refactor(monitor): keep sessions alive on job completion, kill only on errors

- Modify reconcile.sh mutation logic to clear delegate_job_id instead of calling tmux kill-session on 'completed' events
- Retain process termination behavior on 'error' events for safety

.agents/skills/multi-agent-mux-monitor/scripts/reconcile.sh

@@ -118,16 +118,21 @@ _now = datetime.now(timezone.utc)
 _changed = False
 for s in d.get('tmux_sessions', []):
     if s.get('delegate_job_id') == _jid and s.get('status') == 'running':
-        s['status'] = 'terminated'
-        s['terminated_at'] = _now.strftime('%Y-%m-%dT%H:%M:%SZ')
-        s['terminated_at_epoch'] = int(_now.timestamp())
-        s['termination_mode'] = 'auto-detected (MQTT ' + _event + ')'
         _name = s.get('name')
         _srv = s.get('tmux_server') or 'default'
-        _cmd = ['tmux'] + (['-L', _srv] if _srv != 'default' else []) + ['kill-session', '-t', _name]
-        subprocess.run(_cmd, capture_output=True)
-        print('MQTT Monitor: terminated + killed ' + str(_name) + ' on ' + str(_srv), flush=True)
-        _changed = True
+        if _event == 'completed':
+            s['delegate_job_id'] = None
+            print('MQTT Monitor: job completed on ' + str(_name) + ' — session kept alive', flush=True)
+            _changed = True
+        else:
+            s['status'] = 'terminated'
+            s['terminated_at'] = _now.strftime('%Y-%m-%dT%H:%M:%SZ')
+            s['terminated_at_epoch'] = int(_now.timestamp())
+            s['termination_mode'] = 'auto-detected (MQTT ' + _event + ')'
+            _cmd = ['tmux'] + (['-L', _srv] if _srv != 'default' else []) + ['kill-session', '-t', _name]
+            subprocess.run(_cmd, capture_output=True)
+            print('MQTT Monitor: terminated + killed ' + str(_name) + ' on ' + str(_srv) + ' due to MQTT ' + _event, flush=True)
+            _changed = True
 if not _changed:
     raise SystemExit(0)  # nothing matched — skip the write entirely
 '''