From 2efe6413f04c9626ba52c554b4dc87baabd0b05b Mon Sep 17 00:00:00 2001 From: yaojingang Date: Wed, 17 Jun 2026 04:24:04 +0800 Subject: [PATCH] Refresh clean-lock release evidence --- reports/adoption_drift_report.json | 2 +- reports/benchmark_reproducibility.json | 118 +++--- reports/benchmark_reproducibility.md | 47 ++- reports/context_budget.json | 4 +- reports/context_budget_summary.json | 2 +- reports/evidence_consistency.json | 144 ++++---- reports/output_execution_runs.json | 20 +- reports/output_execution_runs.md | 20 +- reports/review-studio.html | 24 +- reports/review-studio.json | 387 +++++++++----------- reports/review-viewer.json | 53 ++- reports/skill-interpretation.html | 2 +- reports/skill-interpretation.json | 53 ++- reports/skill-overview.html | 2 +- reports/skill-overview.json | 53 ++- reports/skillops/daily/2026-06-17.json | 6 +- reports/skillops/daily/2026-06-17.md | 2 +- reports/skillops/weekly/2026-W25.json | 6 +- reports/skillops/weekly/2026-W25.md | 2 +- reports/world_class_evidence_preflight.json | 2 +- reports/world_class_evidence_preflight.md | 2 +- 21 files changed, 438 insertions(+), 513 deletions(-) diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json index 2d99ca5..31008b1 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": "2026-06-16T20:21:16Z", + "generated_at": "2026-06-16T20:23:32Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index 3e2a7c9..1fcf83c 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,50 +3,43 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "4a1a5295708ba3570821583652ef91fda0f0874f", + "commit": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", "git_status": { "available": true, "dirty": true, - "changed_file_count": 62, + "changed_file_count": 19, "generated_dirty": true, - "generated_changed_file_count": 56, - "source_dirty": true, - "source_changed_file_count": 6, + "generated_changed_file_count": 19, + "source_dirty": false, + "source_changed_file_count": 0, "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.md", - " M reports/context_budget_summary.json" - ], - "source_sample": [ - " M scripts/render_benchmark_reproducibility.py", - " M scripts/render_evidence_consistency.py", - " M tests/verify_benchmark_reproducibility.py", - " M tests/verify_evidence_consistency.py", - " M tests/verify_review_studio.py", - "?? scripts/benchmark_release_lock.py" + " 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" ], + "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.md", - " M reports/context_budget_summary.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" ], "generated_dirty_prefixes": [ "dist/", @@ -60,11 +53,11 @@ }, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "e114eec2acbc1cbb7ac578dd4e5165c3ed2b88e4922ba3e64d2c6232a577fc6d", + "evidence_bundle_sha256": "38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98", "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", "output_case_count": 5, @@ -81,36 +74,35 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 9, - "world_class_source_blocked_count": 10, + "world_class_source_pass_count": 10, + "world_class_source_blocked_count": 9, "public_claim_ready": false, - "public_claim_blocker_count": 5, + "public_claim_blocker_count": 4, "working_tree_dirty": true, - "changed_file_count": 62, - "source_tree_dirty": true, - "source_changed_file_count": 6, + "changed_file_count": 19, + "source_tree_dirty": false, + "source_changed_file_count": 0, "generated_tree_dirty": true, - "generated_changed_file_count": 56 + "generated_changed_file_count": 19 }, "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 (9/19 pass, 10 blocked)" + "world-class source checks are not all accepted (10/19 pass, 9 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": false, - "commit": "4a1a5295708ba3570821583652ef91fda0f0874f", + "ready": true, + "commit": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", "status_scope": "generation-time status before this report is written", - "source_changed_file_count": 6, - "generated_changed_file_count": 56, - "reason": "source files were dirty at generation time" + "source_changed_file_count": 0, + "generated_changed_file_count": 19, + "reason": "only generated evidence artifacts were dirty at generation time" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -118,7 +110,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "e114eec2acbc1cbb7ac578dd4e5165c3ed2b88e4922ba3e64d2c6232a577fc6d" + "sha256": "38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -191,8 +183,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7966, - "sha256": "c9c054c2e0a731644c659c5005b871e33072c3d12612793ba2a5df5b8873eba3" + "bytes": 7967, + "sha256": "3b9c37bdf02259b0e87d9f9fc5980512a2e95d9bcca32fd109b7a622d453b652" }, { "label": "blind_review", @@ -269,63 +261,63 @@ "path": "reports/world_class_evidence_plan.json", "exists": true, "bytes": 22784, - "sha256": "2beb888d7992fc72073251632a6e85c4075278f9bcea946a46a7e11f8f43e0ca" + "sha256": "4193115d881d4f68e61d2729633f88dd91d55d982af3db70691aafeba852f1ba" }, { "label": "world_class_evidence_ledger", "path": "reports/world_class_evidence_ledger.json", "exists": true, - "bytes": 26019, - "sha256": "22c85613d7bef62c4d0a4c94b77a8596090dc55c40e1663370d16d903e0b1ffb" + "bytes": 26016, + "sha256": "cb66d3284045b5993d25447f011cc70737dc760765ea3a3b7ae653194f0c4ff4" }, { "label": "world_class_evidence_intake", "path": "reports/world_class_evidence_intake.json", "exists": true, "bytes": 20646, - "sha256": "d3f44570e605e6e1b1557889ccca18efbbd8acc1d9a9c638f59961b3dc3e9026" + "sha256": "002fbf07989a804595fdcb51b6d0c8177dc035a1dc8d084b8294a274d21fbc1b" }, { "label": "world_class_evidence_preflight", "path": "reports/world_class_evidence_preflight.json", "exists": true, - "bytes": 68674, - "sha256": "c9d5fc06305c41f0870f32f30c0440a95e6fbdba402326e339cfd0c771ff960d" + "bytes": 66981, + "sha256": "758807fa5749e0dd46f46d311abfad8af7dd70663e8876569b1a4b8414b42ace" }, { "label": "world_class_submission_review", "path": "reports/world_class_submission_review.json", "exists": true, - "bytes": 17302, - "sha256": "96624a5b7f79aa0ac43ce60d30486290b9a91f0735254e31329f02e1ee291050" + "bytes": 17299, + "sha256": "f5b1e0e44aeb6e1999182d40fca421ab0a66b91154efc7b518e9ed6f6ac20dd2" }, { "label": "world_class_operator_runbook", "path": "reports/world_class_operator_runbook.json", "exists": true, - "bytes": 28935, - "sha256": "a7b7809d3b423bf647a528c3b0f6991f2ea3874afdd93a4d6ba74eb189131f2a" + "bytes": 28871, + "sha256": "8da2e2cde3adecec955f7745a4b761edc5af871d1720409cbd4f3b4b4482510e" }, { "label": "world_class_operator_runbook_markdown", "path": "reports/world_class_operator_runbook.md", "exists": true, - "bytes": 17576, - "sha256": "d72777b421b57f0cf8f31b4d048cf92512e49216d0b0c05cec1686d4aea638ce" + "bytes": 17521, + "sha256": "bfac92bc14f3080b9d723f32a4848aa3cfc10d4c3ee2e3844b65153f34c87c0a" }, { "label": "world_class_operator_runbook_html", "path": "reports/world_class_operator_runbook.html", "exists": true, - "bytes": 24019, - "sha256": "73d8ef2898f25ae899a618b723f40a6907646c303effa21cbde6156d01a95fc7" + "bytes": 23958, + "sha256": "46b435f98d8a91501580fa1426a8ab0d0f57b3bc92ecd17f42332e655fd2bd85" }, { "label": "world_class_claim_guard", "path": "reports/world_class_claim_guard.json", "exists": true, "bytes": 18596, - "sha256": "abe7f7d60c0025e140373fadaefbed4063f285c140c74b9c7cfb464e354bb526" + "sha256": "c846ffc8565a40c270e711a58e968b005afd75be6df1a442b020deebe850386f" } ], "missing_artifacts": [], diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 2dac0eb..195f93b 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,16 +1,16 @@ # Benchmark Reproducibility Generated at: `2026-06-17` -Commit: `4a1a5295708ba3570821583652ef91fda0f0874f` +Commit: `ed6960f65dbba0a36c335835f2ac6e8133435ea7` Working tree dirty at generation: `true` -Source tree dirty at generation: `true` +Source tree dirty at generation: `false` Generated evidence dirty at generation: `true` -Evidence bundle SHA256: `e114eec2acbc1cbb7ac578dd4e5165c3ed2b88e4922ba3e64d2c6232a577fc6d` +Evidence bundle SHA256: `38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98` ## Summary - reproducibility ready: `true` -- release lock ready: `false` +- release lock ready: `true` - methodology complete: `true` - required artifacts: `25` - missing artifacts: `0` @@ -22,12 +22,12 @@ Evidence bundle SHA256: `e114eec2acbc1cbb7ac578dd4e5165c3ed2b88e4922ba3e64d2c623 - provider evidence complete: `false` - human review complete: `false` - world-class ready: `false` -- world-class source checks: `9` pass / `19` total; `10` blocked +- world-class source checks: `10` pass / `19` total; `9` blocked - public claim ready: `false` -- public claim blockers: `5` -- changed files at generation: `62` -- source changed files at generation: `6` -- generated changed files at generation: `56` +- public claim blockers: `4` +- changed files at generation: `19` +- source changed files at generation: `0` +- generated changed files at generation: `19` 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. @@ -39,23 +39,22 @@ 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 (9/19 pass, 10 blocked) | +| world-class source checks are not all accepted (10/19 pass, 9 blocked) | ## Release Lock -- ready: `false` -- reason: source files were dirty at generation time +- ready: `true` +- reason: only generated evidence artifacts 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: `e114eec2acbc1cbb7ac578dd4e5165c3ed2b88e4922ba3e64d2c6232a577fc6d` +- sha256: `38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98` ## Methodology Sections @@ -77,7 +76,7 @@ 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 | `c9c054c2e0a7` | +| output_execution | `reports/output_execution_runs.json` | present | `3b9c37bdf022` | | 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` | @@ -88,15 +87,15 @@ This report proves local benchmark reproducibility only. It keeps external provi | 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 | `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` | +| 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` | ## Reproduction Commands diff --git a/reports/context_budget.json b/reports/context_budget.json index 454ed98..e17fc48 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -6,9 +6,9 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1112816, + "other_text_tokens": 1112796, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1113613, + "estimated_total_text_tokens": 1113593, "deferred_resource_tokens": 507713, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ diff --git a/reports/context_budget_summary.json b/reports/context_budget_summary.json index 541ac56..02083d7 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -1,5 +1,5 @@ { - "generated_at": "2026-03-31", + "generated_at": "2026-06-17", "targets": [ { "label": "root", diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index 3c3f8b0..d54e92f 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -207,8 +207,8 @@ "key": "benchmark-release-lock-self-consistency", "label": "Benchmark release lock matches source dirty state", "status": "pass", - "expected": false, - "actual": false, + "expected": true, + "actual": true, "paths": [ "reports/benchmark_reproducibility.json" ], @@ -222,7 +222,7 @@ "actual": { "available": true, "clean": false, - "changed_file_count": 62 + "changed_file_count": 21 }, "paths": [ "reports/benchmark_reproducibility.json" @@ -263,8 +263,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "4a1a5295708ba3570821583652ef91fda0f0874f", - "actual": "4a1a5295708ba3570821583652ef91fda0f0874f", + "expected": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", + "actual": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", "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": false, + "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 9, - "world_class_source_blocked_count": 10, + "world_class_source_pass_count": 10, + "world_class_source_blocked_count": 9, "public_claim_ready": false, - "public_claim_blocker_count": 5 + "public_claim_blocker_count": 4 }, "actual": { - "release_lock_ready": false, + "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 9, - "world_class_source_blocked_count": 10, + "world_class_source_pass_count": 10, + "world_class_source_blocked_count": 9, "public_claim_ready": false, - "public_claim_blocker_count": 5 + "public_claim_blocker_count": 4 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -313,13 +313,13 @@ "status": "pass", "expected": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, - "adoption_rate": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, + "adoption_rate": 100.0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "source_types": { "manual": 1 @@ -327,13 +327,13 @@ }, "actual": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, - "adoption_rate": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, + "adoption_rate": 100.0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "source_types": { "manual": 1 @@ -356,8 +356,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 19, - "source_pass_count": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "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": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "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": 9 + "source_pass_count": 10 }, "actual": { "ready": false, @@ -397,7 +397,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 19, - "source_pass_count": 9 + "source_pass_count": 10 }, "paths": [ "reports/world_class_evidence_ledger.json", @@ -409,8 +409,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "4a1a5295708ba3570821583652ef91fda0f0874f", - "actual": "4a1a5295708ba3570821583652ef91fda0f0874f", + "expected": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", + "actual": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", "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": false, + "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 9, - "world_class_source_blocked_count": 10, + "world_class_source_pass_count": 10, + "world_class_source_blocked_count": 9, "public_claim_ready": false, - "public_claim_blocker_count": 5 + "public_claim_blocker_count": 4 }, "actual": { - "release_lock_ready": false, + "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 9, - "world_class_source_blocked_count": 10, + "world_class_source_pass_count": 10, + "world_class_source_blocked_count": 9, "public_claim_ready": false, - "public_claim_blocker_count": 5 + "public_claim_blocker_count": 4 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -459,13 +459,13 @@ "status": "pass", "expected": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, - "adoption_rate": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, + "adoption_rate": 100.0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "source_types": { "manual": 1 @@ -473,13 +473,13 @@ }, "actual": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, - "adoption_rate": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, + "adoption_rate": 100.0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "source_types": { "manual": 1 @@ -502,8 +502,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 19, - "source_pass_count": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "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": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "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": 9 + "source_pass_count": 10 }, "actual": { "ready": false, @@ -543,7 +543,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 19, - "source_pass_count": 9 + "source_pass_count": 10 }, "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": 9, + "source_pass_count": 10, "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": [ @@ -1402,8 +1402,7 @@ "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", - "Adoption sample" + "External events" ] } ] @@ -1417,7 +1416,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 19, - "source_pass_count": 9, + "source_pass_count": 10, "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": [ @@ -1477,8 +1476,7 @@ "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", - "Adoption sample" + "External events" ] } ] @@ -1828,15 +1826,15 @@ "expected": { "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 9, - "world_class_source_blocked_count": 10, + "world_class_source_pass_count": 10, + "world_class_source_blocked_count": 9, "public_claim_ready": false }, "actual": { "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 9, - "world_class_source_blocked_count": 10, + "world_class_source_pass_count": 10, + "world_class_source_blocked_count": 9, "public_claim_ready": false }, "paths": [ @@ -1852,8 +1850,8 @@ "expected": { "pending_count": 4, "source_check_count": 19, - "source_pass_count": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "ready_to_claim_world_class": false, "preflight_counts_as_evidence": false, "credential_value_exposed": false @@ -1861,8 +1859,8 @@ "actual": { "pending_count": 4, "source_check_count": 19, - "source_pass_count": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "ready_to_claim_world_class": false, "preflight_counts_as_evidence": false, "credential_value_exposed": false @@ -2116,8 +2114,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 19, - "source_pass_count": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "plan_keys": [ "human-adjudication", "native-client-telemetry", @@ -2265,8 +2263,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 19, - "source_pass_count": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "plan_keys": [ "human-adjudication", "native-client-telemetry", diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 197697a..5fcb6af 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": 29.28, + "duration_ms": 29.21, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.7, + "duration_ms": 28.64, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.28, + "duration_ms": 28.14, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.04, + "duration_ms": 28.12, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.34, + "duration_ms": 28.94, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.95, + "duration_ms": 29.34, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.32, + "duration_ms": 28.98, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.58, + "duration_ms": 29.47, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.26, + "duration_ms": 27.51, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.95, + "duration_ms": 27.08, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index 6d7d425..d86514f 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 | 29.28 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 28.7 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 29.28 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 28.04 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 28.34 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 27.95 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 32.32 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 28.58 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 28.26 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 27.95 | 98 | 100.0 | pass | +| 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 | ## Next Fixes diff --git a/reports/review-studio.html b/reports/review-studio.html index e551a38..2970260 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

