kenn-io--agentsview
wehub-resource-sync
f99010fae1
CI / lint (push) Failing after 1s
CI / frontend (push) Failing after 1s
CI / scripts (push) Failing after 1s
CI / Go Test (ubuntu-latest) (push) Failing after 0s
CI / frontend-node-25 (push) Failing after 1s
CI / docs (push) Failing after 0s
CI / coverage (push) Failing after 0s
CI / e2e (push) Failing after 0s
Docker / build-and-push (push) Failing after 1s
CI / integration (push) Failing after 4m43s
CI / Go Test (windows-latest) (push) Has been cancelled
CI / Desktop Unit Tests (Windows) (push) Has been cancelled
Desktop Artifacts / Desktop Build (Linux (arm64)) (push) Has been cancelled
Desktop Artifacts / Desktop Build (Linux) (push) Has been cancelled
Desktop Artifacts / Desktop Build (Windows) (push) Has been cancelled
Desktop Artifacts (macOS) / Desktop Build (macOS (aarch64)) (push) Has been cancelled
Desktop Artifacts (macOS) / Desktop Build (macOS (x86_64)) (push) Has been cancelled
75 行
1.6 KiB
JSON
75 行
1.6 KiB
JSON
[
|
|
{
|
|
"name": "prompt quality penalties explain score delta",
|
|
"input": {
|
|
"Outcome": "completed",
|
|
"OutcomeConfidence": "high",
|
|
"Heuristics": {
|
|
"ShortPromptCount": 1,
|
|
"UnstructuredStart": true,
|
|
"MissingSuccessCriteriaCount": 1,
|
|
"MissingVerificationCount": 1,
|
|
"NoCodeContextCount": 1
|
|
}
|
|
},
|
|
"want_baseline_score": 100,
|
|
"want_score": 94,
|
|
"want_delta": -6,
|
|
"want_grade": "A",
|
|
"want_basis": [
|
|
"outcome",
|
|
"prompt_quality",
|
|
"context_quality"
|
|
],
|
|
"want_penalties": {
|
|
"constraintless_first_prompt": 1,
|
|
"missing_success_criteria": 1,
|
|
"code_task_without_context": 4
|
|
}
|
|
},
|
|
{
|
|
"name": "repeated prompts cap low confidence score delta",
|
|
"input": {
|
|
"Outcome": "unknown",
|
|
"OutcomeConfidence": "low",
|
|
"Heuristics": {
|
|
"DuplicatePromptCount": 8
|
|
}
|
|
},
|
|
"want_baseline_score": null,
|
|
"want_score": 100,
|
|
"want_delta": null,
|
|
"want_grade": "A",
|
|
"want_basis": [
|
|
"outcome",
|
|
"prompt_quality"
|
|
],
|
|
"want_penalties": null
|
|
},
|
|
{
|
|
"name": "workflow loop penalty adds workflow basis",
|
|
"input": {
|
|
"Outcome": "completed",
|
|
"OutcomeConfidence": "high",
|
|
"HasToolCalls": true,
|
|
"RetryCount": 2,
|
|
"Heuristics": {
|
|
"RunawayToolLoopCount": 4
|
|
}
|
|
},
|
|
"want_baseline_score": 90,
|
|
"want_score": 85,
|
|
"want_delta": -5,
|
|
"want_grade": "B",
|
|
"want_basis": [
|
|
"outcome",
|
|
"tool_health",
|
|
"workflow_quality"
|
|
],
|
|
"want_penalties": {
|
|
"tool_retries": 10,
|
|
"repeated_failing_tool_cycles": 5
|
|
}
|
|
}
|
|
]
|