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
co-authored by
Claude Opus 4.8
Claude Opus 4.8
parent
bb07558d70
commit
9840c2a860
@@ -42,6 +42,7 @@ reply=$(awk '
|
||||
/^[[:space:]]*CLOSE_ISSUE[[:space:]]*$/{next}
|
||||
/^[[:space:]]*MERGE_PR[[:space:]]*$/{next}
|
||||
/^[[:space:]]*HALT_AUTOPILOT[[:space:]]*$/{next}
|
||||
/^[[:space:]]*BOUNCE:[[:space:]]*@/{next}
|
||||
s{ if(/^[[:space:]]*END_SUBTASKS/){s=0}; next }
|
||||
p{ if(/^[[:space:]]*END_PR_DESCRIPTION/){p=0}; next }
|
||||
{print}
|
||||
@@ -137,10 +138,36 @@ if [ "$MODE" != "pr" ]; then
|
||||
;;
|
||||
esac
|
||||
fi
|
||||
elif grep -qiE '^[[:space:]]*BOUNCE:[[:space:]]*@(junior|senior|lead)' /tmp/agent_out.md; then
|
||||
# @qa wants the dev to fix something. Send it back — never fix it ourselves. After 3 bounces,
|
||||
# stop and hand to the human. QA's feedback is already posted (the reply comment above).
|
||||
if [ -z "$IS_PR" ]; then
|
||||
echo "BOUNCE marker but this run is not on a PR thread — skipping"
|
||||
else
|
||||
target=$(grep -oiE 'BOUNCE:[[:space:]]*@(junior|senior|lead)' /tmp/agent_out.md | head -1 \
|
||||
| grep -oiE '(junior|senior|lead)' | tr '[:upper:]' '[:lower:]')
|
||||
[ -z "$target" ] && target=$(curl -sS "${hdr[@]}" "$API/pulls/$NUM" | jq -r '.user.login // "junior"')
|
||||
# Count how many times this PR has already been bounced (marker in the trigger comment).
|
||||
prior=$(curl -sS "${hdr[@]}" "$API/issues/$NUM/comments?limit=100" \
|
||||
| jq -r 'if type=="array" then [.[]|select(.body|test("autopilot fix attempt"))]|length else 0 end' 2>/dev/null)
|
||||
prior=${prior:-0}
|
||||
if [ "$prior" -ge 3 ]; then
|
||||
echo "@qa autopilot: 3 bounces already — halting"
|
||||
del_autopilot_label "${ISSNUM:-$NUM}"
|
||||
post "$(printf '🤖 **@qa** — 🛑 still not right after 3 fix attempts. Stopping autopilot (removed the `autopilot` label). @ffaerber please take over — details in the comments above.')"
|
||||
else
|
||||
n=$((prior + 1))
|
||||
echo "@qa autopilot: bounce $n/3 -> @$target"
|
||||
curl -sS -X POST -H "Authorization: token $AGENT_TOKEN" -H "Content-Type: application/json" \
|
||||
"$API/issues/$NUM/comments" \
|
||||
-d "$(jq -nc --arg b "@$target please address @qa's feedback above and update this PR (autopilot fix attempt $n/3)." '{body:$b}')" \
|
||||
-w '\nbounce -> HTTP %{http_code}\n' || true
|
||||
fi
|
||||
fi
|
||||
elif grep -qiE '^[[:space:]]*HALT_AUTOPILOT[[:space:]]*$' /tmp/agent_out.md; then
|
||||
echo "@qa autopilot: HALT — removing 'autopilot' label from #${ISSNUM:-$NUM}"
|
||||
del_autopilot_label "${ISSNUM:-$NUM}"
|
||||
post "$(printf '🤖 **@qa** — 🛑 found a problem, so I did NOT merge. Removed the `autopilot` label (back to human control). @ffaerber please decide next steps (details above).')"
|
||||
post "$(printf '🤖 **@qa** — 🛑 this needs a human decision (not a dev fix). Removed the `autopilot` label (back to human control). @ffaerber please decide next steps (details above).')"
|
||||
fi
|
||||
exit 0
|
||||
fi
|
||||
@@ -247,11 +274,23 @@ if [ "$NEW" = "true" ]; then
|
||||
echo "autopilot: auto-triggering @qa to review PR #$prnum"
|
||||
curl -sS -X POST -H "Authorization: token $AGENT_TOKEN" -H "Content-Type: application/json" \
|
||||
"$API/issues/$prnum/comments" \
|
||||
-d "$(jq -nc --arg b "@qa please verify this PR (autopilot: issue #$NUM is labeled autopilot). Merge it if correct, or halt and remove the label if you find a problem." '{body:$b}')" \
|
||||
-d "$(jq -nc --arg b "@qa please verify this PR (autopilot: issue #$NUM is labeled autopilot). Merge it if correct, or bounce it back to the dev with exactly what needs fixing." '{body:$b}')" \
|
||||
-w '\ntrigger-qa -> HTTP %{http_code}\n' || true
|
||||
fi
|
||||
else
|
||||
# Resume: just link the PR — its body and the diff already carry the description, so we don't
|
||||
# repeat the full write-up in the comment (the reasoning trail below shows what this run did).
|
||||
prpost "$prnum" "$(printf '🤖 **@%s** — pushed an update to the PR:\n- %s%s' "$NAME" "$url" "$activity")"
|
||||
# AUTOPILOT: after a dev pushes a fix (e.g. following a @qa bounce), hand back to @qa to re-verify.
|
||||
if [ "$AUTOPILOT" = "true" ] && [ -n "$AGENT_TOKEN" ] && [ -n "$prnum" ]; then
|
||||
case "$NAME" in
|
||||
junior|senior|lead)
|
||||
echo "autopilot: dev pushed a fix — re-triggering @qa to re-verify PR #$prnum"
|
||||
curl -sS -X POST -H "Authorization: token $AGENT_TOKEN" -H "Content-Type: application/json" \
|
||||
"$API/issues/$prnum/comments" \
|
||||
-d "$(jq -nc --arg b "@qa please re-verify this PR (autopilot). Merge it if now correct, or bounce it back with exactly what still needs fixing." '{body:$b}')" \
|
||||
-w '\ntrigger-qa -> HTTP %{http_code}\n' || true
|
||||
;;
|
||||
esac
|
||||
fi
|
||||
fi
|
||||
|
||||
Reference in New Issue
Block a user