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

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 false

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

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

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

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

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 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
@@ -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 9/19 pass; 10 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 10/19 pass; 9 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 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.
+
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.
@@ -861,14 +861,14 @@
-

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 false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false

-

漂移信号

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

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
-

日常运维

决策
proposal-review
提案数
5
Approval Count
0
Pending Review Count
0
发布锁
否
世界级
否
Writes Source Files
否
Auto Patch Enabled
否
-

周度队列

决策
curator-review
Week Id
2026-W25
日报数
2
唯一机会
5
待批准复核
1
提案复核
4
Top Score
88
发布锁
否
Writes Source Files
否
Auto Patch Enabled
否
+

日常运维

决策
proposal-review
提案数
5
Approval Count
0
Pending Review Count
0
发布锁
是
世界级
否
Writes Source Files
否
Auto Patch Enabled
否
+

周度队列

决策
curator-review
Week Id
2026-W25
日报数
2
唯一机会
5
待批准复核
1
提案复核
4
Top Score
88
发布锁
是
Writes Source Files
否
Auto Patch Enabled
否
@@ -886,7 +886,7 @@

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 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.
+
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.
@@ -901,12 +901,12 @@
-

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

  • 阻断release lock is not clean or commit is unavailable
  • 阻断provider-backed model holdout evidence is incomplete
  • 阻断human blind-review adjudication is incomplete
  • 阻断world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)
  • 阻断world-class source checks are not all accepted (9/19 pass, 10 blocked)
+

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

  • 阻断provider-backed model holdout evidence is incomplete
  • 阻断human blind-review adjudication is incomplete
  • 阻断world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)
  • 阻断world-class source checks are not all accepted (10/19 pass, 9 blocked)
-

