- When agents may become stuck or unresponsive
- For long-running multi-agent workflows
- When automated recovery is desired
Process
- Health check all active agents and convoys
- Detect stuck or unresponsive agents via heartbeats
- Recover - restart, reassign, or escalate as needed
- Report patrol findings with trend analysis
Monitoring Roles
- Deacon: Daemon supervisor, monitors overall health
- Witness: Per-rig lifecycle manager for workers
- Boot (Dog): Watches the Deacon every 5 minutes
Recovery Modes
- restart: Restart the stuck agent session
- reassign: Move beads to a different agent
- escalate: Alert human for manual intervention
Tool Use
Invoke via babysitter process: methodologies/gastown/gastown-patrol