Add clusters report command

[RomneyDa]

Summary

• add gitcrawl clusters-report to render top clusters as a Markdown report
• include JSON output for the hydrated report payload
• document the command and add CLI coverage

Proof/Example:
./gitcrawl clusters-report openclaw/openclaw --limit 3 --min-size 5

->

# Cluster Report: openclaw/openclaw

Generated: 2026-05-25T21:28:35Z UTC
View: top 3 clusters, min size 5, sorted by size

**Totals:** 3 clusters, 119 listed members, 3 open, 0 closed.

## At a Glance

| Rank | Cluster | Members | Status | Representative | Updated |
| ---: | --- | ---: | --- | --- | --- |
| 1 | `search-output-border-f43e` | 40 | active | PR #76920 | 2026-05-25 |
| 2 | `driver-prime-sketch-zjw7` | 40 | active | PR #78342 | 2026-05-25 |
| 3 | `result-maple-margin-1r1o` | 39 | active | PR #81700 | 2026-05-25 |

## 1. fix(telegram): preserve forum topic routing

- Cluster: `search-output-border-f43e` (`1`)
- Status: active
- Members: 40 total, 8 shown
- Representative: PR #76920
- Last updated: 2026-05-25

| Type | Number | State | Score | Title | Labels |
| --- | ---: | --- | ---: | --- | --- |
| PR | [#76920](https://github.com/openclaw/openclaw/pull/76920) | open | 1.000 | fix(telegram): preserve forum topic routing | channel: matrix, channel: telegram, gateway, scripts, size: L, proof: supplied, mantis: telegram-visible-proof |
| PR | [#43808](https://github.com/openclaw/openclaw/pull/43808) | open | 0.940 | cron: honor delivery.threadId for Telegram announce delivery | app: web-ui, gateway, size: M |
| PR | [#49704](https://github.com/openclaw/openclaw/pull/49704) | open | 0.940 | fix(cron): announce delivery for Telegram forum topics | docs, channel: telegram, size: S |
| Issue | [#52286](https://github.com/openclaw/openclaw/issues/52286) | open | 0.940 | [Bug] message tool sends files to DM instead of staying in Telegram topic | bug, bug:behavior |
| PR | [#52824](https://github.com/openclaw/openclaw/pull/52824) | open | 0.940 | fix(announce): preserve threadId in subagent announce for Telegram DM topics | channel: telegram, agents, size: S |
| Issue | [#73900](https://github.com/openclaw/openclaw/issues/73900) | open | 0.940 | [Bug]: main/systemEvent cron heartbeat inherits global heartbeat.to and leaks topic reminder to DM |  |
| PR | [#73583](https://github.com/openclaw/openclaw/pull/73583) | open | 0.834 | Fix Telegram status and group reply delivery | channel: telegram, size: L |
| PR | [#85403](https://github.com/openclaw/openclaw/pull/85403) | open | 0.834 | fix(telegram): suppress message-tool reply previews | channel: telegram, size: L, proof: supplied, proof: sufficient, mantis: telegram-visible-proof, P1, rating: 🐚 platinum hermit, merge-risk: 🚨 compatibility, status: 👀 ready for maintainer look, proof: 📸 screenshot |

Key snippets:

- [#76920](https://github.com/openclaw/openclaw/pull/76920): ## Summary - Keep Telegram thread-not-found fallback for General topic (`message_thread_id=1`), while failing closed for explicit non-General forum topic sends and direct/private topic sends. - Preserve Telegram topic routing for automatic
- [#43808](https://github.com/openclaw/openclaw/pull/43808): ## Summary - Problem: isolated cron announce delivery accepted `delivery.threadId` in job config, but the cron delivery plan/target plumbing never carried that field into outbound delivery. - Why it matters: Telegram forum-topic cron jobs
- [#49704](https://github.com/openclaw/openclaw/pull/49704): ## Problem Cron jobs with `delivery.mode = "announce"` silently fail to deliver to Telegram forum topics. The `deliveryStatus` shows `"not-delivered"` with no surfaced error, even with valid targets like `telegram:-GROUP/TOPIC` or `telegram

