frostbyte_neo/yao-meta-skill
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity
Files
5fbed1d27327064522a8aecfa77f99c2425554d0
yao-meta-skill/reports/world_class_operator_runbook.json
T
yaojingang 6ccb9c86ba Refresh operator UX evidence
2026-06-20 20:37:23 +08:00

1692 lines
82 KiB
JSON
Raw Blame History

{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-20",
"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": 19,
"source_pass_count": 12,
"source_blocked_count": 7,
"repair_checklist_count": 11,
"repair_blocked_count": 11,
"phase_queue_count": 2,
"phase_queue_blocked_count": 2,
"phase_queue_row_count": 11,
"phase_queue_next_phase": "unblock-access",
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"phase_queue_counts_as_completion": false,
"coordination_step_count": 6,
"coordination_user_required_step_count": 6,
"coordination_pending_evidence_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"coordination_counts_as_completion": false,
"release_gate_ready": false,
"release_gate_blocked_count": 4,
"release_gate_check_count": 5,
"release_gate_counts_as_completion": false,
"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": true,
"objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
"current": "model-executed 10; token-observed 10",
"execution_runbook": [
"Set one provider API key in the operator shell, such as OPENAI_API_KEY or DEEPSEEK_API_KEY; never commit or print the value.",
"For OpenAI Responses: python3 scripts/yao.py output-exec --provider-runner openai --provider-model ${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini} --timeout-seconds 60",
"For DeepSeek Chat Completions: python3 scripts/yao.py output-exec --provider-runner deepseek --provider-model deepseek-v4-flash --provider-api-format chat-completions --provider-thinking disabled --api-key-env DEEPSEEK_API_KEY --timeout-seconds 120",
"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": 10,
"timing_observed_count": 10,
"token_observed_count": 10,
"accepted": true
},
"source_checklist": [
{
"evidence_key": "provider-holdout",
"label": "Provider model run",
"field": "model_executed_count",
"expected": ">0",
"actual": 10,
"status": "pass",
"source_accepted": true,
"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": true,
"next_action": "Provider execution should record timing metadata."
},
{
"evidence_key": "provider-holdout",
"label": "Token usage observed",
"field": "token_observed_count",
"expected": ">0",
"actual": 10,
"status": "pass",
"source_accepted": true,
"next_action": "Provider execution should return non-estimated token usage."
}
],
"blocked_source_check_count": 0,
"next_source_actions": [],
"repair_checklist": [
{
"action_id": "provider-holdout-precheck-provider-api-key",
"evidence_key": "provider-holdout",
"repair_type": "precheck",
"target": "provider-api-key",
"phase": "unblock-access",
"priority": 20,
"owner": "operator with provider credentials",
"status": "blocked",
"blocking_reason": "Required env_any precheck is missing.",
"next_action": "Set one provider API key in the operator shell, such as OPENAI_API_KEY or DEEPSEEK_API_KEY; never commit or print the value.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "prechecks",
"counts_as_completion": false
}
],
"repair_blocked_count": 1,
"repair_counts_as_completion": false,
"phase_queue": [
{
"phase": "unblock-access",
"label": "Unblock access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"operator with provider credentials"
],
"evidence_keys": [
"provider-holdout"
],
"next_action_id": "provider-holdout-precheck-provider-api-key",
"next_action": "Set one provider API key in the operator shell, such as OPENAI_API_KEY or DEEPSEEK_API_KEY; never commit or print the value.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false,
"rows": [
{
"action_id": "provider-holdout-precheck-provider-api-key",
"evidence_key": "provider-holdout",
"repair_type": "precheck",
"target": "provider-api-key",
"phase": "unblock-access",
"priority": 20,
"owner": "operator with provider credentials",
"status": "blocked",
"blocking_reason": "Required env_any precheck is missing.",
"next_action": "Set one provider API key in the operator shell, such as OPENAI_API_KEY or DEEPSEEK_API_KEY; never commit or print the value.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "prechecks",
"counts_as_completion": false
