yaojingang
515 lines
24 KiB
JSON
515 lines
24 KiB
JSON
{
|
|
"schema_version": "1.0",
|
|
"ok": true,
|
|
"generated_at": "2026-06-16",
|
|
"skill_dir": ".",
|
|
"summary": {
|
|
"evidence_item_count": 4,
|
|
"pending_count": 4,
|
|
"accepted_count": 0,
|
|
"awaiting_submission_count": 4,
|
|
"ready_for_ledger_review_count": 0,
|
|
"valid_packet_source_incomplete_count": 0,
|
|
"invalid_submission_count": 0,
|
|
"source_check_count": 13,
|
|
"source_pass_count": 6,
|
|
"source_blocked_count": 7,
|
|
"ready_to_claim_world_class": false,
|
|
"runbook_counts_as_completion": false,
|
|
"decision": "collect-evidence"
|
|
},
|
|
"submissions": {
|
|
"directory": "evidence/world_class/submissions",
|
|
"runbook_counts_submission_as_completion": false
|
|
},
|
|
"items": [
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"label": "Provider Holdout",
|
|
"category": "external",
|
|
"owner": "operator with provider credentials",
|
|
"ledger_status": "pending",
|
|
"intake_readiness": "awaiting-submission",
|
|
"review_state": "awaiting-submission",
|
|
"source_accepted": false,
|
|
"objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
|
|
"current": "model-executed 0; token-observed 0",
|
|
"execution_runbook": [
|
|
"YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> 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"
|
|
],
|
|
"blocking_reason": "No evidence packet has been submitted for review.",
|
|
"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",
|
|
"validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
|
|
"review_queue": "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 ."
|
|
},
|
|
"must_collect": {
|
|
"provenance_requirements": [
|
|
"provider-backed model run",
|
|
"observed timing",
|
|
"observed token metadata"
|
|
],
|
|
"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."
|
|
]
|
|
},
|
|
"evidence_artifacts": [
|
|
"reports/output_execution_runs.json",
|
|
"reports/output_execution_runs.md",
|
|
"reports/skill_os2_audit.json",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/provider-holdout.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"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."
|
|
}
|
|
],
|
|
"blocked_source_check_count": 2,
|
|
"next_source_actions": [
|
|
"Run provider-backed output-exec with real credentials.",
|
|
"Provider execution should return non-estimated token usage."
|
|
],
|
|
"submission_state": {
|
|
"status": "missing",
|
|
"path": "evidence/world_class/submissions/provider-holdout.json",
|
|
"artifact_ref_count": 0,
|
|
"attested_real_evidence": false,
|
|
"privacy_contract_satisfied": false,
|
|
"ledger_counts_as_completion": false
|
|
},
|
|
"anti_overclaim": {
|
|
"planned_work_counts_as_evidence": false,
|
|
"metadata_fallback_counts_as_native_enforcement": false,
|
|
"pending_review_counts_as_human_decision": false,
|
|
"local_command_runner_counts_as_provider_model": false
|
|
}
|
|
},
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"label": "Human Adjudication",
|
|
"category": "human",
|
|
"owner": "human reviewer",
|
|
"ledger_status": "pending",
|
|
"intake_readiness": "awaiting-submission",
|
|
"review_state": "awaiting-submission",
|
|
"source_accepted": false,
|
|
"objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
|
|
"current": "0/5 decisions; pending 5",
|
|
"execution_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",
|
|
"Edit reports/output_review_decisions.json with winner_variant values and reviewer metadata.",
|
|
"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"
|
|
],
|
|
"blocking_reason": "No evidence packet has been submitted for review.",
|
|
"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",
|
|
"validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
|
|
"review_queue": "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 ."
|
|
},
|
|
"must_collect": {
|
|
"provenance_requirements": [
|
|
"real reviewer identity",
|
|
"blind A/B decisions",
|
|
"answer key unopened until decisions exist"
|
|
],
|
|
"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."
|
|
]
|
|
},
|
|
"evidence_artifacts": [
|
|
"reports/output_blind_review_pack.md",
|
|
"reports/output_review_kit.md",
|
|
"reports/output_review_decisions.json",
|
|
"reports/output_review_adjudication.json",
|
|
"reports/output_review_adjudication.md",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/human-adjudication.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"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."
|
|
}
|
|
],
|
|
"blocked_source_check_count": 2,
|
|
"next_source_actions": [
|
|
"Record a reviewer choice for every pair.",
|
|
"Every pair needs one valid human judgment."