## 2. fix: scope agent admin gateway calls

- Cluster: `driver-prime-sketch-zjw7` (`2`)
- Status: active
- Members: 40 total, 8 shown
- Representative: PR #78342
- Last updated: 2026-05-25

| Type | Number | State | Score | Title | Labels |
| --- | ---: | --- | ---: | --- | --- |
| PR | [#78342](https://github.com/openclaw/openclaw/pull/78342) | open | 1.000 | fix: scope agent admin gateway calls | docs, gateway, commands, size: S, triage: refactor-only, triage: blank-template, triage: needs-real-behavior-proof |
| PR | [#80125](https://github.com/openclaw/openclaw/pull/80125) | open | 0.959 | Fix/core bug audit | size: S, triage: refactor-only, triage: blank-template, triage: needs-real-behavior-proof |
| PR | [#85467](https://github.com/openclaw/openclaw/pull/85467) | open | 0.946 | fix(embedded-runner): wrap agent.processEvents in session write lock | agents, size: XS, triage: refactor-only, triage: blank-template, triage: needs-real-behavior-proof, P1, rating: 🧂 unranked krab, merge-risk: 🚨 session-state, merge-risk: 🚨 availability, status: 📣 needs proof |
| PR | [#80997](https://github.com/openclaw/openclaw/pull/80997) | open | 0.943 | Chore/gog autoheal workflow docs | scripts, size: S, triage: refactor-only, triage: blank-template, triage: needs-real-behavior-proof |
| PR | [#83940](https://github.com/openclaw/openclaw/pull/83940) | open | 0.943 | Feat/cron consecutive skips tracking | docs, cli, agents, size: M, triage: refactor-only, triage: blank-template, triage: needs-real-behavior-proof, dependencies-changed, rating: 🌊 off-meta tidepool |
| PR | [#84962](https://github.com/openclaw/openclaw/pull/84962) | open | 0.940 | Railway/fix control UI origin | docs, docker, size: XS, triage: refactor-only, triage: blank-template, triage: needs-real-behavior-proof, P2, rating: 🧂 unranked krab, merge-risk: 🚨 automation, merge-risk: 🚨 compatibility, merge-risk: 🚨 security-boundary, status: 📣 needs proof |
| PR | [#83689](https://github.com/openclaw/openclaw/pull/83689) | open | 0.939 | fix(pi-embedded-runner): handle concatenated tool-call argument JSON | agents, size: S, triage: refactor-only, triage: blank-template, triage: needs-real-behavior-proof, P2, rating: 🧂 unranked krab, merge-risk: 🚨 compatibility, status: 📣 needs proof |
| PR | [#72449](https://github.com/openclaw/openclaw/pull/72449) | open | 0.936 | Fix/cron parse undefined | cli, size: S, triage: refactor-only, triage: blank-template, triage: needs-real-behavior-proof, P2, rating: 🧂 unranked krab, merge-risk: 🚨 compatibility, merge-risk: 🚨 availability, status: 📣 needs proof |

Key snippets:

- [#78342](https://github.com/openclaw/openclaw/pull/78342): ## Summary Describe the problem and fix in 2–5 bullets: 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 labele
- [#80125](https://github.com/openclaw/openclaw/pull/80125): ## Summary Describe the problem and fix in 2–5 bullets: 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 labele
- [#85467](https://github.com/openclaw/openclaw/pull/85467): installSessionEventWriteLock previously targeted session._processAgentEvent, which was removed in pi-coding-agent v0.75.4. Events now flow through Agent.processEvents (pi-agent-core) -> _handleAgentEvent listener -> appendMessage -> appendF

