yaojingang
330 lines
12 KiB
JSON
330 lines
12 KiB
JSON
{
|
|
"schema_version": "1.0",
|
|
"ok": true,
|
|
"generated_at": "2026-06-15",
|
|
"skill_dir": ".",
|
|
"summary": {
|
|
"review_item_count": 4,
|
|
"accepted_count": 0,
|
|
"awaiting_submission_count": 4,
|
|
"valid_packet_source_incomplete_count": 0,
|
|
"ready_for_ledger_review_count": 0,
|
|
"fix_submission_count": 0,
|
|
"unmatched_submission_count": 0,
|
|
"invalid_submission_count": 0,
|
|
"source_check_count": 13,
|
|
"source_pass_count": 6,
|
|
"source_blocked_count": 7,
|
|
"ready_to_claim_world_class": false,
|
|
"review_counts_submission_as_completion": false,
|
|
"decision": "awaiting-submissions"
|
|
},
|
|
"submissions": {
|
|
"directory": "evidence/world_class/submissions",
|
|
"review_counts_submission_as_completion": false
|
|
},
|
|
"items": [
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"label": "Provider Holdout",
|
|
"category": "external",
|
|
"owner": "operator with provider credentials",
|
|
"ledger_status": "pending",
|
|
"submission_status": "missing",
|
|
"intake_status": "missing",
|
|
"source_accepted": false,
|
|
"review_state": "awaiting-submission",
|
|
"blocking_reason": "No evidence packet has been submitted for review.",
|
|
"submission_path": "evidence/world_class/submissions/provider-holdout.json",
|
|
"submitted_by": "",
|
|
"submitted_at": "",
|
|
"artifact_ref_count": 0,
|
|
"intake_errors": [],
|
|
"observed_state": {
|
|
"model_executed_count": 0,
|
|
"timing_observed_count": 10,
|
|
"token_observed_count": 0,
|
|
"accepted": false
|
|
},
|
|
"source_checklist": [
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"label": "Provider model run",
|
|
"field": "model_executed_count",
|
|
"expected": ">0",
|
|
"actual": 0,
|
|
"status": "blocked",
|
|
"source_accepted": false,
|
|
"next_action": "Run provider-backed output-exec with real credentials."
|
|
},
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"label": "Timing observed",
|
|
"field": "timing_observed_count",
|
|
"expected": ">0",
|
|
"actual": 10,
|
|
"status": "pass",
|
|
"source_accepted": false,
|
|
"next_action": "Provider execution should record timing metadata."
|
|
},
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"label": "Token usage observed",
|
|
"field": "token_observed_count",
|
|
"expected": ">0",
|
|
"actual": 0,
|
|
"status": "blocked",
|
|
"source_accepted": false,
|
|
"next_action": "Provider execution should return non-estimated token usage."
|
|
}
|
|
],
|
|
"source_check_count": 3,
|
|
"source_pass_count": 1,
|
|
"source_blocked_count": 2,
|
|
"success_checks": [
|
|
"reports/output_execution_runs.json summary.model_executed_count > 0",
|
|
"reports/output_execution_runs.json summary.timing_observed_count > 0",
|
|
"reports/output_execution_runs.json summary.token_observed_count > 0",
|
|
"reports/skill_os2_audit.json item provider-holdout status becomes pass"
|
|
],
|
|
"privacy_contract": [
|
|
"Do not commit provider credentials or environment dumps.",
|
|
"The output execution report records output hashes and aggregate run metadata, not raw provider prompts."
|
|
],
|
|
"next_action": "Run provider-backed holdout cases with real credentials and commit only aggregate evidence."
|
|
},
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"label": "Human Adjudication",
|
|
"category": "human",
|
|
"owner": "human reviewer",
|
|
"ledger_status": "pending",
|
|
"submission_status": "missing",
|
|
"intake_status": "missing",
|
|
"source_accepted": false,
|
|
"review_state": "awaiting-submission",
|
|
"blocking_reason": "No evidence packet has been submitted for review.",
|
|
"submission_path": "evidence/world_class/submissions/human-adjudication.json",
|
|
"submitted_by": "",
|
|
"submitted_at": "",
|
|
"artifact_ref_count": 0,
|
|
"intake_errors": [],
|
|
"observed_state": {
|
|
"pair_count": 5,
|
|
"judgment_count": 0,
|
|
"pending_count": 5,
|
|
"invalid_decision_count": 0,
|
|
"answer_revealed_count": 0,
|
|
"accepted": false
|
|
},
|
|
"source_checklist": [
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"label": "Review pairs exist",
|
|
"field": "pair_count",
|
|
"expected": ">0",
|
|
"actual": 5,
|
|
"status": "pass",
|
|
"source_accepted": false,
|
|
"next_action": "Generate the blind A/B review pack."