}
]
}
],
"phase_queue_blocked_count": 1,
"phase_queue_counts_as_completion": false,
"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_reviewer_approved": false,
"ledger_reviewer": "",
"ledger_reviewed_at": "",
"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",
"Record reviewer choices in a separate JSON, JSONL, or CSV decision source with reviewer, reviewed_at, case_id, winner_variant, confidence, required reason, and truthful reviewer_attestation only.",
"python3 scripts/yao.py output-review-import --input <reviewer-decisions.json> --blind-review-attested --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"
],
"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/output_review_adjudication.json summary.reviewer_metadata_present is true",
"reports/output_review_adjudication.json summary.blind_review_attested is true",
"reports/output_review_adjudication.json review_integrity.blind_pack_sha256 exists and matches reports/output_review_decisions.json",
"reports/output_review_adjudication.json pairs and reviewer_checklist store prompt_sha256, not raw prompt text",
"reports/output_review_adjudication.json summary.ready_for_human_evidence is true",
"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.",
"Reviewer reasons must be rubric-based and must not include raw user data or private customer detail.",
"The decision importer rejects raw prompt, output, transcript, message, and answer-key fields.",
"The adjudication evidence stores prompt_sha256 instead of raw prompt text.",
"The decision and adjudication artifacts preserve blind_pack_sha256 so reviewers can audit exactly which pack was judged.",
"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",
"scripts/import_output_review_decisions.py",
"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,
"reviewer_metadata_present": false,
"reason_required": true,
"blind_review_attested": false,
"raw_content_excluded_attested": true,
"reviewer_reason_required_attested": true,
"ready_for_human_evidence": false,
"raw_content_allowed": false,
"raw_content_path_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 and reason 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": "human-adjudication",
"label": "Reviewer metadata",
"field": "reviewer_metadata_present",
"expected": "true",
"actual": false,
"status": "blocked",
"source_accepted": false,
"next_action": "Record reviewer and reviewed_at before adjudication can count."
},
{
"evidence_key": "human-adjudication",
"label": "Reason required",
"field": "reason_required",
"expected": "true",
"actual": true,
"status": "pass",
"source_accepted": false,
"next_action": "Keep reason mandatory for every imported or direct reviewer decision."
},
{
"evidence_key": "human-adjudication",
"label": "Blind review attested",
"field": "blind_review_attested",
"expected": "true",
"actual": false,
"status": "blocked",
"source_accepted": false,
"next_action": "Set reviewer_attestation only after choices are completed before opening the answer key."
},
{
"evidence_key": "human-adjudication",
"label": "Raw content attested",
"field": "raw_content_excluded_attested",
"expected": "true",
"actual": true,
"status": "pass",
"source_accepted": false,
"next_action": "Attest that reviewer decisions exclude raw prompts, outputs, transcripts, messages, and private user content."
},
{
"evidence_key": "human-adjudication",
"label": "Raw content blocked",
"field": "raw_content_allowed",
"expected": "false",
"actual": false,
"status": "pass",
"source_accepted": false,
"next_action": "Adjudication evidence should store prompt hashes and reviewer metadata, not raw prompts, outputs, transcripts, or messages."
},
{
"evidence_key": "human-adjudication",
"label": "Human evidence ready",
"field": "ready_for_human_evidence",
"expected": "true",
"actual": false,
"status": "blocked",
"source_accepted": false,
"next_action": "Complete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints."
}
],
"blocked_source_check_count": 5,
"next_source_actions": [
"Record a reviewer choice and reason for every pair.",
"Every pair needs one valid human judgment.",
"Record reviewer and reviewed_at before adjudication can count.",
"Set reviewer_attestation only after choices are completed before opening the answer key.",
"Complete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints."
