autopilot(qa): bounce back to the dev instead of halting; stop after 3 bounces

Per maintainer: @qa must never change code — it only accepts a PR or sends it back to the dev with
precise instructions. Replaces the halt-on-any-problem behavior with a bounce loop:

- QA prompt: emit MERGE_PR (approve), or `BOUNCE: @<dev>` after spelling out exactly what to change.
  HALT_AUTOPILOT is now only for problems a dev can't fix (needs a human decision).
- publish.sh: on BOUNCE, re-trigger the named dev (via AGENT_TOKEN) with "autopilot fix attempt N/3".
  Count prior attempts from the PR thread; at 3 it stops (removes the label) and hands to @ffaerber.
- publish.sh: after a dev pushes a fix (resume), auto-re-trigger @qa to re-verify — closing the loop
  (dev fix -> qa re-check -> merge or bounce again).
- Updated the initial @qa trigger wording (bounce, not halt).

Verified: BOUNCE target parsing and the 3-strike counter (attempts 1/3,2/3,3/3 then HALT).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Felix Faerber
2026-07-04 23:18:00 +03:00
co-authored by Claude Opus 4.8
parent bb07558d70
commit 9840c2a860
2 changed files with 55 additions and 13 deletions
+14 -11
View File
@@ -71,17 +71,20 @@ if [ "$MODE" = "comment" ]; then
a human does that."
if [ "$AUTOPILOT" = "true" ]; then
ACTION="$ACTION
AUTOPILOT MODE IS ACTIVE (this issue/PR carries the 'autopilot' label). This grants you a
NARROW, one-time merge authority for THIS PR only:
- If, after verifying, the PR is correct and any CI checks are green, end your reply with EXACTLY
one line: 'MERGE_PR'. The automation will then merge the PR and close the linked issue for you.
Do NOT merge via any other means; only the MERGE_PR marker triggers the merge.
- If you find ANY bug, doubt, or the change is not clearly correct, do NOT merge. Instead describe
the problem clearly and end your reply with EXACTLY one line: 'HALT_AUTOPILOT'. The automation
removes the 'autopilot' label (returning this issue to normal human control) and leaves
it for @ffaerber to decide next steps. Never auto-bounce back to a dev.
Emit AT MOST one of MERGE_PR or HALT_AUTOPILOT, and only after you have actually verified. When in
doubt, prefer HALT_AUTOPILOT."
AUTOPILOT MODE IS ACTIVE (this issue/PR carries the 'autopilot' label). You are the quality gate.
You do NOT edit code or fix anything yourself — you either accept the PR or send it back to the dev
with precise instructions. After actually verifying, end your reply with EXACTLY one of:
- 'MERGE_PR' — the change is correct and any CI is green. The automation merges the PR and closes
the linked issue. Do NOT merge by any other means; only this marker triggers the merge.
- 'BOUNCE: @<dev>' — something needs changing. FIRST spell out, specifically and actionably, exactly
what the dev must change (name the file, label, value, hostname, etc.), THEN end with the BOUNCE
line naming who should fix it (@junior / @senior / @lead — usually whoever built it; @senior or
@lead for something harder). The automation sends the PR back to that dev and then re-verifies
with you. After 3 bounces it stops automatically and hands to @ffaerber — so make each round
count and list ALL problems at once, not one at a time.
Use BOUNCE for anything a dev can fix. Only use 'HALT_AUTOPILOT' when the problem is NOT fixable by
a dev — the request itself is ambiguous or needs a human decision — to hand back to @ffaerber.
Emit AT MOST one of MERGE_PR / BOUNCE / HALT_AUTOPILOT, and only after you have actually verified."
fi
fi
else