mirror of
https://github.com/magnus919/agent-skills.git
synced 2026-09-11 19:47:12 +03:00
9d6bddad61
* test(evals): scope claims to harness model fixtures and revision Append the neckbeard claims-scoping sentence to one representative expected_output per per-skill manifest so every corpus member states VAL-EVL-032 scope (harness, model, fixtures, revision under test). Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> * test(product-lifecycle): upgrade integrated launch trajectory Add an explicit launch-decision assertion to the new-product lifecycle case so the integrated product-launch scenario terminates in a launch decision recorded as a lifecycle evidence-ledger entry (VAL-CRP-010), and scope its expected_output claims per VAL-EVL-032. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> * test(production-excellence): add integrated migration reconciliation failure case Add integrated-migration-reconciliation-failure: the production-excellence gate model returns No-go on a reconciliation mismatch, records the failure evidence, produces a rollback/roll-forward decision with an accountable owner, and does not proceed to launch (VAL-CRP-012). Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> * test(agent-production-operations): add privacy boundary escalation case Add integrated-privacy-boundary-escalation (VAL-CRP-015): the runtime control plan halts a cross-boundary EU PII trace export before any data processing, names the privacy boundary, and escalates to jurisdiction- specific legal review and a human operator. Also add a tool-authority- health handoff assertion to the read-only contract case (VAL-CRP-016). Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> * test(lifecycle-evals): add lifecycle evaluation corpus Add the #204 corpus home: run tooling (run-corpus.sh, fake adapter only), programmatic coverage validator (validate-corpus-coverage.py), machine- readable coverage index + human-readable coverage matrix, regression- detection and fixture/source notes, the bounded discovery brief, and a one-snapshot committed set of fake-adapter per-trial run artifacts with harness/model/date scoping fields. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> --------- Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
50 lines
1.3 KiB
JSON
50 lines
1.3 KiB
JSON
{
|
|
"schema_version": 1,
|
|
"trial_id": "54841341-e39b-47ab-9ff7-cbb874e7a615",
|
|
"candidate": {
|
|
"skill_name": "conditional-customer-success",
|
|
"skill_path": "conditional-customer-success",
|
|
"tree_hash": "39ede540f58ad8d0"
|
|
},
|
|
"case": {
|
|
"case_id": "b2b-subscription-success-plan-and-health",
|
|
"prompt_hash": "f463d713ae1a79c6",
|
|
"fixture_hashes": {}
|
|
},
|
|
"adapter": {
|
|
"name": "fake",
|
|
"version": "0.1.0"
|
|
},
|
|
"harness": {
|
|
"name": "fake",
|
|
"version": "0.1.0"
|
|
},
|
|
"model": {
|
|
"provider": "unspecified",
|
|
"model_id": "unspecified"
|
|
},
|
|
"permissions": {},
|
|
"network_policy": "unspecified",
|
|
"limits": {
|
|
"timeout_seconds": 120,
|
|
"network_policy": "unspecified"
|
|
},
|
|
"cache_state": "unspecified",
|
|
"started_at": "2026-08-03T00:03:33.713706+00:00",
|
|
"finished_at": "2026-08-03T00:03:33.713870+00:00",
|
|
"status": "completed",
|
|
"outputs": {
|
|
"response": "[fake] Processed case 'b2b-subscription-success-plan-and-health': I manage customer success for a B2B SaaS platform with 200 accounts, named accou",
|
|
"activation_evidence": "skill loaded from conditional-customer-success/SKILL.md",
|
|
"artifact_digests": {},
|
|
"tool_event_count": 8
|
|
},
|
|
"duration_ms": 0.011791998986154795,
|
|
"token_usage": {
|
|
"input_tokens": 100,
|
|
"output_tokens": 50
|
|
},
|
|
"failures": [],
|
|
"missing_evidence": []
|
|
}
|