to detect hosted installer drift	high	candidate	May 1, 2026, 02:53 UTC	records/openclaw-openclaw/items/73855.md
#75375	boot-md startup hook blocks gateway event loop, causing apparent outage on every restart	high	candidate	May 1, 2026, 02:48 UTC	records/openclaw-openclaw/items/75375.md

Recently Reviewed

Item	Title	Outcome	Status	Reviewed
#73817	fix(media): allow private openai compatible audio transcription endpoints	keep_open / kept_open	complete	May 1, 2026, 03:12 UTC
#75381	Fix TUI exit after gateway disconnect	keep_open / kept_open	complete	May 1, 2026, 03:11 UTC
#75380	provider-payload.jsonl and cache-trace.jsonl grow unbounded — no rotation/max-size policy	keep_open / kept_open	complete	May 1, 2026, 03:10 UTC
#74873	feat(gateway): write drain manifest on shutdown for session recovery	keep_open / kept_open	complete	May 1, 2026, 03:10 UTC
#44695	feat(onboarding): complete zh-CN locale onboarding bundle + review fixes	keep_open / kept_open	complete	May 1, 2026, 03:09 UTC
#75284	fix(agents): trim trailing assistant turns during session file repair (#75271)	keep_open / kept_open	complete	May 1, 2026, 03:08 UTC
#75183	fix: simplify bundled runtime dependency repair	keep_open / kept_open	complete	May 1, 2026, 03:08 UTC
#71820	feat(bluebubbles): add reply-context API fallback for cache misses	keep_open / kept_open	complete	May 1, 2026, 03:08 UTC
#73210	Auto-TTS: add voice-only delivery mode + improve system prompt for natural speech output	keep_open / kept_open	complete	May 1, 2026, 03:08 UTC
#73303	v2026.4.26: gateway restart can hang ~3-4 min before new process starts	keep_open / kept_open	complete	May 1, 2026, 03:08 UTC

ClawHub (openclaw/clawhub)

Current Run

Workflow status

Repository: openclaw/clawhub

Updated: Apr 29, 2026, 22:23 UTC

State: Review publish complete

Merged review artifacts for run 25135463730. Folder reconciliation moved tracked files to match current GitHub open/closed state, and the dashboard reflects completed shards. Run: https://github.com/openclaw/clawsweeper/actions/runs/25135463730

Queue

Metric	Count
Target repository	openclaw/clawhub
Open issues	230
Open PRs	17
Open items total	247
Reviewed files	924
Unreviewed open items	0
Archived closed files	26

Review Outcomes

Metric	Count
Fresh reviewed issues in the last 7 days	877
Proposed issue closes	0 (0% of reviewed issues)
Fresh reviewed PRs in the last 7 days	34
Proposed PR closes	0 (0% of reviewed PRs)
Fresh verified reviews in the last 7 days	911
Proposed closes awaiting apply	0 (0% of fresh reviews)
Work candidates awaiting promotion	45
Closed by Codex apply	8
Failed or stale reviews	13

Cadence

Metric	Coverage
Hourly cadence coverage	0/57 current (57 due, 0%)
Hourly hot item cadence (<7d)	0/57 current (57 due, 0%)
Daily cadence coverage	0/188 current (188 due, 0%)
Daily PR cadence	0/17 current (17 due, 0%)
Daily new issue cadence (<30d)	0/171 current (171 due, 0%)
Weekly older issue cadence	667/674 current (7 due, 99%)
Due now by cadence	252

Audit Health

Repository: openclaw/clawhub

Last audit: Apr 29, 2026, 18:44 UTC

Status: Passing

Targeted review input: 756

Metric	Count
Scan complete	yes
Open items seen	925
Missing eligible open records	0
Missing maintainer-authored open records	5
Missing protected open records	0
Missing recently-created open records	0
Archived records that are open again	0
Stale item records	0
Duplicate records	0
Protected proposed closes	0
Stale reviews	1

Item	Category	Title	Detail
None

Latest Run Activity

Latest review: Apr 29, 2026, 22:22 UTC. Latest close: Apr 29, 2026, 17:17 UTC. Latest comment sync: Apr 29, 2026, 22:15 UTC.

