diff --git a/registry/index.json b/registry/index.json index 82fd7d35..78a6332d 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59" + "package_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index 00e626e9..6fdb18cb 100644 --- a/registry/packages/yao-meta-skill.json +++ b/registry/packages/yao-meta-skill.json @@ -16,8 +16,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8" + "package_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { "openai": "pass", @@ -48,7 +48,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json index 31008b16..876c5a30 100644 --- a/reports/adoption_drift_report.json +++ b/reports/adoption_drift_report.json @@ -1,7 +1,7 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-16T20:23:32Z", + "generated_at": "2026-06-16T20:30:45Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", diff --git a/reports/architecture_maintainability.json b/reports/architecture_maintainability.json index f3106937..36a2cf9f 100644 --- a/reports/architecture_maintainability.json +++ b/reports/architecture_maintainability.json @@ -4,10 +4,10 @@ "generated_at": "2026-06-13", "skill_dir": ".", "summary": { - "python_file_count": 225, - "script_file_count": 149, + "python_file_count": 226, + "script_file_count": 150, "test_file_count": 76, - "internal_module_count": 65, + "internal_module_count": 66, "cli_script_count": 86, "command_handler_count": 68, "entrypoint_command_handler_count": 18, @@ -96,6 +96,14 @@ "early_watch": false, "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." }, + { + "path": "scripts/world_class_submission_kit_rendering.py", + "lines": 576, + "kind": "internal-module", + "severity": "pass", + "early_watch": false, + "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." + }, { "path": "scripts/render_evidence_consistency.py", "lines": 571, @@ -111,14 +119,6 @@ "severity": "pass", "early_watch": false, "recommendation": "Move data loading and large section renderers into focused review_studio_* modules." - }, - { - "path": "scripts/adjudicate_output_review.py", - "lines": 566, - "kind": "cli-script", - "severity": "pass", - "early_watch": false, - "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." } ], "watchlist": [], diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md index 86e51c62..0012f366 100644 --- a/reports/architecture_maintainability.md +++ b/reports/architecture_maintainability.md @@ -5,10 +5,10 @@ Generated at: `2026-06-13` ## Summary - decision: `pass` -- python files: `225` -- scripts: `149` +- python files: `226` +- scripts: `150` - tests: `76` -- internal modules: `65` +- internal modules: `66` - CLI scripts: `86` - Yao CLI command handlers: `68` - entrypoint command handlers: `18` @@ -51,9 +51,9 @@ No near-threshold files found. | `scripts/optimize_description.py` | `585` | `cli-script` | `pass` | | `scripts/trust_check.py` | `582` | `cli-script` | `pass` | | `tests/verify_world_class_evidence_ledger.py` | `579` | `test` | `pass` | +| `scripts/world_class_submission_kit_rendering.py` | `576` | `internal-module` | `pass` | | `scripts/render_evidence_consistency.py` | `571` | `cli-script` | `pass` | | `scripts/render_review_studio.py` | `568` | `cli-script` | `pass` | -| `scripts/adjudicate_output_review.py` | `566` | `cli-script` | `pass` | ## Release Rule diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index 1fcf83c1..076f076f 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,43 +3,48 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", + "commit": "2efe6413f04c9626ba52c554b4dc87baabd0b05b", "git_status": { "available": true, "dirty": true, - "changed_file_count": 19, + "changed_file_count": 65, "generated_dirty": true, - "generated_changed_file_count": 19, - "source_dirty": false, - "source_changed_file_count": 0, + "generated_changed_file_count": 61, + "source_dirty": true, + "source_changed_file_count": 4, "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", " M reports/adoption_drift_report.json", + " M reports/adoption_drift_report.md", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", + " M reports/compiled_targets.json", " M reports/context_budget.json", - " M reports/context_budget_summary.json", - " M reports/evidence_consistency.json", - " M reports/output_execution_runs.json", - " M reports/output_execution_runs.md", - " M reports/review-studio.html", - " M reports/review-studio.json", - " M reports/review-viewer.json", - " M reports/skill-interpretation.html" + " M reports/context_budget.md", + " M reports/context_budget_summary.json" + ], + "source_sample": [ + " M scripts/prepare_world_class_submission_kit.py", + " M scripts/world_class_submission_kit_rendering.py", + " M tests/verify_world_class_submission_kit.py", + "?? scripts/world_class_phase_queue.py" ], - "source_sample": [], "generated_sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", " M reports/adoption_drift_report.json", + " M reports/adoption_drift_report.md", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", + " M reports/compiled_targets.json", " M reports/context_budget.json", - " M reports/context_budget_summary.json", - " M reports/evidence_consistency.json", - " M reports/output_execution_runs.json", - " M reports/output_execution_runs.md", - " M reports/review-studio.html", - " M reports/review-studio.json", - " M reports/review-viewer.json", - " M reports/skill-interpretation.html" + " M reports/context_budget.md", + " M reports/context_budget_summary.json" ], "generated_dirty_prefixes": [ "dist/", @@ -53,13 +58,13 @@ }, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98", - "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "evidence_bundle_sha256": "7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a", + "source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -74,35 +79,36 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "public_claim_ready": false, - "public_claim_blocker_count": 4, + "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 19, - "source_tree_dirty": false, - "source_changed_file_count": 0, + "changed_file_count": 65, + "source_tree_dirty": true, + "source_changed_file_count": 4, "generated_tree_dirty": true, - "generated_changed_file_count": 19 + "generated_changed_file_count": 61 }, "public_claim": { "ready": false, "scope": "public benchmark or world-class readiness claim", "blockers": [ + "release lock is not clean or commit is unavailable", "provider-backed model holdout evidence is incomplete", "human blind-review adjudication is incomplete", "world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)", - "world-class source checks are not all accepted (10/19 pass, 9 blocked)" + "world-class source checks are not all accepted (9/19 pass, 10 blocked)" ], "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks." }, "release_lock": { - "ready": true, - "commit": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", + "ready": false, + "commit": "2efe6413f04c9626ba52c554b4dc87baabd0b05b", "status_scope": "generation-time status before this report is written", - "source_changed_file_count": 0, - "generated_changed_file_count": 19, - "reason": "only generated evidence artifacts were dirty at generation time" + "source_changed_file_count": 4, + "generated_changed_file_count": 61, + "reason": "source files were dirty at generation time" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -110,7 +116,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98" + "sha256": "7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -183,8 +189,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7967, - "sha256": "3b9c37bdf02259b0e87d9f9fc5980512a2e95d9bcca32fd109b7a622d453b652" + "bytes": 7966, + "sha256": "f40063a2ada31c29a3ac9b5965f0887cad6bc19190ec0a3a6b15c92ce5c27b49" }, { "label": "blind_review", @@ -218,106 +224,106 @@ "label": "trust_report", "path": "reports/security_trust_report.json", "exists": true, - "bytes": 135139, - "sha256": "a18583795da7c3ffc0d355bc5465382b50f1a737a33e62b1e4b182496c9e4c5e" + "bytes": 135749, + "sha256": "b1d4729668d1dbf035b593e77dd2a3730e9aa4b3971014d37617ba5e0222df90" }, { "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, - "bytes": 29589, - "sha256": "364a150344f461934d36ca59c0f5f6e1ed487fbfa3b30cfdff548ded277dd5c5" + "bytes": 29715, + "sha256": "8b0d2a84027e0956b11acabc46e5ea5b9d7a311087b792eb57dd544bcd284671" }, { "label": "registry_audit", "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "d0157e4c0242955a3870f11eb00649f77e14b75f393874ea110b8f8e6eca89fb" + "sha256": "0a0ccb00f9f7769c56f109589983562e91f7663f2c96c219d284c3d36eafe58e" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "755a9c6788ccc0624682e523fe0154ac8b471bc4e41ed132f9866143762f398e" + "sha256": "7aa6c25e8154d246ace49f7ab9159fa85f96d1d4ebb7e2bb03c7b223260a908b" }, { "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, - "bytes": 8758, - "sha256": "15b77ec2b4738df891457d1d65f914751f30d6cd816a377e5c50c5a0b6d35b78" + "bytes": 8604, + "sha256": "34cc602c025c82a478a647d58008414f92c70e72046ca79979d3b038f3d793d2" }, { "label": "skill_os2_audit", "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14466, - "sha256": "16cbe378cc1a5ef847022c274af42ec8b6f7c346c8a06f59e6f6e3060d666177" + "sha256": "920bd7f7b3b0fb01c572ed12d9ff788a34a7592d00d9825004d3faba90ebb17b" }, { "label": "world_class_evidence_plan", "path": "reports/world_class_evidence_plan.json", "exists": true, "bytes": 22784, - "sha256": "4193115d881d4f68e61d2729633f88dd91d55d982af3db70691aafeba852f1ba" + "sha256": "2beb888d7992fc72073251632a6e85c4075278f9bcea946a46a7e11f8f43e0ca" }, { "label": "world_class_evidence_ledger", "path": "reports/world_class_evidence_ledger.json", "exists": true, - "bytes": 26016, - "sha256": "cb66d3284045b5993d25447f011cc70737dc760765ea3a3b7ae653194f0c4ff4" + "bytes": 26019, + "sha256": "22c85613d7bef62c4d0a4c94b77a8596090dc55c40e1663370d16d903e0b1ffb" }, { "label": "world_class_evidence_intake", "path": "reports/world_class_evidence_intake.json", "exists": true, "bytes": 20646, - "sha256": "002fbf07989a804595fdcb51b6d0c8177dc035a1dc8d084b8294a274d21fbc1b" + "sha256": "d3f44570e605e6e1b1557889ccca18efbbd8acc1d9a9c638f59961b3dc3e9026" }, { "label": "world_class_evidence_preflight", "path": "reports/world_class_evidence_preflight.json", "exists": true, - "bytes": 66981, - "sha256": "758807fa5749e0dd46f46d311abfad8af7dd70663e8876569b1a4b8414b42ace" + "bytes": 68674, + "sha256": "c9d5fc06305c41f0870f32f30c0440a95e6fbdba402326e339cfd0c771ff960d" }, { "label": "world_class_submission_review", "path": "reports/world_class_submission_review.json", "exists": true, - "bytes": 17299, - "sha256": "f5b1e0e44aeb6e1999182d40fca421ab0a66b91154efc7b518e9ed6f6ac20dd2" + "bytes": 17302, + "sha256": "96624a5b7f79aa0ac43ce60d30486290b9a91f0735254e31329f02e1ee291050" }, { "label": "world_class_operator_runbook", "path": "reports/world_class_operator_runbook.json", "exists": true, - "bytes": 28871, - "sha256": "8da2e2cde3adecec955f7745a4b761edc5af871d1720409cbd4f3b4b4482510e" + "bytes": 28935, + "sha256": "a7b7809d3b423bf647a528c3b0f6991f2ea3874afdd93a4d6ba74eb189131f2a" }, { "label": "world_class_operator_runbook_markdown", "path": "reports/world_class_operator_runbook.md", "exists": true, - "bytes": 17521, - "sha256": "bfac92bc14f3080b9d723f32a4848aa3cfc10d4c3ee2e3844b65153f34c87c0a" + "bytes": 17576, + "sha256": "d72777b421b57f0cf8f31b4d048cf92512e49216d0b0c05cec1686d4aea638ce" }, { "label": "world_class_operator_runbook_html", "path": "reports/world_class_operator_runbook.html", "exists": true, - "bytes": 23958, - "sha256": "46b435f98d8a91501580fa1426a8ab0d0f57b3bc92ecd17f42332e655fd2bd85" + "bytes": 24019, + "sha256": "73d8ef2898f25ae899a618b723f40a6907646c303effa21cbde6156d01a95fc7" }, { "label": "world_class_claim_guard", "path": "reports/world_class_claim_guard.json", "exists": true, "bytes": 18596, - "sha256": "c846ffc8565a40c270e711a58e968b005afd75be6df1a442b020deebe850386f" + "sha256": "abe7f7d60c0025e140373fadaefbed4063f285c140c74b9c7cfb464e354bb526" } ], "missing_artifacts": [], diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 195f93b9..493c9483 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,33 +1,33 @@ # Benchmark Reproducibility Generated at: `2026-06-17` -Commit: `ed6960f65dbba0a36c335835f2ac6e8133435ea7` +Commit: `2efe6413f04c9626ba52c554b4dc87baabd0b05b` Working tree dirty at generation: `true` -Source tree dirty at generation: `false` +Source tree dirty at generation: `true` Generated evidence dirty at generation: `true` -Evidence bundle SHA256: `38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98` +Evidence bundle SHA256: `7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a` ## Summary - reproducibility ready: `true` -- release lock ready: `true` +- release lock ready: `false` - methodology complete: `true` - required artifacts: `25` - missing artifacts: `0` -- source contract sha256: `6fbdbed9dfdc` -- archive sha256: `0db54f788046` +- source contract sha256: `7fa19df8aeba` +- archive sha256: `7db44f059844` - output cases: `5` - disclosed failure cases: `3` - reproduction commands: `23` - provider evidence complete: `false` - human review complete: `false` - world-class ready: `false` -- world-class source checks: `10` pass / `19` total; `9` blocked +- world-class source checks: `9` pass / `19` total; `10` blocked - public claim ready: `false` -- public claim blockers: `4` -- changed files at generation: `19` -- source changed files at generation: `0` -- generated changed files at generation: `19` +- public claim blockers: `5` +- changed files at generation: `65` +- source changed files at generation: `4` +- generated changed files at generation: `61` This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit and dirty samples are generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below. @@ -39,22 +39,23 @@ This report proves local benchmark reproducibility only. It keeps external provi | Blocker | | --- | +| release lock is not clean or commit is unavailable | | provider-backed model holdout evidence is incomplete | | human blind-review adjudication is incomplete | | world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) | -| world-class source checks are not all accepted (10/19 pass, 9 blocked) | +| world-class source checks are not all accepted (9/19 pass, 10 blocked) | ## Release Lock -- ready: `true` -- reason: only generated evidence artifacts were dirty at generation time +- ready: `false` +- reason: source files were dirty at generation time - status scope: generation-time status before this report is written ## Evidence Bundle - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `25` / `25` -- sha256: `38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98` +- sha256: `7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a` ## Methodology Sections @@ -76,26 +77,26 @@ This report proves local benchmark reproducibility only. It keeps external provi | output_cases | `evals/output/cases.jsonl` | present | `a6ae96857116` | | output_schema | `evals/output/schema.json` | present | `8ee340c95064` | | output_scorecard | `reports/output_quality_scorecard.json` | present | `0806258a8e08` | -| output_execution | `reports/output_execution_runs.json` | present | `3b9c37bdf022` | +| output_execution | `reports/output_execution_runs.json` | present | `f40063a2ada3` | | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` | | review_adjudication | `reports/output_review_adjudication.json` | present | `91fd88dd9b0f` | | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` | | runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` | -| trust_report | `reports/security_trust_report.json` | present | `a18583795da7` | -| python_compatibility | `reports/python_compatibility.json` | present | `364a150344f4` | -| registry_audit | `reports/registry_audit.json` | present | `d0157e4c0242` | -| package_verification | `reports/package_verification.json` | present | `755a9c6788cc` | -| install_simulation | `reports/install_simulation.json` | present | `15b77ec2b473` | -| skill_os2_audit | `reports/skill_os2_audit.json` | present | `16cbe378cc1a` | -| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `4193115d881d` | -| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `cb66d3284045` | -| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `002fbf07989a` | -| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `758807fa5749` | -| world_class_submission_review | `reports/world_class_submission_review.json` | present | `f5b1e0e44aeb` | -| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `8da2e2cde3ad` | -| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `bfac92bc14f3` | -| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `46b435f98d8a` | -| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `c846ffc8565a` | +| trust_report | `reports/security_trust_report.json` | present | `b1d4729668d1` | +| python_compatibility | `reports/python_compatibility.json` | present | `8b0d2a84027e` | +| registry_audit | `reports/registry_audit.json` | present | `0a0ccb00f9f7` | +| package_verification | `reports/package_verification.json` | present | `7aa6c25e8154` | +| install_simulation | `reports/install_simulation.json` | present | `34cc602c025c` | +| skill_os2_audit | `reports/skill_os2_audit.json` | present | `920bd7f7b3b0` | +| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `2beb888d7992` | +| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `22c85613d7be` | +| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `d3f44570e605` | +| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `c9d5fc06305c` | +| world_class_submission_review | `reports/world_class_submission_review.json` | present | `96624a5b7f79` | +| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `a7b7809d3b42` | +| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `d72777b421b5` | +| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `73d8ef2898f2` | +| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `abe7f7d60c00` | ## Reproduction Commands diff --git a/reports/context_budget.json b/reports/context_budget.json index e17fc48b..9a87425a 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -6,16 +6,16 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1112796, + "other_text_tokens": 1115158, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1113593, - "deferred_resource_tokens": 507713, + "estimated_total_text_tokens": 1115955, + "deferred_resource_tokens": 509352, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 446533, - "file_count": 149 + "estimated_tokens": 448172, + "file_count": 150 }, { "path": "references", @@ -36,8 +36,8 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 446533, - "file_count": 149 + "estimated_tokens": 448172, + "file_count": 150 } ], "deferred_resource_governance": { @@ -59,14 +59,14 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 446533, - "file_count": 149, + "estimated_tokens": 448172, + "file_count": 150, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } ], "summary": "Large deferred resources are indexed and backed by evidence." }, - "relevant_file_count": 704, + "relevant_file_count": 706, "unused_resource_dirs": [], "quality_signal_points": 130, "quality_density": 131.3 diff --git a/reports/context_budget.md b/reports/context_budget.md index c33ef9b4..685ab82e 100644 --- a/reports/context_budget.md +++ b/reports/context_budget.md @@ -2,7 +2,7 @@ | Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status | | --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- | -| root | `.` | `production` | 1000 | 990 | 797 | 507713 | `governed` | scripts:446533 | 131.3 | - | ok | +| root | `.` | `production` | 1000 | 990 | 797 | 509352 | `governed` | scripts:448172 | 131.3 | - | ok | | complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok | | governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok | diff --git a/reports/context_budget_summary.json b/reports/context_budget_summary.json index 02083d73..ab3814b2 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -1,5 +1,5 @@ { - "generated_at": "2026-06-17", + "generated_at": "2026-03-31", "targets": [ { "label": "root", @@ -8,12 +8,12 @@ "budget_limit": 1000, "initial_tokens": 990, "skill_body_tokens": 797, - "deferred_resource_tokens": 507713, + "deferred_resource_tokens": 509352, "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 446533, - "file_count": 149 + "estimated_tokens": 448172, + "file_count": 150 } ], "deferred_resource_governance": { @@ -35,8 +35,8 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 446533, - "file_count": 149, + "estimated_tokens": 448172, + "file_count": 150, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } ], diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index d54e92f5..5666777f 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -189,12 +189,12 @@ "status": "pass", "expected": { "status": "pass", - "detail": "initial load 990/1000; deferred 507713/120000; top deferred scripts 446533; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 509352/120000; top deferred scripts 448172; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "actual": { "status": "pass", - "detail": "initial load 990/1000; deferred 507713/120000; top deferred scripts 446533; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 509352/120000; top deferred scripts 448172; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "paths": [ @@ -207,8 +207,8 @@ "key": "benchmark-release-lock-self-consistency", "label": "Benchmark release lock matches source dirty state", "status": "pass", - "expected": true, - "actual": true, + "expected": false, + "actual": false, "paths": [ "reports/benchmark_reproducibility.json" ], @@ -222,7 +222,7 @@ "actual": { "available": true, "clean": false, - "changed_file_count": 21 + "changed_file_count": 66 }, "paths": [ "reports/benchmark_reproducibility.json" @@ -263,8 +263,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", - "actual": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", + "expected": "2efe6413f04c9626ba52c554b4dc87baabd0b05b", + "actual": "2efe6413f04c9626ba52c554b4dc87baabd0b05b", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -276,30 +276,30 @@ "label": "overview embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "actual": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -313,13 +313,13 @@ "status": "pass", "expected": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, + "adoption_rate": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "source_types": { "manual": 1 @@ -327,13 +327,13 @@ }, "actual": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, + "adoption_rate": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "source_types": { "manual": 1 @@ -356,8 +356,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -368,8 +368,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -389,7 +389,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 19, - "source_pass_count": 10 + "source_pass_count": 9 }, "actual": { "ready": false, @@ -397,7 +397,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 19, - "source_pass_count": 10 + "source_pass_count": 9 }, "paths": [ "reports/world_class_evidence_ledger.json", @@ -409,8 +409,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", - "actual": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", + "expected": "2efe6413f04c9626ba52c554b4dc87baabd0b05b", + "actual": "2efe6413f04c9626ba52c554b4dc87baabd0b05b", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -422,30 +422,30 @@ "label": "interpretation embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "actual": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -459,13 +459,13 @@ "status": "pass", "expected": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, + "adoption_rate": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "source_types": { "manual": 1 @@ -473,13 +473,13 @@ }, "actual": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, + "adoption_rate": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "source_types": { "manual": 1 @@ -502,8 +502,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -514,8 +514,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -535,7 +535,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 19, - "source_pass_count": 10 + "source_pass_count": 9 }, "actual": { "ready": false, @@ -543,7 +543,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 19, - "source_pass_count": 10 + "source_pass_count": 9 }, "paths": [ "reports/world_class_evidence_ledger.json", @@ -1342,7 +1342,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 19, - "source_pass_count": 10, + "source_pass_count": 9, "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -1402,7 +1402,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -1416,7 +1417,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 19, - "source_pass_count": 10, + "source_pass_count": 9, "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -1476,7 +1477,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -1527,7 +1529,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 149 + "file_count": 150 }, { "path": "evals", @@ -1542,7 +1544,7 @@ "file_count": 235 } ], - "file_count": 452, + "file_count": 453, "folder_count": 4, "distribution": [ { @@ -1567,7 +1569,7 @@ }, { "label": "scripts", - "value": 149 + "value": 150 }, { "label": "evals", @@ -1615,7 +1617,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 149 + "file_count": 150 }, { "path": "evals", @@ -1630,7 +1632,7 @@ "file_count": 235 } ], - "file_count": 452, + "file_count": 453, "folder_count": 4, "distribution": [ { @@ -1655,7 +1657,7 @@ }, { "label": "scripts", - "value": 149 + "value": 150 }, { "label": "evals", @@ -1826,15 +1828,15 @@ "expected": { "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "public_claim_ready": false }, "actual": { "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "public_claim_ready": false }, "paths": [ @@ -1850,8 +1852,8 @@ "expected": { "pending_count": 4, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "ready_to_claim_world_class": false, "preflight_counts_as_evidence": false, "credential_value_exposed": false @@ -1859,8 +1861,8 @@ "actual": { "pending_count": 4, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "ready_to_claim_world_class": false, "preflight_counts_as_evidence": false, "credential_value_exposed": false @@ -2114,8 +2116,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "plan_keys": [ "human-adjudication", "native-client-telemetry", @@ -2263,8 +2265,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "plan_keys": [ "human-adjudication", "native-client-telemetry", @@ -2419,10 +2421,10 @@ "score `91`", "`16` gates", "`3` warnings", - "`63` declared internal modules", - "`86 / 86` CLI help smoke checks passing across `149` scripts", - "`688` zip entries", - "archive with `688` entries", + "`64` declared internal modules", + "`86 / 86` CLI help smoke checks passing across `150` scripts", + "`689` zip entries", + "archive with `689` entries", "`12` installer permission checks enforced", "`0` permission failures", "`25` required artifacts", diff --git a/reports/install_simulation.json b/reports/install_simulation.json index d53e1ae2..f9afe3b4 100644 --- a/reports/install_simulation.json +++ b/reports/install_simulation.json @@ -8,7 +8,7 @@ "installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill", "summary": { "archive_present": true, - "archive_entry_count": 688, + "archive_entry_count": 689, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 5fcb6afc..767163cb 100644 --- a/reports/output_execution_runs.json +++ b/reports/output_execution_runs.json @@ -34,7 +34,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.21, + "duration_ms": 26.23, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.64, + "duration_ms": 26.04, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.14, + "duration_ms": 26.25, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.12, + "duration_ms": 26.22, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.94, + "duration_ms": 26.07, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.34, + "duration_ms": 25.73, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.98, + "duration_ms": 26.03, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.47, + "duration_ms": 25.68, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.51, + "duration_ms": 26.14, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.08, + "duration_ms": 26.21, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index d86514f2..96bc4c3c 100644 --- a/reports/output_execution_runs.md +++ b/reports/output_execution_runs.md @@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext | Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status | | --- | --- | --- | --- | ---: | ---: | ---: | --- | -| skill-package-contract | baseline | command | local-output-eval-runner | 29.21 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 28.64 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 28.14 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 28.12 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 28.94 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 29.34 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 28.98 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 29.47 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 27.51 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 27.08 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 26.23 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 26.04 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 26.25 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 26.22 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 26.07 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 25.73 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.03 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 25.68 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.14 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.21 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/package_verification.json b/reports/package_verification.json index 60e97ea1..c372b4b4 100644 --- a/reports/package_verification.json +++ b/reports/package_verification.json @@ -8,8 +8,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", - "archive_entry_count": 688, + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", + "archive_entry_count": 689, "failure_count": 0, "warning_count": 0 }, diff --git a/reports/package_verification.md b/reports/package_verification.md index 476dd283..96668ccf 100644 --- a/reports/package_verification.md +++ b/reports/package_verification.md @@ -4,7 +4,7 @@ - Package directory: `dist` - Targets: `4 / 4` adapters present - Archive present: `True` -- Archive SHA256: `0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8` +- Archive SHA256: `7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2` - Failures: `0` - Warnings: `0` diff --git a/reports/python_compatibility.json b/reports/python_compatibility.json index 304330f0..9de1052d 100644 --- a/reports/python_compatibility.json +++ b/reports/python_compatibility.json @@ -5,7 +5,7 @@ "root": ".", "summary": { "target_python": "3.11", - "file_count": 228, + "file_count": 229, "issue_count": 0, "syntax_error_count": 0, "fstring_311_violation_count": 0, @@ -826,6 +826,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/world_class_phase_queue.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/world_class_preflight_layout.py", "ok": true, diff --git a/reports/python_compatibility.md b/reports/python_compatibility.md index 378317f4..333c75f2 100644 --- a/reports/python_compatibility.md +++ b/reports/python_compatibility.md @@ -6,7 +6,7 @@ Generated at: `2026-06-13` - decision: `pass` - target python: `3.11` -- files scanned: `228` +- files scanned: `229` - issues: `0` - syntax errors: `0` - f-string 3.11 violations: `0` diff --git a/reports/registry_audit.json b/reports/registry_audit.json index cd42a5c7..a371143f 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,8 +21,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8" + "package_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { "openai": "pass", @@ -53,7 +53,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59" + "package_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index e717ebbc..7ee5dc4d 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,8 +6,8 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59` -- Archive SHA256: `0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8` +- Package SHA256: `7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4` +- Archive SHA256: `7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2` - Install simulated: `True` ## Compatibility diff --git a/reports/review-studio.html b/reports/review-studio.html index 2970260f..ef827bee 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -759,12 +759,12 @@