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

+

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

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
diff --git a/reports/review-studio.json b/reports/review-studio.json index c61bbe3..c1a9c5a 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -108,7 +108,7 @@ "key": "operations-loop", "label": "运营回路", "status": "pass", - "detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false", + "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", "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 9/19 pass; 10 blocked; overclaim guard true", + "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 10/19 pass; 9 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 9/19 pass; 10 blocked; overclaim guard true", + "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 10/19 pass; 9 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 0", + "current": "external source events 0; adoption samples 1", "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": 1, - "source_blocked_count": 2, + "source_pass_count": 2, + "source_blocked_count": 1, "blocked_checks": [ { "label": "External events", @@ -1036,14 +1036,6 @@ "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": [ @@ -1060,19 +1052,6 @@ "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", @@ -1087,7 +1066,7 @@ "counts_as_completion": false } ], - "repair_blocked_count": 3, + "repair_blocked_count": 2, "repair_counts_as_completion": false, "commands": [ { @@ -1631,7 +1610,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 19, - "source_pass_count": 9, + "source_pass_count": 10, "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": [ @@ -1691,8 +1670,7 @@ "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", - "Adoption sample" + "External events" ] } ] @@ -2225,11 +2203,11 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "e114eec2acbc1cbb7ac578dd4e5165c3ed2b88e4922ba3e64d2c6232a577fc6d", + "evidence_bundle_sha256": "38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98", "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", "output_case_count": 5, @@ -2246,18 +2224,18 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 9, - "world_class_source_blocked_count": 10, + "world_class_source_pass_count": 10, + "world_class_source_blocked_count": 9, "public_claim_ready": false, - "public_claim_blocker_count": 5, + "public_claim_blocker_count": 4, "working_tree_dirty": true, - "changed_file_count": 62, - "source_tree_dirty": true, - "source_changed_file_count": 6, + "changed_file_count": 19, + "source_tree_dirty": false, + "source_changed_file_count": 0, "generated_tree_dirty": true, - "generated_changed_file_count": 56 + "generated_changed_file_count": 19 }, - "commit": "4a1a5295708ba3570821583652ef91fda0f0874f", + "commit": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", "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.", @@ -2549,14 +2527,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 0, + "adoption_rate": 100.0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -2565,7 +2543,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "failure_types": {}, "source_types": { @@ -2840,7 +2818,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "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:///", @@ -2893,8 +2871,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -3320,7 +3298,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "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:///", @@ -3357,7 +3335,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -3378,8 +3356,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -3395,8 +3373,8 @@ } ], "source_check_count": 3, - "source_pass_count": 1, - "source_blocked_count": 2, + "source_pass_count": 2, + "source_blocked_count": 1, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", @@ -5046,7 +5024,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.43, + "duration_ms": 29.21, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5074,7 +5052,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.15, + "duration_ms": 28.64, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5097,7 +5075,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.9, + "duration_ms": 28.14, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5125,7 +5103,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.98, + "duration_ms": 28.12, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5148,7 +5126,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.99, + "duration_ms": 28.94, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5176,7 +5154,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.99, + "duration_ms": 29.34, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5199,7 +5177,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.48, + "duration_ms": 28.98, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5226,7 +5204,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.39, + "duration_ms": 29.47, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5249,7 +5227,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.22, + "duration_ms": 27.51, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5278,7 +5256,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.25, + "duration_ms": 27.08, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -6059,50 +6037,43 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "4a1a5295708ba3570821583652ef91fda0f0874f", + "commit": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", "git_status": { "available": true, "dirty": true, - "changed_file_count": 62, + "changed_file_count": 19, "generated_dirty": true, - "generated_changed_file_count": 56, - "source_dirty": true, - "source_changed_file_count": 6, + "generated_changed_file_count": 19, + "source_dirty": false, + "source_changed_file_count": 0, "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.md", - " M reports/context_budget_summary.json" - ], - "source_sample": [ - " M scripts/render_benchmark_reproducibility.py", - " M scripts/render_evidence_consistency.py", - " M tests/verify_benchmark_reproducibility.py", - " M tests/verify_evidence_consistency.py", - " M tests/verify_review_studio.py", - "?? scripts/benchmark_release_lock.py" + " 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" ], + "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.md", - " M reports/context_budget_summary.