Window	Reviews	Close decisions	Keep-open decisions	Failed/stale reviews	Closed	Comments synced	Apply skips
Last 15 minutes	0	0	0	0	0	0	0
Last hour	0	0	0	0	0	0	0
Last 24 hours	0	0	0	0	0	0	0

Recently Closed

Item	Title	Reason	Closed	Report
#1434	Sonarbay-skill incorrectly flaged.	closed externally after review	Apr 29, 2026, 17:17 UTC	records/openclaw-clawhub/closed/1434.md
#1376	False positive: openclaw-workspace-sync flagged as suspicious	closed externally after review	Apr 29, 2026, 17:06 UTC	records/openclaw-clawhub/closed/1376.md
#1812	Skill be flagged as suspicious and being marked hidden	closed externally after review	Apr 29, 2026, 13:48 UTC	records/openclaw-clawhub/closed/1812.md
#1891	[codex] remove card link hover underlines	kept open	Apr 29, 2026, 08:25 UTC	records/openclaw-clawhub/closed/1891.md
#1889	fix: restore ClawHub public UI	closed externally after review	Apr 29, 2026, 07:52 UTC	records/openclaw-clawhub/closed/1889.md
#1881	chore(ci): update package publish artifact action	closed externally after review	Apr 29, 2026, 05:31 UTC	records/openclaw-clawhub/closed/1881.md
#1880	feat: add featured plugin curation	kept open	Apr 29, 2026, 05:13 UTC	records/openclaw-clawhub/closed/1880.md
#1871	[codex] Add skills/plugins search typeahead	closed externally after review	Apr 29, 2026, 04:24 UTC	records/openclaw-clawhub/closed/1871.md
#1878	feat: add ClawHub rescan guidance workflow	kept open	Apr 29, 2026, 03:02 UTC	records/openclaw-clawhub/closed/1878.md
#1875	fix: move stars link into settings	closed externally after review	Apr 29, 2026, 02:50 UTC	records/openclaw-clawhub/closed/1875.md

Work Candidates

Item	Title	Priority	Status	Reviewed	Report
#1226	clawhub package publish fails with "openclaw.plugin.json required" error	high	candidate	Apr 29, 2026, 22:11 UTC	records/openclaw-clawhub/items/1226.md
#1170	[Bug] [Blocking] ClawHub Cli publish bug	high	candidate	Apr 29, 2026, 22:09 UTC	records/openclaw-clawhub/items/1170.md
#1432	False 'suspicious' flag: registry metadata not extracting openclaw.requires.env from published files	high	candidate	Apr 29, 2026, 22:05 UTC	records/openclaw-clawhub/items/1432.md
#1756	Search results shift after initial render — high-relevance skills missing from top until scroll cycle	high	candidate	Apr 29, 2026, 22:04 UTC	records/openclaw-clawhub/items/1756.md
#1205	clawhub publish fails: Convex multiple paginated queries in syncSkillSearchDigestsForOwnerPublisherId (CLI v0.9.0)	high	candidate	Apr 29, 2026, 22:03 UTC	records/openclaw-clawhub/items/1205.md
#1197	publish fails: "multiple paginated queries" Convex error on first publish	high	candidate	Apr 29, 2026, 22:02 UTC	records/openclaw-clawhub/items/1197.md
#1176	publish/sync fails for all skills: "multiple paginated queries" Convex error	high	candidate	Apr 29, 2026, 22:02 UTC	records/openclaw-clawhub/items/1176.md
#1195	Publish fails: Convex paginated query error in syncSkillSearchDigestsForOwnerPublisherId	high	candidate	Apr 29, 2026, 22:02 UTC	records/openclaw-clawhub/items/1195.md
#937	[Bug] clawhub update --all always reports 'local changes (no match)' after v0.8.0 — persists immediately after force-update	high	candidate	Apr 29, 2026, 22:01 UTC	records/openclaw-clawhub/items/937.md
#1683	显示 @yangzhichao814-cell/ apexsearch的重复项	high	candidate	Apr 29, 2026, 21:42 UTC	records/openclaw-clawhub/items/1683.md

