iiRecord
Agentic AI Atlas · GAP-SUBOBS-004: Subagent Health and Timeout Monitoring
page:docs-harness-features-backlog-gaps-subagent-observability-gap-subobs-004a5c.ai
II.
Page reference

page:docs-harness-features-backlog-gaps-subagent-observability-gap-subobs-004

Reading · 1 min

GAP-SUBOBS-004: Subagent Health and Timeout Monitoring reference

Monitor health of running subagents: detect hangs, timeouts, excessive token usage. Alert and auto-recover.

Pagewiki/docs/harness-features-backlog/gaps/subagent-observability/GAP-SUBOBS-004.mdOutgoing · 0Incoming · 1

GAP-SUBOBS-004: Subagent Health and Timeout Monitoring

FieldValue
Categorysubagent-observability
PriorityMedium
EffortM
StatusMissing

Description

Monitor health of running subagents: detect hangs, timeouts, excessive token usage. Alert and auto-recover.

Current State

Basic timeout on invokeHarness(). No health monitoring or auto-recovery.

Target State

Continuous health monitoring for running subagents. Hang detection (no output for configurable period). Token budget enforcement per subagent. Auto-recovery: retry, fallback to different harness, or abort with partial results.

Dependencies

Key Files

ComponentPath
Harness invokerpackages/sdk/src/harness/invoker.ts
Config modulepackages/sdk/src/config/

Recommendation

Phase 3 implementation. Add health monitor to invokeHarness(). Detect hangs via output silence. Enforce token budgets. Implement auto-recovery strategies.