yaojingang
962 lines
40 KiB
JSON
962 lines
40 KiB
JSON
{
|
|
"schema_version": "1.0",
|
|
"ok": true,
|
|
"generated_at": "2026-06-17",
|
|
"skill_dir": ".",
|
|
"summary": {
|
|
"evidence_item_count": 4,
|
|
"precheck_count": 14,
|
|
"precheck_pass_count": 9,
|
|
"precheck_missing_count": 1,
|
|
"precheck_optional_count": 1,
|
|
"precheck_human_required_count": 1,
|
|
"precheck_external_required_count": 2,
|
|
"collection_ready_count": 1,
|
|
"collection_blocked_count": 3,
|
|
"source_check_count": 13,
|
|
"source_pass_count": 6,
|
|
"source_blocked_count": 7,
|
|
"pending_count": 4,
|
|
"ready_to_claim_world_class": false,
|
|
"credential_value_exposed": false,
|
|
"preflight_counts_as_evidence": false,
|
|
"decision": "collection-preflight-blocked"
|
|
},
|
|
"status_counts": {
|
|
"blocked": 3,
|
|
"ready-for-human-review": 1
|
|
},
|
|
"precheck_status_counts": {
|
|
"pass": 9,
|
|
"missing": 1,
|
|
"optional": 1,
|
|
"human-required": 1,
|
|
"external-required": 2
|
|
},
|
|
"items": [
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"label": "Provider Holdout",
|
|
"category": "external",
|
|
"owner": "operator with provider credentials",
|
|
"status": "blocked",
|
|
"ledger_status": "pending",
|
|
"intake_readiness": "awaiting-submission",
|
|
"review_state": "awaiting-submission",
|
|
"source_accepted": false,
|
|
"prechecks": [
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"key": "output-cases",
|
|
"label": "Output eval cases",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Keep output holdout cases available before provider execution.",
|
|
"secret_value_redacted": false,
|
|
"path": "evals/output/cases.jsonl",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"key": "provider-runner",
|
|
"label": "Provider runner",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Use the provider runner instead of the local command runner for model-backed evidence.",
|
|
"secret_value_redacted": false,
|
|
"path": "scripts/provider_output_eval_runner.py",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"key": "openai-api-key",
|
|
"label": "Provider credential",
|
|
"kind": "env",
|
|
"required": true,
|
|
"next_action": "Set OPENAI_API_KEY in the operator shell; never commit or print the value.",
|
|
"secret_value_redacted": true,
|
|
"env": "OPENAI_API_KEY",
|
|
"status": "missing",
|
|
"actual": "not-set",
|
|
"default": ""
|
|
},
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"key": "provider-model",
|
|
"label": "Provider model",
|
|
"kind": "env",
|
|
"required": false,
|
|
"next_action": "Optionally set YAO_OUTPUT_EVAL_MODEL; the runbook defaults to gpt-4.1-mini.",
|
|
"secret_value_redacted": false,
|
|
"env": "YAO_OUTPUT_EVAL_MODEL",
|
|
"status": "optional",
|
|
"actual": "not-set",
|
|
"default": "gpt-4.1-mini"
|
|
}
|
|
],
|
|
"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."
|
|
}
|
|
],
|
|
"next_action": "Set OPENAI_API_KEY in the operator shell; never commit or print the value.",
|
|
"submission_path": "evidence/world_class/submissions/provider-holdout.json",
|
|
"template_path": "evidence/world_class/templates/provider-holdout.intake.json",
|
|
"commands": {
|
|
"prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions",
|
|
"prepare_prefilled_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions --prefill-artifacts",
|
|
"validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
|
|
"submission_review": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
|
|
"refresh_ledger": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
|
|
"guard_claim": "python3 scripts/yao.py world-class-claim-guard ."