Recently Reviewed

Item	Title	Outcome	Status	Reviewed
#1525	shejian ClawHub Skill has been tagged as suspicious but everything looks fine in the scan results from VirusTotal Thanks	keep_open / kept_open	failed	Apr 29, 2026, 22:22 UTC
#1538	clawhub dashboard is unavailable	keep_open / kept_open	failed	Apr 29, 2026, 22:21 UTC
#1818	False positive: agenttrust-scanner flagged as suspicious	keep_open / kept_open	failed	Apr 29, 2026, 22:20 UTC
#1900	accidently delete my account， cant create new one use github	keep_open / kept_open	complete	Apr 29, 2026, 22:15 UTC
#1862	False positive: asr-hotwords flagged as suspicious	keep_open / kept_open	complete	Apr 29, 2026, 22:14 UTC
#1422	ai-capability-analyzer has been incorrectly flagged	keep_open / kept_open	complete	Apr 29, 2026, 22:14 UTC
#1707	Bug Summary: Missing Token in search and explore Commands	keep_open / kept_open	failed	Apr 29, 2026, 22:13 UTC
#1407	Skill page shows stale SKILL.md content after publishing new versions	keep_open / kept_open	complete	Apr 29, 2026, 22:13 UTC
#1446	False Positive: Skill [Memory Never Forget v2.2.2] incorrectly flagged as suspicious by OpenClaw Security Scan	keep_open / kept_open	failed	Apr 29, 2026, 22:13 UTC
#1503	False positive: axonflow/governance-policies flagged as suspicious — security policy templates	keep_open / kept_open	complete	Apr 29, 2026, 22:12 UTC

ClawSweeper (openclaw/clawsweeper)

Current Run

Workflow status

Repository: openclaw/clawsweeper

Updated: unknown

State: Idle

No workflow status has been published yet.

Queue

Metric	Count
Target repository	openclaw/clawsweeper
Open issues	0
Open PRs	0
Open items total	0
Reviewed files	5
Unreviewed open items	0
Archived closed files	0

Review Outcomes

Metric	Count
Fresh reviewed issues in the last 7 days	0
Proposed issue closes	0 (- of reviewed issues)
Fresh reviewed PRs in the last 7 days	5
Proposed PR closes	0 (0% of reviewed PRs)
Fresh verified reviews in the last 7 days	5
Proposed closes awaiting apply	0 (0% of fresh reviews)
Work candidates awaiting promotion	1
Closed by Codex apply	0
Failed or stale reviews	0

Cadence

Metric	Coverage
Hourly cadence coverage	0/5 current (5 due, 0%)
Hourly hot item cadence (<7d)	0/5 current (5 due, 0%)
Daily cadence coverage	0/0 current (0 due, -)
Daily PR cadence	0/0 current (0 due, -)
Daily new issue cadence (<30d)	0/0 current (0 due, -)
Weekly older issue cadence	0/0 current (0 due, -)
Due now by cadence	5

Audit Health

No audit has been published yet. Run npm run audit -- --update-dashboard to refresh this section.

Latest Run Activity

Latest review: May 1, 2026, 02:03 UTC. Latest close: unknown. Latest comment sync: May 1, 2026, 02:03 UTC.

Window	Reviews	Close decisions	Keep-open decisions	Failed/stale reviews	Closed	Comments synced	Apply skips
Last 15 minutes	0	0	0	0	0	0	0
Last hour	0	0	0	0	0	0	0
Last 24 hours	2	0	2	0	0	2	0

Recently Closed

Item	Title	Reason	Closed	Report
None

Work Candidates

Item	Title	Priority	Status	Reviewed	Report
#19	test: exercise automerge repair smoke	high	candidate	Apr 29, 2026, 13:41 UTC	records/openclaw-clawsweeper/items/19.md

Recently Reviewed

Item	Title	Outcome	Status	Reviewed
#24	fix: repair automerge merge conflicts after merge race	keep_open / kept_open	complete	May 1, 2026, 02:03 UTC
#23	fix: repair dirty automerge prs	keep_open / kept_open	complete	May 1, 2026, 01:29 UTC
#20	test: suppress duplicate remaining-risk prose	keep_open / kept_open	complete	Apr 29, 2026, 14:08 UTC
#19	test: exercise automerge repair smoke	keep_open / kept_open	complete	Apr 29, 2026, 13:41 UTC
#18	docs: document clawsweeper self smoke target	keep_open / kept_open	complete	Apr 29, 2026, 13:18 UTC

How It Works

ClawSweeper is split into two operational systems:

• issue/PR sweeper: scheduler, review lane, apply lane, audit, reconcile, and dashboard publishing
• commit sweeper: main-branch commit dispatch, cheap code/non-code classification, one Codex review worker per code-bearing commit, report publishing, and optional target commit checks

Scheduler

The issue/PR scheduler decides what to scan and how often. New and active items get more attention; older quiet items fall back to a slower cadence.

