darrenhinde
|
e43eaff317
|
feat(evals): add BehaviorEvaluator and improve test validation
- Add BehaviorEvaluator for validating agent behavior expectations:
- mustUseTools/mustNotUseTools validation
- minToolCalls/maxToolCalls validation
- requiresApproval/requiresContext/shouldDelegate checks
- Fix test schema to allow behavior alone (without expectedViolations)
- Add 41 unit tests for BehaviorEvaluator, TestCaseSchema, and YAML loading
- Improve test-runner event logging with meaningful tool/message details
- Fix glob import for ESM compatibility
- Add new test cases for bash, context loading, and approval scenarios
|
2025-11-26 01:10:51 +00:00 |
|