agents: review round 2 — split-PR flow, thread recency, mention boundaries, learnings cap, pm model #96

Merged
ffaerber merged 1 commits from fix/review-round2 into main 2026-07-06 19:12:28 +02:00
1 Commits
Author SHA1 Message Date
Felix FaerberandClaude Opus 4.8 e9df9d6bdd agents: review round 2 — split-PR flow, thread recency, mention boundaries, learnings cap, pm model
ci / lint (pull_request) Successful in 11s
ci / lint (push) Skipped
- publish.sh: resolve_prs matches ai/issue-N AND ai/issue-N-<slug> split branches
  (exact-only silently stalled DELEGATE:@qa and autopilot MERGE_PR on slugged
  work); qa hand-off lists all open PRs; autopilot refuses to merge multi-PR
  issues (drops the label, hands to the human) — merging one of several open
  PRs is half a change deployed. Retro's state=all resolve matches slugs too.
- fetch-thread.sh: paginate and keep the NEWEST 100 comments — a bare limit=100
  kept the OLDEST page and dropped recent decisions on long threads.
- route.sh: word-boundary mention matching ("@internal" no longer routes to
  @intern); a comment with no real agent mention now SKIPS gracefully
  (mode=skip outputs + step guards in agent.yml) instead of a red run.
- run-agent.sh: LEARNINGS.md cap is line-aware and keeps the NEWEST entries
  (retros append at the bottom; the old head -c cut the latest lessons first).
- agents.json/README: @pm gemma4 -> minimax-m3 — the retro rule demands an
  investigating PM, and gemma4 posted 0 tool calls on every run; minimax is the
  model @qa demonstrably uses tools with.
- agent.yml: document the PR-thread concurrency-group caveat.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-06 20:11:45 +03:00