## 3. fix(auth): drop stale Codex OAuth routing

- Cluster: `result-maple-margin-1r1o` (`3`)
- Status: active
- Members: 39 total, 8 shown
- Representative: PR #81700
- Last updated: 2026-05-25

| Type | Number | State | Score | Title | Labels |
| --- | ---: | --- | ---: | --- | --- |
| PR | [#81700](https://github.com/openclaw/openclaw/pull/81700) | open | 1.000 | fix(auth): drop stale Codex OAuth routing | commands, agents, maintainer, size: L, extensions: codex, P2, impact:session-state, impact:auth-provider, rating: 🧂 unranked krab, merge-risk: 🚨 compatibility, merge-risk: 🚨 auth-provider, merge-risk: 🚨 session-state |
| Issue | [#83223](https://github.com/openclaw/openclaw/issues/83223) | open | 0.940 | v2026.5.16-beta.5 audit: migrated openai/gpt-5.5 route still looks up openai-codex auth before fallback | P2, clawsweeper:no-new-fix-pr, clawsweeper:needs-maintainer-review, clawsweeper:needs-product-decision, clawsweeper:needs-live-repro, impact:session-state, impact:auth-provider |
| PR | [#83451](https://github.com/openclaw/openclaw/pull/83451) | open | 0.940 | fix(auth): preserve Codex sidecar Keychain recovery | commands, agents, maintainer, size: M, P2, impact:security, impact:auth-provider, rating: 🧂 unranked krab, merge-risk: 🚨 compatibility, merge-risk: 🚨 auth-provider, merge-risk: 🚨 security-boundary |
| PR | [#75030](https://github.com/openclaw/openclaw/pull/75030) | open | 0.832 | fix(auth): explain masked oauth profiles | agents, size: S, proof: supplied, proof: sufficient, P2, rating: 🐚 platinum hermit, merge-risk: 🚨 compatibility, merge-risk: 🚨 auth-provider, status: 👀 ready for maintainer look |
| PR | [#83383](https://github.com/openclaw/openclaw/pull/83383) | open | 0.829 | fix(auth): clean refresh contention diagnostics | agents, maintainer, size: M, P2, rating: 🐚 platinum hermit, status: 👀 ready for maintainer look |
| PR | [#85413](https://github.com/openclaw/openclaw/pull/85413) | open | 0.823 | Fix OpenAI compaction runtime routing | gateway, agents, size: L, extensions: codex, triage: mock-only-proof, P2, rating: 🧂 unranked krab, merge-risk: 🚨 auth-provider, status: 📣 needs proof |
| PR | [#86476](https://github.com/openclaw/openclaw/pull/86476) | open | 0.804 | Keep Codex turn timeouts inside Codex | agents, maintainer, size: S, extensions: codex, P1, rating: 🦪 silver shellfish, merge-risk: 🚨 compatibility, merge-risk: 🚨 auth-provider, merge-risk: 🚨 availability, status: 📣 needs proof |
| Issue | [#8673](https://github.com/openclaw/openclaw/issues/8673) | open |  | Add retry logic to OAuth token refresh | enhancement, P2, clawsweeper:no-new-fix-pr, clawsweeper:needs-maintainer-review, clawsweeper:needs-product-decision, clawsweeper:source-repro, impact:auth-provider, issue-rating: 🦞 diamond lobster |

Key snippets:

- [#81700](https://github.com/openclaw/openclaw/pull/81700): ## Summary - expand Codex OAuth refresh-failure classification to match current refresh-token reuse, expiry, invalidation, revocation, and account-mismatch messages - keep stale persisted/session-selected Codex auth profiles and stale `aut
- [#83223](https://github.com/openclaw/openclaw/issues/83223): ## Scope One macOS LaunchAgent-backed OpenClaw instance was updated from `2026.5.12` to the latest beta available from upstream tags at audit time: `v2026.5.16-beta.5`. This report is sanitized. The host is referred to as Host S. Private
- [#83451](https://github.com/openclaw/openclaw/pull/83451): ## Summary - preserve the read-only macOS Keychain fallback for legacy Codex `oauthRef` sidecar decryption - keep `openclaw doctor --fix` able to migrate Keychain-only legacy sidecars back to inline OAuth credentials - keep the re-auth pat

Tests

• go test ./...

[clawsweeper]

Codex review: needs maintainer review before merge. Reviewed May 25, 2026, 5:54 PM ET / 21:54 UTC.

