GH#18538: worker-is-triager model for review-followup issues (follow-up to #18610)#18743
Conversation
…kers decide, humans approve (GH#18538 follow-up)
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 36 minutes and 56 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 (1)
✨ 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 22:11:08 UTC 2026: Code review monitoring started 📈 Current Quality Metrics
Generated on: Mon Apr 13 22:11:11 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
Up to standards ✅🟢 Issues
|
|



Summary
Flips SCANNER_NEEDS_REVIEW default from true to false and rewrites the issue-body preamble as worker-facing triage instructions mandating three outcomes: (A) premise falsified → close with rationale, (B) premise correct + fix obvious → implement and PR, (C) premise correct but genuinely ambiguous → post decision comment with analysis + recommendation + specific question, then escalate. Humans approve, they don't re-do analysis. PR #18610 applied needs-maintainer-review unconditionally at issue creation — that was the exact 'punt analysis to a human' anti-pattern prompts/build.txt 'Reasoning responsibility' forbids at the reasoning layer, applied to the dispatch layer instead.
Files Changed
.agents/scripts/post-merge-review-scanner.sh
Runtime Testing
Resolves #18538
aidevops.sh v3.8.8 plugin for OpenCode v1.4.3 with claude-sonnet-4-6 spent 17h 38m and 8,145 tokens on this as a headless worker.