|
|
],
|
|
"submission_state": {
|
|
"status": "missing",
|
|
"path": "evidence/world_class/submissions/human-adjudication.json",
|
|
"artifact_ref_count": 0,
|
|
"attested_real_evidence": false,
|
|
"privacy_contract_satisfied": false,
|
|
"ledger_counts_as_completion": false
|
|
},
|
|
"anti_overclaim": {
|
|
"planned_work_counts_as_evidence": false,
|
|
"metadata_fallback_counts_as_native_enforcement": false,
|
|
"pending_review_counts_as_human_decision": false,
|
|
"local_command_runner_counts_as_provider_model": false
|
|
}
|
|
},
|
|
{
|
|
"evidence_key": "native-permission-enforcement",
|
|
"label": "Native Permission Enforcement",
|
|
"category": "external",
|
|
"owner": "target client or installer integrator",
|
|
"ledger_status": "pending",
|
|
"intake_readiness": "awaiting-submission",
|
|
"review_state": "awaiting-submission",
|
|
"source_accepted": false,
|
|
"objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
|
|
"current": "native-enforced targets 0; installer-enforced targets 4",
|
|
"execution_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"
|
|
],
|
|
"blocking_reason": "No evidence packet has been submitted for review.",
|
|
"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",
|
|
"validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
|
|
"review_queue": "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 ."
|
|
},
|
|
"must_collect": {
|
|
"provenance_requirements": [
|
|
"real target client or external installer runtime guard",
|
|
"native enforcement flag or externally accepted guard proof",
|
|
"residual risk retained for fallback targets"
|
|
],
|
|
"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."
|
|
]
|
|
},
|
|
"evidence_artifacts": [
|
|
"dist/targets/*/adapter.json",
|
|
"reports/runtime_permission_probes.json",
|
|
"reports/runtime_permission_probes.md",
|
|
"reports/install_simulation.json",
|
|
"reports/install_simulation.md",
|
|
"security/permission_policy.json",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/native-permission-enforcement.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"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."
|
|
}
|
|
],
|
|
"blocked_source_check_count": 1,
|
|
"next_source_actions": [
|
|
"Collect real target-client or external runtime guard proof."
|
|
],
|
|
"submission_state": {
|
|
"status": "missing",
|
|
"path": "evidence/world_class/submissions/native-permission-enforcement.json",
|
|
"artifact_ref_count": 0,
|
|
"attested_real_evidence": false,
|
|
"privacy_contract_satisfied": false,
|
|
"ledger_counts_as_completion": false
|
|
},
|
|
"anti_overclaim": {
|
|
"planned_work_counts_as_evidence": false,
|
|
"metadata_fallback_counts_as_native_enforcement": false,
|
|
"pending_review_counts_as_human_decision": false,
|
|
"local_command_runner_counts_as_provider_model": false
|
|
}
|
|
},
|
|
{
|
|
"evidence_key": "native-client-telemetry",
|
|
"label": "Native Client Telemetry",
|
|
"category": "external",
|
|
"owner": "Browser/Chrome/IDE/provider client integrator",
|
|
"ledger_status": "pending",
|
|
"intake_readiness": "awaiting-submission",
|
|
"review_state": "awaiting-submission",
|
|
"source_accepted": false,
|
|
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
|
|
"current": "external source events 0; adoption samples 0",
|
|
"execution_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"
|
|
],
|
|
"blocking_reason": "No evidence packet has been submitted for review.",
|
|
"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",
|
|
"validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
|
|
"review_queue": "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 ."
|
|
},
|
|
"must_collect": {
|
|
"provenance_requirements": [
|
|
"real external client source",
|
|
"metadata-only event",
|
|
"local-first import path"
|
|
],
|
|
"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."
|
|
]
|
|
},
|
|
"evidence_artifacts": [
|
|
"reports/adoption_drift_report.json",
|
|
"reports/adoption_drift_report.md",
|
|
"reports/telemetry_hook_recipes.json",
|
|
"scripts/telemetry_native_host.py",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/native-client-telemetry.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"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."
|
|
}
|
|
],
|
|
"blocked_source_check_count": 2,
|
|
"next_source_actions": [
|
|
"Import at least one metadata-only event from a real client.",
|
|
"Telemetry must include adoption outcome evidence."
|
|
],
|
|
"submission_state": {
|
|
"status": "missing",
|
|
"path": "evidence/world_class/submissions/native-client-telemetry.json",
|
|
"artifact_ref_count": 0,
|
|
"attested_real_evidence": false,
|
|
"privacy_contract_satisfied": false,
|
|
"ledger_counts_as_completion": false
|
|
},
|
|
"anti_overclaim": {
|
|
"planned_work_counts_as_evidence": false,
|
|
"metadata_fallback_counts_as_native_enforcement": false,
|
|
"pending_review_counts_as_human_decision": false,
|
|
"local_command_runner_counts_as_provider_model": false
|
|
}
|
|
}
|
|
],
|
|
"source_reports": {
|
|
"ledger": "reports/world_class_evidence_ledger.json",
|
|
"intake": "reports/world_class_evidence_intake.json",
|
|
"submission_review": "reports/world_class_submission_review.json",
|
|
"claim_guard": "reports/world_class_claim_guard.json"
|
|
},
|
|
"artifacts": {
|
|
"json": "reports/world_class_operator_runbook.json",
|
|
"markdown": "reports/world_class_operator_runbook.md",
|
|
"html": "reports/world_class_operator_runbook.html"
|
|
}
|
|
}
|