|
|
},
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"label": "No pending decisions",
|
|
"field": "pending_count",
|
|
"expected": "==0",
|
|
"actual": 5,
|
|
"status": "blocked",
|
|
"source_accepted": false,
|
|
"next_action": "Record a reviewer choice for every pair."
|
|
},
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"label": "Judgments complete",
|
|
"field": "judgment_count",
|
|
"expected": "==pair_count",
|
|
"actual": 0,
|
|
"status": "blocked",
|
|
"source_accepted": false,
|
|
"next_action": "Every pair needs one valid human judgment."
|
|
},
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"label": "No invalid decisions",
|
|
"field": "invalid_decision_count",
|
|
"expected": "==0",
|
|
"actual": 0,
|
|
"status": "pass",
|
|
"source_accepted": false,
|
|
"next_action": "Fix malformed winner/confidence entries."
|
|
}
|
|
],
|
|
"source_check_count": 4,
|
|
"source_pass_count": 2,
|
|
"source_blocked_count": 2,
|
|
"success_checks": [
|
|
"reports/output_review_adjudication.json summary.pending_count == 0",
|
|
"reports/output_review_adjudication.json summary.judgment_count == summary.pair_count",
|
|
"reports/output_review_adjudication.json summary.invalid_decision_count == 0",
|
|
"reports/skill_os2_audit.json item human-adjudication status becomes pass"
|
|
],
|
|
"privacy_contract": [
|
|
"Reviewer decisions should not include raw user data or private customer detail.",
|
|
"Keep the answer key separate until after decisions are recorded."
|
|
],
|
|
"next_action": "Record real A/B choices in the decision template, then regenerate adjudication."
|
|
},
|
|
{
|
|
"evidence_key": "native-permission-enforcement",
|
|
"label": "Native Permission Enforcement",
|
|
"category": "external",
|
|
"owner": "target client or installer integrator",
|
|
"ledger_status": "pending",
|
|
"submission_status": "missing",
|
|
"intake_status": "missing",
|
|
"source_accepted": false,
|
|
"review_state": "awaiting-submission",
|
|
"blocking_reason": "No evidence packet has been submitted for review.",
|
|
"submission_path": "evidence/world_class/submissions/native-permission-enforcement.json",
|
|
"submitted_by": "",
|
|
"submitted_at": "",
|
|
"artifact_ref_count": 0,
|
|
"intake_errors": [],
|
|
"observed_state": {
|
|
"native_enforcement_count": 0,
|
|
"metadata_fallback_count": 4,
|
|
"installer_enforcement_pass_count": 4,
|
|
"installer_permission_failure_count": 0,
|
|
"installer_enforcement_ready": true,
|
|
"residual_risk_count": 4,
|
|
"failure_count": 0,
|
|
"accepted": false
|
|
},
|
|
"source_checklist": [
|
|
{
|
|
"evidence_key": "native-permission-enforcement",
|
|
"label": "Native enforcement",
|
|
"field": "native_enforcement_count",
|
|
"expected": ">0",
|
|
"actual": 0,
|
|
"status": "blocked",
|
|
"source_accepted": false,
|
|
"next_action": "Collect real target-client or external runtime guard proof."
|
|
},
|
|
{
|
|
"evidence_key": "native-permission-enforcement",
|
|
"label": "Probe failures",
|
|
"field": "failure_count",
|
|
"expected": "==0",
|
|
"actual": 0,
|
|
"status": "pass",
|
|
"source_accepted": false,
|
|
"next_action": "Runtime permission probes must stay clean."
