66 lines
2.1 KiB
JSON
66 lines
2.1 KiB
JSON
|
{
|
||
|
|
"report": {
|
||
|
|
"schema": "agent-eval-report-v1",
|
||
|
|
"suite_version": "agent-quality-baseline-v1",
|
||
|
|
"suite_sha256": "b5cd3b798a01a48ddf0081f2fcc2a917f93681a3ee2fa55bbf4190466de3bef8",
|
||
|
|
"agent_version": "agent-baseline-v1",
|
||
|
|
"model_config_ref": "runtime-config://voice/agent-baseline-v1",
|
||
|
|
"environment": "mock",
|
||
|
|
"executed_at": "2026-08-24T10:00:00Z",
|
||
|
|
"evaluated_at": "2026-08-24T01:24:36.953421Z",
|
||
|
|
"result": "PASSED",
|
||
|
|
"metrics": {
|
||
|
|
"cases_total": 10,
|
||
|
|
"cases_passed": 10,
|
||
|
|
"conversation_success_rate": 1,
|
||
|
|
"first_response_p95_ms": 1260,
|
||
|
|
"interruption_recovery_rate": 1,
|
||
|
|
"average_response_chars": 36.8,
|
||
|
|
"salutation_accuracy": 1,
|
||
|
|
"memory_accuracy": 1,
|
||
|
|
"fabricated_facts": 0,
|
||
|
|
"story_source_completeness": 1,
|
||
|
|
"sensitive_information_handling_rate": 1,
|
||
|
|
"category_counts": {
|
||
|
|
"conflicting_fact": 1,
|
||
|
|
"emotional_topic": 1,
|
||
|
|
"long_pause": 1,
|
||
|
|
"memory_recall": 1,
|
||
|
|
"name_date_ambiguity": 1,
|
||
|
|
"network_fluctuation": 1,
|
||
|
|
"normal_chat": 1,
|
||
|
|
"repeated_expression": 1,
|
||
|
|
"sensitive_information": 1,
|
||
|
|
"user_interruption": 1
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"failed_checks": []
|
||
|
|
},
|
||
|
|
"registration_payload": {
|
||
|
|
"evidence_type": "AGENT_QUALITY_V1",
|
||
|
|
"suite_version": "agent-quality-baseline-v1",
|
||
|
|
"result": "PASSED",
|
||
|
|
"metrics": {
|
||
|
|
"agent_version": "agent-baseline-v1",
|
||
|
|
"average_response_chars": 36.8,
|
||
|
|
"cases_passed": 10,
|
||
|
|
"cases_total": 10,
|
||
|
|
"conversation_success_rate": 1,
|
||
|
|
"environment": "mock",
|
||
|
|
"executed_at": "2026-08-24T10:00:00Z",
|
||
|
|
"fabricated_facts": 0,
|
||
|
|
"failed_check_count": 0,
|
||
|
|
"first_response_p95_ms": 1260,
|
||
|
|
"interruption_recovery_rate": 1,
|
||
|
|
"memory_accuracy": 1,
|
||
|
|
"model_config_ref": "runtime-config://voice/agent-baseline-v1",
|
||
|
|
"report_schema": "agent-eval-report-v1",
|
||
|
|
"salutation_accuracy": 1,
|
||
|
|
"sensitive_information_handling_rate": 1,
|
||
|
|
"story_source_completeness": 1,
|
||
|
|
"suite_sha256": "b5cd3b798a01a48ddf0081f2fcc2a917f93681a3ee2fa55bbf4190466de3bef8"
|
||
|
|
},
|
||
|
|
"report_ref": "artifact://agent-eval-report.mock.v1.json"
|
||
|
|
}
|
||
|
|
}
|