Summary
Adds a gitcrawl clusters-report CLI command that renders Markdown or JSON cluster reports, documents it, and adds CLI coverage.

Reproducibility: not applicable. this is a feature PR rather than a bug report. The review path is source inspection plus the PR body's terminal proof for the new command.

Review metrics: 2 noteworthy metrics.

• Command surface: 1 CLI command added. A new public command is the main maintainer-visible API change.
• Changed files: 4 files affected. The diff stays limited to CLI code, CLI tests, and public docs.

Merge readiness
Overall: 🐚 platinum hermit
Proof: 🦞 diamond lobster
Patch quality: 🐚 platinum hermit
Result: ready for maintainer review.

Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch.

Rank-up moves:

• none

Next step before merge
No repair lane is needed because review found no actionable patch defect; this MEMBER-authored PR should stay in normal maintainer review.

Security
Cleared: The diff adds local CLI reporting, docs, and tests without changing dependency sources, CI, secrets, auth, or network execution paths.

Review details

Best possible solution:

Land the bounded CLI reporting command after normal maintainer review and CI, preserving the existing display-cluster and source-qualified detail behavior.

Do we have a high-confidence way to reproduce the issue?

Not applicable; this is a feature PR rather than a bug report. The review path is source inspection plus the PR body's terminal proof for the new command.

Is this the best way to solve the issue?

Yes; the implementation reuses the existing display cluster summary/detail APIs and includes coverage for Markdown output, JSON output, and run/durable source collisions.

AGENTS.md: not found in the target repository.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 5046dd0f1d6a.

Label changes

Label changes:

• add rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🦞 diamond lobster and patch quality is 🐚 platinum hermit.
• add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (terminal): The PR body includes after-fix terminal output from ./gitcrawl clusters-report openclaw/openclaw --limit 3 --min-size 5 showing the new Markdown report on real cluster data.
• remove status: ⏳ waiting on author: Current PR status label is status: 👀 ready for maintainer look.
• remove rating: 🦐 gold shrimp: Current PR rating is rating: 🐚 platinum hermit, so this older rating label is no longer current.

Label justifications:

• P2: This is a normal-priority CLI feature with useful maintainer workflow value and limited blast radius.
• rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🦞 diamond lobster and patch quality is 🐚 platinum hermit.
• status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (terminal): The PR body includes after-fix terminal output from ./gitcrawl clusters-report openclaw/openclaw --limit 3 --min-size 5 showing the new Markdown report on real cluster data.
• proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes after-fix terminal output from ./gitcrawl clusters-report openclaw/openclaw --limit 3 --min-size 5 showing the new Markdown report on real cluster data.

Evidence reviewed

What I checked:

• Current main lacks the command: A current-main search for clusters-report, clusters report, and Cluster Report across README, SPEC, CLI, and store code returned no matches, so the requested command is not already implemented on main. (5046dd0f1d6a)
• PR adds the command implementation: The PR head wires clusters-report into command dispatch and adds runClustersReport, which reads display cluster summaries and source-qualified details before writing Markdown or JSON output. (internal/cli/app.go:177, 22e0ea1656ed)
• Report rendering uses existing cluster surfaces: The new implementation calls ListDisplayClusterSummaries and passes each summary's Source into ClusterDetail, matching the existing run/durable display model instead of inventing a parallel cluster path. (internal/cli/app.go:1423, 22e0ea1656ed)
• Tests cover output and source disambiguation: The PR adds CLI coverage for Markdown and JSON report output plus a regression test that colliding run/durable cluster IDs use the correct detail source. (internal/cli/app_test.go:1957, 22e0ea1656ed)
• Patch hygiene check: git diff --check reported no whitespace or conflict-marker issues for the PR diff. (22e0ea1656ed)
• Maintainer routing context: The GitHub context reports author association MEMBER, so the conservative cleanup rule keeps this PR open for explicit maintainer handling.

