Result of running an evaluation test case.
| 82 | |
| 83 | @dataclass |
| 84 | class EvalResult: |
| 85 | """Result of running an evaluation test case.""" |
| 86 | |
| 87 | test_name: str |
| 88 | passed: bool |
| 89 | tool_trajectory_score: float |
| 90 | response_match_score: float |
| 91 | actual_tools_called: list[str] |
| 92 | actual_response: str |
| 93 | errors: list[str] |
| 94 | |
| 95 | |
| 96 | class AgentEvaluator: |