Conversation
Co-authored-by: HappyOnigiri <nodemeld+happy-onigiri@gmail.com>
|
Cursor Agent can help with this pull request. Just |
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
🚧 Files skipped from review as they are similar to previous changes (1)
📝 WalkthroughWalkthroughCodeRabbitの「Review failed」ステータス検出と、それに基づく自動再開(resume)投稿ロジックをsrc/auto_fixer.pyに追加し、関連ドキュメントとテストを更新しました。公開APIの署名変更はなく、既存の自動再開フローを拡張しています。 Changes
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Possibly related PRs
Suggested labels
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches
🧪 Generate unit tests (beta)
Comment |
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@README.md`:
- Around line 177-183: Update the README.md to make the description of the
coderabbit_auto_resume setting consistent: in the Full schema block update the
coderabbit_auto_resume entry to state it resumes on both rate-limit windows and
when CodeRabbit posts a "Review failed" status comment caused by head-commit
changes (matching the earlier paragraph), and ensure the example
usage/documentation text and any default/boolean notes for
coderabbit_auto_resume reflect the same behavior so readers cannot miss the new
auto-resume trigger.
In `@src/auto_fixer.py`:
- Around line 2054-2055: active_review_failed set by
_get_active_coderabbit_review_failed is not passed through to
_update_done_label_if_completed on the no-review-target path, allowing a PR with
an active "Review failed" to be marked refix:done; update the calls to
_update_done_label_if_completed (including the no-review-target branch around
where resume_comment_posted_for_pr is used) to pass
coderabbit_review_failed_active=bool(active_review_failed) (and mirror the same
fix in the other affected block around lines 2082-2108) so the function receives
the active review-failed flag.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: cee26cec-7ad9-41f3-a1e7-5e56e27e0b19
📒 Files selected for processing (5)
.refix.yaml.sampleREADME.ja.mdREADME.mdsrc/auto_fixer.pytests/test_auto_fixer.py
…rabbit_review_failed_active を追加 active_review_failed が CI-fix 後の完了判定に伝播せず、「Review failed」アクティブな PR が誤って refix:done に遷移する可能性があった。
…d トリガーを追記 Full schema ブロックのコメントが rate-limit のみ記載で「Review failed」による 自動 resume トリガーが欠落していたため、説明文と一貫性を持つよう更新。
🤖 Refix Status処理済みレビュー一覧 (System Use Only)
|
There was a problem hiding this comment.
♻️ Duplicate comments (1)
src/auto_fixer.py (1)
2431-2447:⚠️ Potential issue | 🟠 Major
coderabbit_review_failed_activeをこの呼び出しにも渡してください。この no-review-target 経路だけ
coderabbit_review_failed_activeが未伝播です。active_review_failedが残っている PR でも_update_done_label_if_completed()がrefix:doneに戻してしまい、auto_merge_enabled次第ではそのまま auto-merge 判定まで進み得ます。修正例
_update_done_label_if_completed( repo=repo, pr_number=pr_number, has_review_targets=False, review_fix_started=review_fix_started, review_fix_added_commits=review_fix_added_commits, review_fix_failed=review_fix_failed, state_saved=True, commits_by_phase=commits_by_phase, pr_data=pr_data, review_comments=review_comments, issue_comments=issue_comments, dry_run=dry_run, summarize_only=summarize_only, auto_merge_enabled=auto_merge_enabled, coderabbit_rate_limit_active=bool(active_rate_limit), + coderabbit_review_failed_active=bool(active_review_failed), )🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@src/auto_fixer.py` around lines 2431 - 2447, The no-review-target call to _update_done_label_if_completed is missing the coderabbit_review_failed_active flag so PRs with active_review_failed can be incorrectly marked refix:done and potentially auto-merged; update this invocation to pass coderabbit_review_failed_active=coderabbit_review_failed_active (matching other call sites) so the function receives and respects that state when deciding label updates and auto-merge behavior.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Duplicate comments:
In `@src/auto_fixer.py`:
- Around line 2431-2447: The no-review-target call to
_update_done_label_if_completed is missing the coderabbit_review_failed_active
flag so PRs with active_review_failed can be incorrectly marked refix:done and
potentially auto-merged; update this invocation to pass
coderabbit_review_failed_active=coderabbit_review_failed_active (matching other
call sites) so the function receives and respects that state when deciding label
updates and auto-merge behavior.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 93c55c41-db2a-4d8e-bcff-ee517eb7750f
📒 Files selected for processing (2)
src/auto_fixer.pytests/test_auto_fixer.py
🚧 Files skipped from review as they are similar to previous changes (1)
- tests/test_auto_fixer.py
Summary
Related issues
Changes
coderabbit_auto_resume_max_per_runlimits and preventing duplicate posts.refix:runningstatus while an activeReview failedcomment exists.README.md,README.ja.md, and.refix.yaml.sampleto document the new auto-resume trigger.Testing
Review faileddetection, auto-resume posting, and per-run limit enforcement.make ci.Checklist
Summary by CodeRabbit
新機能
動作変更 / バグ修正
ドキュメント
テスト