],
"repair_checklist": [
{
"action_id": "human-adjudication-precheck-human-reviewer",
"evidence_key": "human-adjudication",
"repair_type": "precheck",
"target": "human-reviewer",
"phase": "unblock-access",
"priority": 20,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Required human precheck is human-required.",
"next_action": "Assign a real reviewer identity before claiming human adjudication.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "prechecks",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-blind_review_attested",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "blind_review_attested",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value False does not satisfy 'true'.",
"next_action": "Set reviewer_attestation only after choices are completed before opening the answer key.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-judgment_count",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "judgment_count",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '==pair_count'.",
"next_action": "Every pair needs one valid human judgment.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-pending_count",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "pending_count",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value 5 does not satisfy '==0'.",
"next_action": "Record a reviewer choice and reason for every pair.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-ready_for_human_evidence",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "ready_for_human_evidence",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value False does not satisfy 'true'.",
"next_action": "Complete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-reviewer_metadata_present",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "reviewer_metadata_present",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value False does not satisfy 'true'.",
"next_action": "Record reviewer and reviewed_at before adjudication can count.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
}
],
"repair_blocked_count": 6,
"repair_counts_as_completion": false,
"phase_queue": [
{
"phase": "unblock-access",
"label": "Unblock access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"human reviewer"
],
"evidence_keys": [
"human-adjudication"
],
"next_action_id": "human-adjudication-precheck-human-reviewer",
"next_action": "Assign a real reviewer identity before claiming human adjudication.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false,
"rows": [
{
"action_id": "human-adjudication-precheck-human-reviewer",
"evidence_key": "human-adjudication",
"repair_type": "precheck",
"target": "human-reviewer",
"phase": "unblock-access",
"priority": 20,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Required human precheck is human-required.",
"next_action": "Assign a real reviewer identity before claiming human adjudication.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "prechecks",
"counts_as_completion": false
}
]
},
{
"phase": "collect-source",
"label": "Collect source",
"priority": 40,
"status": "blocked",
"blocked_count": 5,
"row_count": 5,
"owners": [
"human reviewer"
],
"evidence_keys": [
"human-adjudication"
],
"next_action_id": "human-adjudication-source-check-blind_review_attested",
"next_action": "Set reviewer_attestation only after choices are completed before opening the answer key.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false,
"rows": [
{
"action_id": "human-adjudication-source-check-blind_review_attested",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "blind_review_attested",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value False does not satisfy 'true'.",
"next_action": "Set reviewer_attestation only after choices are completed before opening the answer key.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-judgment_count",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "judgment_count",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '==pair_count'.",
"next_action": "Every pair needs one valid human judgment.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-pending_count",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "pending_count",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value 5 does not satisfy '==0'.",
"next_action": "Record a reviewer choice and reason for every pair.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-ready_for_human_evidence",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "ready_for_human_evidence",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value False does not satisfy 'true'.",
"next_action": "Complete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-reviewer_metadata_present",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "reviewer_metadata_present",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value False does not satisfy 'true'.",
"next_action": "Record reviewer and reviewed_at before adjudication can count.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
}
]
}
],
"phase_queue_blocked_count": 2,
"phase_queue_counts_as_completion": false,
"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_reviewer_approved": false,
"ledger_reviewer": "",
"ledger_reviewed_at": "",
"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."
],