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

Blueprint21/21

2.0 coverage; extensions partial 0, planned 0; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

149 scripts scanned; secrets found

Py Compat0

228 files scanned for Python 3.11

Arch Debt0

696 largest lines; 0 watchlist; 2 early; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock true

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

182 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

688 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

+
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

5 blockers; local reproducible true

Blueprint21/21

2.0 coverage; extensions partial 0, planned 0; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

150 scripts scanned; secrets found

Py Compat0

229 files scanned for Python 3.11

Arch Debt0

696 largest lines; 0 watchlist; 2 early; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock true

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

182 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

689 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

审查闸门

-
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 990/1000; deferred 507713/120000; top deferred scripts 446533; resource governance governed; quality density 131.3

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 149 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 228 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

225 Python files; 0 hotspots; 0 watchlist files; 2 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true

reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 10/19 pass; 9 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md 证据
+
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 990/1000; deferred 509352/120000; top deferred scripts 448172; resource governance governed; quality density 131.3

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 150 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 229 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

226 Python files; 0 hotspots; 0 watchlist files; 2 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true

reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 9/19 pass; 10 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

@@ -774,12 +774,12 @@

阻断事项

无。

-

关注事项

  • 输出实验5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5
  • 人工批准0 active waivers; 1 warning gates still need reviewer decision
  • 世界证据4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 10/19 pass; 9 blocked; overclaim guard true
+

关注事项

  • 输出实验5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5
  • 人工批准0 active waivers; 1 warning gates still need reviewer decision
  • 世界证据4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 9/19 pass; 10 blocked; overclaim guard true

修复动作

-
关注

输出实验

补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。同步补足盲审声明。

没有输出质量和人工盲评证据时，Skill 只能证明会触发，不能证明输出真的更好且经得起审查。
修复位置
evals/output/cases.jsonl + reports/output_quality_scorecard.md + reports/output_review_kit.html + reports/output_review_adjudication.md + reports/output_review_decisions.json
验证命令
python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review
关注

人工批准

对保留的 warning 写入 reviewer、理由、范围和到期时间，或修掉 warning。

warning 可以被接受，但必须可审计、会过期，并且不能掩盖 blocker。
修复位置
reports/review_waivers.md
验证命令
python3 scripts/render_review_waivers.py .
关注

世界证据

补齐 provider、真人盲评、原生权限执行和真实客户端遥测证据，或明确本次发布不声明 world-class 完成。

世界级结论必须来自已接受的外部/人工证据；计划、metadata fallback、待评审和本地命令都不能替代完成证据。
修复位置
reports/world_class_operator_runbook.html + reports/world_class_evidence_ledger.md + reports/world_class_evidence_intake.md + reports/world_class_submission_review.md
验证命令
python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py review-studio .

证据采集

以下条目仍需真实外部或人工证据；提交文件、校验命令和阻断检查必须同时闭环。

pending · external

Provider Holdout

model-executed 0; token-observed 0

提交
evidence/world_class/submissions/provider-holdout.json
模板
evidence/world_class/templates/provider-holdout.intake.json
阻断
2 blocked / 1 pass
修复
3 repair rows; counts as completion: false
下一步
Run provider-backed holdout cases with real credentials and commit only aggregate evidence.
阻断检查
  • Provider model runmodel_executed_count: 0 / >0Run provider-backed output-exec with real credentials.
  • Token usage observedtoken_observed_count: 0 / >0Provider execution should return non-estimated token usage.
修复清单
  • #20 · unblock-access · precheckopenai-api-keyoperator with provider credentialsRequired env precheck is missing.Set OPENAI_API_KEY in the operator shell; never commit or print the value.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkmodel_executed_countoperator with provider credentialsCurrent value 0 does not satisfy '>0'.Run provider-backed output-exec with real credentials.python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60 && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checktoken_observed_countoperator with provider credentialsCurrent value 0 does not satisfy '>0'.Provider execution should return non-estimated token usage.python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60 && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.
  2. export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}
  3. python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60
采集契约
来源要求
  • provider-backed model run
  • observed timing
  • observed token metadata
通过条件
  • 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
证据资产
  • 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
资产角色

source: world-class-submission-kit; counts as evidence: false; prefill counts as evidence: false

  • submission-ref1 / 1 readyartifact_refs: trueRows marked submission-ref are the aggregate paths expected in artifact_refs.
  • supporting-evidence6 / 6 readyartifact_refs: falseSupporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.
隐私边界
  • Do not commit provider credentials or environment dumps.
  • The output execution report records output hashes and aggregate run metadata, not raw provider prompts.
pending · human

Human Adjudication

0/5 decisions; pending 5

提交
evidence/world_class/submissions/human-adjudication.json
模板
evidence/world_class/templates/human-adjudication.intake.json
阻断
5 blocked / 5 pass
修复
6 repair rows; counts as completion: false
下一步
Record real A/B choices, reviewer metadata, and blind-review attestation, then regenerate adjudication.
阻断检查
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice and reason for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
  • Reviewer metadatareviewer_metadata_present: False / trueRecord reviewer and reviewed_at before adjudication can count.
  • Blind review attestedblind_review_attested: False / trueSet reviewer_attestation only after choices are completed before opening the answer key.
  • Human evidence readyready_for_human_evidence: False / trueComplete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints.
修复清单
  • #20 · unblock-access · precheckhuman-reviewerhuman reviewerRequired human precheck is human-required.Assign a real reviewer identity before claiming human adjudication.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkblind_review_attestedhuman reviewerCurrent value False does not satisfy 'true'.Set reviewer_attestation only after choices are completed before opening the answer key.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkjudgment_counthuman reviewerCurrent value 0 does not satisfy '==pair_count'.Every pair needs one valid human judgment.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkpending_counthuman reviewerCurrent value 5 does not satisfy '==0'.Record a reviewer choice and reason for every pair.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkready_for_human_evidencehuman reviewerCurrent value False does not satisfy 'true'.Complete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkreviewer_metadata_presenthuman reviewerCurrent value False does not satisfy 'true'.Record reviewer and reviewed_at before adjudication can count.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. python3 scripts/yao.py output-review-kit --write-template
  2. Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.
  3. python3 scripts/adjudicate_output_review.py --write-template
采集契约
来源要求
  • real reviewer identity
  • blind A/B decisions
  • answer key unopened until decisions exist
通过条件
  • 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
证据资产
  • 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
资产角色

source: world-class-submission-kit; counts as evidence: false; prefill counts as evidence: false