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" ], "generated_dirty_prefixes": [ "dist/", @@ -6116,11 +6087,11 @@ }, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "e114eec2acbc1cbb7ac578dd4e5165c3ed2b88e4922ba3e64d2c6232a577fc6d", + "evidence_bundle_sha256": "38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98", "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", "output_case_count": 5, @@ -6137,36 +6108,35 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 9, - "world_class_source_blocked_count": 10, + "world_class_source_pass_count": 10, + "world_class_source_blocked_count": 9, "public_claim_ready": false, - "public_claim_blocker_count": 5, + "public_claim_blocker_count": 4, "working_tree_dirty": true, - "changed_file_count": 62, - "source_tree_dirty": true, - "source_changed_file_count": 6, + "changed_file_count": 19, + "source_tree_dirty": false, + "source_changed_file_count": 0, "generated_tree_dirty": true, - "generated_changed_file_count": 56 + "generated_changed_file_count": 19 }, "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 (9/19 pass, 10 blocked)" + "world-class source checks are not all accepted (10/19 pass, 9 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": false, - "commit": "4a1a5295708ba3570821583652ef91fda0f0874f", + "ready": true, + "commit": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", "status_scope": "generation-time status before this report is written", - "source_changed_file_count": 6, - "generated_changed_file_count": 56, - "reason": "source files were dirty at generation time" + "source_changed_file_count": 0, + "generated_changed_file_count": 19, + "reason": "only generated evidence artifacts were dirty at generation time" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -6174,7 +6144,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "e114eec2acbc1cbb7ac578dd4e5165c3ed2b88e4922ba3e64d2c6232a577fc6d" + "sha256": "38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -6247,8 +6217,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7966, - "sha256": "c9c054c2e0a731644c659c5005b871e33072c3d12612793ba2a5df5b8873eba3" + "bytes": 7967, + "sha256": "3b9c37bdf02259b0e87d9f9fc5980512a2e95d9bcca32fd109b7a622d453b652" }, { "label": "blind_review", @@ -6325,63 +6295,63 @@ "path": "reports/world_class_evidence_plan.json", "exists": true, "bytes": 22784, - "sha256": "2beb888d7992fc72073251632a6e85c4075278f9bcea946a46a7e11f8f43e0ca" + "sha256": "4193115d881d4f68e61d2729633f88dd91d55d982af3db70691aafeba852f1ba" }, { "label": "world_class_evidence_ledger", "path": "reports/world_class_evidence_ledger.json", "exists": true, - "bytes": 26019, - "sha256": "22c85613d7bef62c4d0a4c94b77a8596090dc55c40e1663370d16d903e0b1ffb" + "bytes": 26016, + "sha256": "cb66d3284045b5993d25447f011cc70737dc760765ea3a3b7ae653194f0c4ff4" }, { "label": "world_class_evidence_intake", "path": "reports/world_class_evidence_intake.json", "exists": true, "bytes": 20646, - "sha256": "d3f44570e605e6e1b1557889ccca18efbbd8acc1d9a9c638f59961b3dc3e9026" + "sha256": "002fbf07989a804595fdcb51b6d0c8177dc035a1dc8d084b8294a274d21fbc1b" }, { "label": "world_class_evidence_preflight", "path": "reports/world_class_evidence_preflight.json", "exists": true, - "bytes": 68674, - "sha256": "c9d5fc06305c41f0870f32f30c0440a95e6fbdba402326e339cfd0c771ff960d" + "bytes": 66981, + "sha256": "758807fa5749e0dd46f46d311abfad8af7dd70663e8876569b1a4b8414b42ace" }, { "label": "world_class_submission_review", "path": "reports/world_class_submission_review.json", "exists": true, - "bytes": 17302, - "sha256": "96624a5b7f79aa0ac43ce60d30486290b9a91f0735254e31329f02e1ee291050" + "bytes": 17299, + "sha256": "f5b1e0e44aeb6e1999182d40fca421ab0a66b91154efc7b518e9ed6f6ac20dd2" }, { "label": "world_class_operator_runbook", "path": "reports/world_class_operator_runbook.json", "exists": true, - "bytes": 28935, - "sha256": "a7b7809d3b423bf647a528c3b0f6991f2ea3874afdd93a4d6ba74eb189131f2a" + "bytes": 28871, + "sha256": "8da2e2cde3adecec955f7745a4b761edc5af871d1720409cbd4f3b4b4482510e" }, { "label": "world_class_operator_runbook_markdown", "path": "reports/world_class_operator_runbook.md", "exists": true, - "bytes": 17576, - "sha256": "d72777b421b57f0cf8f31b4d048cf92512e49216d0b0c05cec1686d4aea638ce" + "bytes": 17521, + "sha256": "bfac92bc14f3080b9d723f32a4848aa3cfc10d4c3ee2e3844b65153f34c87c0a" }, { "label": "world_class_operator_runbook_html", "path": "reports/world_class_operator_runbook.html", "exists": true, - "bytes": 24019, - "sha256": "73d8ef2898f25ae899a618b723f40a6907646c303effa21cbde6156d01a95fc7" + "bytes": 23958, + "sha256": "46b435f98d8a91501580fa1426a8ab0d0f57b3bc92ecd17f42332e655fd2bd85" }, { "label": "world_class_claim_guard", "path": "reports/world_class_claim_guard.json", "exists": true, "bytes": 18596, - "sha256": "abe7f7d60c0025e140373fadaefbed4063f285c140c74b9c7cfb464e354bb526" + "sha256": "c846ffc8565a40c270e711a58e968b005afd75be6df1a442b020deebe850386f" } ], "missing_artifacts": [], @@ -6521,7 +6491,7 @@ "skill_os2_coverage": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "item_count": 21, @@ -17720,9 +17690,9 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1112808, + "other_text_tokens": 1112796, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1113605, + "estimated_total_text_tokens": 1113593, "deferred_resource_tokens": 507713, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ @@ -19695,7 +19665,7 @@ "adoption_drift": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-17", + "generated_at": "2026-06-16T20:23:32Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -19719,14 +19689,14 @@ }, "summary": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 0, + "adoption_rate": 100.0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -19735,7 +19705,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "failure_types": {}, "source_types": { @@ -19747,31 +19717,31 @@ { "skill": "yao-meta-skill", "events": 1, - "adoption_events": 0, - "accepted": 0, + "adoption_events": 1, + "accepted": 1, "edited": 0, "rejected": 0, "missed": 0, - "adoption_rate": 0 + "adoption_rate": 100.0 } ], "next_iteration_candidates": [], "recent_events": [ { "command": "unknown", - "event": "review_event", + "event": "skill_activation", "skill": "yao-meta-skill", "source": "manual", "version": "1.1.0", - "activation_type": "manual", - "outcome": "reviewed", + "activation_type": "explicit", + "outcome": "accepted", "failure_type": "none", - "timestamp": "2026-06-13T12:00:00Z" + "timestamp": "2026-06-13T10:00:00Z" } ], "failures": [], "artifacts": { - "events_jsonl": "reports/telemetry_events.jsonl", + "events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl", "json": "reports/adoption_drift_report.json", "markdown": "reports/adoption_drift_report.md" } @@ -19792,7 +19762,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -19809,7 +19779,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -20258,7 +20228,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true }, "actions": [ @@ -20307,7 +20277,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -20327,7 +20297,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -20580,7 +20550,7 @@ "no_route_opportunity_count": 0 }, "release_state": { - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4 @@ -21156,7 +21126,7 @@ "world_class_evidence_ledger": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17", + "generated_at": "2026-06-13", "skill_dir": ".", "decision": "evidence-pending", "ready_to_claim_world_class": false, @@ -21171,8 +21141,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -21188,8 +21158,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -21641,7 +21611,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "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:///", @@ -21678,7 +21648,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -21699,8 +21669,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -21716,8 +21686,8 @@ } ], "source_check_count": 3, - "source_pass_count": 1, - "source_blocked_count": 2, + "source_pass_count": 2, + "source_blocked_count": 1, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", @@ -21758,7 +21728,7 @@ "world_class_evidence_intake": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "schema_present": true, @@ -22085,7 +22055,7 @@ "source_accepted": false, "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -22169,14 +22139,14 @@ "collection_ready_count": 1, "collection_blocked_count": 3, "source_check_count": 19, - "source_pass_count": 9, - "source_blocked_count": 10, - "repair_checklist_count": 14, - "repair_blocked_count": 14, + "source_pass_count": 10, + "source_blocked_count": 9, + "repair_checklist_count": 13, + "repair_blocked_count": 13, "repair_ready_count": 0, "repair_phase_counts": { "unblock-access": 4, - "collect-source": 10 + "collect-source": 9 }, "next_repair_action_id": "human-adjudication-precheck-human-reviewer", "next_repair_phase": "unblock-access", @@ -22933,8 +22903,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -23018,21 +22988,6 @@ "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", @@ -23396,8 +23351,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -23548,21 +23503,6 @@ "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", @@ -23679,7 +23619,7 @@ "world_class_submission_review": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17", + "generated_at": "2026-06-13", "skill_dir": ".", "decision": "awaiting-submissions", "ready_to_claim_world_class": false, @@ -23692,8 +23632,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "review_counts_submission_as_completion": false, "summary": { "review_item_count": 4, @@ -23705,8 +23645,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "ready_to_claim_world_class": false, "review_counts_submission_as_completion": false, "decision": "awaiting-submissions" @@ -24056,7 +23996,7 @@ "intake_errors": [], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -24077,8 +24017,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -24094,8 +24034,8 @@ } ], "source_check_count": 3, - "source_pass_count": 1, - "source_blocked_count": 2, + "source_pass_count": 2, + "source_blocked_count": 1, "success_checks": [ "reports/adoption_drift_report.json summary.source_types.external > 0", "reports/adoption_drift_report.json summary.adoption_sample_count > 0", @@ -24121,7 +24061,7 @@ "world_class_operator_runbook": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "evidence_item_count": 4, @@ -24132,8 +24072,8 @@ "valid_packet_source_incomplete_count": 0, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "ready_to_claim_world_class": false, "runbook_counts_as_completion": false, "decision": "collect-evidence" @@ -24607,7 +24547,7 @@ "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 0", + "current": "external source events 0; adoption samples 1", "execution_runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.", @@ -24655,7 +24595,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -24676,8 +24616,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -24692,10 +24632,9 @@ "next_action": "Telemetry must stay metadata-only." } ], - "blocked_source_check_count": 2, + "blocked_source_check_count": 1, "next_source_actions": [ - "Import at least one metadata-only event from a real client.", - "Telemetry must include adoption outcome evidence." + "Import at least one metadata-only event from a real client." ], "submission_state": { "status": "missing", @@ -24731,7 +24670,7 @@ "world_class_claim_guard": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "ledger_ready_to_claim_world_class": false, diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 883220c..e06b629 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": 9, + "source_pass_count": 10, "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": [ @@ -472,8 +472,7 @@ "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", - "Adoption sample" + "External events" ] } ] @@ -1006,11 +1005,11 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "e114eec2acbc1cbb7ac578dd4e5165c3ed2b88e4922ba3e64d2c6232a577fc6d", + "evidence_bundle_sha256": "38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98", "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", "output_case_count": 5, @@ -1027,18 +1026,18 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 9, - "world_class_source_blocked_count": 10, + "world_class_source_pass_count": 10, + "world_class_source_blocked_count": 9, "public_claim_ready": false, - "public_claim_blocker_count": 5, + "public_claim_blocker_count": 4, "working_tree_dirty": true, - "changed_file_count": 62, - "source_tree_dirty": true, - "source_changed_file_count": 6, + "changed_file_count": 19, + "source_tree_dirty": false, + "source_changed_file_count": 0, "generated_tree_dirty": true, - "generated_changed_file_count": 56 + "generated_changed_file_count": 19 }, - "commit": "4a1a5295708ba3570821583652ef91fda0f0874f", + "commit": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", "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.", @@ -1330,14 +1329,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 0, + "adoption_rate": 100.0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -1346,7 +1345,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "failure_types": {}, "source_types": { @@ -1621,7 +1620,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "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:///", @@ -1674,8 +1673,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -2101,7 +2100,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "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:///", @@ -2138,7 +2137,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -2159,8 +2158,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -2176,8 +2175,8 @@ } ], "source_check_count": 3, - "source_pass_count": 1, - "source_blocked_count": 2, + "source_pass_count": 2, + "source_blocked_count": 1, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", diff --git a/reports/skill-interpretation.html b/reports/skill-interpretation.html index 23f2808..59c5cc5 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 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
+

