feat: AI supervisor pipeline self-heal via reasoning prompt#2277
feat: AI supervisor pipeline self-heal via reasoning prompt#2277marcusquinn merged 1 commit intomainfrom
Conversation
Add item 12 (Pipeline health) to the AI reasoning prompt. When Phase 3 throughput metrics show zero evaluations while tasks are queued, the AI creates a diagnostic task to fix ai-lifecycle.sh — the same action a human would take in an interactive session. One line of prompt replaces 150 lines of deterministic streak counters, cooldown stamps, and threshold constants.
|
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
⌛ 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. 📒 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 �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Wed Feb 25 03:58:39 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
|
1 participant
Summary
Why
Phase 3 was silently broken for days (PR #2275). The fix was a one-line SQL column change that any interactive session could diagnose in minutes. The supervisor already has all the information it needs (Phase 3 metrics added in v2.128.0) — it just wasn't told to act on it.
Instead of writing 150 lines of bash to detect and react to pipeline failures deterministically, we tell the AI what to look for and let it decide. The AI already runs every pulse (Phase 14), already sees the health metrics, and already has
create_taskas an action type.Changes
ai-reason.sh: Added item 12 (Pipeline health) to the analysis framework inbuild_reasoning_prompt().