|
|
},
|
|
"submission_kit": {
|
|
"prepare_command": "python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions",
|
|
"prefill_command": "python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions --prefill-artifacts",
|
|
"output_dir": "evidence/world_class/submissions",
|
|
"draft_path": "evidence/world_class/submissions/provider-holdout.json",
|
|
"template_path": "evidence/world_class/templates/provider-holdout.intake.json",
|
|
"artifact_role_contract": {
|
|
"schema_version": "1.0",
|
|
"role_source": "world-class-submission-kit",
|
|
"counts_as_evidence": false,
|
|
"artifact_prefill_counts_as_evidence": false,
|
|
"submission_ref_total_count": 1,
|
|
"submission_ref_ready_count": 1,
|
|
"supporting_evidence_total_count": 6,
|
|
"supporting_evidence_ready_count": 6,
|
|
"roles": [
|
|
{
|
|
"role": "submission-ref",
|
|
"label": "Submission refs",
|
|
"copy_to_artifact_refs": true,
|
|
"description": "Rows marked submission-ref are the aggregate paths expected in artifact_refs."
|
|
},
|
|
{
|
|
"role": "supporting-evidence",
|
|
"label": "Supporting evidence",
|
|
"copy_to_artifact_refs": false,
|
|
"description": "Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs."
|
|
}
|
|
]
|
|
},
|
|
"drafts_count_as_evidence": false,
|
|
"artifact_prefill_counts_as_evidence": false
|
|
},
|
|
"runbook": [
|
|
"Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.",
|
|
"export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}",
|
|
"python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
]
|
|
},
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"label": "Human Adjudication",
|
|
"category": "human",
|
|
"owner": "human reviewer",
|
|
"status": "ready-for-human-review",
|
|
"ledger_status": "pending",
|
|
"intake_readiness": "awaiting-submission",
|
|
"review_state": "awaiting-submission",
|
|
"source_accepted": false,
|
|
"prechecks": [
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"key": "review-kit",
|
|
"label": "Blind review kit",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Open the blind review kit and record real reviewer choices.",
|
|
"secret_value_redacted": false,
|
|
"path": "reports/output_review_kit.html",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"key": "decision-template",
|
|
"label": "Decision template",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Import real A/B decisions with `python3 scripts/yao.py output-review-import --input <reviewer-decisions.json> --run-adjudication`.",
|
|
"secret_value_redacted": false,
|
|
"path": "reports/output_review_decisions.json",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"key": "decision-importer",
|
|
"label": "Decision importer",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Use the importer to reject raw content fields and normalize reviewer decisions before adjudication.",
|
|
"secret_value_redacted": false,
|
|
"path": "scripts/import_output_review_decisions.py",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"key": "human-reviewer",
|
|
"label": "Human reviewer",
|
|
"kind": "human",
|
|
"required": true,
|
|
"next_action": "Assign a real reviewer identity before claiming human adjudication.",
|
|
"secret_value_redacted": false,
|
|
"status": "human-required",
|
|
"actual": "external-human-action"
|
|
}
|
|
],
|
|
"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."
|
|
}
|
|
],
|
|
"next_action": "Assign a real reviewer identity before claiming human adjudication.",
|
|
"submission_path": "evidence/world_class/submissions/human-adjudication.json",
|
|
"template_path": "evidence/world_class/templates/human-adjudication.intake.json",
|
|
"commands": {
|
|
"prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions",
|
|
"prepare_prefilled_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions --prefill-artifacts",
|
|
"validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
|
|
"submission_review": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
|
|
"refresh_ledger": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
|
|
"guard_claim": "python3 scripts/yao.py world-class-claim-guard ."
|
|
},
|
|
"submission_kit": {
|
|
"prepare_command": "python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions",
|
|
"prefill_command": "python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions --prefill-artifacts",
|
|
"output_dir": "evidence/world_class/submissions",
|
|
"draft_path": "evidence/world_class/submissions/human-adjudication.json",
|
|
"template_path": "evidence/world_class/templates/human-adjudication.intake.json",
|
|
"artifact_role_contract": {
|
|
"schema_version": "1.0",
|
|
"role_source": "world-class-submission-kit",
|
|
"counts_as_evidence": false,
|
|
"artifact_prefill_counts_as_evidence": false,
|
|
"submission_ref_total_count": 2,
|
|
"submission_ref_ready_count": 2,
|
|
"supporting_evidence_total_count": 8,
|
|
"supporting_evidence_ready_count": 8,
|
|
"roles": [
|
|
{
|
|
"role": "submission-ref",
|
|
"label": "Submission refs",
|
|
"copy_to_artifact_refs": true,
|
|
"description": "Rows marked submission-ref are the aggregate paths expected in artifact_refs."