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
diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index 10e687e..48bc16b 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": 9, + "source_pass_count": 10, "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": [ @@ -472,8 +472,7 @@ "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", - "Adoption sample" + "External events" ] } ] @@ -1010,11 +1009,11 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "e114eec2acbc1cbb7ac578dd4e5165c3ed2b88e4922ba3e64d2c6232a577fc6d", + "evidence_bundle_sha256": "38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98", "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", "output_case_count": 5, @@ -1031,18 +1030,18 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 9, - "world_class_source_blocked_count": 10, + "world_class_source_pass_count": 10, + "world_class_source_blocked_count": 9, "public_claim_ready": false, - "public_claim_blocker_count": 5, + "public_claim_blocker_count": 4, "working_tree_dirty": true, - "changed_file_count": 62, - "source_tree_dirty": true, - "source_changed_file_count": 6, + "changed_file_count": 19, + "source_tree_dirty": false, + "source_changed_file_count": 0, "generated_tree_dirty": true, - "generated_changed_file_count": 56 + "generated_changed_file_count": 19 }, - "commit": "4a1a5295708ba3570821583652ef91fda0f0874f", + "commit": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", "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.", @@ -1334,14 +1333,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 0, + "adoption_rate": 100.0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -1350,7 +1349,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "failure_types": {}, "source_types": { @@ -1625,7 +1624,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "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:///", @@ -1678,8 +1677,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -2105,7 +2104,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "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:///", @@ -2142,7 +2141,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -2163,8 +2162,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -2180,8 +2179,8 @@ } ], "source_check_count": 3, - "source_pass_count": 1, - "source_blocked_count": 2, + "source_pass_count": 2, + "source_blocked_count": 1, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", diff --git a/reports/skill-overview.html b/reports/skill-overview.html index c6258ee..ea47108 100644 --- a/reports/skill-overview.html +++ b/reports/skill-overview.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 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
+

