feat(stop): fully purge registry entries on stop --purge-conversation and add zombie pre-gate

.agents/skills/multi-agent-mux-stop/scripts/stop_session.sh

@@ -27,8 +27,10 @@
 # Exit codes:
 #   0 = success (or already-stopped no-op) | 1 = YAML not found / not registered
 #   2 = invalid args | 3 = interactive confirmation required (--yes 누락)
+#   4 = purge aborted (tmux session survived the kill chain)
 set -euo pipefail
 
+# shellcheck disable=SC1091
 source "$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)/lib.sh"
 
 usage() {
@@ -68,7 +70,8 @@ done
 [ -n "$SESSION_NAME" ] || { echo "ERROR: --session required" >&2; usage; exit 2; }
 [ -f "$AGENT_SESSIONS_YAML" ] || { echo "ERROR: $AGENT_SESSIONS_YAML not found" >&2; exit 1; }
 
-export TMUX_SERVER_NAME="$(resolve_tmux_server "$SESSION_NAME")"
+TMUX_SERVER_NAME="$(resolve_tmux_server "$SESSION_NAME")"
+export TMUX_SERVER_NAME
 
 # --agent 미지정 시 이름 suffix 로 fallback (P1-F)
 if [ -z "$AGENT" ]; then
@@ -190,6 +193,21 @@ else
   echo "tmux already dead, just updating YAML"
 fi
 
+# Purge pre-gate: 레코드 제거는 tmux 사망이 확인된 경우에만 허용한다.
+# (kill 체인은 best-effort — 세션이 살아남으면 monitor drift-B 가
+#  레코드 없는 세션을 running 으로 자동 재등록해 purge 가 조용히 뒤집힌다)
+if [ "$PURGE" = "1" ] && [ "$TMUX_ALIVE" = "1" ]; then
+  _wait_session_gone "$SESSION_NAME" 5 || true   # SIGKILL 폴백의 비동기 회수 윈도우 흡수
+  if tmux has-session -t "$SESSION_NAME" 2>/dev/null; then
+    echo "ERROR: session '$SESSION_NAME' is still alive after the kill chain." >&2
+    echo "  Refusing registry removal — records preserved (no state was modified)." >&2
+    echo "  Diagnose the stuck TUI (tmux attach -t '$SESSION_NAME'), then re-run" >&2
+    echo "  stop_session.sh --purge-conversation --yes (retry is safe/idempotent)." >&2
+    delegate_publish_event "$DELEGATE_JOB_ID" error "purge aborted: tmux session still alive"
+    exit 4
+  fi
+fi
+
 atomic_dump_yaml "$AGENT_SESSIONS_YAML" \
   SESSION_NAME="$SESSION_NAME" AGENT="$AGENT" PURGE="$PURGE" \
   NOW_ISO="$NOW_ISO" NOW_EPOCH="$NOW_EPOCH" LAST_STATUS="$LAST_STATUS" \
@@ -216,12 +234,7 @@ if target is None:
     print(f"ERROR: disappeared during script: {name}", flush=True)
     raise SystemExit(1)
 
-if purge:
-    target['status'] = 'terminated'
-    target['terminated_at'] = now
-    target['terminated_at_epoch'] = int(os.environ['NOW_EPOCH'])
-    target['termination_mode'] = 'purge'
-else:
+if not purge:
     target['status'] = 'stopped'
     target['stopped_at'] = now
     target['stopped_at_epoch'] = int(os.environ['NOW_EPOCH'])
@@ -324,9 +337,13 @@ elif purge and not purge_uuid:
     print("WARN: --purge-conversation requested but no workspace-scoped UUID resolved; nothing purged", flush=True)
 
 if purge:
-    target['resumable'] = False
-
-print(f"updated: {name} status={target['status']}", flush=True)
+    d['tmux_sessions'] = [s for s in d.get('tmux_sessions', []) if s.get('name') != name]
+    if purge_uuid:
+        print(f"removed: {name} (registry entry fully purged from YAML+DB)", flush=True)
+    else:
+        print(f"removed: {name} (registry entry purged from YAML+DB; WARN: conversation artifacts unresolved — disk copies may remain)", flush=True)
+else:
+    print(f"updated: {name} status={target['status']}", flush=True)
 PYEOF
 
 delegate_publish_event "$DELEGATE_JOB_ID" completed "session terminated"