"repair_checklist": [
{
"action_id": "native-permission-enforcement-precheck-native-guard",
"evidence_key": "native-permission-enforcement",
"repair_type": "precheck",
"target": "native-guard",
"phase": "unblock-access",
"priority": 20,
"owner": "target client or installer integrator",
"status": "blocked",
"blocking_reason": "Required external precheck is external-required.",
"next_action": "Attach a real target-client or external installer runtime guard; metadata fallback is not enough.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "prechecks",
"counts_as_completion": false
},
{
"action_id": "native-permission-enforcement-source-check-native_enforcement_count",
"evidence_key": "native-permission-enforcement",
"repair_type": "source-check",
"target": "native_enforcement_count",
"phase": "collect-source",
"priority": 40,
"owner": "target client or installer integrator",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '>0'.",
"next_action": "Collect real target-client or external runtime guard proof.",
"verification_command": "python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
}
],
"repair_blocked_count": 2,
"repair_counts_as_completion": false,
"phase_queue": [
{
"phase": "unblock-access",
"label": "Unblock access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"target client or installer integrator"
],
"evidence_keys": [
"native-permission-enforcement"
],
"next_action_id": "native-permission-enforcement-precheck-native-guard",
"next_action": "Attach a real target-client or external installer runtime guard; metadata fallback is not enough.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false,
"rows": [
{
"action_id": "native-permission-enforcement-precheck-native-guard",
"evidence_key": "native-permission-enforcement",
"repair_type": "precheck",
"target": "native-guard",
"phase": "unblock-access",
"priority": 20,
"owner": "target client or installer integrator",
"status": "blocked",
"blocking_reason": "Required external precheck is external-required.",
"next_action": "Attach a real target-client or external installer runtime guard; metadata fallback is not enough.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "prechecks",
"counts_as_completion": false
}
]
},
{
"phase": "collect-source",
"label": "Collect source",
"priority": 40,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"target client or installer integrator"
],
"evidence_keys": [
"native-permission-enforcement"
],
"next_action_id": "native-permission-enforcement-source-check-native_enforcement_count",
"next_action": "Collect real target-client or external runtime guard proof.",
"verification_command": "python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false,
"rows": [
{
"action_id": "native-permission-enforcement-source-check-native_enforcement_count",
"evidence_key": "native-permission-enforcement",
"repair_type": "source-check",
"target": "native_enforcement_count",
"phase": "collect-source",
"priority": 40,
"owner": "target client or installer integrator",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '>0'.",
"next_action": "Collect real target-client or external runtime guard proof.",
"verification_command": "python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
}
]
}
],
"phase_queue_blocked_count": 2,
"phase_queue_counts_as_completion": false,
"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_reviewer_approved": false,
"ledger_reviewer": "",
"ledger_reviewed_at": "",
"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 1",
"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": 1,
"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": 1,
"status": "pass",
"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": 1,
"next_source_actions": [
"Import at least one metadata-only event from a real client."
],
"repair_checklist": [
{
"action_id": "native-client-telemetry-precheck-external-client",
"evidence_key": "native-client-telemetry",
"repair_type": "precheck",
"target": "external-client",
"phase": "unblock-access",
"priority": 20,
"owner": "Browser/Chrome/IDE/provider client integrator",
"status": "blocked",
"blocking_reason": "Required external precheck is external-required.",
"next_action": "Install a real Browser, Chrome, IDE, or provider client that emits metadata-only events.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "prechecks",
"counts_as_completion": false
},
{
"action_id": "native-client-telemetry-source-check-external_source_events",
"evidence_key": "native-client-telemetry",
"repair_type": "source-check",
"target": "external_source_events",
"phase": "collect-source",
"priority": 40,
"owner": "Browser/Chrome/IDE/provider client integrator",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '>0'.",
"next_action": "Import at least one metadata-only event from a real client.",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
}
],
"repair_blocked_count": 2,
"repair_counts_as_completion": false,
"phase_queue": [
{
"phase": "unblock-access",
"label": "Unblock access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-precheck-external-client",
"next_action": "Install a real Browser, Chrome, IDE, or provider client that emits metadata-only events.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false,
"rows": [
{