|
|
},
|
|
{
|
|
"evidence_key": "native-permission-enforcement",
|
|
"label": "Installer support",
|
|
"field": "installer_enforcement_ready",
|
|
"expected": "true",
|
|
"actual": true,
|
|
"status": "pass",
|
|
"source_accepted": false,
|
|
"next_action": "Installer enforcement is supporting evidence, not native proof."
|
|
}
|
|
],
|
|
"source_check_count": 3,
|
|
"source_pass_count": 2,
|
|
"source_blocked_count": 1,
|
|
"success_checks": [
|
|
"reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
|
|
"reports/runtime_permission_probes.json summary.failure_count == 0",
|
|
"reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence",
|
|
"reports/skill_os2_audit.json item native-permission-enforcement status becomes pass"
|
|
],
|
|
"privacy_contract": [
|
|
"Do not mark native_enforcement true for metadata-only fallbacks.",
|
|
"Keep residual risks visible for targets that still rely on operator enforcement."
|
|
],
|
|
"next_action": "Integrate a real target-client or external installer runtime guard before claiming native permission enforcement."
|
|
},
|
|
{
|
|
"evidence_key": "native-client-telemetry",
|
|
"label": "Native Client Telemetry",
|
|
"category": "external",
|
|
"owner": "Browser/Chrome/IDE/provider client integrator",
|
|
"ledger_status": "pending",
|
|
"submission_status": "missing",
|
|
"intake_status": "missing",
|
|
"source_accepted": false,
|
|
"review_state": "awaiting-submission",
|
|
"blocking_reason": "No evidence packet has been submitted for review.",
|
|
"submission_path": "evidence/world_class/submissions/native-client-telemetry.json",
|
|
"submitted_by": "",
|
|
"submitted_at": "",
|
|
"artifact_ref_count": 0,
|
|
"intake_errors": [],
|
|
"observed_state": {
|
|
"external_source_events": 0,
|
|
"adoption_sample_count": 0,
|
|
"raw_content_allowed": false,
|
|
"risk_band": "low",
|
|
"accepted": false
|
|
},
|
|
"source_checklist": [
|
|
{
|
|
"evidence_key": "native-client-telemetry",
|
|
"label": "External events",
|
|
"field": "external_source_events",
|
|
"expected": ">0",
|
|
"actual": 0,
|
|
"status": "blocked",
|
|
"source_accepted": false,
|
|
"next_action": "Import at least one metadata-only event from a real client."
|
|
},
|
|
{
|
|
"evidence_key": "native-client-telemetry",
|
|
"label": "Adoption sample",
|
|
"field": "adoption_sample_count",
|
|
"expected": ">0",
|
|
"actual": 0,
|
|
"status": "blocked",
|
|
"source_accepted": false,
|
|
"next_action": "Telemetry must include adoption outcome evidence."
|
|
},
|
|
{
|
|
"evidence_key": "native-client-telemetry",
|
|
"label": "Raw content blocked",
|
|
"field": "raw_content_allowed",
|
|
"expected": "false",
|
|
"actual": false,
|
|
"status": "pass",
|
|
"source_accepted": false,
|
|
"next_action": "Telemetry must stay metadata-only."
|
|
}
|
|
],
|
|
"source_check_count": 3,
|
|
"source_pass_count": 1,
|
|
"source_blocked_count": 2,
|
|
"success_checks": [
|
|
"reports/adoption_drift_report.json summary.source_types.external > 0",
|
|
"reports/adoption_drift_report.json summary.adoption_sample_count > 0",
|
|
"reports/skill_os2_audit.json item native-client-telemetry status becomes pass"
|
|
],
|
|
"privacy_contract": [
|
|
"Telemetry must remain metadata-only and local-first.",
|
|
"Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field."
|
|
],
|
|
"next_action": "Install a real client against the native host and import production metadata-only events."
|
|
}
|
|
],
|
|
"unmatched_submissions": [],
|
|
"source_reports": {
|
|
"ledger": "reports/world_class_evidence_ledger.json",
|
|
"intake": "reports/world_class_evidence_intake.json"
|
|
},
|
|
"artifacts": {
|
|
"json": "reports/world_class_submission_review.json",
|
|
"markdown": "reports/world_class_submission_review.md"
|
|
}
|
|
}
|