  • submission-ref2 / 2 readyartifact_refs: trueRows marked submission-ref are the aggregate paths expected in artifact_refs.
  • supporting-evidence8 / 8 readyartifact_refs: falseSupporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.
隐私边界
  • 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.
pending · external

Native Permission Enforcement

native-enforced targets 0; installer-enforced targets 4

提交
evidence/world_class/submissions/native-permission-enforcement.json
模板
evidence/world_class/templates/native-permission-enforcement.intake.json
阻断
1 blocked / 2 pass
修复
2 repair rows; counts as completion: false
下一步
Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.
阻断检查
  • Native enforcementnative_enforcement_count: 0 / >0Collect real target-client or external runtime guard proof.
修复清单
  • #20 · unblock-access · prechecknative-guardtarget client or installer integratorRequired external precheck is external-required.Attach a real target-client or external installer runtime guard; metadata fallback is not enough.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checknative_enforcement_counttarget client or installer integratorCurrent value 0 does not satisfy '>0'.Collect real target-client or external runtime guard proof.python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.
  2. Update the generated target adapter only when the guard is actually enforced by that target.
  3. python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip
采集契约
来源要求
  • real target client or external installer runtime guard
  • native enforcement flag or externally accepted guard proof
  • residual risk retained for fallback targets
通过条件
  • 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
证据资产
  • dist/targets/*/adapter.json
  • reports/runtime_permission_probes.json
  • reports/runtime_permission_probes.md
  • reports/install_simulation.json
  • reports/install_simulation.md
资产角色

source: world-class-submission-kit; counts as evidence: false; prefill counts as evidence: false

  • submission-ref2 / 2 readyartifact_refs: trueRows marked submission-ref are the aggregate paths expected in artifact_refs.
  • supporting-evidence11 / 11 readyartifact_refs: falseSupporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.
隐私边界
  • Do not mark native_enforcement true for metadata-only fallbacks.
  • Keep residual risks visible for targets that still rely on operator enforcement.
pending · external

Native Client Telemetry

external source events 0; adoption samples 1

提交
evidence/world_class/submissions/native-client-telemetry.json
模板
evidence/world_class/templates/native-client-telemetry.intake.json
阻断
1 blocked / 2 pass
修复
2 repair rows; counts as completion: false
下一步
Install a real client against the native host and import production metadata-only events.
阻断检查
  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
修复清单
  • #20 · unblock-access · precheckexternal-clientBrowser/Chrome/IDE/provider client integratorRequired external precheck is external-required.Install a real Browser, Chrome, IDE, or provider client that emits metadata-only events.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkexternal_source_eventsBrowser/Chrome/IDE/provider client integratorCurrent value 0 does not satisfy '>0'.Import at least one metadata-only event from a real client.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
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. 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>/
  2. Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.
  3. python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
采集契约
来源要求
  • real external client source
  • metadata-only event
  • local-first import path
通过条件
  • 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
证据资产
  • 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
资产角色

source: world-class-submission-kit; counts as evidence: false; prefill counts as evidence: false

  • submission-ref2 / 2 readyartifact_refs: trueRows marked submission-ref are the aggregate paths expected in artifact_refs.
  • supporting-evidence6 / 6 readyartifact_refs: falseSupporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.
隐私边界
  • 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.
+
关注

输出实验

补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。同步补足盲审声明。

没有输出质量和人工盲评证据时，Skill 只能证明会触发，不能证明输出真的更好且经得起审查。
修复位置
evals/output/cases.jsonl + reports/output_quality_scorecard.md + reports/output_review_kit.html + reports/output_review_adjudication.md + reports/output_review_decisions.json
验证命令
python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review
关注

人工批准

对保留的 warning 写入 reviewer、理由、范围和到期时间，或修掉 warning。

warning 可以被接受，但必须可审计、会过期，并且不能掩盖 blocker。
修复位置
reports/review_waivers.md
验证命令
python3 scripts/render_review_waivers.py .
关注

世界证据

补齐 provider、真人盲评、原生权限执行和真实客户端遥测证据，或明确本次发布不声明 world-class 完成。

世界级结论必须来自已接受的外部/人工证据；计划、metadata fallback、待评审和本地命令都不能替代完成证据。
修复位置
reports/world_class_operator_runbook.html + reports/world_class_evidence_ledger.md + reports/world_class_evidence_intake.md + reports/world_class_submission_review.md
验证命令
python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py review-studio .

证据采集

以下条目仍需真实外部或人工证据；提交文件、校验命令和阻断检查必须同时闭环。

pending · external

Provider Holdout

model-executed 0; token-observed 0

提交
evidence/world_class/submissions/provider-holdout.json
模板
evidence/world_class/templates/provider-holdout.intake.json
阻断
2 blocked / 1 pass
修复
3 repair rows; counts as completion: false
下一步
Run provider-backed holdout cases with real credentials and commit only aggregate evidence.
阻断检查
  • Provider model runmodel_executed_count: 0 / >0Run provider-backed output-exec with real credentials.
  • Token usage observedtoken_observed_count: 0 / >0Provider execution should return non-estimated token usage.
修复清单
  • #20 · unblock-access · precheckopenai-api-keyoperator with provider credentialsRequired env precheck is missing.Set OPENAI_API_KEY in the operator shell; never commit or print the value.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkmodel_executed_countoperator with provider credentialsCurrent value 0 does not satisfy '>0'.Run provider-backed output-exec with real credentials.python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60 && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checktoken_observed_countoperator with provider credentialsCurrent value 0 does not satisfy '>0'.Provider execution should return non-estimated token usage.python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60 && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.
  2. export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}
  3. python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60
采集契约
来源要求
  • provider-backed model run
  • observed timing
  • observed token metadata
通过条件
  • 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
证据资产
  • 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
资产角色

source: world-class-submission-kit; counts as evidence: false; prefill counts as evidence: false

  • submission-ref1 / 1 readyartifact_refs: trueRows marked submission-ref are the aggregate paths expected in artifact_refs.
  • supporting-evidence6 / 6 readyartifact_refs: falseSupporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.
隐私边界
  • Do not commit provider credentials or environment dumps.
  • The output execution report records output hashes and aggregate run metadata, not raw provider prompts.
pending · human

Human Adjudication

0/5 decisions; pending 5

提交
evidence/world_class/submissions/human-adjudication.json
模板
evidence/world_class/templates/human-adjudication.intake.json
阻断
5 blocked / 5 pass
修复
6 repair rows; counts as completion: false
下一步
Record real A/B choices, reviewer metadata, and blind-review attestation, then regenerate adjudication.
阻断检查
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice and reason for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
  • Reviewer metadatareviewer_metadata_present: False / trueRecord reviewer and reviewed_at before adjudication can count.
  • Blind review attestedblind_review_attested: False / trueSet reviewer_attestation only after choices are completed before opening the answer key.
  • Human evidence readyready_for_human_evidence: False / trueComplete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints.
修复清单
  • #20 · unblock-access · precheckhuman-reviewerhuman reviewerRequired human precheck is human-required.Assign a real reviewer identity before claiming human adjudication.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkblind_review_attestedhuman reviewerCurrent value False does not satisfy 'true'.Set reviewer_attestation only after choices are completed before opening the answer key.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkjudgment_counthuman reviewerCurrent value 0 does not satisfy '==pair_count'.Every pair needs one valid human judgment.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkpending_counthuman reviewerCurrent value 5 does not satisfy '==0'.Record a reviewer choice and reason for every pair.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkready_for_human_evidencehuman reviewerCurrent value False does not satisfy 'true'.Complete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkreviewer_metadata_presenthuman reviewerCurrent value False does not satisfy 'true'.Record reviewer and reviewed_at before adjudication can count.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. python3 scripts/yao.py output-review-kit --write-template
  2. Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.
  3. python3 scripts/adjudicate_output_review.py --write-template
采集契约
来源要求
  • real reviewer identity
  • blind A/B decisions
  • answer key unopened until decisions exist
通过条件
  • 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
证据资产
  • 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
资产角色

source: world-class-submission-kit; counts as evidence: false; prefill counts as evidence: false

  • submission-ref2 / 2 readyartifact_refs: trueRows marked submission-ref are the aggregate paths expected in artifact_refs.
  • supporting-evidence8 / 8 readyartifact_refs: falseSupporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.
隐私边界
  • 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.
pending · external

Native Permission Enforcement

native-enforced targets 0; installer-enforced targets 4

提交
evidence/world_class/submissions/native-permission-enforcement.json
模板
evidence/world_class/templates/native-permission-enforcement.intake.json
阻断
1 blocked / 2 pass
修复
2 repair rows; counts as completion: false
下一步
Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.
阻断检查
  • Native enforcementnative_enforcement_count: 0 / >0Collect real target-client or external runtime guard proof.
修复清单
  • #20 · unblock-access · prechecknative-guardtarget client or installer integratorRequired external precheck is external-required.Attach a real target-client or external installer runtime guard; metadata fallback is not enough.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checknative_enforcement_counttarget client or installer integratorCurrent value 0 does not satisfy '>0'.Collect real target-client or external runtime guard proof.python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.
  2. Update the generated target adapter only when the guard is actually enforced by that target.
  3. python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip
采集契约
来源要求
  • real target client or external installer runtime guard
  • native enforcement flag or externally accepted guard proof
  • residual risk retained for fallback targets
通过条件
  • 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
证据资产
  • dist/targets/*/adapter.json
  • reports/runtime_permission_probes.json
  • reports/runtime_permission_probes.md
  • reports/install_simulation.json
  • reports/install_simulation.md
资产角色

source: world-class-submission-kit; counts as evidence: false; prefill counts as evidence: false

  • submission-ref2 / 2 readyartifact_refs: trueRows marked submission-ref are the aggregate paths expected in artifact_refs.
  • supporting-evidence11 / 11 readyartifact_refs: falseSupporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.
隐私边界
  • Do not mark native_enforcement true for metadata-only fallbacks.
  • Keep residual risks visible for targets that still rely on operator enforcement.
pending · external

Native Client Telemetry

external source events 0; adoption samples 0

提交
evidence/world_class/submissions/native-client-telemetry.json
模板
evidence/world_class/templates/native-client-telemetry.intake.json
阻断
2 blocked / 1 pass
修复
3 repair rows; counts as completion: false
下一步
Install a real client against the native host and import production metadata-only events.
阻断检查
  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
  • Adoption sampleadoption_sample_count: 0 / >0Telemetry must include adoption outcome evidence.
修复清单
  • #20 · unblock-access · precheckexternal-clientBrowser/Chrome/IDE/provider client integratorRequired external precheck is external-required.Install a real Browser, Chrome, IDE, or provider client that emits metadata-only events.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkadoption_sample_countBrowser/Chrome/IDE/provider client integratorCurrent value 0 does not satisfy '>0'.Telemetry must include adoption outcome evidence.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
  • #40 · collect-source · source-checkexternal_source_eventsBrowser/Chrome/IDE/provider client integratorCurrent value 0 does not satisfy '>0'.Import at least one metadata-only event from a real client.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
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. 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>/
  2. Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.
  3. python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
采集契约
来源要求
  • real external client source
  • metadata-only event
  • local-first import path
通过条件
  • 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
证据资产
  • 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
资产角色

source: world-class-submission-kit; counts as evidence: false; prefill counts as evidence: false

  • submission-ref2 / 2 readyartifact_refs: trueRows marked submission-ref are the aggregate paths expected in artifact_refs.
  • supporting-evidence6 / 6 readyartifact_refs: falseSupporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.
隐私边界
  • 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.
@@ -831,17 +831,17 @@
-

上下文

initial load 990/1000; deferred 507713/120000; top deferred scripts 446533; resource governance governed; quality density 131.3

+

上下文

initial load 990/1000; deferred 509352/120000; top deferred scripts 448172; resource governance governed; quality density 131.3

编译证据

Review reports/compiled_targets.md before packaging to inspect target adapter modes, generated files, preserved semantics, warnings, and unsupported features.

-

信任报告

Secret
0
脚本数
149
网络脚本
3
Help 失败
0
包体哈希
6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59
+

信任报告

Secret
0
脚本数
150
网络脚本
3
Help 失败
0
包体哈希
7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4

安全边界

高风险 secret、远程 inline execution、缺失依赖策略或无法解释的脚本接口应阻断 governed release。

-

Python 兼容

目标 Python
3.11
文件数
228
问题数
0
语法错误
0
F-string 3.11
0
+

Python 兼容

目标 Python
3.11
文件数
229
问题数
0
语法错误
0
F-string 3.11
0

解释器边界

CI 和发布审查以 Python 3.11 兼容为底线；本地更高版本允许的新语法不能绕过兼容门禁。

@@ -861,8 +861,8 @@
-

运营回路

1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true

-

漂移信号

事件数
1
采用率
100
漏触发
0
Bad Output Count
0
风险带
low
+

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true

+

漂移信号

事件数
1
采用率
0
漏触发
0
Bad Output Count
0
风险带
low
@@ -880,13 +880,13 @@

批准台账

Waiver Count
0
Active Count
0
Expired Count
0
Invalid Count
0
覆盖 Gate
0

批准候选

-
可批准 · needs-reviewer-decision

Output Lab

review pending 5; model-executed 0; output failures 0

Gate
output-lab
证据
reports/output_review_adjudication.md
选项
accepted-risk, false-positive, temporary-exception
边界
Does not count as provider, human, or public world-class completion evidence.

审查条件

  • Reviewer confirms this release does not claim provider-backed or human-adjudicated output superiority.
  • Reviewer names the release scope and expiry date.
  • Reviewer links output_review_adjudication or output_execution evidence.
建议命令python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md
不可批准 · cannot-waive

World-Class Evidence

4 pending evidence entries; 1 human pending; 3 external pending

Gate
world-class-evidence
证据
reports/world_class_evidence_ledger.md
选项
无
边界
Non-waivable completion boundary.

审查条件

  • Do not use a waiver to claim public world-class readiness.
  • Either submit accepted ledger evidence or state that this release does not claim world-class completion.
  • Keep claim guard active until ledger summary.ready_to_claim_world_class is true.
建议命令python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-claim-guard .
+
可批准 · needs-reviewer-decision

Output Lab

review pending 5; model-executed 0; output failures 0

Gate
output-lab
证据
reports/output_review_adjudication.md
选项
accepted-risk, false-positive, temporary-exception
边界
Does not count as provider, human, or public world-class completion evidence.

审查条件

  • Reviewer confirms this release does not claim provider-backed or human-adjudicated output superiority.
  • Reviewer names the release scope and expiry date.
  • Reviewer links output_review_adjudication or output_execution evidence.
建议命令python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-17 --evidence reports/output_review_adjudication.md
不可批准 · cannot-waive

World-Class Evidence

4 pending evidence entries; 1 human pending; 3 external pending

Gate
world-class-evidence
证据
reports/world_class_evidence_ledger.md
选项
无
边界
Non-waivable completion boundary.

审查条件

  • Do not use a waiver to claim public world-class readiness.
  • Either submit accepted ledger evidence or state that this release does not claim world-class completion.
  • Keep claim guard active until ledger summary.ready_to_claim_world_class is true.
建议命令python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-claim-guard .

世界证据

这里列出每个 world-class 证据项的当前状态、完成定义、证据来源、隐私约束和下一步；计划、metadata fallback、待评审和本地命令不会被当成完成证据。

-
待补证 · external

Provider Holdout

Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.

负责人
operator with provider credentials
当前状态
model-executed 0; token-observed 0
下一步
Run provider-backed holdout cases with real credentials and commit only aggregate evidence.
观测值
model_executed_count: 0; timing_observed_count: 10; token_observed_count: 0; accepted: False
提交态
status: missing; path: evidence/world_class/submissions/provider-holdout.json; attested_real_evidence: False; privacy_contract_satisfied: False

执行步骤

  • 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

完成定义

  • 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

证据来源

  • 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

隐私约束

  • Do not commit provider credentials or environment dumps.
  • The output execution report records output hashes and aggregate run metadata, not raw provider prompts.

源证据检查

  • Provider model runmodel_executed_count: 0 / >0Run provider-backed output-exec with real credentials.
  • Timing observedtiming_observed_count: 10 / >0Provider execution should record timing metadata.
  • Token usage observedtoken_observed_count: 0 / >0Provider execution should return non-estimated token usage.
待补证 · human

Human Adjudication

Record real blind A/B reviewer decisions before claiming human output review completion.

负责人
human reviewer
当前状态
0/5 decisions; pending 5
下一步
Record real A/B choices, reviewer metadata, and blind-review attestation, then regenerate adjudication.
观测值
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
提交态
status: missing; path: evidence/world_class/submissions/human-adjudication.json; attested_real_evidence: False; privacy_contract_satisfied: False

执行步骤

  • 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

完成定义

  • 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

证据来源

  • 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

隐私约束

  • 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.