"action_id": "native-client-telemetry-precheck-external-client",
"evidence_key": "native-client-telemetry",
"repair_type": "precheck",
"target": "external-client",
"phase": "unblock-access",
"priority": 20,
"owner": "Browser/Chrome/IDE/provider client integrator",
"status": "blocked",
"blocking_reason": "Required external precheck is external-required.",
"next_action": "Install a real Browser, Chrome, IDE, or provider client that emits metadata-only events.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "prechecks",
"counts_as_completion": false
}
]
},
{
"phase": "collect-source",
"label": "Collect source",
"priority": 40,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-external_source_events",
"next_action": "Import at least one metadata-only event from a real client.",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false,
"rows": [
{
"action_id": "native-client-telemetry-source-check-external_source_events",
"evidence_key": "native-client-telemetry",
"repair_type": "source-check",
"target": "external_source_events",
"phase": "collect-source",
"priority": 40,
"owner": "Browser/Chrome/IDE/provider client integrator",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '>0'.",
"next_action": "Import at least one metadata-only event from a real client.",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
}
]
}
],
"phase_queue_blocked_count": 2,
"phase_queue_counts_as_completion": false,
"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_reviewer_approved": false,
"ledger_reviewer": "",
"ledger_reviewed_at": "",
"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
}
}
],
"coordination_plan": [
{
"step_id": "prepare-evidence-session",
"phase": "prepare",
"evidence_key": "",
"owner": "assistant + user",
"requires_user_input": true,
"user_action": "Confirm provider access, reviewer availability, target client path, and telemetry client path before collection starts.",
"assistant_action": "Run preflight and prepare submission drafts without accepting them as evidence.",
"external_dependency": "User-selected provider, reviewer, and real client surfaces.",
"command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-submission-kit . --output-dir evidence/world_class/submissions --prefill-artifacts",
"pass_condition": "Preflight lists the same pending evidence keys and no credential values are printed.",
"artifact": "reports/world_class_evidence_preflight.json",
"privacy_boundary": "Drafts and preflight are planning artifacts only; they do not count as evidence.",
"counts_as_completion": false
},
{
"step_id": "collect-provider-holdout",
"phase": "provider-holdout",
"evidence_key": "provider-holdout",
"owner": "assistant + operator with provider credentials",
"requires_user_input": true,
"user_action": "Provide the selected provider API key through an environment variable and confirm the provider, model, endpoint, and API format to use.",
"assistant_action": "Run provider-backed output execution, verify aggregate timing and token metadata, then prepare the evidence packet.",
"external_dependency": "Valid provider credentials and a live provider endpoint.",
"command": "python3 scripts/yao.py output-exec . --provider-runner <openai|deepseek> --provider-model <model> --timeout-seconds 60",
"pass_condition": "reports/output_execution_runs.json has model_executed_count > 0 and token_observed_count > 0.",
"artifact": "reports/output_execution_runs.json",
"privacy_boundary": "Commit aggregate metadata only; do not commit API keys, raw prompts, raw outputs, or provider request payloads.",
"counts_as_completion": false
},
{
"step_id": "collect-human-adjudication",
"phase": "human-review",
"evidence_key": "human-adjudication",
"owner": "human reviewer + assistant",
"requires_user_input": true,
"user_action": "Open the blind review kit, choose winners for all pairs, add reviewer metadata and reasons, and keep the answer key hidden until decisions are saved.",
"assistant_action": "Generate the review kit, import decisions, validate integrity, and prepare the human evidence packet.",
"external_dependency": "A real human reviewer who can make blind A/B judgments.",
"command": "python3 scripts/yao.py output-review-kit . && python3 scripts/yao.py output-review .",
"pass_condition": "reports/output_review_adjudication.json has pending_count == 0 and ready_for_human_evidence == true.",
"artifact": "reports/output_review_adjudication.json",
"privacy_boundary": "Store reviewer choices, reasons, hashes, and attestations; do not store raw prompts or answer-key exposure before decisions.",
"counts_as_completion": false
},
{
"step_id": "collect-native-permission-enforcement",
"phase": "native-permission",
"evidence_key": "native-permission-enforcement",
"owner": "target client or installer integrator + assistant",
"requires_user_input": true,
"user_action": "Select a real target client or external installer guard that can enforce declared capabilities instead of metadata-only fallback.",
"assistant_action": "Run runtime permission probes, package verification, install simulation, and prepare the native enforcement evidence packet.",
"external_dependency": "A real target runtime, extension, client, or installer guard that can block undeclared capabilities.",
"command": "python3 scripts/yao.py runtime-permissions . --package-dir dist",
