v1.5.0
Agent Vitals v1.5.0
Highlights:
- Content-based loop detection: SHA-256 fingerprint + word-level Jaccard similarity for loop/stuck disambiguation via
output_textparameter onmonitor.step() - Framework-specific threshold profiles: Auto-detected from adapter type, with
langgraph,crewai, anddspyprofiles shipped in thresholds.yaml ThresholdProfiledataclass andVitalsConfig.for_framework()API for per-framework threshold tuningADAPTER_FRAMEWORK_MAPfor automatic profile resolution from all 8 adapters- New
output_similarityandoutput_fingerprintfields onVitalsSnapshot - Zero regression from v1.4.0 baseline across 70-trace backtest corpus
- CI lint fixes (removed unused imports)
- 386 tests passing
Detection precision (cross-agent, 40 traces):
- vitals.any: P=1.000 R=1.000
- loop: P=0.875 R=1.000
- stuck: P=1.000 R=0.800
- thrash: P=1.000 R=1.000
Detection precision (combined, 70 traces):
- vitals.any: P=1.000 R=0.982
- loop: P=0.909 R=0.870
Content-based similarity addresses the 2 remaining loop FPs (signal-identical stuck traces) for new traces collected with output_text.