源证据检查

  • Review pairs existpair_count: 5 / >0Generate the blind A/B review pack.
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice and reason for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
  • No invalid decisionsinvalid_decision_count: 0 / ==0Fix malformed winner/confidence entries.
  • Reviewer metadatareviewer_metadata_present: False / trueRecord reviewer and reviewed_at before adjudication can count.
  • Reason requiredreason_required: True / trueKeep reason mandatory for every imported or direct reviewer decision.
  • Blind review attestedblind_review_attested: False / trueSet reviewer_attestation only after choices are completed before opening the answer key.
  • Raw content attestedraw_content_excluded_attested: True / trueAttest that reviewer decisions exclude raw prompts, outputs, transcripts, messages, and private user content.
  • Raw content blockedraw_content_allowed: False / falseAdjudication evidence should store prompt hashes and reviewer metadata, not raw prompts, outputs, transcripts, or messages.
  • Human evidence readyready_for_human_evidence: False / trueComplete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints.
待补证 · external

Native Permission Enforcement

Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.

负责人
target client or installer integrator
当前状态
native-enforced targets 0; installer-enforced targets 4
下一步
Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.
观测值
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
提交态
status: missing; path: evidence/world_class/submissions/native-permission-enforcement.json; attested_real_evidence: False; privacy_contract_satisfied: False

执行步骤

  • 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

完成定义

  • 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

证据来源

  • 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

隐私约束

  • Do not mark native_enforcement true for metadata-only fallbacks.
  • Keep residual risks visible for targets that still rely on operator enforcement.

源证据检查

  • Native enforcementnative_enforcement_count: 0 / >0Collect real target-client or external runtime guard proof.
  • Probe failuresfailure_count: 0 / ==0Runtime permission probes must stay clean.
  • Installer supportinstaller_enforcement_ready: True / trueInstaller enforcement is supporting evidence, not native proof.
待补证 · external

Native Client Telemetry

Import production metadata-only events from a real external client into the local drift loop.

负责人
Browser/Chrome/IDE/provider client integrator
当前状态
external source events 0; adoption samples 1
下一步
Install a real client against the native host and import production metadata-only events.
观测值
external_source_events: 0; adoption_sample_count: 1; raw_content_allowed: False; risk_band: low; accepted: False
提交态
status: missing; path: evidence/world_class/submissions/native-client-telemetry.json; attested_real_evidence: False; privacy_contract_satisfied: False

执行步骤

  • 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

完成定义

  • 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

证据来源

  • 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

隐私约束

  • 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.

源证据检查

  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
  • Adoption sampleadoption_sample_count: 1 / >0Telemetry must include adoption outcome evidence.
  • Raw content blockedraw_content_allowed: False / falseTelemetry must stay metadata-only.
+
待补证 · external

Provider Holdout

Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.

负责人
operator with provider credentials
当前状态
model-executed 0; token-observed 0
下一步
Run provider-backed holdout cases with real credentials and commit only aggregate evidence.
观测值
model_executed_count: 0; timing_observed_count: 10; token_observed_count: 0; accepted: False
提交态
status: missing; path: evidence/world_class/submissions/provider-holdout.json; attested_real_evidence: False; privacy_contract_satisfied: False

执行步骤

  • 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

完成定义

  • 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

证据来源

  • 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

隐私约束

  • Do not commit provider credentials or environment dumps.
  • The output execution report records output hashes and aggregate run metadata, not raw provider prompts.

源证据检查

  • Provider model runmodel_executed_count: 0 / >0Run provider-backed output-exec with real credentials.
  • Timing observedtiming_observed_count: 10 / >0Provider execution should record timing metadata.
  • Token usage observedtoken_observed_count: 0 / >0Provider execution should return non-estimated token usage.
待补证 · human

Human Adjudication

Record real blind A/B reviewer decisions before claiming human output review completion.

负责人
human reviewer
当前状态
0/5 decisions; pending 5
下一步
Record real A/B choices, reviewer metadata, and blind-review attestation, then regenerate adjudication.
观测值
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
提交态
status: missing; path: evidence/world_class/submissions/human-adjudication.json; attested_real_evidence: False; privacy_contract_satisfied: False

执行步骤

  • 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

完成定义

  • 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

证据来源

  • 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

隐私约束

  • 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.

源证据检查

  • Review pairs existpair_count: 5 / >0Generate the blind A/B review pack.
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice and reason for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
  • No invalid decisionsinvalid_decision_count: 0 / ==0Fix malformed winner/confidence entries.
  • Reviewer metadatareviewer_metadata_present: False / trueRecord reviewer and reviewed_at before adjudication can count.
  • Reason requiredreason_required: True / trueKeep reason mandatory for every imported or direct reviewer decision.
  • Blind review attestedblind_review_attested: False / trueSet reviewer_attestation only after choices are completed before opening the answer key.
  • Raw content attestedraw_content_excluded_attested: True / trueAttest that reviewer decisions exclude raw prompts, outputs, transcripts, messages, and private user content.
  • Raw content blockedraw_content_allowed: False / falseAdjudication evidence should store prompt hashes and reviewer metadata, not raw prompts, outputs, transcripts, or messages.
  • Human evidence readyready_for_human_evidence: False / trueComplete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints.
待补证 · external

Native Permission Enforcement

Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.

负责人
target client or installer integrator
当前状态
native-enforced targets 0; installer-enforced targets 4
下一步
Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.
观测值
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
提交态
status: missing; path: evidence/world_class/submissions/native-permission-enforcement.json; attested_real_evidence: False; privacy_contract_satisfied: False

执行步骤

  • 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

完成定义

  • 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

证据来源

  • 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

隐私约束

  • Do not mark native_enforcement true for metadata-only fallbacks.
  • Keep residual risks visible for targets that still rely on operator enforcement.

源证据检查

  • Native enforcementnative_enforcement_count: 0 / >0Collect real target-client or external runtime guard proof.
  • Probe failuresfailure_count: 0 / ==0Runtime permission probes must stay clean.
  • Installer supportinstaller_enforcement_ready: True / trueInstaller enforcement is supporting evidence, not native proof.
待补证 · external

Native Client Telemetry

Import production metadata-only events from a real external client into the local drift loop.

负责人
Browser/Chrome/IDE/provider client integrator
当前状态
external source events 0; adoption samples 0
下一步
Install a real client against the native host and import production metadata-only events.
观测值
external_source_events: 0; adoption_sample_count: 0; raw_content_allowed: False; risk_band: low; accepted: False
提交态
status: missing; path: evidence/world_class/submissions/native-client-telemetry.json; attested_real_evidence: False; privacy_contract_satisfied: False

执行步骤

  • 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

完成定义

  • 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

证据来源

  • 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

隐私约束

  • 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.

源证据检查

  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
  • Adoption sampleadoption_sample_count: 0 / >0Telemetry must include adoption outcome evidence.
  • Raw content blockedraw_content_allowed: False / falseTelemetry must stay metadata-only.
@@ -901,12 +901,12 @@
-

公开声明

本地复现
是
发布锁
是
可公开声明
否
声明阻断
4
Provider 证据
否
人审完成
否
世界级就绪
否
-

声明阻断

+

公开声明

本地复现
是
发布锁
否
可公开声明
否
声明阻断
5
Provider 证据
否
人审完成
否
世界级就绪
否
+

声明阻断

-

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 10/19 pass; 9 blocked; overclaim guard true

+

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 9/19 pass; 10 blocked; overclaim guard true

证据台账

Ledger Entry Count
4
Accepted Count
0
待审
4
Human Pending Count
1
External Pending Count
3
Overclaim Guard Active
是
Ready To Claim World Class
否
@@ -922,12 +922,12 @@

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

-

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8
+

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

-

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
688
失败数
0
警告数
0
归档哈希
0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8
+