"pass_condition": "reports/runtime_permission_probes.json has native_enforcement_count > 0 and failure_count == 0.",
"artifact": "reports/runtime_permission_probes.json",
"privacy_boundary": "Do not mark metadata fallback as native enforcement; keep residual risks visible for fallback targets.",
"counts_as_completion": false
},
{
"step_id": "collect-native-client-telemetry",
"phase": "native-telemetry",
"evidence_key": "native-client-telemetry",
"owner": "real client integrator + assistant",
"requires_user_input": true,
"user_action": "Install the native host manifest in a real Browser, Chrome, IDE, or provider client and trigger a metadata-only event.",
"assistant_action": "Generate native host assets, import the external event JSONL, refresh adoption drift, and prepare the telemetry evidence packet.",
"external_dependency": "A real client process that emits metadata-only telemetry through the native host.",
"command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl --source external",
"pass_condition": "reports/adoption_drift_report.json has source_types.external > 0 and adoption_sample_count > 0.",
"artifact": "reports/adoption_drift_report.json",
"privacy_boundary": "Telemetry must remain metadata-only; do not store raw prompts, outputs, transcripts, notes, or messages.",
"counts_as_completion": false
},
{
"step_id": "review-and-release-gate",
"phase": "release-gate",
"evidence_key": "",
"owner": "assistant + ledger reviewer",
"requires_user_input": true,
"user_action": "Approve only validated evidence packets and confirm the release wording after the claim guard passes.",
"assistant_action": "Run intake, submission review, ledger, claim guard, benchmark, evidence consistency, Review Studio, and CI before final publish.",
"external_dependency": "Accepted evidence packets for every pending world-class key.",
"command": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-claim-guard . && make ci-test",
"pass_condition": "Ledger ready_to_claim_world_class, benchmark public_claim_ready, claim guard violation_count == 0, Review Studio has no blockers, and CI passes.",
"artifact": "reports/world_class_evidence_ledger.json",
"privacy_boundary": "Release evidence may include aggregate reports and hashes only; raw content and credentials remain out of git.",
"counts_as_completion": false
}
],
"release_gate": {
"ready": false,
"decision": "blocked-until-evidence-accepted",
"check_count": 5,
"blocked_count": 4,
"checks": [
{
"key": "world_class_ledger_ready",
"label": "World-class ledger ready",
"passed": false,
"current": "evidence-pending",
"expected": "ready_to_claim_world_class == true",
"artifact": "reports/world_class_evidence_ledger.json"
},
{
"key": "claim_guard_clean",
"label": "Claim guard clean",
"passed": false,
"current": "violations 0; ledger ready False",
"expected": "violation_count == 0 and ledger_ready_to_claim_world_class == true",
"artifact": "reports/world_class_claim_guard.json"
},
{
"key": "benchmark_public_claim_ready",
"label": "Benchmark public claim ready",
"passed": false,
"current": "public_claim_ready False",
"expected": "public_claim_ready == true",
"artifact": "reports/benchmark_reproducibility.json"
},
{
"key": "review_studio_clean",
"label": "Review Studio clean",
"passed": false,
"current": "blockers 0; warnings 3",
"expected": "blocker_count == 0 and warning_count == 0",
"artifact": "reports/review-studio.json"
},
{
"key": "evidence_consistency_clean",
"label": "Evidence consistency clean",
"passed": true,
"current": "consistent",
"expected": "decision == consistent and fail_count == 0",
"artifact": "reports/evidence_consistency.json"
}
],
"blocked_checks": [
{
"key": "world_class_ledger_ready",
"label": "World-class ledger ready",
"passed": false,
"current": "evidence-pending",
"expected": "ready_to_claim_world_class == true",
"artifact": "reports/world_class_evidence_ledger.json"
},
{
"key": "claim_guard_clean",
"label": "Claim guard clean",
"passed": false,
"current": "violations 0; ledger ready False",
"expected": "violation_count == 0 and ledger_ready_to_claim_world_class == true",
"artifact": "reports/world_class_claim_guard.json"
},
{
"key": "benchmark_public_claim_ready",
"label": "Benchmark public claim ready",
"passed": false,
"current": "public_claim_ready False",
"expected": "public_claim_ready == true",
"artifact": "reports/benchmark_reproducibility.json"
},
{
"key": "review_studio_clean",
"label": "Review Studio clean",
"passed": false,
"current": "blockers 0; warnings 3",
"expected": "blocker_count == 0 and warning_count == 0",
"artifact": "reports/review-studio.json"
}
],
"final_manual_check": "Run make ci-test in a clean worktree and verify GitHub Actions before converting the PR out of Draft.",
"counts_as_completion": false
},
"repair_checklist": [
{
"action_id": "human-adjudication-precheck-human-reviewer",
"evidence_key": "human-adjudication",
"repair_type": "precheck",
"target": "human-reviewer",
"phase": "unblock-access",
"priority": 20,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Required human precheck is human-required.",
"next_action": "Assign a real reviewer identity before claiming human adjudication.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "prechecks",
"counts_as_completion": false
},
{
