Agent monitor v2 (live sessions, stalls, spend)
get_agent_monitorMonitor in-progress tickets, showing elapsed time, stall status, token spend, and orchestration details to catch stuck tickets.
Instructions
Live snapshot of the board's currently-running work: every In Progress ticket with elapsed time since it went In Progress (from the ticket_events.jsonl audit log, falling back to its earliest work-log entry or createdDate when there's no recorded status event), its last event (most recent audit event or work-log entry, whichever is newer) with age, token spend so far vs its cap: label and the resulting spend ratio, and a stalled flag (no event/work-log activity within stallMinutes, default 30). Also reports costSoFar and capCost in dollars (via project-config-overridable pricing; capCost is null when no model can be inferred for the ticket). Each ticket also carries lastDispatch ({worker, model, parallel, note, ageMinutes}, null if record_dispatch was never called for it) — who's actively working it, a sub-agent or the orchestrator — so the board can render an orchestration chip without a separate call. Sorted most-recently-active first, with a top-level summary (count, stalledCount, subAgentCount, parallelCount, totalSpend, totalCap, totalCostSoFar, totalCapCost, stalledTickets). Pairs with churn mode: a stalled ticket mid-churn usually means the agent is stuck or has gone quiet. Use it to see what's underway, who/what is running it, and catch stuck tickets.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| asOf | No | Reference time (ISO) to measure elapsed/idle against; defaults to now. | |
| project | Yes | ||
| stallHours | No | Deprecated alias for stallMinutes (converted to minutes); ignored if stallMinutes is given. | |
| stallMinutes | No | Inactivity minutes after which an In Progress ticket is flagged stalled. Defaults to 30. |