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
689
失败数
0
警告数
0
归档哈希
7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2
diff --git a/reports/review-studio.json b/reports/review-studio.json index c1a9c5ad..6aa30a2f 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -44,7 +44,7 @@ "key": "context-budget", "label": "上下文", "status": "pass", - "detail": "initial load 990/1000; deferred 507713/120000; top deferred scripts 446533; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 509352/120000; top deferred scripts 448172; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json", "link": "context_budget.md" }, @@ -60,7 +60,7 @@ "key": "trust-report", "label": "信任报告", "status": "pass", - "detail": "0 secrets; 149 scripts; 3 network-capable scripts; 0 help smoke failures", + "detail": "0 secrets; 150 scripts; 3 network-capable scripts; 0 help smoke failures", "evidence": "reports/security_trust_report.json", "link": "security_trust_report.md" }, @@ -68,7 +68,7 @@ "key": "python-compat", "label": "Python 兼容", "status": "pass", - "detail": "Python 3.11; 228 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards", + "detail": "Python 3.11; 229 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards", "evidence": "reports/python_compatibility.json", "link": "python_compatibility.md" }, @@ -76,7 +76,7 @@ "key": "architecture-maintainability", "label": "架构维护", "status": "pass", - "detail": "225 Python files; 0 hotspots; 0 watchlist files; 2 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint", + "detail": "226 Python files; 0 hotspots; 0 watchlist files; 2 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint", "evidence": "reports/architecture_maintainability.json", "link": "architecture_maintainability.md" }, @@ -108,7 +108,7 @@ "key": "operations-loop", "label": "运营回路", "status": "pass", - "detail": "1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true", + "detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true", "evidence": "reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly", "link": "adoption_drift_report.md" }, @@ -124,7 +124,7 @@ "key": "world-class-evidence", "label": "世界证据", "status": "warn", - "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 10/19 pass; 9 blocked; overclaim guard true", + "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 9/19 pass; 10 blocked; overclaim guard true", "evidence": "reports/world_class_evidence_ledger.json", "link": "world_class_evidence_ledger.md" }, @@ -212,7 +212,7 @@ "key": "world-class-evidence", "label": "世界证据", "status": "warn", - "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 10/19 pass; 9 blocked; overclaim guard true", + "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 9/19 pass; 10 blocked; overclaim guard true", "evidence": "reports/world_class_evidence_ledger.json", "link": "world_class_evidence_ledger.md" } @@ -1022,12 +1022,12 @@ "category": "external", "status": "pending", "readiness": "awaiting-submission", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "next_action": "Install a real client against the native host and import production metadata-only events.", "submission_path": "evidence/world_class/submissions/native-client-telemetry.json", "template_path": "evidence/world_class/templates/native-client-telemetry.intake.json", - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "blocked_checks": [ { "label": "External events", @@ -1036,6 +1036,14 @@ "expected": ">0", "status": "blocked", "next_action": "Import at least one metadata-only event from a real client." + }, + { + "label": "Adoption sample", + "field": "adoption_sample_count", + "actual": 0, + "expected": ">0", + "status": "blocked", + "next_action": "Telemetry must include adoption outcome evidence." } ], "repair_rows": [ @@ -1052,6 +1060,19 @@ "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", "counts_as_completion": false }, + { + "action_id": "native-client-telemetry-source-check-adoption_sample_count", + "repair_type": "source-check", + "target": "adoption_sample_count", + "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": "Telemetry must include adoption outcome evidence.", + "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 + }, { "action_id": "native-client-telemetry-source-check-external_source_events", "repair_type": "source-check", @@ -1066,7 +1087,7 @@ "counts_as_completion": false } ], - "repair_blocked_count": 2, + "repair_blocked_count": 3, "repair_counts_as_completion": false, "commands": [ { @@ -1610,7 +1631,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 19, - "source_pass_count": 10, + "source_pass_count": 9, "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -1670,7 +1691,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -1711,7 +1733,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 149 + "file_count": 150 }, { "path": "evals", @@ -1726,7 +1748,7 @@ "file_count": 235 } ], - "file_count": 452, + "file_count": 453, "folder_count": 4, "distribution": [ { @@ -1751,7 +1773,7 @@ }, { "label": "scripts", - "value": 149 + "value": 150 }, { "label": "evals", @@ -1881,7 +1903,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 149 + "file_count": 150 }, { "path": "evals", @@ -2203,13 +2225,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98", - "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "evidence_bundle_sha256": "7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a", + "source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -2224,18 +2246,18 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "public_claim_ready": false, - "public_claim_blocker_count": 4, + "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 19, - "source_tree_dirty": false, - "source_changed_file_count": 0, + "changed_file_count": 65, + "source_tree_dirty": true, + "source_changed_file_count": 4, "generated_tree_dirty": true, - "generated_changed_file_count": 19 + "generated_changed_file_count": 61 }, - "commit": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", + "commit": "2efe6413f04c9626ba52c554b4dc87baabd0b05b", "missing_artifacts": [], "limitations": [ "The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.", @@ -2319,9 +2341,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 241, - "script_count": 149, - "internal_module_count": 63, + "scanned_files": 242, + "script_count": 150, + "internal_module_count": 64, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -2339,8 +2361,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 241, - "package_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59" + "package_hash_file_count": 242, + "package_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4" }, "skill_atlas": { "skill_count": 12, @@ -2378,8 +2400,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8" + "package_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { "openai": "pass", @@ -2410,12 +2432,12 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-17" }, "failures": [], "warnings": [] @@ -2426,8 +2448,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", - "archive_entry_count": 688, + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", + "archive_entry_count": 689, "failure_count": 0, "warning_count": 0 }, @@ -2438,7 +2460,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 688, + "archive_entry_count": 689, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -2505,12 +2527,12 @@ { "field": "archive_sha256", "from": "", - "to": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8" + "to": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59" + "to": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4" } ] }, @@ -2527,14 +2549,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -2543,7 +2565,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -2818,7 +2840,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "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:///", @@ -2871,8 +2893,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -3298,7 +3320,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "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:///", @@ -3335,7 +3357,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -3356,8 +3378,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -3373,8 +3395,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", @@ -5024,7 +5046,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.21, + "duration_ms": 34.46, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5052,7 +5074,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.64, + "duration_ms": 33.43, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5075,7 +5097,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.14, + "duration_ms": 31.94, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5103,7 +5125,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.12, + "duration_ms": 30.52, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5126,7 +5148,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.94, + "duration_ms": 29.74, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5154,7 +5176,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.34, + "duration_ms": 28.9, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5177,7 +5199,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.98, + "duration_ms": 30.98, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5204,7 +5226,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.47, + "duration_ms": 30.58, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5227,7 +5249,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.51, + "duration_ms": 29.58, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5256,7 +5278,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.08, + "duration_ms": 30.13, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -6037,43 +6059,48 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", + "commit": "2efe6413f04c9626ba52c554b4dc87baabd0b05b", "git_status": { "available": true, "dirty": true, - "changed_file_count": 19, + "changed_file_count": 65, "generated_dirty": true, - "generated_changed_file_count": 19, - "source_dirty": false, - "source_changed_file_count": 0, + "generated_changed_file_count": 61, + "source_dirty": true, + "source_changed_file_count": 4, "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", " M reports/adoption_drift_report.json", + " M reports/adoption_drift_report.md", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", + " M reports/compiled_targets.json", " M reports/context_budget.json", - " M reports/context_budget_summary.json", - " M reports/evidence_consistency.json", - " M reports/output_execution_runs.json", - " M reports/output_execution_runs.md", - " M reports/review-studio.html", - " M reports/review-studio.json", - " M reports/review-viewer.json", - " M reports/skill-interpretation.html" + " M reports/context_budget.md", + " M reports/context_budget_summary.json" + ], + "source_sample": [ + " M scripts/prepare_world_class_submission_kit.py", + " M scripts/world_class_submission_kit_rendering.py", + " M tests/verify_world_class_submission_kit.py", + "?? scripts/world_class_phase_queue.py" ], - "source_sample": [], "generated_sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", " M reports/adoption_drift_report.json", + " M reports/adoption_drift_report.md", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", + " M reports/compiled_targets.json", " M reports/context_budget.json", - " M reports/context_budget_summary.json", - " M reports/evidence_consistency.json", - " M reports/output_execution_runs.json", - " M reports/output_execution_runs.md", - " M reports/review-studio.html", - " M reports/review-studio.json", - " M reports/review-viewer.json", - " M reports/skill-interpretation.html" + " M reports/context_budget.md", + " M reports/context_budget_summary.json" ], "generated_dirty_prefixes": [ "dist/", @@ -6087,13 +6114,13 @@ }, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98", - "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "evidence_bundle_sha256": "7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a", + "source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -6108,35 +6135,36 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "public_claim_ready": false, - "public_claim_blocker_count": 4, + "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 19, - "source_tree_dirty": false, - "source_changed_file_count": 0, + "changed_file_count": 65, + "source_tree_dirty": true, + "source_changed_file_count": 4, "generated_tree_dirty": true, - "generated_changed_file_count": 19 + "generated_changed_file_count": 61 }, "public_claim": { "ready": false, "scope": "public benchmark or world-class readiness claim", "blockers": [ + "release lock is not clean or commit is unavailable", "provider-backed model holdout evidence is incomplete", "human blind-review adjudication is incomplete", "world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)", - "world-class source checks are not all accepted (10/19 pass, 9 blocked)" + "world-class source checks are not all accepted (9/19 pass, 10 blocked)" ], "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks." }, "release_lock": { - "ready": true, - "commit": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", + "ready": false, + "commit": "2efe6413f04c9626ba52c554b4dc87baabd0b05b", "status_scope": "generation-time status before this report is written", - "source_changed_file_count": 0, - "generated_changed_file_count": 19, - "reason": "only generated evidence artifacts were dirty at generation time" + "source_changed_file_count": 4, + "generated_changed_file_count": 61, + "reason": "source files were dirty at generation time" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -6144,7 +6172,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98" + "sha256": "7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -6217,8 +6245,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7967, - "sha256": "3b9c37bdf02259b0e87d9f9fc5980512a2e95d9bcca32fd109b7a622d453b652" + "bytes": 7966, + "sha256": "f40063a2ada31c29a3ac9b5965f0887cad6bc19190ec0a3a6b15c92ce5c27b49" }, { "label": "blind_review", @@ -6252,106 +6280,106 @@ "label": "trust_report", "path": "reports/security_trust_report.json", "exists": true, - "bytes": 135139, - "sha256": "a18583795da7c3ffc0d355bc5465382b50f1a737a33e62b1e4b182496c9e4c5e" + "bytes": 135749, + "sha256": "b1d4729668d1dbf035b593e77dd2a3730e9aa4b3971014d37617ba5e0222df90" }, { "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, - "bytes": 29589, - "sha256": "364a150344f461934d36ca59c0f5f6e1ed487fbfa3b30cfdff548ded277dd5c5" + "bytes": 29715, + "sha256": "8b0d2a84027e0956b11acabc46e5ea5b9d7a311087b792eb57dd544bcd284671" }, { "label": "registry_audit", "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "d0157e4c0242955a3870f11eb00649f77e14b75f393874ea110b8f8e6eca89fb" + "sha256": "0a0ccb00f9f7769c56f109589983562e91f7663f2c96c219d284c3d36eafe58e" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "755a9c6788ccc0624682e523fe0154ac8b471bc4e41ed132f9866143762f398e" + "sha256": "7aa6c25e8154d246ace49f7ab9159fa85f96d1d4ebb7e2bb03c7b223260a908b" }, { "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, - "bytes": 8758, - "sha256": "15b77ec2b4738df891457d1d65f914751f30d6cd816a377e5c50c5a0b6d35b78" + "bytes": 8604, + "sha256": "34cc602c025c82a478a647d58008414f92c70e72046ca79979d3b038f3d793d2" }, { "label": "skill_os2_audit", "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14466, - "sha256": "16cbe378cc1a5ef847022c274af42ec8b6f7c346c8a06f59e6f6e3060d666177" + "sha256": "920bd7f7b3b0fb01c572ed12d9ff788a34a7592d00d9825004d3faba90ebb17b" }, { "label": "world_class_evidence_plan", "path": "reports/world_class_evidence_plan.json", "exists": true, "bytes": 22784, - "sha256": "4193115d881d4f68e61d2729633f88dd91d55d982af3db70691aafeba852f1ba" + "sha256": "2beb888d7992fc72073251632a6e85c4075278f9bcea946a46a7e11f8f43e0ca" }, { "label": "world_class_evidence_ledger", "path": "reports/world_class_evidence_ledger.json", "exists": true, - "bytes": 26016, - "sha256": "cb66d3284045b5993d25447f011cc70737dc760765ea3a3b7ae653194f0c4ff4" + "bytes": 26019, + "sha256": "22c85613d7bef62c4d0a4c94b77a8596090dc55c40e1663370d16d903e0b1ffb" }, { "label": "world_class_evidence_intake", "path": "reports/world_class_evidence_intake.json", "exists": true, "bytes": 20646, - "sha256": "002fbf07989a804595fdcb51b6d0c8177dc035a1dc8d084b8294a274d21fbc1b" + "sha256": "d3f44570e605e6e1b1557889ccca18efbbd8acc1d9a9c638f59961b3dc3e9026" }, { "label": "world_class_evidence_preflight", "path": "reports/world_class_evidence_preflight.json", "exists": true, - "bytes": 66981, - "sha256": "758807fa5749e0dd46f46d311abfad8af7dd70663e8876569b1a4b8414b42ace" + "bytes": 68674, + "sha256": "c9d5fc06305c41f0870f32f30c0440a95e6fbdba402326e339cfd0c771ff960d" }, { "label": "world_class_submission_review", "path": "reports/world_class_submission_review.json", "exists": true, - "bytes": 17299, - "sha256": "f5b1e0e44aeb6e1999182d40fca421ab0a66b91154efc7b518e9ed6f6ac20dd2" + "bytes": 17302, + "sha256": "96624a5b7f79aa0ac43ce60d30486290b9a91f0735254e31329f02e1ee291050" }, { "label": "world_class_operator_runbook", "path": "reports/world_class_operator_runbook.json", "exists": true, - "bytes": 28871, - "sha256": "8da2e2cde3adecec955f7745a4b761edc5af871d1720409cbd4f3b4b4482510e" + "bytes": 28935, + "sha256": "a7b7809d3b423bf647a528c3b0f6991f2ea3874afdd93a4d6ba74eb189131f2a" }, { "label": "world_class_operator_runbook_markdown", "path": "reports/world_class_operator_runbook.md", "exists": true, - "bytes": 17521, - "sha256": "bfac92bc14f3080b9d723f32a4848aa3cfc10d4c3ee2e3844b65153f34c87c0a" + "bytes": 17576, + "sha256": "d72777b421b57f0cf8f31b4d048cf92512e49216d0b0c05cec1686d4aea638ce" }, { "label": "world_class_operator_runbook_html", "path": "reports/world_class_operator_runbook.html", "exists": true, - "bytes": 23958, - "sha256": "46b435f98d8a91501580fa1426a8ab0d0f57b3bc92ecd17f42332e655fd2bd85" + "bytes": 24019, + "sha256": "73d8ef2898f25ae899a618b723f40a6907646c303effa21cbde6156d01a95fc7" }, { "label": "world_class_claim_guard", "path": "reports/world_class_claim_guard.json", "exists": true, "bytes": 18596, - "sha256": "c846ffc8565a40c270e711a58e968b005afd75be6df1a442b020deebe850386f" + "sha256": "abe7f7d60c0025e140373fadaefbed4063f285c140c74b9c7cfb464e354bb526" } ], "missing_artifacts": [], @@ -6491,7 +6519,7 @@ "skill_os2_coverage": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "summary": { "item_count": 21, @@ -6620,7 +6648,7 @@ "label": "Trust Security", "status": "pass", "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.", - "current": "149 scripts; secrets 0; help failures 0", + "current": "150 scripts; secrets 0; help failures 0", "command": "python3 scripts/yao.py trust .", "test": "python3 tests/verify_trust_check.py", "evidence": [ @@ -6694,7 +6722,7 @@ "label": "Registry Distribution", "status": "pass", "objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.", - "current": "archive entries 688; install failures 0", + "current": "archive entries 689; install failures 0", "command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .", "test": "python3 tests/verify_registry_audit.py", "evidence": [ @@ -7302,7 +7330,7 @@ "compiled_targets": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "summary": { "target_count": 5, @@ -12271,7 +12299,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "package_dir": "tests/tmp_review_studio/dist", + "package_dir": "dist", "expected_capabilities": [ "file_write", "network", @@ -12311,7 +12339,7 @@ { "target": "openai", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json", + "adapter": "dist/targets/openai/adapter.json", "permission_model": "metadata-only", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -12408,7 +12436,7 @@ { "target": "claude", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json", + "adapter": "dist/targets/claude/adapter.json", "permission_model": "neutral-source-plus-adapter", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -12490,7 +12518,7 @@ { "target": "generic", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json", + "adapter": "dist/targets/generic/adapter.json", "permission_model": "agent-skills-compatible-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -12572,7 +12600,7 @@ { "target": "vscode", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json", + "adapter": "dist/targets/vscode/adapter.json", "permission_model": "vscode-workspace-trust-plus-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -12662,9 +12690,9 @@ "ok": true, "skill_dir": ".", "summary": { - "scanned_files": 241, - "script_count": 149, - "internal_module_count": 63, + "scanned_files": 242, + "script_count": 150, + "internal_module_count": 64, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -12682,8 +12710,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 241, - "package_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59" + "package_hash_file_count": 242, + "package_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4" }, "failures": [], "warnings": [], @@ -14540,6 +14568,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/world_class_phase_queue.py", + "interface": "internal-module", + "interface_declared": true, + "interface_reason": "Imported by prepare_world_class_submission_kit.py to group repair rows into an operator execution queue.", + "has_argparse": false, + "has_main_guard": false, + "uses_input": false, + "uses_network": false, + "uses_file_write": false, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/world_class_preflight_layout.py", "interface": "internal-module", @@ -14827,7 +14869,7 @@ "checked_count": 86, "passed_count": 86, "failed_count": 0, - "skipped_count": 63, + "skipped_count": 64, "failed_scripts": [], "results": [ { @@ -15876,6 +15918,10 @@ "path": "scripts/world_class_native_telemetry_evidence.py", "reason": "internal module" }, + { + "path": "scripts/world_class_phase_queue.py", + "reason": "internal module" + }, { "path": "scripts/world_class_preflight_layout.py", "reason": "internal module" @@ -16137,11 +16183,11 @@ "python_compatibility": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "root": ".", "summary": { "target_python": "3.11", - "file_count": 228, + "file_count": 229, "issue_count": 0, "syntax_error_count": 0, "fstring_311_violation_count": 0, @@ -16962,6 +17008,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/world_class_phase_queue.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/world_class_preflight_layout.py", "ok": true, @@ -17536,13 +17588,13 @@ "architecture_maintainability": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "summary": { - "python_file_count": 225, - "script_file_count": 149, + "python_file_count": 226, + "script_file_count": 150, "test_file_count": 76, - "internal_module_count": 65, + "internal_module_count": 66, "cli_script_count": 86, "command_handler_count": 68, "entrypoint_command_handler_count": 18, @@ -17631,6 +17683,14 @@ "early_watch": false, "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." }, + { + "path": "scripts/world_class_submission_kit_rendering.py", + "lines": 576, + "kind": "internal-module", + "severity": "pass", + "early_watch": false, + "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." + }, { "path": "scripts/render_evidence_consistency.py", "lines": 571, @@ -17646,14 +17706,6 @@ "severity": "pass", "early_watch": false, "recommendation": "Move data loading and large section renderers into focused review_studio_* modules." - }, - { - "path": "scripts/adjudicate_output_review.py", - "lines": 566, - "kind": "cli-script", - "severity": "pass", - "early_watch": false, - "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." } ], "watchlist": [], @@ -17690,16 +17742,16 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1112796, + "other_text_tokens": 1115108, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1113593, - "deferred_resource_tokens": 507713, + "estimated_total_text_tokens": 1115905, + "deferred_resource_tokens": 509352, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 446533, - "file_count": 149 + "estimated_tokens": 448172, + "file_count": 150 }, { "path": "references", @@ -17720,8 +17772,8 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 446533, - "file_count": 149 + "estimated_tokens": 448172, + "file_count": 150 } ], "deferred_resource_governance": { @@ -17743,14 +17795,14 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 446533, - "file_count": 149, + "estimated_tokens": 448172, + "file_count": 150, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } ], "summary": "Large deferred resources are indexed and backed by evidence." }, - "relevant_file_count": 704, + "relevant_file_count": 706, "unused_resource_dirs": [], "quality_signal_points": 130, "quality_density": 131.3 @@ -18594,7 +18646,7 @@ }, "catalog": { "workspace_root": ".", - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skills": [ { "name": "yao-meta-skill", @@ -18745,6 +18797,7 @@ "scripts/world_class_human_evidence.py", "scripts/world_class_native_permission_evidence.py", "scripts/world_class_native_telemetry_evidence.py", + "scripts/world_class_phase_queue.py", "scripts/world_class_preflight_layout.py", "scripts/world_class_provider_evidence.py", "scripts/world_class_repair_checklist.py", @@ -18833,8 +18886,8 @@ "report": "reports/adoption_drift_report.json", "risk_band": "low", "event_count": 1, - "adoption_sample_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "adoption_rate": 0, "candidate_count": 0 } }, @@ -19497,7 +19550,7 @@ "name": "incident-command-governor", "path": "examples/governed-incident-command/generated-skill", "reason": "review overdue by cadence monthly", - "age_days": 74, + "age_days": 78, "allowed_days": 31, "actionable": false, "scope": "example" @@ -19665,7 +19718,7 @@ "adoption_drift": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-16T20:23:32Z", + "generated_at": "2026-06-17", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -19689,14 +19742,14 @@ }, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -19705,7 +19758,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -19717,31 +19770,31 @@ { "skill": "yao-meta-skill", "events": 1, - "adoption_events": 1, - "accepted": 1, + "adoption_events": 0, + "accepted": 0, "edited": 0, "rejected": 0, "missed": 0, - "adoption_rate": 100.0 + "adoption_rate": 0 } ], "next_iteration_candidates": [], "recent_events": [ { "command": "unknown", - "event": "skill_activation", + "event": "review_event", "skill": "yao-meta-skill", "source": "manual", "version": "1.1.0", - "activation_type": "explicit", - "outcome": "accepted", + "activation_type": "manual", + "outcome": "reviewed", "failure_type": "none", - "timestamp": "2026-06-13T10:00:00Z" + "timestamp": "2026-06-13T12:00:00Z" } ], "failures": [], "artifacts": { - "events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl", + "events_jsonl": "reports/telemetry_events.jsonl", "json": "reports/adoption_drift_report.json", "markdown": "reports/adoption_drift_report.md" } @@ -20585,7 +20638,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "summary": { "waiver_count": 0, "active_count": 0, @@ -20675,7 +20728,7 @@ "Reviewer links output_review_adjudication or output_execution evidence." ], "suggested_evidence": "reports/output_review_adjudication.md", - "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md", + "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-17 --evidence reports/output_review_adjudication.md", "world_class_boundary": "Does not count as provider, human, or public world-class completion evidence." }, { @@ -20705,7 +20758,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "source": "tests/tmp_review_studio/empty_review_annotations_input.json", + "source": "reports/review_annotations_input.json", "summary": { "annotation_count": 0, "open_count": 0, @@ -21126,7 +21179,7 @@ "world_class_evidence_ledger": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "decision": "evidence-pending", "ready_to_claim_world_class": false, @@ -21141,8 +21194,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -21158,8 +21211,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -21611,7 +21664,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "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:///", @@ -21648,7 +21701,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -21669,8 +21722,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -21686,8 +21739,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", @@ -21728,7 +21781,7 @@ "world_class_evidence_intake": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "summary": { "schema_present": true, @@ -22055,7 +22108,7 @@ "source_accepted": false, "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -22139,14 +22192,14 @@ "collection_ready_count": 1, "collection_blocked_count": 3, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, - "repair_checklist_count": 13, - "repair_blocked_count": 13, + "source_pass_count": 9, + "source_blocked_count": 10, + "repair_checklist_count": 14, + "repair_blocked_count": 14, "repair_ready_count": 0, "repair_phase_counts": { "unblock-access": 4, - "collect-source": 9 + "collect-source": 10 }, "next_repair_action_id": "human-adjudication-precheck-human-reviewer", "next_repair_phase": "unblock-access", @@ -22903,8 +22956,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -22988,6 +23041,21 @@ "source": "prechecks", "counts_as_completion": false }, + { + "action_id": "native-client-telemetry-source-check-adoption_sample_count", + "evidence_key": "native-client-telemetry", + "repair_type": "source-check", + "target": "adoption_sample_count", + "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": "Telemetry must include adoption outcome evidence.", + "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-client-telemetry-source-check-external_source_events", "evidence_key": "native-client-telemetry", @@ -23351,8 +23419,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -23503,6 +23571,21 @@ "source": "source_checklist", "counts_as_completion": false }, + { + "action_id": "native-client-telemetry-source-check-adoption_sample_count", + "evidence_key": "native-client-telemetry", + "repair_type": "source-check", + "target": "adoption_sample_count", + "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": "Telemetry must include adoption outcome evidence.", + "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-client-telemetry-source-check-external_source_events", "evidence_key": "native-client-telemetry", @@ -23619,7 +23702,7 @@ "world_class_submission_review": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "decision": "awaiting-submissions", "ready_to_claim_world_class": false, @@ -23632,8 +23715,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "review_counts_submission_as_completion": false, "summary": { "review_item_count": 4, @@ -23645,8 +23728,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "ready_to_claim_world_class": false, "review_counts_submission_as_completion": false, "decision": "awaiting-submissions" @@ -23996,7 +24079,7 @@ "intake_errors": [], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -24017,8 +24100,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -24034,8 +24117,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "success_checks": [ "reports/adoption_drift_report.json summary.source_types.external > 0", "reports/adoption_drift_report.json summary.adoption_sample_count > 0", @@ -24061,7 +24144,7 @@ "world_class_operator_runbook": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "summary": { "evidence_item_count": 4, @@ -24072,8 +24155,8 @@ "valid_packet_source_incomplete_count": 0, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "ready_to_claim_world_class": false, "runbook_counts_as_completion": false, "decision": "collect-evidence" @@ -24547,7 +24630,7 @@ "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", + "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:///", "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.", @@ -24595,7 +24678,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -24616,8 +24699,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -24632,9 +24715,10 @@ "next_action": "Telemetry must stay metadata-only." } ], - "blocked_source_check_count": 1, + "blocked_source_check_count": 2, "next_source_actions": [ - "Import at least one metadata-only event from a real client." + "Import at least one metadata-only event from a real client.", + "Telemetry must include adoption outcome evidence." ], "submission_state": { "status": "missing", @@ -24670,7 +24754,7 @@ "world_class_claim_guard": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "summary": { "ledger_ready_to_claim_world_class": false, @@ -25473,8 +25557,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8" + "package_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { "openai": "pass", @@ -25505,16 +25589,16 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-17" }, "index": { "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "package_count": 1, "packages": [ { @@ -25530,7 +25614,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59" + "package_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4" } ] }, @@ -25553,8 +25637,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", - "archive_entry_count": 688, + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", + "archive_entry_count": 689, "failure_count": 0, "warning_count": 0 }, @@ -26212,14 +26296,14 @@ "install_simulation": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", - "package_dir": "tests/tmp_review_studio/dist", - "install_root": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill", - "installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill", + "package_dir": "dist", + "install_root": "dist/install-simulation/simulate-yao-meta-skill", + "installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill", "summary": { "archive_present": true, - "archive_entry_count": 688, + "archive_entry_count": 689, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -26237,7 +26321,7 @@ { "id": "archive-present", "status": "pass", - "detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip" + "detail": "Package archive exists: dist/yao-meta-skill.zip" }, { "id": "archive-safe-paths", @@ -26483,16 +26567,16 @@ "failures": [], "warnings": [], "artifacts": { - "archive": "tests/tmp_review_studio/dist/yao-meta-skill.zip", - "package_manifest": "tests/tmp_review_studio/dist/manifest.json", - "json": "tests/tmp_review_studio/install_simulation.json", - "markdown": "tests/tmp_review_studio/install_simulation.md" + "archive": "dist/yao-meta-skill.zip", + "package_manifest": "dist/manifest.json", + "json": "reports/install_simulation.json", + "markdown": "reports/install_simulation.md" } }, "upgrade_check": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "previous": { "name": "yao-meta-skill", "version": "1.0.0", @@ -26561,12 +26645,12 @@ { "field": "archive_sha256", "from": "", - "to": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8" + "to": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59" + "to": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4" } ] }, @@ -26581,8 +26665,8 @@ "artifacts": { "previous_package": "registry/examples/yao-meta-skill-1.0.0.json", "current_package": "reports/registry_audit.json", - "json": "tests/tmp_review_studio/upgrade_check.json", - "markdown": "tests/tmp_review_studio/upgrade_check.md" + "json": "reports/upgrade_check.json", + "markdown": "reports/upgrade_check.md" } }, "manifest": { diff --git a/reports/review-viewer.json b/reports/review-viewer.json index e06b629b..93e9cd40 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -412,7 +412,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 19, - "source_pass_count": 10, + "source_pass_count": 9, "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -472,7 +472,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -513,7 +514,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 149 + "file_count": 150 }, { "path": "evals", @@ -528,7 +529,7 @@ "file_count": 235 } ], - "file_count": 452, + "file_count": 453, "folder_count": 4, "distribution": [ { @@ -553,7 +554,7 @@ }, { "label": "scripts", - "value": 149 + "value": 150 }, { "label": "evals", @@ -683,7 +684,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 149 + "file_count": 150 }, { "path": "evals", @@ -1005,13 +1006,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98", - "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "evidence_bundle_sha256": "7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a", + "source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1026,18 +1027,18 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "public_claim_ready": false, - "public_claim_blocker_count": 4, + "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 19, - "source_tree_dirty": false, - "source_changed_file_count": 0, + "changed_file_count": 65, + "source_tree_dirty": true, + "source_changed_file_count": 4, "generated_tree_dirty": true, - "generated_changed_file_count": 19 + "generated_changed_file_count": 61 }, - "commit": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", + "commit": "2efe6413f04c9626ba52c554b4dc87baabd0b05b", "missing_artifacts": [], "limitations": [ "The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.", @@ -1121,9 +1122,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 241, - "script_count": 149, - "internal_module_count": 63, + "scanned_files": 242, + "script_count": 150, + "internal_module_count": 64, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -1141,8 +1142,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 241, - "package_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59" + "package_hash_file_count": 242, + "package_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4" }, "skill_atlas": { "skill_count": 12, @@ -1180,8 +1181,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8" + "package_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { "openai": "pass", @@ -1212,12 +1213,12 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-17" }, "failures": [], "warnings": [] @@ -1228,8 +1229,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", - "archive_entry_count": 688, + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", + "archive_entry_count": 689, "failure_count": 0, "warning_count": 0 }, @@ -1240,7 +1241,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 688, + "archive_entry_count": 689, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1307,12 +1308,12 @@ { "field": "archive_sha256", "from": "", - "to": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8" + "to": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59" + "to": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4" } ] }, @@ -1329,14 +1330,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -1345,7 +1346,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -1620,7 +1621,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "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:///", @@ -1673,8 +1674,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -2100,7 +2101,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "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:///", @@ -2137,7 +2138,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -2158,8 +2159,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -2175,8 +2176,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index a9efcc69..94ac8d20 100644 --- a/reports/security_trust_report.json +++ b/reports/security_trust_report.json @@ -2,9 +2,9 @@ "ok": true, "skill_dir": ".", "summary": { - "scanned_files": 241, - "script_count": 149, - "internal_module_count": 63, + "scanned_files": 242, + "script_count": 150, + "internal_module_count": 64, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -22,8 +22,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 241, - "package_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59" + "package_hash_file_count": 242, + "package_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4" }, "failures": [], "warnings": [], @@ -1880,6 +1880,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/world_class_phase_queue.py", + "interface": "internal-module", + "interface_declared": true, + "interface_reason": "Imported by prepare_world_class_submission_kit.py to group repair rows into an operator execution queue.", + "has_argparse": false, + "has_main_guard": false, + "uses_input": false, + "uses_network": false, + "uses_file_write": false, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/world_class_preflight_layout.py", "interface": "internal-module", @@ -2167,7 +2181,7 @@ "checked_count": 86, "passed_count": 86, "failed_count": 0, - "skipped_count": 63, + "skipped_count": 64, "failed_scripts": [], "results": [ { @@ -3216,6 +3230,10 @@ "path": "scripts/world_class_native_telemetry_evidence.py", "reason": "internal module" }, + { + "path": "scripts/world_class_phase_queue.py", + "reason": "internal module" + }, { "path": "scripts/world_class_preflight_layout.py", "reason": "internal module" diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index 907fa0fe..9303f48e 100644 --- a/reports/security_trust_report.md +++ b/reports/security_trust_report.md @@ -1,9 +1,9 @@ # Security Trust Report - OK: `True` -- Scanned files: `241` -- Scripts: `149` -- Internal script modules: `63` +- Scanned files: `242` +- Scripts: `150` +- Internal script modules: `64` - Secret findings: `0` - Network-capable scripts: `3` - Network policy covered scripts: `3` @@ -15,8 +15,8 @@ - CLI help smoke failures: `0` - Interactive scripts: `0` - Package hash scope: `source-contract-without-generated-reports` -- Package hash files: `241` -- Package SHA256: `6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59` +- Package hash files: `242` +- Package SHA256: `7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4` ## Failures @@ -193,6 +193,7 @@ | scripts/world_class_human_evidence.py | internal-module | True | False | False | False | False | False | False | Imported by world_class_evidence_contract.py to validate blind A/B human adjudication evidence from decision rows. | | scripts/world_class_native_permission_evidence.py | internal-module | True | False | False | False | False | False | False | Imported by world_class_evidence_contract.py to validate runtime permission evidence from target-level probe rows. | | scripts/world_class_native_telemetry_evidence.py | internal-module | True | False | False | False | False | False | False | Imported by world_class_evidence_contract.py to validate native client telemetry evidence from metadata event rows. | +| scripts/world_class_phase_queue.py | internal-module | True | False | False | False | False | False | False | Imported by prepare_world_class_submission_kit.py to group repair rows into an operator execution queue. | | scripts/world_class_preflight_layout.py | internal-module | True | False | False | False | False | False | False | Imported by render_world_class_preflight.py to keep preflight HTML layout out of data assembly. | | scripts/world_class_provider_evidence.py | internal-module | True | False | False | False | False | False | False | Imported by world_class_evidence_contract.py to validate provider-backed holdout execution evidence from run rows. | | scripts/world_class_repair_checklist.py | internal-module | True | False | False | False | False | False | False | Shared by submission kit generation to turn readiness blockers into actionable repair rows. | diff --git a/reports/skill-interpretation.html b/reports/skill-interpretation.html index 59c5cc59..a6960d7c 100644 --- a/reports/skill-interpretation.html +++ b/reports/skill-interpretation.html @@ -929,7 +929,7 @@ -