• hot/new and recently active items are checked hourly, with a 5-minute intake schedule for the newest queue edge
• target repositories can forward issue and PR events with repository_dispatch; those exact item runs use a dedicated single job to review one item, sync the durable comment, and apply only safe close proposals for that same item
• pull requests and issues younger than 30 days are checked daily once they leave the hot window
• older inactive issues are checked weekly
• apply wakes every 15 minutes and exits quickly when there are no unchanged high-confidence close proposals

Review Lane

Review is proposal-only. It never closes items.

• A planner scans open issues and PRs, then assigns exact item numbers to shards.
• Manual runs can pass item_number or comma-separated item_numbers to review exact Audit Health findings without scanning for a normal batch.
• Each shard checks out the selected target repository at main.
• Codex reviews with gpt-5.5, high reasoning, fast service tier, and a 10-minute per-item timeout.
• Each item becomes a flat report under records/<repo-slug>/items/<number>.md with the decision, evidence, Codex /review-style PR findings, suggested comment, runtime metadata, and GitHub snapshot hash.
• High-confidence allowed close decisions become proposed_close.
• After publish, the lane checks the selected items' single marker-backed Codex review comment. Missing comments and missing metadata are synced immediately; existing comments are refreshed only when stale, currently weekly.
• PR review comments keep the top-level note concise, put source links and full evidence in collapsed details, and use hidden verdict/action markers for the trusted ClawSweeper repair loop; see docs/pr-review-comments.md.

Apply Lane

Apply reads existing reports and mutates GitHub only when the stored review is still valid.

• Updates the single marker-backed Codex automated review comment in place.
• Closes only unchanged high-confidence proposals.
• Reuses the review comment when closing; no duplicate close comment.
• Moves closed or already-closed reports to records/<repo-slug>/closed/<number>.md.
• Moves reopened archived reports back to the repo’s items/ folder as stale.
• Commits checkpoints and dashboard heartbeats during long runs.

Apply wakes every 15 minutes, no-ops when there are no unchanged high-confidence close proposals, and narrows scheduled runs to the currently eligible proposal list so idle runs do not scan unrelated keep-open records. It defaults to all item kinds, no age floor, a 2-second close delay, and 50 fresh closes per checkpoint. If it reaches the requested limit, it queues another apply run with the same settings.

Exact event runs skip the bulk planner, shard matrix, artifact upload, and separate publish job. They still use the same review and apply code paths, but only for the selected item number and only with immediate-safe reasons enabled by default: implemented_on_main and duplicate_or_superseded. stale_insufficient_info is never applied to young items; apply requires those issue reports to be at least 30 days old unless a manual run explicitly changes the threshold.

The README dashboard is fleet-scoped. Each configured repository gets its own record folder, workflow status marker, audit-health marker, cadence counts, and recent activity section. The top dashboard aggregates those repository snapshots so event runs from one repo do not hide the state of another.

There is still one deterministic apply path for writes. Review can propose and sync stale public review comments, but closing remains guarded by apply so a fresh GitHub snapshot, labels, maintainer-authorship, and unchanged item state are checked immediately before mutation.

Commit Review Lane

Commit review is intentionally separate from issue/PR cleanup. It never closes items, writes comments, or fixes code.

• Target repositories forward push events from main with repository_dispatch.
• Manual runs can pass commit_sha, optional before_sha, optional additional_prompt, enabled, and create_checks.
• The receiver verifies the selected commits are reachable from origin/main.
• Before selecting and reviewing commits, the receiver waits 15 minutes by default (CLAWSWEEPER_COMMIT_REVIEW_SETTLE_SECONDS=900) so a push range has time to settle across GitHub and the runner.
• The plan job expands ranges, pages large backfills at GitHub's matrix limit, and classifies each commit before Codex starts.
• Pure documentation, changelog, README/license, and asset-only commits get a skipped report without spending Codex time.
• Mixed commits and code-bearing commits start one Codex worker per commit. The worker checks out current target main and reviews the selected commit by SHA/range instead of detaching the whole repository at that commit.
• Codex is prompted to read beyond the diff: changed files, callers/callees, runtime entry points, adjacent tests/docs, dependency manifests, release notes, advisories, web sources, and focused live tests when useful.
• Each commit writes exactly one report at records/<repo-slug>/commits/<40-char-sha>.md.
• Reruns overwrite the same report, including reruns with an additional_prompt.
• Report results are nothing_found, findings, inconclusive, failed, or skipped_non_code.
• Optional GitHub Checks use the ClawSweeper Commit Review name on the target commit. Clean or skipped reports are green; high-confidence high/critical findings fail; lower-severity, inconclusive, and failed reviews are neutral.
• Finding reports are dispatched to the repair intake when CLAWSWEEPER_COMMIT_FINDINGS_ENABLED is not false. ClawSweeper owns the audit log and any repair PR.