|
|
},
|
|
{
|
|
"role": "supporting-evidence",
|
|
"label": "Supporting evidence",
|
|
"copy_to_artifact_refs": false,
|
|
"description": "Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs."
|
|
}
|
|
]
|
|
},
|
|
"drafts_count_as_evidence": false,
|
|
"artifact_prefill_counts_as_evidence": false
|
|
},
|
|
"runbook": [
|
|
"python3 scripts/yao.py output-review-kit --write-template",
|
|
"Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.",
|
|
"python3 scripts/adjudicate_output_review.py --write-template",
|
|
"Record reviewer choices in a separate JSON, JSONL, or CSV decision source with case_id, winner_variant, confidence, and reason only.",
|
|
"python3 scripts/yao.py output-review-import --input <reviewer-decisions.json> --run-adjudication",
|
|
"python3 scripts/yao.py output-review",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
]
|
|
},
|
|
{
|
|
"evidence_key": "native-permission-enforcement",
|
|
"label": "Native Permission Enforcement",
|
|
"category": "external",
|
|
"owner": "target client or installer integrator",
|
|
"status": "blocked",
|
|
"ledger_status": "pending",
|
|
"intake_readiness": "awaiting-submission",
|
|
"review_state": "awaiting-submission",
|
|
"source_accepted": false,
|
|
"prechecks": [
|
|
{
|
|
"evidence_key": "native-permission-enforcement",
|
|
"key": "permission-policy",
|
|
"label": "Permission policy",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Keep approved high-permission capabilities explicit.",
|
|
"secret_value_redacted": false,
|
|
"path": "security/permission_policy.json",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "native-permission-enforcement",
|
|
"key": "permission-probes",
|
|
"label": "Runtime probes",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Refresh runtime permission probes after packaging changes.",
|
|
"secret_value_redacted": false,
|
|
"path": "reports/runtime_permission_probes.json",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "native-permission-enforcement",
|
|
"key": "native-guard",
|
|
"label": "Native guard",
|
|
"kind": "external",
|
|
"required": true,
|
|
"next_action": "Attach a real target-client or external installer runtime guard; metadata fallback is not enough.",
|
|
"secret_value_redacted": false,
|
|
"status": "external-required",
|
|
"actual": "external-integration-required"
|
|
}
|
|
],
|
|
"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."
|
|
}
|
|
],
|
|
"next_action": "Attach a real target-client or external installer runtime guard; metadata fallback is not enough.",
|
|
"submission_path": "evidence/world_class/submissions/native-permission-enforcement.json",
|
|
"template_path": "evidence/world_class/templates/native-permission-enforcement.intake.json",
|
|
"commands": {
|
|
"prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions",
|
|
"prepare_prefilled_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions --prefill-artifacts",
|
|
"validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
|
|
"submission_review": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
|
|
"refresh_ledger": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
|
|
"guard_claim": "python3 scripts/yao.py world-class-claim-guard ."
|
|
},
|
|
"submission_kit": {
|
|
"prepare_command": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions",
|
|
"prefill_command": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions --prefill-artifacts",
|
|
"output_dir": "evidence/world_class/submissions",
|
|
"draft_path": "evidence/world_class/submissions/native-permission-enforcement.json",
|
|
"template_path": "evidence/world_class/templates/native-permission-enforcement.intake.json",
|
|
"artifact_role_contract": {
|
|
"schema_version": "1.0",
|
|
"role_source": "world-class-submission-kit",
|
|
"counts_as_evidence": false,
|
|
"artifact_prefill_counts_as_evidence": false,
|
|
"submission_ref_total_count": 2,
|
|
"submission_ref_ready_count": 2,
|
|
"supporting_evidence_total_count": 11,
|
|
"supporting_evidence_ready_count": 11,
|
|
"roles": [
|
|
{
|
|
"role": "submission-ref",
|
|
"label": "Submission refs",
|
|
"copy_to_artifact_refs": true,
|
|
"description": "Rows marked submission-ref are the aggregate paths expected in artifact_refs."