世界证据World Evidence

世界级证据尚未完成：4 项待补，0 项已接受。World-class evidence is not complete: 4 pending, 0 accepted.

证据待补Evidence pending
待补证据Pending4仍需外部或人工证据接受。External or human evidence still needs acceptance.
已接受Accepted0已通过 source check 与提交契约。Passed source checks and submission contract.
源检查Source Checks10 / 19通过数 / 总检查数。Passed checks / total checks.
外部证据External evidence

提供商留出Provider Holdout

缺少真实 provider 模型运行和 token metadata。Missing a real provider model run and token metadata.

阻塞检查Blocked Checks
  • 提供商实跑Provider model run
  • Token 用量Token usage observed
人工证据Human evidence

人工盲评Human Adjudication

盲评 pair 仍待真实 reviewer 决策。Blind-review pairs still need real reviewer decisions.

阻塞检查Blocked Checks
  • 无待判定No pending decisions
  • 盲评完成Judgments complete
  • Reviewer metadataReviewer metadata
外部证据External evidence

原生权限Native Permission

原生 runtime enforcement 仍待目标客户端或外部安装器证明。Native runtime enforcement still needs target-client or external-installer proof.

阻塞检查Blocked Checks
  • 原生执行Native enforcement
外部证据External evidence

原生遥测Native Telemetry

真实外部客户端 metadata-only 事件仍未导入。Real external-client metadata-only events have not been imported yet.

阻塞检查Blocked Checks
  • 外部事件External events
+

世界证据World Evidence

世界级证据尚未完成：4 项待补，0 项已接受。World-class evidence is not complete: 4 pending, 0 accepted.

证据待补Evidence pending
待补证据Pending4仍需外部或人工证据接受。External or human evidence still needs acceptance.
已接受Accepted0已通过 source check 与提交契约。Passed source checks and submission contract.
源检查Source Checks9 / 19通过数 / 总检查数。Passed checks / total checks.
外部证据External evidence

提供商留出Provider Holdout

缺少真实 provider 模型运行和 token metadata。Missing a real provider model run and token metadata.

阻塞检查Blocked Checks
  • 提供商实跑Provider model run
  • Token 用量Token usage observed
人工证据Human evidence

人工盲评Human Adjudication

盲评 pair 仍待真实 reviewer 决策。Blind-review pairs still need real reviewer decisions.

阻塞检查Blocked Checks
  • 无待判定No pending decisions
  • 盲评完成Judgments complete
  • Reviewer metadataReviewer metadata
外部证据External evidence

原生权限Native Permission

原生 runtime enforcement 仍待目标客户端或外部安装器证明。Native runtime enforcement still needs target-client or external-installer proof.

阻塞检查Blocked Checks
  • 原生执行Native enforcement
外部证据External evidence

原生遥测Native Telemetry

真实外部客户端 metadata-only 事件仍未导入。Real external-client metadata-only events have not been imported yet.

阻塞检查Blocked Checks
  • 外部事件External events
  • 采用样本Adoption sample
@@ -940,7 +940,7 @@

让 reviewer 快速确认关键文件、目录和资产分布。Lets reviewers confirm key files, directories, and asset distribution quickly.

-
资产分布Asset Distribution452项452 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
+
资产分布Asset Distribution453项453 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index 48bc16b6..ba5c0fc0 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -412,7 +412,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 19, - "source_pass_count": 10, + "source_pass_count": 9, "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -472,7 +472,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -513,7 +514,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 149 + "file_count": 150 }, { "path": "evals", @@ -528,7 +529,7 @@ "file_count": 235 } ], - "file_count": 452, + "file_count": 453, "folder_count": 4, "distribution": [ { @@ -553,7 +554,7 @@ }, { "label": "scripts", - "value": 149 + "value": 150 }, { "label": "evals", @@ -687,7 +688,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 149 + "file_count": 150 }, { "path": "evals", @@ -1009,13 +1010,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98", - "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "evidence_bundle_sha256": "7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a", + "source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1030,18 +1031,18 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "public_claim_ready": false, - "public_claim_blocker_count": 4, + "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 19, - "source_tree_dirty": false, - "source_changed_file_count": 0, + "changed_file_count": 65, + "source_tree_dirty": true, + "source_changed_file_count": 4, "generated_tree_dirty": true, - "generated_changed_file_count": 19 + "generated_changed_file_count": 61 }, - "commit": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", + "commit": "2efe6413f04c9626ba52c554b4dc87baabd0b05b", "missing_artifacts": [], "limitations": [ "The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.", @@ -1125,9 +1126,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 241, - "script_count": 149, - "internal_module_count": 63, + "scanned_files": 242, + "script_count": 150, + "internal_module_count": 64, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -1145,8 +1146,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 241, - "package_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59" + "package_hash_file_count": 242, + "package_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4" }, "skill_atlas": { "skill_count": 12, @@ -1184,8 +1185,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8" + "package_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { "openai": "pass", @@ -1216,12 +1217,12 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-17" }, "failures": [], "warnings": [] @@ -1232,8 +1233,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", - "archive_entry_count": 688, + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", + "archive_entry_count": 689, "failure_count": 0, "warning_count": 0 }, @@ -1244,7 +1245,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 688, + "archive_entry_count": 689, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1311,12 +1312,12 @@ { "field": "archive_sha256", "from": "", - "to": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8" + "to": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59" + "to": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4" } ] }, @@ -1333,14 +1334,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -1349,7 +1350,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -1624,7 +1625,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "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:///", @@ -1677,8 +1678,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -2104,7 +2105,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "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:///", @@ -2141,7 +2142,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -2162,8 +2163,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -2179,8 +2180,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", diff --git a/reports/skill-os-2-review.md b/reports/skill-os-2-review.md index 5e83d83f..7cc858d0 100644 --- a/reports/skill-os-2-review.md +++ b/reports/skill-os-2-review.md @@ -135,13 +135,13 @@ Next move: add real client or installer permission enforcement integration. | Output Eval | `5` cases, with-skill pass rate `100`, baseline pass rate `0`, with file-backed, near-neighbor, boundary coverage, `10` local command-runner execution runs, `0` recorded fixture runs, `0` provider model-executed runs in root release evidence, `10` estimated token counts, provider runner v0 available, `5` blind A/B review pairs, a generated `reports/output_review_decisions.json` template, `0 / 5` reviewer decisions pending, `0` answer keys revealed, and `5` pending answers hidden | | Runtime Conformance | `5 / 5` targets passing | | Target Compiler | `5 / 5` compiled target contracts generated for OpenAI, Claude, generic, Agent Skills compatible, and VS Code / Copilot outputs, including target permission contracts and target-native behavior contracts | -| Trust | `0` secret findings, `1` pinned dependency file, `63` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `86 / 86` CLI help smoke checks passing across `149` scripts, source-contract hash scope explicit | +| Trust | `0` secret findings, `1` pinned dependency file, `64` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `86 / 86` CLI help smoke checks passing across `150` scripts, source-contract hash scope explicit | | Permission Governance | `3 / 3` required high-permission capabilities approved, `0` missing, `0` invalid, `0` expired | | Runtime Permission Probes | `4 / 4` target adapters probed, `0` native-enforcement adapters, `4` explicit metadata fallbacks, `4` residual risks retained for reviewer visibility | | Skill Atlas | `12` scanned skills, `1` actionable root skill, `1` telemetry report, `0` actionable route collisions, `0` actionable owner gaps, `0` actionable stale skills, `0` actionable drift signals, `24` scoped non-actionable issue signals retained for visibility | | Registry Audit | package metadata generated with version, owner, license, source checksum, archive checksum, Skill IR provenance, and compatibility matrix | -| Package Verification | `4 / 4` target adapters present, archive verified, `688` zip entries, `0` failures, `0` warnings | -| Install Simulation | archive with `688` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings | +| Package Verification | `4 / 4` target adapters present, archive verified, `689` zip entries, `0` failures, `0` warnings | +| Install Simulation | archive with `689` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings | | Local Install Sync Preflight | `make sync-local-install` and `make sync-active-install` rebuild the package first, then sync only after install simulation passes with `12` enforced installer permission checks and `0` permission failures | | Upgrade Check | current package declares `minor` over the 1.0.0 baseline, recommended bump is `minor`, and release notes include added targets plus checksum changes | | Adoption Drift | `1` metadata-only review event, `1` adoption sample, adoption `100`, risk band `low`; optional `yao.py` CLI capture, external client `telemetry-emit`, `5` `telemetry-hooks` recipes, Browser/Chrome native messaging host, and validated external JSONL import are available but off by default for reproducible release evidence; raw `reports/telemetry_events.jsonl` is gitignored and blocked from zip packages | diff --git a/reports/skill-overview.html b/reports/skill-overview.html index ea471080..ccaf8645 100644 --- a/reports/skill-overview.html +++ b/reports/skill-overview.html @@ -929,7 +929,7 @@
路径Path作用Role类型Type
SKILL.mdSkill 入口文件Skill entrypoint文件file
README.md人类可读使用说明Human-readable usage guide文件file
agents/interface.yaml跨平台接口元数据Neutral interface metadata文件file
manifest.json生命周期与打包元数据Lifecycle and portability metadata文件file
references扩展指导与复用资料Extended guidance and reusable notes目录folder
scripts确定性脚本或本地工具Deterministic helpers or local tooling目录folder
evals触发与质量检查Trigger and quality checks目录folder
reports生成的证据与总结报告Generated evidence and overview artifacts目录folder
-

世界证据World Evidence

世界级证据尚未完成：4 项待补，0 项已接受。World-class evidence is not complete: 4 pending, 0 accepted.