"action_id": "native-client-telemetry-precheck-external-client",
"evidence_key": "native-client-telemetry",
"repair_type": "precheck",
"target": "external-client",
"phase": "unblock-access",
"priority": 20,
"owner": "Browser/Chrome/IDE/provider client integrator",
"status": "blocked",
"blocking_reason": "Required external precheck is external-required.",
"next_action": "Install a real Browser, Chrome, IDE, or provider client that emits metadata-only events.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "prechecks",
"counts_as_completion": false
},
{
"action_id": "native-permission-enforcement-precheck-native-guard",
"evidence_key": "native-permission-enforcement",
"repair_type": "precheck",
"target": "native-guard",
"phase": "unblock-access",
"priority": 20,
"owner": "target client or installer integrator",
"status": "blocked",
"blocking_reason": "Required external precheck is external-required.",
"next_action": "Attach a real target-client or external installer runtime guard; metadata fallback is not enough.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "prechecks",
"counts_as_completion": false
},
{
"action_id": "provider-holdout-precheck-provider-api-key",
"evidence_key": "provider-holdout",
"repair_type": "precheck",
"target": "provider-api-key",
"phase": "unblock-access",
"priority": 20,
"owner": "operator with provider credentials",
"status": "blocked",
"blocking_reason": "Required env_any precheck is missing.",
"next_action": "Set one provider API key in the operator shell, such as OPENAI_API_KEY or DEEPSEEK_API_KEY; never commit or print the value.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "prechecks",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-blind_review_attested",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "blind_review_attested",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value False does not satisfy 'true'.",
"next_action": "Set reviewer_attestation only after choices are completed before opening the answer key.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-judgment_count",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "judgment_count",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '==pair_count'.",
"next_action": "Every pair needs one valid human judgment.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-pending_count",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "pending_count",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value 5 does not satisfy '==0'.",
"next_action": "Record a reviewer choice and reason for every pair.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-ready_for_human_evidence",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "ready_for_human_evidence",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value False does not satisfy 'true'.",
"next_action": "Complete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-reviewer_metadata_present",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "reviewer_metadata_present",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value False does not satisfy 'true'.",
"next_action": "Record reviewer and reviewed_at before adjudication can count.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "native-client-telemetry-source-check-external_source_events",
"evidence_key": "native-client-telemetry",
"repair_type": "source-check",
"target": "external_source_events",
"phase": "collect-source",
"priority": 40,
"owner": "Browser/Chrome/IDE/provider client integrator",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '>0'.",
"next_action": "Import at least one metadata-only event from a real client.",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "native-permission-enforcement-source-check-native_enforcement_count",
"evidence_key": "native-permission-enforcement",
"repair_type": "source-check",
"target": "native_enforcement_count",
"phase": "collect-source",
"priority": 40,
"owner": "target client or installer integrator",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '>0'.",
"next_action": "Collect real target-client or external runtime guard proof.",
"verification_command": "python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
}
],
"phase_queue": [
{
"phase": "unblock-access",
"label": "Unblock access",
"priority": 20,
"status": "blocked",
"blocked_count": 4,
"row_count": 4,
"owners": [
"Browser/Chrome/IDE/provider client integrator",
"human reviewer",
"operator with provider credentials",
"target client or installer integrator"
],
"evidence_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"next_action_id": "human-adjudication-precheck-human-reviewer",
"next_action": "Assign a real reviewer identity before claiming human adjudication.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false,
"rows": [
{
"action_id": "human-adjudication-precheck-human-reviewer",
"evidence_key": "human-adjudication",
"repair_type": "precheck",
"target": "human-reviewer",
"phase": "unblock-access",
"priority": 20,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Required human precheck is human-required.",
"next_action": "Assign a real reviewer identity before claiming human adjudication.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "prechecks",
"counts_as_completion": false
},
{