|
|
},
|
|
{
|
|
"role": "supporting-evidence",
|
|
"label": "Supporting evidence",
|
|
"copy_to_artifact_refs": false,
|
|
"description": "Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs."
|
|
}
|
|
]
|
|
},
|
|
"drafts_count_as_evidence": false,
|
|
"artifact_prefill_counts_as_evidence": false
|
|
},
|
|
"runbook": [
|
|
"Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.",
|
|
"Update the generated target adapter only when the guard is actually enforced by that target.",
|
|
"python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip",
|
|
"python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation",
|
|
"python3 scripts/yao.py runtime-permissions . --package-dir dist",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
]
|
|
},
|
|
{
|
|
"evidence_key": "native-client-telemetry",
|
|
"label": "Native Client Telemetry",
|
|
"category": "external",
|
|
"owner": "Browser/Chrome/IDE/provider client integrator",
|
|
"status": "blocked",
|
|
"ledger_status": "pending",
|
|
"intake_readiness": "awaiting-submission",
|
|
"review_state": "awaiting-submission",
|
|
"source_accepted": false,
|
|
"prechecks": [
|
|
{
|
|
"evidence_key": "native-client-telemetry",
|
|
"key": "native-host",
|
|
"label": "Native telemetry host",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Use the native host to receive metadata-only client events.",
|
|
"secret_value_redacted": false,
|
|
"path": "scripts/telemetry_native_host.py",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "native-client-telemetry",
|
|
"key": "hook-recipes",
|
|
"label": "Hook recipes",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Refresh telemetry hook recipes before external client installation.",
|
|
"secret_value_redacted": false,
|
|
"path": "reports/telemetry_hook_recipes.json",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "native-client-telemetry",
|
|
"key": "external-client",
|
|
"label": "External client",
|
|
"kind": "external",
|
|
"required": true,
|
|
"next_action": "Install a real Browser, Chrome, IDE, or provider client that emits metadata-only events.",
|
|
"secret_value_redacted": false,
|
|
"status": "external-required",
|
|
"actual": "external-integration-required"
|
|
}
|
|
],
|
|
"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."
|
|
}
|
|
],
|
|
"next_action": "Install a real Browser, Chrome, IDE, or provider client that emits metadata-only events.",
|
|
"submission_path": "evidence/world_class/submissions/native-client-telemetry.json",
|
|
"template_path": "evidence/world_class/templates/native-client-telemetry.intake.json",
|
|
"commands": {
|
|
"prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions",
|
|
"prepare_prefilled_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions --prefill-artifacts",
|
|
"validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
|
|
"submission_review": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
|
|
"refresh_ledger": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
|
|
"guard_claim": "python3 scripts/yao.py world-class-claim-guard ."
|
|
},
|
|
"submission_kit": {
|
|
"prepare_command": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions",
|
|
"prefill_command": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions --prefill-artifacts",
|
|
"output_dir": "evidence/world_class/submissions",
|
|
"draft_path": "evidence/world_class/submissions/native-client-telemetry.json",
|
|
"template_path": "evidence/world_class/templates/native-client-telemetry.intake.json",
|
|
"artifact_role_contract": {
|
|
"schema_version": "1.0",
|
|
"role_source": "world-class-submission-kit",
|
|
"counts_as_evidence": false,
|
|
"artifact_prefill_counts_as_evidence": false,
|
|
"submission_ref_total_count": 2,
|
|
"submission_ref_ready_count": 2,
|
|
"supporting_evidence_total_count": 6,
|
|
"supporting_evidence_ready_count": 6,
|
|
"roles": [
|
|
{
|
|
"role": "submission-ref",
|
|
"label": "Submission refs",
|
|
"copy_to_artifact_refs": true,
|
|
"description": "Rows marked submission-ref are the aggregate paths expected in artifact_refs."
