Skip to content

Separate human-only PR intake signals#307

Closed
Jhacarreiro wants to merge 1 commit into
openclaw:mainfrom
Jhacarreiro:pr/pr-intake-human-only
Closed

Separate human-only PR intake signals#307
Jhacarreiro wants to merge 1 commit into
openclaw:mainfrom
Jhacarreiro:pr/pr-intake-human-only

Conversation

@Jhacarreiro

@Jhacarreiro Jhacarreiro commented Jun 16, 2026

Copy link
Copy Markdown
Contributor

Summary

  • classify ClawSweeper status/rating/merge-risk labels as metadata signals rather than automatic repair blockers
  • emit requires_human results for PRs that only have human/workflow metadata and no repairable blocker
  • avoid creating automatic repair jobs for comment-only or label-only cases when proof: sufficient is already present
  • add an optional watch-silence fingerprint config so known watchlisted PRs stay quiet until their stable state changes

Rationale

Repair-only intake should enqueue jobs only when there is an objective repairable blocker, such as failed checks, dirty/blocked merge state, changes requested, or unresolved actionable review threads. Stale labels and human workflow status should be reported separately for maintainer attention instead of creating repair work.

Verification

  • corepack pnpm install --frozen-lockfile
  • corepack pnpm run build:repair
  • node --test test/repair/pr-repair-intake.test.ts

@clawsweeper

clawsweeper Bot commented Jun 16, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

Codex review: needs real behavior proof before merge. Reviewed June 16, 2026, 3:01 AM ET / 07:01 UTC.

Summary
The branch changes src/repair/pr-repair-intake.ts to separate human/workflow metadata from repairable blockers and add optional watch-silence fingerprinting.

Reproducibility: yes. for the review finding: the GitHub pnpm check log reproduces the format failure. Current-main bug reproduction is otherwise not applicable because this PR adds new automation behavior.

Review metrics: 2 noteworthy metrics.

  • Changed surface: 1 source file changed; 175 additions, 6 deletions. The whole behavioral change is concentrated in the repair-intake script that creates automation jobs.
  • Tests changed: 0 test files changed. The new human-only and watch-silence paths are not accompanied by a test diff in this PR.

Merge readiness
Overall: 🦪 silver shellfish
Proof: 🦪 silver shellfish
Patch quality: 🦐 gold shrimp
Result: blocked until real behavior proof from a real setup is added.

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

Rank-up moves:

  • [P1] Fix the src/repair/pr-repair-intake.ts formatting reported by CI.
  • [P1] Add redacted terminal output from a real repair:pr-intake --dry-run showing the new human-only and normal repair-job cases.

Proof guidance:

  • [P1] Needs real behavior proof before merge: The PR only lists build/test commands, so it needs redacted terminal output or logs from a real after-fix intake dry run before merge; updating the PR body should trigger a fresh review, or a maintainer can comment @clawsweeper re-review. After adding proof, update the PR body; ClawSweeper should re-review automatically. If it does not, the PR author or someone with repository write access can comment @clawsweeper re-review.

Risk before merge

  • [P1] The branch cannot pass the repository handoff gate until the src/repair/pr-repair-intake.ts formatting failure is fixed.
  • [P1] The new classifier can suppress or create repair jobs, so maintainers need proof that metadata-only PRs become human-only while objective blockers still enqueue repair work.
  • [P1] The optional watch-silence config is a new operational knob and needs maintainer-visible validation before it is trusted in automation.

Maintainer options:

  1. Fix validation and proof before merge (recommended)
    Format the touched file and add redacted real dry-run output showing requires_human, silent, changed-watch, and ordinary repair-job cases behave as intended.
  2. Pause for automation policy review
    If maintainers are unsure about suppressing metadata-only jobs, keep the PR paused until the permanent repair-intake policy is confirmed.

Next step before merge

  • [P1] The PR needs contributor-supplied real behavior proof and a formatting fix; ClawSweeper should not queue repair markers while the proof gate is missing.

Security
Cleared: The diff changes local repair-intake classification and maintainer-supplied JSON config reading; no concrete security or supply-chain regression was found.

Review findings

  • [P2] Run the formatter on the intake changes — src/repair/pr-repair-intake.ts:42-43
Review details

Best possible solution:

Land the intake split only after the file is formatted, focused coverage validates the new classifications, and the PR body includes redacted dry-run output from representative real PR states.

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

Yes for the review finding: the GitHub pnpm check log reproduces the format failure. Current-main bug reproduction is otherwise not applicable because this PR adds new automation behavior.

Is this the best way to solve the issue?

No, not yet: the implementation direction is plausible, but the current branch is not the best mergeable solution until formatting is fixed and real intake-output proof establishes the classification boundary.