"action_id": "native-client-telemetry-precheck-external-client",
"evidence_key": "native-client-telemetry",
"repair_type": "precheck",
"target": "external-client",
"phase": "unblock-access",
"priority": 20,
"owner": "Browser/Chrome/IDE/provider client integrator",
"status": "blocked",
"blocking_reason": "Required external precheck is external-required.",
"next_action": "Install a real Browser, Chrome, IDE, or provider client that emits metadata-only events.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "prechecks",
"counts_as_completion": false
},
{
"action_id": "native-permission-enforcement-precheck-native-guard",
"evidence_key": "native-permission-enforcement",
"repair_type": "precheck",
"target": "native-guard",
"phase": "unblock-access",
"priority": 20,
"owner": "target client or installer integrator",
"status": "blocked",
"blocking_reason": "Required external precheck is external-required.",
"next_action": "Attach a real target-client or external installer runtime guard; metadata fallback is not enough.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "prechecks",
"counts_as_completion": false
},
{
"action_id": "provider-holdout-precheck-provider-api-key",
"evidence_key": "provider-holdout",
"repair_type": "precheck",
"target": "provider-api-key",
"phase": "unblock-access",
"priority": 20,
"owner": "operator with provider credentials",
"status": "blocked",
"blocking_reason": "Required env_any precheck is missing.",
"next_action": "Set one provider API key in the operator shell, such as OPENAI_API_KEY or DEEPSEEK_API_KEY; never commit or print the value.",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "prechecks",
"counts_as_completion": false
}
]
},
{
"phase": "collect-source",
"label": "Collect source",
"priority": 40,
"status": "blocked",
"blocked_count": 7,
"row_count": 7,
"owners": [
"Browser/Chrome/IDE/provider client integrator",
"human reviewer",
"target client or installer integrator"
],
"evidence_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement"
],
"next_action_id": "human-adjudication-source-check-blind_review_attested",
"next_action": "Set reviewer_attestation only after choices are completed before opening the answer key.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false,
"rows": [
{
"action_id": "human-adjudication-source-check-blind_review_attested",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "blind_review_attested",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value False does not satisfy 'true'.",
"next_action": "Set reviewer_attestation only after choices are completed before opening the answer key.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-judgment_count",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "judgment_count",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '==pair_count'.",
"next_action": "Every pair needs one valid human judgment.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-pending_count",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "pending_count",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value 5 does not satisfy '==0'.",
"next_action": "Record a reviewer choice and reason for every pair.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-ready_for_human_evidence",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "ready_for_human_evidence",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value False does not satisfy 'true'.",
"next_action": "Complete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "human-adjudication-source-check-reviewer_metadata_present",
"evidence_key": "human-adjudication",
"repair_type": "source-check",
"target": "reviewer_metadata_present",
"phase": "collect-source",
"priority": 40,
"owner": "human reviewer",
"status": "blocked",
"blocking_reason": "Current value False does not satisfy 'true'.",
"next_action": "Record reviewer and reviewed_at before adjudication can count.",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "native-client-telemetry-source-check-external_source_events",
"evidence_key": "native-client-telemetry",
"repair_type": "source-check",
"target": "external_source_events",
"phase": "collect-source",
"priority": 40,
"owner": "Browser/Chrome/IDE/provider client integrator",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '>0'.",
"next_action": "Import at least one metadata-only event from a real client.",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
},
{
"action_id": "native-permission-enforcement-source-check-native_enforcement_count",
"evidence_key": "native-permission-enforcement",
"repair_type": "source-check",
"target": "native_enforcement_count",
"phase": "collect-source",
"priority": 40,
"owner": "target client or installer integrator",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '>0'.",
"next_action": "Collect real target-client or external runtime guard proof.",
"verification_command": "python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"source": "source_checklist",
"counts_as_completion": false
}
]
}
],
"source_reports": {
"ledger": "reports/world_class_evidence_ledger.json",
"intake": "reports/world_class_evidence_intake.json",
"preflight": "reports/world_class_evidence_preflight.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"
}
}
Reference in New Issue View Git Blame Copy Permalink