Use pnpm commit-reports -- --since 24h to review recent reports and add --findings, --non-clean, --repo, or --author to narrow the list. The storage stays flat so a rerun can overwrite exactly one file for a commit without rediscovering a date bucket.

Safety Model

• Maintainer-authored items are excluded from automated closes.
• Protected labels block close proposals.
• Open PRs with GitHub closing references block issue closes until the PR is resolved.
• Open same-author issue/PR pairs block one-sided closes.
• Codex runs without GitHub write tokens.
• Issue/PR event jobs create target write and report-push credentials only after Codex exits.
• Commit review workers give Codex only a read-scoped target token as GH_TOKEN so it can inspect mentioned issues, PRs, workflow runs, and commit metadata.
• Commit write/check credentials are created only after Codex exits.
• CI makes the target checkout read-only for reviews.
• Reviews fail if Codex leaves tracked or untracked changes behind.
• Snapshot changes block apply unless the only change is the bot’s own review comment.
• Commit Check Runs are optional and disabled by default.

Audit

pnpm run audit compares live GitHub state with generated records without moving files. It reports missing open records, archived open records, stale records, duplicates, protected-label proposed closes, and stale review-status records. Protected proposed closes are reported only for active repo items/ records because archived repo closed/ records are historical and cannot be applied. Missing open records are classified as eligible, maintainer-authored, protected, or recently created so strict audit mode can flag actionable drift without treating expected queue lag or excluded items as failures. Use --update-dashboard to publish the latest audit health into this README without making every normal dashboard heartbeat scan all open GitHub items. Audit Health includes a copyable item_numbers input for reviewable findings such as missing eligible records, reopened archived records, and stale reviews. The workflow refreshes Audit Health on a separate six-hour schedule, and it can be run manually with audit_dashboard=true.

Local Run

Requires Node 24.

Issue/PR sweeper:

source ~/.profile
corepack enable
pnpm install
pnpm run build
pnpm run plan -- --target-repo openclaw/openclaw --batch-size 5 --shard-count 100 --max-pages 250 --codex-model gpt-5.5 --codex-reasoning-effort high --codex-service-tier fast
pnpm run review -- --target-repo openclaw/openclaw --target-dir ../openclaw --batch-size 5 --max-pages 250 --artifact-dir artifacts/reviews --codex-model gpt-5.5 --codex-reasoning-effort high --codex-service-tier fast --codex-timeout-ms 600000
pnpm run apply-artifacts -- --target-repo openclaw/openclaw --artifact-dir artifacts/reviews
pnpm run audit -- --target-repo openclaw/openclaw --max-pages 250 --sample-limit 25 --update-dashboard
pnpm run reconcile -- --target-repo openclaw/openclaw --dry-run

Apply unchanged proposals later:

source ~/.profile
corepack enable
pnpm run apply-decisions -- --target-repo openclaw/openclaw --limit 20 --apply-kind all

Sync durable review comments without closing:

source ~/.profile
corepack enable
pnpm run apply-decisions -- --target-repo openclaw/openclaw --sync-comments-only --comment-sync-min-age-days 7 --processed-limit 1000 --limit 0

List commit reports:

source ~/.profile
corepack enable
pnpm run build
pnpm commit-reports -- --since 24h
pnpm commit-reports -- --since 24h --findings
pnpm commit-reports -- --repo openclaw/openclaw --author steipete --since 7d

Manually rerun commit review through GitHub Actions:

gh workflow run commit-review.yml \
  --repo openclaw/clawsweeper \
  --ref main \
  -f target_repo=openclaw/openclaw \
  -f commit_sha=<commit-sha> \
  -f before_sha=<parent-or-range-start-sha> \
  -f create_checks=false \
  -f enabled=true \
  -f additional_prompt='Optional extra review focus.'