Likely related people:

• Peter Steinberger: Recent history and blame on the CLI and cluster store paths show repeated maintenance of internal/cli/app.go and cluster detail/source behavior. (role: recent area contributor; confidence: high; commits: 30d6676ad741, 51e8294e67f9, 36f6ede; files: internal/cli/app.go, internal/store/clusters.go)
• Vincent Koc: Git history shows substantial earlier work on cluster summaries, ghcrawl-style cluster views, and cluster/TUI parity used by this report command. (role: cluster feature contributor; confidence: high; commits: 7c3b1da, f42b6166d548, a418ffaca655; files: internal/store/clusters.go, internal/cli/tui.go, internal/cli/app.go)
• Dallin Romney: Beyond this PR, current history includes prior CLI work in internal/cli/app.go, making the author a relevant adjacent contributor rather than only the proposer. (role: adjacent CLI contributor; confidence: medium; commits: 940f940; files: internal/cli/app.go)

What the crustacean ranks mean

• 🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
• 🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
• 🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
• 🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
• 🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
• 🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
• 🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

How this review workflow works

• ClawSweeper keeps one durable marker-backed review comment per issue or PR.
• Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
• A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
• PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
• Maintainers can also comment @clawsweeper review to request a fresh review only.
• Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
• Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
• Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

[clawsweeper]

ClawSweeper PR egg

✨ Hatched: 🥚 common Frosted Merge Sprite

Hatch command

Comment @clawsweeper hatch when this PR is hatchable.

Hatchability rules:

• Merged PRs are hatchable.
• Open PRs are hatchable when they are status: 👀 ready for maintainer look, status: 🚀 automerge armed, or labeled clawsweeper:automerge.
• Closed unmerged PRs are hatchable only when one of those hatchable labels is still present in the durable record.

Rarity: 🥚 common.
Trait: stacks clean commits.
Image traits: location proof lagoon; accessory green check lantern; palette amber, ink, and glacier blue; mood curious; pose curling around a status light; shell soft velvet shell; lighting subtle sparkle highlights; background quiet workflow signs.
Share on X: post this hatch
Copy: My PR egg hatched a 🥚 common Frosted Merge Sprite in ClawSweeper.

What is this egg doing here?

• Eggs appear after the PR passes real-behavior proof. It is here for vibes, not verdicts: it does not change labels, ratings, merge decisions, or automation.
• The shell reacts to review momentum: open follow-up work warms it up, re-review makes it wobble, and a clean final review lets it hatch.
• Hatchability usually comes from sufficient real-behavior proof, no blocking P0/P1/P2 findings, no security attention needed, and clean correctness. A merged PR is already final, so merge makes the egg hatchable independently.
• The hatch is seeded from this repository and PR number, so the same PR keeps the same creature; the reviewed head SHA can only change safe visual details.
• Rarity is just collectible sparkle: 🥚 common, 🌱 uncommon, 💎 rare, ✨ glimmer, and 🌈 legendary.

[RomneyDa]

@clawsweeper re-review

[clawsweeper]

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

Re-review progress:

• State: Superseded
• Detail: A newer re-review for this item started before this run finished, so GitHub cancelled this older run. Check the latest ClawSweeper run for the current result.
• Run: https://github.com/openclaw/clawsweeper/actions/runs/26421033981
• Updated: 2026-05-25T21:48:57.969Z

[RomneyDa]

@clawsweeper re-review

[clawsweeper]

🦞👀
ClawSweeper picked this up.

Command router queued. I will update this comment with the next step.

Re-review progress:

• State: Complete
• Detail: The targeted re-review finished, the durable review comment was updated, and the synced verdict was routed.
• Run: https://github.com/openclaw/clawsweeper/actions/runs/26420516857
• Updated: 2026-05-25T21:37:58.147Z

[RomneyDa]

@clawsweeper re-review

[clawsweeper]

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

Re-review progress:

• State: Complete
• Detail: The targeted re-review finished, the durable review comment was updated, and the synced verdict was routed.
• Run: https://github.com/openclaw/clawsweeper/actions/runs/26421404172
• Updated: 2026-05-25T22:05:57.520Z