Merge pull request 'autopilot(qa): bounce to dev instead of halt; stop after 3' (#51) from fix/autopilot-bounce into main

.gitea/workflows/scripts/publish.sh

@@ -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

.gitea/workflows/scripts/run-agent.sh

@@ -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
+   AUTOPILOT MODE IS ACTIVE (this issue/PR carries the 'autopilot' label). You are the quality gate.
-   NARROW, one-time merge authority for THIS PR only:
+   You do NOT edit code or fix anything yourself — you either accept the PR or send it back to the dev
-   - If, after verifying, the PR is correct and any CI checks are green, end your reply with EXACTLY
+   with precise instructions. After actually verifying, end your reply with EXACTLY one of:
-     one line: 'MERGE_PR'. The automation will then merge the PR and close the linked issue for you.
+   - 'MERGE_PR' — the change is correct and any CI is green. The automation merges the PR and closes
-     Do NOT merge via any other means; only the MERGE_PR marker triggers the merge.
+     the linked issue. Do NOT merge by any other means; only this marker triggers the merge.
-   - If you find ANY bug, doubt, or the change is not clearly correct, do NOT merge. Instead describe
+   - 'BOUNCE: @<dev>' — something needs changing. FIRST spell out, specifically and actionably, exactly
-     the problem clearly and end your reply with EXACTLY one line: 'HALT_AUTOPILOT'. The automation
+     what the dev must change (name the file, label, value, hostname, etc.), THEN end with the BOUNCE
-     removes the 'autopilot' label (returning this issue to normal human control) and leaves
+     line naming who should fix it (@junior / @senior / @lead — usually whoever built it; @senior or
-     it for @ffaerber to decide next steps. Never auto-bounce back to a dev.
+     @lead for something harder). The automation sends the PR back to that dev and then re-verifies
-   Emit AT MOST one of MERGE_PR or HALT_AUTOPILOT, and only after you have actually verified. When in
+     with you. After 3 bounces it stops automatically and hands to @ffaerber — so make each round
-   doubt, prefer HALT_AUTOPILOT."
+     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