GH#18538: emit worker-actionable review-followup issue bodies#18607
GH#18538: emit worker-actionable review-followup issue bodies#18607marcusquinn merged 1 commit intomainfrom
Conversation
The post-merge-review-scanner used to emit issue bodies with bot comments truncated to 200 chars mid-sentence and no file:line refs, forcing workers to re-fetch the PR review API just to understand the task. Two Sonnet workers timed out on issue #18538 doing exactly that, triggering the t2008 no-progress fail-safe. Rewrite the body builder so each issue includes: - A 'Files to modify' bullet list with deduped `path:line` refs - A 'Worker Guidance' section with explicit implementation steps - Full inline comments (capped at 2000 chars each, blockquoted) - Full PR review summaries - Direct links to the inline comments on GitHub Also move the completed t1990 entry from the Ready section to Done in TODO.md, addressing the original Gemini comment on PR #18417 that issue #18538 was tracking.
Completion Summary
|
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
|
Warning Rate limit exceeded
Your organization is not enrolled in usage-based pricing. Contact your admin to enable usage-based pricing to continue reviews beyond the rate limit, or try again in 6 minutes and 7 seconds. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report SonarCloud: 0 bugs, 0 vulnerabilities, 226 code smells Mon Apr 13 04:39:29 UTC 2026: Code review monitoring started 📈 Current Quality Metrics
Generated on: Mon Apr 13 04:39:31 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
|
Up to standards ✅🟢 Issues
|
…triage (GH#18538) PR #18607 made review-followup issue bodies worker-actionable (file:line refs, full bot bodies, Worker Guidance), but rich body context cannot rescue a finding whose factual premise is wrong. The original GH#18538 was triggered by a Gemini comment claiming the TODO.md "Ready" section is auto-generated (it is not — todo-ready.sh is read-only). Workers reading even a perfectly-mentored body would still chase a false premise. This PR adds a `needs-maintainer-review` label by default at issue creation time, gating worker auto-dispatch until a human verifies the bot's premise. The triager picks one of three paths (accept/reject/modify-scope), each documented in a new "Triage required" preamble in the issue body. Together with #18607 this turns 0 wasted dispatches per false-premise finding (instead of GH#18538's 2 dispatches → t2008 escalation → manual intervention). Configurable via SCANNER_NEEDS_REVIEW env var (default true). Set to "false" to allow direct dispatch for trusted-finding pipelines. Resolves #18538
…triage (GH#18538) (#18610) PR #18607 made review-followup issue bodies worker-actionable (file:line refs, full bot bodies, Worker Guidance), but rich body context cannot rescue a finding whose factual premise is wrong. The original GH#18538 was triggered by a Gemini comment claiming the TODO.md "Ready" section is auto-generated (it is not — todo-ready.sh is read-only). Workers reading even a perfectly-mentored body would still chase a false premise. This PR adds a `needs-maintainer-review` label by default at issue creation time, gating worker auto-dispatch until a human verifies the bot's premise. The triager picks one of three paths (accept/reject/modify-scope), each documented in a new "Triage required" preamble in the issue body. Together with #18607 this turns 0 wasted dispatches per false-premise finding (instead of GH#18538's 2 dispatches → t2008 escalation → manual intervention). Configurable via SCANNER_NEEDS_REVIEW env var (default true). Set to "false" to allow direct dispatch for trusted-finding pipelines. Resolves #18538
1 participant
Summary
Rewrites post-merge-review-scanner.sh to produce worker-actionable issue bodies (file:line refs, full bot comments, Worker Guidance section) per the t1901 mandatory rule. Also fixes the original Gemini comment on PR #18417 by moving completed t1990 entry from Ready → Done in TODO.md.
Files Changed
.agents/scripts/post-merge-review-scanner.sh,TODO.md
Runtime Testing
Resolves #18538
aidevops.sh v3.8.5 plugin for OpenCode v1.4.3 with claude-opus-4-6 spent 7m and 23,594 tokens on this as a headless worker.