lmiranda
f2a62627d0
feat(projman): add runaway detection and circuit breaker for agents (#236)
Executor self-monitoring:
- 10+ calls without progress → stop and reassess
- Same error 3+ times → circuit breaker, report failure
- 50+ calls → mandatory progress update
- 80+ calls → budget warning, evaluate completion
- 100+ calls → hard stop, save checkpoint
Orchestrator monitoring:
- Detect stuck agents (no progress for X minutes)
- Intervention protocol for runaway agents
- Timeout guidelines by task size (XS: 15min, S: 30min, M: 45min)
- Recovery actions with Status/Failed label
This prevents agents from running indefinitely (400+ tool calls
observed in Sprint 3) and provides clear stopping criteria.
Closes #236
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-28 10:46:04 -05:00
..
2026-01-27 18:01:53 -05:00
2026-01-23 12:46:18 -05:00
2026-01-27 14:36:05 -05:00
2026-01-23 12:16:06 -05:00
2026-01-28 10:05:02 -05:00
2026-01-27 17:38:26 -05:00
2026-01-25 15:18:30 -05:00
2026-01-27 17:44:59 -05:00
2026-01-27 14:36:05 -05:00
2026-01-23 12:18:40 -05:00
2026-01-28 10:46:04 -05:00
2026-01-27 14:36:05 -05:00