Full review comments:

  • [P2] Run the formatter on the intake changes — src/repair/pr-repair-intake.ts:42-43
    pnpm run check reaches format:check and then fails because src/repair/pr-repair-intake.ts is not oxfmt-clean. This blocks the repository's required handoff check for code changes, so the branch needs formatting before merge.
    Confidence: 0.94

Overall correctness: patch is incorrect
Overall confidence: 0.88

AGENTS.md: found and applied where relevant.

Codex review notes: model internal, reasoning high; reviewed against c88270b81889.

Label changes

Label changes:

  • add P2: This is a normal-priority repair-automation improvement with a clear validation blocker and limited file scope.
  • add merge-risk: 🚨 automation: The diff changes which PR states create repair jobs versus human-only output, so a bad classification could suppress or create ClawSweeper automation work.
  • add rating: 🦪 silver shellfish: Overall readiness is 🦪 silver shellfish; proof is 🦪 silver shellfish and patch quality is 🦐 gold shrimp.
  • add status: 📣 needs proof: The PR needs real behavior proof before ClawSweeper can clear the contributor ask. Needs real behavior proof before merge: The PR only lists build/test commands, so it needs redacted terminal output or logs from a real after-fix intake dry run before merge; updating the PR body should trigger a fresh review, or a maintainer can comment @clawsweeper re-review. After adding proof, update the PR body; ClawSweeper should re-review automatically. If it does not, the PR author or someone with repository write access can comment @clawsweeper re-review.

Label justifications:

  • P2: This is a normal-priority repair-automation improvement with a clear validation blocker and limited file scope.
  • merge-risk: 🚨 automation: The diff changes which PR states create repair jobs versus human-only output, so a bad classification could suppress or create ClawSweeper automation work.
  • rating: 🦪 silver shellfish: Overall readiness is 🦪 silver shellfish; proof is 🦪 silver shellfish and patch quality is 🦐 gold shrimp.
  • status: 📣 needs proof: The PR needs real behavior proof before ClawSweeper can clear the contributor ask. Needs real behavior proof before merge: The PR only lists build/test commands, so it needs redacted terminal output or logs from a real after-fix intake dry run before merge; updating the PR body should trigger a fresh review, or a maintainer can comment @clawsweeper re-review. After adding proof, update the PR body; ClawSweeper should re-review automatically. If it does not, the PR author or someone with repository write access can comment @clawsweeper re-review.
Evidence reviewed

What I checked:

Likely related people:

  • Jhacarreiro: GitHub PR history shows Add repair-only PR intake #290 added the repair-only PR intake feature and touched src/repair/pr-repair-intake.ts and its tests. (role: original repair-intake feature contributor; confidence: high; commits: ff5ada9b0c83, 4d54a576216d, f4a1239a49cc; files: src/repair/pr-repair-intake.ts, test/repair/pr-repair-intake.test.ts)
  • Peter Steinberger: Local blame shows the current main repair-intake file and test landed in dc82491, and PR history for Add repair-only PR intake #290 includes follow-up trust-contract work by this person. (role: current-main release and trust-contract contributor; confidence: high; commits: dc824915bb6c, b58b79937f14; files: src/repair/pr-repair-intake.ts, test/repair/pr-repair-intake.test.ts)
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 Bot added rating: 🦪 silver shellfish Thin PR readiness signal; proof, validation, or implementation needs work. status: 📣 needs proof The PR needs real behavior proof before ClawSweeper can clear the contributor ask. P2 Normal priority bug or improvement with limited blast radius. merge-risk: 🚨 automation 🚨 Merging this PR could break CI, automerge, proof capture, label sync, or automation. labels Jun 16, 2026
@steipete

steipete commented Jun 19, 2026

Copy link
Copy Markdown
Contributor

Closing rather than repairing this branch. It combines signal classification with watch-silence state, has no regression coverage for either path, and is superseded operationally by narrower intake work. The useful classification idea can return as a focused, tested change. Thank you for the proposal.

@steipete steipete closed this Jun 19, 2026
@Jhacarreiro

Jhacarreiro commented Jun 19, 2026

Copy link
Copy Markdown
Contributor Author

Closing this branch for now instead of trying to prove it with local operational runs.

If the human-only intake separation is still needed, it should come back as a small, model-agnostic PR with clean checks and upstream-clean tests/proof. Any adapter or non-Codex-specific behavior must not be part of ClawSweeper.

This was referenced Jun 19, 2026
Closed
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

merge-risk: 🚨 automation 🚨 Merging this PR could break CI, automerge, proof capture, label sync, or automation. P2 Normal priority bug or improvement with limited blast radius. rating: 🦪 silver shellfish Thin PR readiness signal; proof, validation, or implementation needs work. status: 📣 needs proof The PR needs real behavior proof before ClawSweeper can clear the contributor ask.

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@Jhacarreiro @steipete