|
|
},
|
|
{
|
|
"role": "supporting-evidence",
|
|
"label": "Supporting evidence",
|
|
"copy_to_artifact_refs": false,
|
|
"description": "Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs."
|
|
}
|
|
]
|
|
},
|
|
"drafts_count_as_evidence": false,
|
|
"artifact_prefill_counts_as_evidence": false
|
|
},
|
|
"runbook": [
|
|
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
|
|
"Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
|
|
"python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl",
|
|
"python3 scripts/yao.py skill-atlas --workspace-root .",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
]
|
|
}
|
|
],
|
|
"prechecks": [
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"key": "output-cases",
|
|
"label": "Output eval cases",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Keep output holdout cases available before provider execution.",
|
|
"secret_value_redacted": false,
|
|
"path": "evals/output/cases.jsonl",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"key": "provider-runner",
|
|
"label": "Provider runner",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Use the provider runner instead of the local command runner for model-backed evidence.",
|
|
"secret_value_redacted": false,
|
|
"path": "scripts/provider_output_eval_runner.py",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"key": "openai-api-key",
|
|
"label": "Provider credential",
|
|
"kind": "env",
|
|
"required": true,
|
|
"next_action": "Set OPENAI_API_KEY in the operator shell; never commit or print the value.",
|
|
"secret_value_redacted": true,
|
|
"env": "OPENAI_API_KEY",
|
|
"status": "missing",
|
|
"actual": "not-set",
|
|
"default": ""
|
|
},
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"key": "provider-model",
|
|
"label": "Provider model",
|
|
"kind": "env",
|
|
"required": false,
|
|
"next_action": "Optionally set YAO_OUTPUT_EVAL_MODEL; the runbook defaults to gpt-4.1-mini.",
|
|
"secret_value_redacted": false,
|
|
"env": "YAO_OUTPUT_EVAL_MODEL",
|
|
"status": "optional",
|
|
"actual": "not-set",
|
|
"default": "gpt-4.1-mini"
|
|
},
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"key": "review-kit",
|
|
"label": "Blind review kit",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Open the blind review kit and record real reviewer choices.",
|
|
"secret_value_redacted": false,
|
|
"path": "reports/output_review_kit.html",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"key": "decision-template",
|
|
"label": "Decision template",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Import real A/B decisions with `python3 scripts/yao.py output-review-import --input <reviewer-decisions.json> --run-adjudication`.",
|
|
"secret_value_redacted": false,
|
|
"path": "reports/output_review_decisions.json",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"key": "decision-importer",
|
|
"label": "Decision importer",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Use the importer to reject raw content fields and normalize reviewer decisions before adjudication.",
|
|
"secret_value_redacted": false,
|
|
"path": "scripts/import_output_review_decisions.py",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"key": "human-reviewer",
|
|
"label": "Human reviewer",
|
|
"kind": "human",
|
|
"required": true,
|
|
"next_action": "Assign a real reviewer identity before claiming human adjudication.",
|
|
"secret_value_redacted": false,
|
|
"status": "human-required",
|
|
"actual": "external-human-action"
|
|
},
|
|
{
|
|
"evidence_key": "native-permission-enforcement",
|
|
"key": "permission-policy",
|
|
"label": "Permission policy",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Keep approved high-permission capabilities explicit.",
|
|
"secret_value_redacted": false,
|
|
"path": "security/permission_policy.json",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "native-permission-enforcement",
|
|
"key": "permission-probes",
|
|
"label": "Runtime probes",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Refresh runtime permission probes after packaging changes.",
|
|
"secret_value_redacted": false,
|
|
"path": "reports/runtime_permission_probes.json",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "native-permission-enforcement",
