disinto-admin/disinto
1
0
Fork 0
Code Issues 15 Pull requests Projects Releases Packages Wiki Activity Actions

chore: gardener housekeeping 2026-04-14
All checks were successful
ci/woodpecker/push/ci Pipeline was successful
Details
ci/woodpecker/pr/ci Pipeline was successful
Details

Browse source
This commit is contained in:
Claude 2026-04-14 22:54:30 +00:00
parent ba3a11fa9d
commit 5733a10858
10 changed files with 20 additions and 24 deletions
Download patch file Download diff file Expand all files Collapse all files

8
dev/AGENTS.md
View file

@ -1,4 +1,4 @@
<!-- last-reviewed: 4e53f508d9b36c60bd68ed5fc497fc8775fec79f -->
<!-- last-reviewed: ba3a11fa9d3d0f780318043b7adca135681ab758 -->
# Dev Agent
**Role**: Implement issues autonomously — write code, push branches, address
@ -55,6 +55,12 @@ PRs owned by other bot users (#374).
**Crash recovery**: on `PHASE:crashed` or non-zero exit, the worktree is **preserved** (not destroyed) for debugging. Location logged. Supervisor housekeeping removes stale crashed worktrees older than 24h.
**Polling loop isolation (#753)**: `docker/agents/entrypoint.sh` now tracks fast-poll PIDs
(`FAST_PIDS`) and calls `wait "${FAST_PIDS[@]}"` instead of `wait` (no-args). This means
long-running dev-agent sessions no longer block the loop from launching the next iteration's
fast polls — the loop only waits for review-poll and dev-poll (the fast agents), never for
the dev-agent subprocess itself.
**Lifecycle**: dev-poll.sh (invoked by polling loop, `check_active dev`) → dev-agent.sh →
tmux session → phase file drives CI/review loop → merge + `mirror_push()` → close issue.
On respawn after `PHASE:escalate`, the stale phase file is cleared first so the session