证据待补Evidence pending
待补证据Pending4仍需外部或人工证据接受。External or human evidence still needs acceptance.
已接受Accepted0已通过 source check 与提交契约。Passed source checks and submission contract.
源检查Source Checks10 / 19通过数 / 总检查数。Passed checks / total checks.
外部证据External evidence

提供商留出Provider Holdout

缺少真实 provider 模型运行和 token metadata。Missing a real provider model run and token metadata.

阻塞检查Blocked Checks
  • 提供商实跑Provider model run
  • Token 用量Token usage observed
人工证据Human evidence

人工盲评Human Adjudication

盲评 pair 仍待真实 reviewer 决策。Blind-review pairs still need real reviewer decisions.

阻塞检查Blocked Checks
  • 无待判定No pending decisions
  • 盲评完成Judgments complete
  • Reviewer metadataReviewer metadata
外部证据External evidence

原生权限Native Permission

原生 runtime enforcement 仍待目标客户端或外部安装器证明。Native runtime enforcement still needs target-client or external-installer proof.

阻塞检查Blocked Checks
  • 原生执行Native enforcement
外部证据External evidence

原生遥测Native Telemetry

真实外部客户端 metadata-only 事件仍未导入。Real external-client metadata-only events have not been imported yet.

阻塞检查Blocked Checks
  • 外部事件External events
+

世界证据World Evidence

世界级证据尚未完成：4 项待补，0 项已接受。World-class evidence is not complete: 4 pending, 0 accepted.

证据待补Evidence pending
待补证据Pending4仍需外部或人工证据接受。External or human evidence still needs acceptance.
已接受Accepted0已通过 source check 与提交契约。Passed source checks and submission contract.
源检查Source Checks9 / 19通过数 / 总检查数。Passed checks / total checks.
外部证据External evidence

提供商留出Provider Holdout

缺少真实 provider 模型运行和 token metadata。Missing a real provider model run and token metadata.

阻塞检查Blocked Checks
  • 提供商实跑Provider model run
  • Token 用量Token usage observed
人工证据Human evidence

人工盲评Human Adjudication

盲评 pair 仍待真实 reviewer 决策。Blind-review pairs still need real reviewer decisions.

阻塞检查Blocked Checks
  • 无待判定No pending decisions
  • 盲评完成Judgments complete
  • Reviewer metadataReviewer metadata
外部证据External evidence

原生权限Native Permission

原生 runtime enforcement 仍待目标客户端或外部安装器证明。Native runtime enforcement still needs target-client or external-installer proof.

阻塞检查Blocked Checks
  • 原生执行Native enforcement
外部证据External evidence

原生遥测Native Telemetry

真实外部客户端 metadata-only 事件仍未导入。Real external-client metadata-only events have not been imported yet.

阻塞检查Blocked Checks
  • 外部事件External events
  • 采用样本Adoption sample
@@ -940,7 +940,7 @@

让 reviewer 快速确认关键文件、目录和资产分布。Lets reviewers confirm key files, directories, and asset distribution quickly.

-
资产分布Asset Distribution452项452 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
+
资产分布Asset Distribution453项453 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
diff --git a/reports/skill-overview.json b/reports/skill-overview.json index d5c943b0..0267ba06 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -411,7 +411,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 19, - "source_pass_count": 10, + "source_pass_count": 9, "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -471,7 +471,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -512,7 +513,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 149 + "file_count": 150 }, { "path": "evals", @@ -527,7 +528,7 @@ "file_count": 235 } ], - "file_count": 452, + "file_count": 453, "folder_count": 4, "distribution": [ { @@ -552,7 +553,7 @@ }, { "label": "scripts", - "value": 149 + "value": 150 }, { "label": "evals", @@ -682,7 +683,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 149 + "file_count": 150 }, { "path": "evals", @@ -1004,13 +1005,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98", - "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "evidence_bundle_sha256": "7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a", + "source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1025,18 +1026,18 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "public_claim_ready": false, - "public_claim_blocker_count": 4, + "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 19, - "source_tree_dirty": false, - "source_changed_file_count": 0, + "changed_file_count": 65, + "source_tree_dirty": true, + "source_changed_file_count": 4, "generated_tree_dirty": true, - "generated_changed_file_count": 19 + "generated_changed_file_count": 61 }, - "commit": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", + "commit": "2efe6413f04c9626ba52c554b4dc87baabd0b05b", "missing_artifacts": [], "limitations": [ "The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.", @@ -1120,9 +1121,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 241, - "script_count": 149, - "internal_module_count": 63, + "scanned_files": 242, + "script_count": 150, + "internal_module_count": 64, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -1140,8 +1141,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 241, - "package_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59" + "package_hash_file_count": 242, + "package_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4" }, "skill_atlas": { "skill_count": 12, @@ -1179,8 +1180,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8" + "package_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { "openai": "pass", @@ -1211,12 +1212,12 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-17" }, "failures": [], "warnings": [] @@ -1227,8 +1228,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", - "archive_entry_count": 688, + "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", + "archive_entry_count": 689, "failure_count": 0, "warning_count": 0 }, @@ -1239,7 +1240,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 688, + "archive_entry_count": 689, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1306,12 +1307,12 @@ { "field": "archive_sha256", "from": "", - "to": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8" + "to": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59" + "to": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4" } ] }, @@ -1328,14 +1329,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -1344,7 +1345,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -1619,7 +1620,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "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:///", @@ -1672,8 +1673,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -2099,7 +2100,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "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:///", @@ -2136,7 +2137,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -2157,8 +2158,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -2174,8 +2175,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", diff --git a/reports/skill_atlas.json b/reports/skill_atlas.json index 1bdbea00..efc9bb35 100644 --- a/reports/skill_atlas.json +++ b/reports/skill_atlas.json @@ -195,6 +195,7 @@ "scripts/world_class_human_evidence.py", "scripts/world_class_native_permission_evidence.py", "scripts/world_class_native_telemetry_evidence.py", + "scripts/world_class_phase_queue.py", "scripts/world_class_preflight_layout.py", "scripts/world_class_provider_evidence.py", "scripts/world_class_repair_checklist.py", diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json index 3eadfb22..1977d87f 100644 --- a/reports/skill_os2_audit.json +++ b/reports/skill_os2_audit.json @@ -197,7 +197,7 @@ "key": "trust-security", "label": "Trust Security", "status": "pass", - "current": "secrets 0; scripts 149; help failures 0", + "current": "secrets 0; scripts 150; help failures 0", "target": "Secrets, scripts, dependencies, permissions, and package hash are reviewable", "evidence": [ { @@ -285,7 +285,7 @@ "key": "registry-distribution", "label": "Registry Distribution", "status": "pass", - "current": "zip entries 688; install failures 0; permission failures 0", + "current": "zip entries 689; install failures 0; permission failures 0", "target": "Package metadata, archive checksum, package verification, and install simulation pass", "evidence": [ { diff --git a/reports/skill_os2_audit.md b/reports/skill_os2_audit.md index 106e632c..f5a479d6 100644 --- a/reports/skill_os2_audit.md +++ b/reports/skill_os2_audit.md @@ -23,11 +23,11 @@ Generated at: `2026-06-13` | Human Adjudication | human-required | 0/5 decisions; pending 5 | Real reviewer decisions, blind-review attestation, and integrity fingerprints recorded before claiming output review completion | Record real A/B choices, reviewer metadata, and blind-review attestation, then regenerate adjudication. | | Benchmark Reproducibility | pass | artifacts 25; missing 0; failures 3 | Public methodology, reproducible commands, required artifacts, and failure disclosure are machine-checkable | Keep the manifest current with every benchmark, package, and release evidence change. | | Runtime Conformance | pass | 5/5 targets pass | Target package structure, metadata, relative paths, and degradation notes pass | Keep target conformance fixtures updated as platform contracts change. | -| Trust Security | pass | secrets 0; scripts 149; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. | +| Trust Security | pass | secrets 0; scripts 150; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. | | Permission Metadata | pass | 4/4 target probes pass; metadata fallback 4; installer enforcement 4 | Packaged adapters expose explicit permission metadata, residual risks, and installer enforcement evidence when available | Preserve residual-risk notes until real native enforcement exists. | | Native Permission Enforcement | external-required | native-enforced targets 0; installer-enforced targets 4 | At least one target/client enforces approved permissions at runtime | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. | | Skill Atlas | pass | 12 skills; actionable collisions 0 | Workspace catalog, route overlap, stale/owner gaps, drift, and no-route opportunities | Feed real drift data into Atlas once client telemetry is installed. | -| Registry Distribution | pass | zip entries 688; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. | +| Registry Distribution | pass | zip entries 689; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. | | Review Studio | pass | decision review; warnings 3; score 91 | One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations | Resolve human/external warning gates before claiming full release readiness. | | Telemetry Drift | pass | events 1; risk low; recipes 5 | Local-first metadata-only event contract, aggregate drift report, hook recipes, and import path | Keep raw JSONL out of distributed packages and use aggregate reports for Atlas. | | Native Client Telemetry | external-required | external source events 0; adoption samples 1 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. | diff --git a/reports/skill_os2_coverage.json b/reports/skill_os2_coverage.json index 62d2b515..22aefe68 100644 --- a/reports/skill_os2_coverage.json +++ b/reports/skill_os2_coverage.json @@ -130,7 +130,7 @@ "label": "Trust Security", "status": "pass", "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.", - "current": "149 scripts; secrets 0; help failures 0", + "current": "150 scripts; secrets 0; help failures 0", "command": "python3 scripts/yao.py trust .", "test": "python3 tests/verify_trust_check.py", "evidence": [ @@ -204,7 +204,7 @@ "label": "Registry Distribution", "status": "pass", "objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.", - "current": "archive entries 688; install failures 0", + "current": "archive entries 689; install failures 0", "command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .", "test": "python3 tests/verify_registry_audit.py", "evidence": [ diff --git a/reports/skill_os2_coverage.md b/reports/skill_os2_coverage.md index 51eed5c4..35c0cfac 100644 --- a/reports/skill_os2_coverage.md +++ b/reports/skill_os2_coverage.md @@ -26,9 +26,9 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, | Skill IR | `pass` | schema 2.0.0; targets 5 | `python3 scripts/yao.py skill-ir .` | `python3 tests/verify_skill_ir.py` | | Output Eval Lab | `pass` | 5 cases; delta 100.0; execution 10 | `python3 scripts/yao.py output-exec . && python3 scripts/yao.py output-review .` | `python3 tests/verify_output_eval_lab.py` | | Runtime Conformance | `pass` | 5/5 targets pass | `python3 scripts/yao.py conformance .` | `python3 tests/verify_conformance_suite.py` | -| Trust Security | `pass` | 149 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` | +| Trust Security | `pass` | 150 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` | | Skill Atlas | `pass` | 12 scanned skills; actionable collisions 0 | `python3 scripts/yao.py skill-atlas --workspace-root .` | `python3 tests/verify_skill_atlas.py` | -| Registry Distribution | `pass` | archive entries 688; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` | +| Registry Distribution | `pass` | archive entries 689; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` | | Review Studio | `pass` | 16 gates; decision review; warnings 3 | `python3 scripts/yao.py review-studio .` | `python3 tests/verify_review_studio.py` | | Telemetry Drift | `pass` | events 1; recipes 5; risk low | `python3 scripts/yao.py telemetry-hooks . && python3 scripts/yao.py adoption-drift .` | `python3 tests/verify_telemetry_hooks.py` | diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index 583a46ce..bc1846f4 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -70,12 +70,12 @@ { "field": "archive_sha256", "from": "", - "to": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8" + "to": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59" + "to": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4" } ] }, diff --git a/reports/world_class_evidence_preflight.json b/reports/world_class_evidence_preflight.json index 22c57f18..1a1a1f4b 100644 --- a/reports/world_class_evidence_preflight.json +++ b/reports/world_class_evidence_preflight.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "evidence_item_count": 4, diff --git a/reports/world_class_evidence_preflight.md b/reports/world_class_evidence_preflight.md index 958e56f7..cb7ce7b0 100644 --- a/reports/world_class_evidence_preflight.md +++ b/reports/world_class_evidence_preflight.md @@ -1,6 +1,6 @@ # World-Class Evidence Preflight -Generated at: `2026-06-17` +Generated at: `2026-06-13` ## Summary diff --git a/scripts/prepare_world_class_submission_kit.py b/scripts/prepare_world_class_submission_kit.py index b7107385..66c3412c 100644 --- a/scripts/prepare_world_class_submission_kit.py +++ b/scripts/prepare_world_class_submission_kit.py @@ -9,6 +9,7 @@ from typing import Any from render_world_class_evidence_intake import build_intake from world_class_evidence_contract import DISALLOWED_REAL_ARTIFACTS +from world_class_phase_queue import build_phase_queue, summarize_phase_queue from world_class_repair_checklist import build_repair_checklist, summarize_repair_checklist from world_class_source_checks import build_source_checklist, summarize_source_checklist from world_class_submission_matrix import build_evidence_matrix, summarize_evidence_matrix @@ -410,6 +411,7 @@ def build_submission_kit( source_checklist = build_source_checklist(items) evidence_matrix = build_evidence_matrix(items, files, artifact_checklist, source_checklist) repair_checklist = build_repair_checklist(items, files, artifact_checklist, source_checklist, unknown_keys) + phase_queue = build_phase_queue(repair_checklist) manifest_path = output_dir / "submission_manifest.json" readme_path = output_dir / "README.md" output_html = output_html or (output_dir / "index.html") @@ -428,6 +430,7 @@ def build_submission_kit( source_summary = summarize_source_checklist(source_checklist) matrix_summary = summarize_evidence_matrix(evidence_matrix) repair_summary = summarize_repair_checklist(repair_checklist) + phase_queue_summary = summarize_phase_queue(phase_queue) ok = not unknown_keys and skipped_count == 0 output_dir_arg = shell_path(output_dir, skill_dir) requested_key_args = " ".join(f"--evidence-key {shlex.quote(key)}" for key in (evidence_keys or [])) @@ -478,6 +481,7 @@ def build_submission_kit( **source_summary, **matrix_summary, **repair_summary, + **phase_queue_summary, "handoff_step_count": len(handoff_steps), "handoff_blocked_count": sum(1 for item in handoff_steps if item["status"] == "blocked"), "handoff_fix_required_count": sum(1 for item in handoff_steps if item["status"] == "fix-required"), @@ -492,6 +496,7 @@ def build_submission_kit( "source_checklist": source_checklist, "evidence_matrix": evidence_matrix, "repair_checklist": repair_checklist, + "phase_queue": phase_queue, "operator_handoff": handoff_steps, "evidence_items": items, "commands": commands, diff --git a/scripts/world_class_phase_queue.py b/scripts/world_class_phase_queue.py new file mode 100644 index 00000000..ef88cc80 --- /dev/null +++ b/scripts/world_class_phase_queue.py @@ -0,0 +1,76 @@ +#!/usr/bin/env python3 +"""Build phase-ordered operator queues for world-class evidence collection.""" + +from collections import defaultdict +from typing import Any + + +SCRIPT_INTERFACE = "internal-module" +SCRIPT_INTERFACE_REASON = "Imported by prepare_world_class_submission_kit.py to group repair rows into an operator execution queue." + + +PHASE_LABELS = { + "select-evidence": "Select evidence", + "prepare-draft": "Prepare draft", + "unblock-access": "Unblock access", + "attach-artifacts": "Attach artifacts", + "collect-source": "Collect source", + "repair": "Repair", +} + + +def _phase_sort_key(row: dict[str, Any]) -> tuple[int, str, str]: + return ( + int(row.get("priority", 90) or 90), + str(row.get("evidence_key", "")), + str(row.get("target", "")), + ) + + +def build_phase_queue(repair_rows: list[dict[str, Any]]) -> list[dict[str, Any]]: + """Group repair rows by execution phase without changing evidence acceptance.""" + grouped: dict[str, list[dict[str, Any]]] = defaultdict(list) + for row in sorted(repair_rows, key=_phase_sort_key): + phase = str(row.get("phase", "repair") or "repair") + grouped[phase].append(row) + + queue: list[dict[str, Any]] = [] + for phase_rows in sorted(grouped.values(), key=lambda rows: _phase_sort_key(rows[0])): + first = phase_rows[0] + phase = str(first.get("phase", "repair") or "repair") + blocked_rows = [row for row in phase_rows if row.get("status") != "ready"] + owners = sorted({str(row.get("owner", "")).strip() for row in phase_rows if str(row.get("owner", "")).strip()}) + evidence_keys = sorted( + {str(row.get("evidence_key", "")).strip() for row in phase_rows if str(row.get("evidence_key", "")).strip()} + ) + queue.append( + { + "phase": phase, + "label": PHASE_LABELS.get(phase, phase.replace("-", " ").title()), + "priority": int(first.get("priority", 90) or 90), + "status": "blocked" if blocked_rows else "ready", + "blocked_count": len(blocked_rows), + "row_count": len(phase_rows), + "owners": owners, + "evidence_keys": evidence_keys, + "next_action_id": first.get("action_id", ""), + "next_action": first.get("next_action", ""), + "verification_command": first.get("verification_command", ""), + "counts_as_completion": False, + "rows": phase_rows, + } + ) + return queue + + +def summarize_phase_queue(queue: list[dict[str, Any]]) -> dict[str, Any]: + next_item = next((item for item in queue if item.get("status") != "ready"), queue[0] if queue else {}) + return { + "phase_queue_count": len(queue), + "phase_queue_blocked_count": sum(1 for item in queue if item.get("status") != "ready"), + "phase_queue_row_count": sum(int(item.get("row_count", 0) or 0) for item in queue), + "phase_queue_next_phase": next_item.get("phase", ""), + "phase_queue_next_action_id": next_item.get("next_action_id", ""), + "phase_queue_next_command": next_item.get("verification_command", ""), + "phase_queue_counts_as_completion": False, + } diff --git a/scripts/world_class_submission_kit_rendering.py b/scripts/world_class_submission_kit_rendering.py index fe25a525..ae0da581 100644 --- a/scripts/world_class_submission_kit_rendering.py +++ b/scripts/world_class_submission_kit_rendering.py @@ -47,6 +47,27 @@ def render_readme(report: dict[str, Any]) -> str: lines.append( f"| `{item['step_id']}` | `{item['status']}` | `{command}` | {item['completion_signal']} |" ) + lines.extend( + [ + "", + "## Phase Queue", + "", + "This queue groups repair rows by execution phase so operators can clear access, artifact, and source blockers in order. Queue rows are procedural guidance only.", + "", + "| Phase | Status | Rows | Owners | Next action | Verify |", + "| --- | --- | ---: | --- | --- | --- |", + ] + ) + phase_queue = report.get("phase_queue", []) + if phase_queue: + for item in phase_queue: + owners = ", ".join(str(owner) for owner in item.get("owners", [])) or "n/a" + lines.append( + f"| `{item['phase']}` | `{item['status']}` | `{item['row_count']}` | {owners} | " + f"{item['next_action']} | `{item['verification_command']}` |" + ) + else: + lines.append("| `all` | `ready` | `0` | n/a | No phase blockers were generated. | `n/a` |") lines.extend( [ "", @@ -333,6 +354,42 @@ def render_html_repair_checklist(items: list[dict[str, Any]]) -> str: ) +def render_html_phase_queue(items: list[dict[str, Any]]) -> str: + if not items: + return '