|
|
"key": "native-guard",
|
|
"label": "Native guard",
|
|
"kind": "external",
|
|
"required": true,
|
|
"next_action": "Attach a real target-client or external installer runtime guard; metadata fallback is not enough.",
|
|
"secret_value_redacted": false,
|
|
"status": "external-required",
|
|
"actual": "external-integration-required"
|
|
},
|
|
{
|
|
"evidence_key": "native-client-telemetry",
|
|
"key": "native-host",
|
|
"label": "Native telemetry host",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Use the native host to receive metadata-only client events.",
|
|
"secret_value_redacted": false,
|
|
"path": "scripts/telemetry_native_host.py",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "native-client-telemetry",
|
|
"key": "hook-recipes",
|
|
"label": "Hook recipes",
|
|
"kind": "file",
|
|
"required": true,
|
|
"next_action": "Refresh telemetry hook recipes before external client installation.",
|
|
"secret_value_redacted": false,
|
|
"path": "reports/telemetry_hook_recipes.json",
|
|
"status": "pass",
|
|
"actual": "present"
|
|
},
|
|
{
|
|
"evidence_key": "native-client-telemetry",
|
|
"key": "external-client",
|
|
"label": "External client",
|
|
"kind": "external",
|
|
"required": true,
|
|
"next_action": "Install a real Browser, Chrome, IDE, or provider client that emits metadata-only events.",
|
|
"secret_value_redacted": false,
|
|
"status": "external-required",
|
|
"actual": "external-integration-required"
|
|
}
|
|
],
|
|
"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."
|
|
},
|
|
{
|
|
"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."
|
|
},
|
|
{
|
|
"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."
|
|
},
|
|
{
|
|
"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."
|
|
}
|
|
],
|
|
"submissions": {
|
|
"directory": "evidence/world_class/submissions",
|
|
"commands": {
|
|
"prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --output-dir evidence/world_class/submissions",
|
|
"prepare_prefilled_submission": "python3 scripts/yao.py world-class-submission-kit . --output-dir evidence/world_class/submissions --prefill-artifacts",
|
|
"validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
|
|
"submission_review": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
|
|
"refresh_ledger": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
|
|
"guard_claim": "python3 scripts/yao.py world-class-claim-guard ."
|
|
},
|
|
"submission_kit_command": "python3 scripts/yao.py world-class-submission-kit . --output-dir evidence/world_class/submissions",
|
|
"submission_kit_prefill_command": "python3 scripts/yao.py world-class-submission-kit . --output-dir evidence/world_class/submissions --prefill-artifacts",
|
|
"preflight_counts_submission_as_completion": false,
|
|
"drafts_count_as_evidence": false,
|
|
"artifact_prefill_counts_as_evidence": false,
|
|
"artifact_role_contract": {
|
|
"schema_version": "1.0",
|
|
"role_source": "world-class-submission-kit",
|
|
"counts_as_evidence": false,
|
|
"artifact_prefill_counts_as_evidence": false,
|
|
"submission_ref_total_count": 7,
|
|
"submission_ref_ready_count": 7,
|
|
"supporting_evidence_total_count": 31,
|
|
"supporting_evidence_ready_count": 31,
|
|
"roles": [
|
|
{
|
|
"role": "submission-ref",
|
|
"label": "Submission refs",
|
|
"copy_to_artifact_refs": true,
|
|
"description": "Rows marked submission-ref are the aggregate paths expected in artifact_refs."
|
|
},
|
|
{
|
|
"role": "supporting-evidence",
|
|
"label": "Supporting evidence",
|
|
"copy_to_artifact_refs": false,
|
|
"description": "Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs."
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"source_reports": {
|
|
"ledger": "reports/world_class_evidence_ledger.json",
|
|
"intake": "reports/world_class_evidence_intake.json",
|
|
"submission_review": "reports/world_class_submission_review.json",
|
|
"operator_runbook": "reports/world_class_operator_runbook.json"
|
|
},
|
|
"artifacts": {
|
|
"json": "reports/world_class_evidence_preflight.json",
|
|
"markdown": "reports/world_class_evidence_preflight.md",
|
|
"html": "reports/world_class_evidence_preflight.html"
|
|
}
|
|
}
|