Feature Description
Problem Statement
Many agent-generated PRs are rejected for predictable reasons: wrong premise, effort underestimated, change-detector tests, or conflicts with upstream design intent. The pipeline creates issues and PRs but does not systematically mine closed/rejected PRs for patterns that would prevent future failures — the same failure modes recur across cycles because the historical signal is never turned into durable rules.
Proposed Solution
Add a closed-PR postmortem miner that:
- Periodically scans closed/merged/rejected PRs in the fork (
gh pr list --state closed).
- Classifies the close reason by reading the closing comment and labels (e.g.,
rejected, needs-work, implemented-on-main, duplicate).
- Emits durable rules or checklists for the research/analysis stages — e.g., "check for change-detector tests when touching model metadata," "decompose any issue touching provider configs."
- Feeds these rules back into the analysis skill as advisory pre-flight checks.
This turns historical failure data into an improvement signal — the central self-evolution mechanism. It is lightweight because it only reads GitHub metadata and existing close comments.
Value Proposition
- Impact: 0.7
- Effort: 0.4
- Priority Score: 1.18
Research Evidence
- Software engineering literature on postmortems and defect prediction
- AutoGen/OpenHands community feedback loops on rejected PRs
Implementation Plan
- New skill
evolution-postmortem-miner + cron job.
- Step 1: fetch closed PRs since last run (bounded window).
- Step 2: classify close reason from labels + closing comment.
- Step 3: deduplicate against existing rules.
- Step 4: emit new rules as structured checklist entries in the analysis skill's config.
- Output: a rules JSON file consumed by the analysis stage.
Success Criteria
Feature Description
Problem Statement
Many agent-generated PRs are rejected for predictable reasons: wrong premise, effort underestimated, change-detector tests, or conflicts with upstream design intent. The pipeline creates issues and PRs but does not systematically mine closed/rejected PRs for patterns that would prevent future failures — the same failure modes recur across cycles because the historical signal is never turned into durable rules.
Proposed Solution
Add a closed-PR postmortem miner that:
gh pr list --state closed).rejected,needs-work,implemented-on-main,duplicate).This turns historical failure data into an improvement signal — the central self-evolution mechanism. It is lightweight because it only reads GitHub metadata and existing close comments.
Value Proposition
Research Evidence
Implementation Plan
evolution-postmortem-miner+ cron job.Success Criteria