mateclaw/mateclaw-server/src/test/resources/agent-evaluation/goal-service-boundaries-v1.json

103 lines
2.8 KiB
JSON

{
"schemaVersion": 1,
"suiteId": "goal-service-boundaries-v1",
"tasks": [
{
"id": "current-revision-completion",
"task": "current revision completion",
"source": "cycles 004/006/010/013 real service boundaries",
"operation": "CURRENT_REVISION_COMPLETION",
"expected": {
"status": "COMPLETED",
"score": 1.0,
"criteriaCount": 1,
"passedCount": 1,
"firstCriterionText": "report",
"evaluationRevision": 1,
"recordedEvalCallsUsed": 1,
"completionCode": 200
}
},
{
"id": "append-before-verdict",
"task": "append before verdict",
"source": "cycles 004/006/010/013 real service boundaries",
"operation": "APPEND_BEFORE_VERDICT",
"expected": {
"status": "ACTIVE",
"score": 0.5,
"criteriaCount": 2,
"passedCount": 1,
"firstCriterionText": "report",
"evaluationRevision": 0,
"recordedEvalCallsUsed": 1,
"completionCode": 409
}
},
{
"id": "pause-before-verdict",
"task": "pause before verdict",
"source": "cycles 004/006/010/013 real service boundaries",
"operation": "PAUSE_BEFORE_VERDICT",
"expected": {
"status": "PAUSED",
"score": 0.0,
"criteriaCount": 1,
"passedCount": 0,
"firstCriterionText": "report",
"evaluationRevision": 0,
"recordedEvalCallsUsed": 2,
"completionCode": 409
}
},
{
"id": "append-before-bootstrap",
"task": "append before bootstrap",
"source": "cycles 004/006/010/013 real service boundaries",
"operation": "APPEND_BEFORE_BOOTSTRAP",
"expected": {
"status": "ACTIVE",
"score": 0.0,
"criteriaCount": 1,
"passedCount": 0,
"firstCriterionText": "user appendix",
"evaluationRevision": 0,
"recordedEvalCallsUsed": 1,
"completionCode": 0
}
},
{
"id": "replace-definition",
"task": "replace definition",
"source": "cycles 004/006/010/013 real service boundaries",
"operation": "REPLACE_DEFINITION",
"expected": {
"status": "ACTIVE",
"score": 0.0,
"criteriaCount": 0,
"passedCount": 0,
"firstCriterionText": null,
"evaluationRevision": 1,
"recordedEvalCallsUsed": 2,
"completionCode": 409
}
},
{
"id": "aba-definition",
"task": "aba definition",
"source": "cycles 004/006/010/013 real service boundaries",
"operation": "ABA_DEFINITION",
"expected": {
"status": "ACTIVE",
"score": 0.0,
"criteriaCount": 0,
"passedCount": 0,
"firstCriterionText": null,
"evaluationRevision": 2,
"recordedEvalCallsUsed": 1,
"completionCode": 0
}
}
]
}