No phase queue rows were generated.

' + return "".join( + """ +
+
+ #{priority} · {status} +

{label}

+
+
+
Phase
{phase}
+
Rows
{blocked}/{total} blocked
+
Owners
{owners}
+
Evidence
{evidence}
+
Next
{action}
+
Verify
{verify}
+
Counts
does not count as completion
+
+
+ """.format( + status=html_text(item.get("status", "")), + priority=html_text(item.get("priority", "")), + label=html_text(item.get("label", "")), + phase=html_text(item.get("phase", "")), + blocked=html_text(item.get("blocked_count", 0)), + total=html_text(item.get("row_count", 0)), + owners=html_text(", ".join(str(owner) for owner in item.get("owners", [])) or "n/a"), + evidence=html_text(", ".join(str(key) for key in item.get("evidence_keys", [])) or "n/a"), + action=html_text(item.get("next_action", "")), + verify=html_text(item.get("verification_command", "")), + ) + for item in items + ) + + def render_html_handoff(items: list[dict[str, Any]]) -> str: if not items: return '

No operator handoff steps were generated.

' @@ -423,6 +480,7 @@ def render_html(report: dict[str, Any]) -> str: evidence_html = "".join(render_html_item(item) for item in report.get("evidence_items", [])) matrix_html = render_html_matrix(report.get("evidence_matrix", [])) repair_html = render_html_repair_checklist(report.get("repair_checklist", [])) + phase_queue_html = render_html_phase_queue(report.get("phase_queue", [])) handoff_html = render_html_handoff(report.get("operator_handoff", [])) artifact_html = render_html_artifact_checklist(report.get("artifact_checklist", [])) source_html = render_html_source_checklist(report.get("source_checklist", [])) @@ -458,14 +516,16 @@ def render_html(report: dict[str, Any]) -> str: .section {{ padding:32px 0; border-bottom:1px solid var(--line); }} .panel {{ padding:20px; }} .two-col {{ display:grid; grid-template-columns:minmax(0, .45fr) minmax(0, 1fr); gap:18px; align-items:start; }} - .draft-grid, .evidence-grid, .artifact-grid, .source-grid, .matrix-grid, .repair-grid, .handoff-grid {{ display:grid; grid-template-columns:repeat(2, minmax(0,1fr)); gap:16px; }} - .draft-card, .evidence-card, .artifact-card, .source-card, .matrix-card, .repair-card, .handoff-card {{ padding:18px; min-width:0; border:1px solid var(--line); border-radius:8px; background:#fff; }} + .draft-grid, .evidence-grid, .artifact-grid, .source-grid, .matrix-grid, .repair-grid, .handoff-grid, .queue-grid {{ display:grid; grid-template-columns:repeat(2, minmax(0,1fr)); gap:16px; }} + .draft-card, .evidence-card, .artifact-card, .source-card, .matrix-card, .repair-card, .handoff-card, .queue-card {{ padding:18px; min-width:0; border:1px solid var(--line); border-radius:8px; background:#fff; }} .draft-card.written, .draft-card.exists {{ border-left:4px solid var(--pass); }} .draft-card.skipped {{ border-left:4px solid var(--warn); }} .matrix-card.collect-source, .matrix-card.prepare-draft, .matrix-card.fix-artifacts, .matrix-card.fix-draft {{ border-left:4px solid var(--warn); }} .matrix-card.validate-packet {{ border-left:4px solid var(--pass); }} .repair-card.blocked {{ border-left:4px solid var(--warn); }} .repair-card.ready {{ border-left:4px solid var(--pass); }} + .queue-card.blocked {{ border-left:4px solid var(--warn); }} + .queue-card.ready {{ border-left:4px solid var(--pass); }} .handoff-card.blocked, .handoff-card.fix-required {{ border-left:4px solid var(--warn); }} .handoff-card.ready {{ border-left:4px solid var(--pass); }} .evidence-card.awaiting-submission, .evidence-card.fix-submission, .evidence-card.fix-template, .artifact-card.missing, .artifact-card.glob-no-match, .artifact-card.unsafe-path, .artifact-card.raw-content-disallowed {{ border-left:4px solid var(--warn); }} @@ -485,11 +545,11 @@ def render_html(report: dict[str, Any]) -> str: .mini-grid li, .runbook-panel li, .notice li {{ overflow-wrap:anywhere; }} .notice {{ background:var(--soft); border-left:4px solid var(--ink); padding:16px; border-radius:8px; }} .errors {{ color:var(--warn); }} - @media (max-width:820px) {{ .stats, .two-col, .draft-grid, .evidence-grid, .artifact-grid, .source-grid, .matrix-grid, .repair-grid, .handoff-grid, .mini-grid {{ grid-template-columns:1fr; }} h1 {{ font-size:38px; }} .topbar-inner {{ align-items:flex-start; flex-direction:column; }} }} + @media (max-width:820px) {{ .stats, .two-col, .draft-grid, .evidence-grid, .artifact-grid, .source-grid, .matrix-grid, .repair-grid, .handoff-grid, .queue-grid, .mini-grid {{ grid-template-columns:1fr; }} h1 {{ font-size:38px; }} .topbar-inner {{ align-items:flex-start; flex-direction:column; }} }} - +
Evidence Intake @@ -502,6 +562,7 @@ def render_html(report: dict[str, Any]) -> str:

Operator Handoff

These ordered steps make the operator-to-reviewer handoff auditable. They are procedural guardrails and never count as world-class evidence.

{handoff_html}
+

Phase Queue

Repair rows are grouped into execution phases so operators can clear the first blocker before moving to later evidence work. Queue rows remain procedural and never count as accepted evidence.

{phase_queue_html}

Evidence Matrix

The matrix separates submission artifact_refs from supporting assets, then combines draft status, source checks, and the next operator action. It is guidance only and never counts as accepted evidence.

{matrix_html}

Repair Checklist

Each row names one concrete blocker and the next action required before ledger review. This checklist does not count as completion evidence.

{repair_html}

Drafts

{render_html_files(report['files'])}
diff --git a/skill_atlas/catalog.json b/skill_atlas/catalog.json index 3c890003..52f5224f 100644 --- a/skill_atlas/catalog.json +++ b/skill_atlas/catalog.json @@ -151,6 +151,7 @@ "scripts/world_class_human_evidence.py", "scripts/world_class_native_permission_evidence.py", "scripts/world_class_native_telemetry_evidence.py", + "scripts/world_class_phase_queue.py", "scripts/world_class_preflight_layout.py", "scripts/world_class_provider_evidence.py", "scripts/world_class_repair_checklist.py", diff --git a/tests/verify_world_class_submission_kit.py b/tests/verify_world_class_submission_kit.py index e28222c9..179db6e2 100644 --- a/tests/verify_world_class_submission_kit.py +++ b/tests/verify_world_class_submission_kit.py @@ -101,6 +101,13 @@ def main() -> None: assert kit_payload["summary"]["repair_blocked_count"] == 2, kit_payload["summary"] assert kit_payload["summary"]["repair_ready_count"] == 0, kit_payload["summary"] assert kit_payload["summary"]["repair_phase_counts"] == {"collect-source": 2}, kit_payload["summary"] + assert kit_payload["summary"]["phase_queue_count"] == 1, kit_payload["summary"] + assert kit_payload["summary"]["phase_queue_blocked_count"] == 1, kit_payload["summary"] + assert kit_payload["summary"]["phase_queue_row_count"] == 2, kit_payload["summary"] + assert kit_payload["summary"]["phase_queue_next_phase"] == "collect-source", kit_payload["summary"] + assert kit_payload["summary"]["phase_queue_next_action_id"] == "provider-holdout-source-check-model_executed_count", kit_payload["summary"] + assert "output-exec --provider-runner openai" in kit_payload["summary"]["phase_queue_next_command"], kit_payload["summary"] + assert kit_payload["summary"]["phase_queue_counts_as_completion"] is False, kit_payload["summary"] assert kit_payload["summary"]["next_repair_action_id"] == "provider-holdout-source-check-model_executed_count", kit_payload["summary"] assert kit_payload["summary"]["next_repair_phase"] == "collect-source", kit_payload["summary"] assert kit_payload["summary"]["next_repair_owner"] == "operator with provider credentials", kit_payload["summary"] @@ -151,6 +158,17 @@ def main() -> None: assert "real credentials" in repair_rows["model_executed_count"]["next_action"], repair_rows assert "does not satisfy" in repair_rows["token_observed_count"]["blocking_reason"], repair_rows + assert len(kit_payload["phase_queue"]) == 1, kit_payload["phase_queue"] + queue_row = kit_payload["phase_queue"][0] + assert queue_row["phase"] == "collect-source", queue_row + assert queue_row["status"] == "blocked", queue_row + assert queue_row["row_count"] == 2, queue_row + assert queue_row["blocked_count"] == 2, queue_row + assert queue_row["owners"] == ["operator with provider credentials"], queue_row + assert queue_row["evidence_keys"] == ["provider-holdout"], queue_row + assert queue_row["counts_as_completion"] is False, queue_row + assert queue_row["rows"] == kit_payload["repair_checklist"], queue_row + handoff_steps = {item["step_id"]: item for item in kit_payload["operator_handoff"]} assert list(handoff_steps) == [ "prepare-drafts", @@ -204,6 +222,7 @@ def main() -> None: assert kit_manifest["artifact_checklist"] == kit_payload["artifact_checklist"], kit_manifest["artifact_checklist"] assert kit_manifest["source_checklist"] == kit_payload["source_checklist"], kit_manifest["source_checklist"] assert kit_manifest["repair_checklist"] == kit_payload["repair_checklist"], kit_manifest["repair_checklist"] + assert kit_manifest["phase_queue"] == kit_payload["phase_queue"], kit_manifest["phase_queue"] assert kit_manifest["artifacts"]["html"].endswith( f"tests/{TMP.name}/submission_kit/index.html" ), kit_manifest["artifacts"] @@ -216,6 +235,8 @@ def main() -> None: assert "validate intake" in kit_readme, kit_readme assert "Artifact Checklist" in kit_readme, kit_readme assert "Evidence Matrix" in kit_readme, kit_readme + assert "Phase Queue" in kit_readme, kit_readme + assert "This queue groups repair rows by execution phase" in kit_readme, kit_readme assert "Repair Checklist" in kit_readme, kit_readme assert "Operator Handoff" in kit_readme, kit_readme assert "Handoff rows are procedural" in kit_readme, kit_readme @@ -226,6 +247,7 @@ def main() -> None: assert "`submission-ref`" in kit_readme, kit_readme assert "`supporting-evidence`" in kit_readme, kit_readme assert "`collect-source`" in kit_readme, kit_readme + assert "Queue rows are procedural guidance only" in kit_readme, kit_readme assert "Matrix rows are guidance only" in kit_readme, kit_readme assert "Repair rows are procedural guidance and do not count as completion evidence." in kit_readme, kit_readme assert "Source Evidence Snapshot" in kit_readme, kit_readme @@ -239,6 +261,10 @@ def main() -> None: assert "provider-holdout" in kit_html, kit_html assert "Artifact Checklist" in kit_html, kit_html assert "Evidence Matrix" in kit_html, kit_html + assert "Phase Queue" in kit_html, kit_html + assert "queue-card blocked" in kit_html, kit_html + assert "
Phase
collect-source
" in kit_html, kit_html + assert "
Rows
2/2 blocked
" in kit_html, kit_html assert "Repair Checklist" in kit_html, kit_html assert "
Priority
" in kit_html, kit_html assert "
Phase
" in kit_html, kit_html
路径Path作用Role类型Type
SKILL.mdSkill 入口文件Skill entrypoint文件file
README.md人类可读使用说明Human-readable usage guide文件file
agents/interface.yaml跨平台接口元数据Neutral interface metadata文件file
manifest.json生命周期与打包元数据Lifecycle and portability metadata文件file
references扩展指导与复用资料Extended guidance and reusable notes目录folder
scripts确定性脚本或本地工具Deterministic helpers or local tooling目录folder
evals触发与质量检查Trigger and quality checks目录folder
reports生成的证据与总结报告Generated evidence and overview artifacts目录folder