Omit before_sha for a single-commit review. Pass before_sha to review the historic range before_sha..commit_sha.

Manual review runs are proposal-only. Use apply_existing=true to apply unchanged proposals later. Scheduled apply runs process both issues and pull requests by default, subject to the selected repository profile; pass target_repo, apply_kind=issue, or apply_kind=pull_request to narrow a manual run.

Scheduled runs cover the configured product profiles. openclaw/openclaw keeps the existing cadence; openclaw/clawhub runs on offset review/apply/audit crons so its reports live under records/openclaw-clawhub/ without colliding with default repo records. openclaw/clawsweeper is available for manual and event self-review smoke tests. Broad hot-intake sweeps cap scheduled fan-out at 50 one-item shards per run; exact event reviews still use one shard, and normal review backfills can fan out to 100 shards when explicitly configured.

Target repositories can opt into event-level latency by installing the dispatcher workflow in docs/target-dispatcher.md. The dispatcher sends repository_dispatch events to this repository with the target repo and exact item number; ClawSweeper then runs one event job that reviews, comments, and checks immediate safe apply instead of waiting for the next hot-intake cron or bulk publish lane.

Target repositories can opt into main-branch commit review with docs/commit-dispatcher.md. That dispatcher sends push ranges to this repository, where ClawSweeper expands the range and writes one commit report per SHA.

Checks

pnpm run check
pnpm run oxformat

oxformat is an alias for oxfmt; there is no separate oxformat pnpm package. The CI GitHub Actions workflow uses the latest Node release and runs pnpm run check on pushes, pull requests, and manual dispatches. The check gate includes the full test suite, a strict changed-surface coverage threshold, and a full compiled-repo coverage ratchet.

GitHub Actions Setup

Required secrets:

• OPENAI_API_KEY: OpenAI API key used to log Codex in before review shards run.
• CLAWSWEEPER_APP_CLIENT_ID: public GitHub App client ID for clawsweeper. Currently Iv23liOECG0slfuhz093.
• CLAWSWEEPER_APP_PRIVATE_KEY: private key for clawsweeper; plan/review jobs use a short-lived GitHub App installation token for read-heavy target API calls, commit review uses a read-scoped target token while Codex runs, and apply/comment-sync/check jobs use the app token for comments, closes, and optional checks. Keep App credentials scoped to the actions/create-github-app-token step. Review shards run Codex over attacker-controlled issue/PR text, so codexEnv() also strips these App variables before spawning Codex.

Token flow:

• Review shards log Codex in with OPENAI_API_KEY, then run without OpenAI or Codex token environment variables.
• ClawSweeper uses the clawsweeper GitHub App token for read-heavy target context.
• Apply mode uses the same app token for review comments and closes, so GitHub attributes mutations to the app bot account instead of a PAT user.
• Commit review passes Codex only a read-scoped target token as GH_TOKEN for issue/PR/workflow/commit hydration, then creates write/check credentials only after Codex exits.
• The built-in GITHUB_TOKEN commits generated reports back to this repo.

Required clawsweeper app permissions:

• Contents: read/write, for report commits, repair branches, and repository dispatch inputs that need a contents-scoped installation token.
• Issues: read/write, for issue comments, labels, closes, and maintainer command authorization context.
• Pull requests: read/write, for PR comments, labels, merge readiness, repair PRs, and guarded automerge.
• Actions: read/write on openclaw/clawsweeper, for run cancellation, manual dispatch, self-heal, and commit-review continuations.
• Checks: write on target repositories when commit Check Runs should be published.

ClawSweeper no longer falls back to PAT-based write tokens. If the GitHub App installation does not grant the requested permission set, the workflow fails at token creation instead of silently switching identity.

Target repository setup:

• install the issue/PR dispatcher from docs/target-dispatcher.md for exact item event reviews
• install the commit dispatcher from docs/commit-dispatcher.md for main commit reviews
• set CLAWSWEEPER_COMMIT_REVIEW_ENABLED=false to disable commit dispatch without code changes
• set CLAWSWEEPER_COMMIT_REVIEW_CREATE_CHECKS=true only if commit Check Runs should be published
• optionally set CLAWSWEEPER_COMMIT_REVIEW_SETTLE_SECONDS=0 for manual backfills where the target commit range is already settled; the default is 900