gitea/agents
8
0
Fork 0
Code Issues 2 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

agents: retro loop — @pm retro distills learnings into LEARNINGS.md #85

Merged
ffaerber merged 1 commits from feat/retro-learnings into main 2026-07-06 10:03:17 +02:00
Conversation 0 Commits 1 Files Changed 3
+55 -4
1 Commits
Author SHA1 Message Date
Felix FaerberandClaude Opus 4.8 b40f547740 agents: retro loop — "@pm retro" distills learnings into LEARNINGS.md
ci / lint (pull_request) Successful in 11s
Details
ci / lint (push) Skipped 
New learning step: ask @pm for a retrospective on any issue and the system
turns what happened into prompt-visible rules for future runs.

- run-agent.sh: @pm gains a RETRO marker (emit only when the maintainer asks);
  LEARNINGS.md (caller repo root, capped at 4KB) is injected into EVERY agent's
  prompt as "TEAM LEARNINGS" — the feedback loop that makes delegation more
  robust over time.
- publish.sh: on @pm's RETRO marker, open a "retro: issue #N" issue pointing at
  the issue + its PR (state=all resolve, works after merge) and trigger @senior
  on it (has gitea-api to read both threads). The retro produces a LEARNINGS.md
  PR through the NORMAL choreography (senior → pm → qa), so retros are reviewed
  like any change. Strip the RETRO marker from visible replies.
- publish.sh: bounce counter now counts only @qa-authored comments matching the
  exact trigger template — on PR #84 it jumped 1/3 → 3/3 because a qa review
  QUOTED our own "(fix attempt …)" template from the diff, halving the fix
  budget. Template + regex pinned together with a sync note.
- README: document the retro loop.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-06 11:02:19 +03:00