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
diff --git a/reports/skill-overview.json b/reports/skill-overview.json index b87bc70..d5c943b 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": 9, + "source_pass_count": 10, "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": [ @@ -471,8 +471,7 @@ "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", - "Adoption sample" + "External events" ] } ] @@ -1005,11 +1004,11 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "e114eec2acbc1cbb7ac578dd4e5165c3ed2b88e4922ba3e64d2c6232a577fc6d", + "evidence_bundle_sha256": "38a010bc2913be5c7aadd809095c436abf8e566c8c53b8b4a63a821fea6acc98", "source_contract_sha256": "6fbdbed9dfdc8d272caa0a6596312fa524796132dfb3c9e9e1a9cbc801729f59", "archive_sha256": "0db54f7880460ee162ea2779554315c225ad912737660379c0c503f068c636e8", "output_case_count": 5, @@ -1026,18 +1025,18 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 9, - "world_class_source_blocked_count": 10, + "world_class_source_pass_count": 10, + "world_class_source_blocked_count": 9, "public_claim_ready": false, - "public_claim_blocker_count": 5, + "public_claim_blocker_count": 4, "working_tree_dirty": true, - "changed_file_count": 62, - "source_tree_dirty": true, - "source_changed_file_count": 6, + "changed_file_count": 19, + "source_tree_dirty": false, + "source_changed_file_count": 0, "generated_tree_dirty": true, - "generated_changed_file_count": 56 + "generated_changed_file_count": 19 }, - "commit": "4a1a5295708ba3570821583652ef91fda0f0874f", + "commit": "ed6960f65dbba0a36c335835f2ac6e8133435ea7", "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.", @@ -1329,14 +1328,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 0, + "adoption_rate": 100.0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -1345,7 +1344,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "failure_types": {}, "source_types": { @@ -1620,7 +1619,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "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 +1672,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 19, - "source_pass_count": 9, - "source_blocked_count": 10, + "source_pass_count": 10, + "source_blocked_count": 9, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -2100,7 +2099,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "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 +2136,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -2158,8 +2157,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -2175,8 +2174,8 @@ } ], "source_check_count": 3, - "source_pass_count": 1, - "source_blocked_count": 2, + "source_pass_count": 2, + "source_blocked_count": 1, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", diff --git a/reports/skillops/daily/2026-06-17.json b/reports/skillops/daily/2026-06-17.json index 7ee010c..07080fc 100644 --- a/reports/skillops/daily/2026-06-17.json +++ b/reports/skillops/daily/2026-06-17.json @@ -14,7 +14,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -31,7 +31,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -480,7 +480,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true }, "actions": [ diff --git a/reports/skillops/daily/2026-06-17.md b/reports/skillops/daily/2026-06-17.md index 5d6c937..65caad5 100644 --- a/reports/skillops/daily/2026-06-17.md +++ b/reports/skillops/daily/2026-06-17.md @@ -14,7 +14,7 @@ Generated at: `2026-06-17` - local blueprint ready: `true` - public world-class ready: `false` - world-class pending: `4` -- release lock ready: `false` +- release lock ready: `true` - evidence consistency ok: `true` This report is an operations cockpit for explicit-source SkillOps. It does not scan private logs, write source files, apply patches, or count as world-class external or human evidence. diff --git a/reports/skillops/weekly/2026-W25.json b/reports/skillops/weekly/2026-W25.json index 8c1ed2f..8f21344 100644 --- a/reports/skillops/weekly/2026-W25.json +++ b/reports/skillops/weekly/2026-W25.json @@ -15,7 +15,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -35,7 +35,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -288,7 +288,7 @@ "no_route_opportunity_count": 0 }, "release_state": { - "release_lock_ready": false, + "release_lock_ready": true, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4 diff --git a/reports/skillops/weekly/2026-W25.md b/reports/skillops/weekly/2026-W25.md index e8b03e0..a52113b 100644 --- a/reports/skillops/weekly/2026-W25.md +++ b/reports/skillops/weekly/2026-W25.md @@ -13,7 +13,7 @@ Week: `2026-W25` - top_score: `88` - skill_count: `12` - actionable_portfolio_issue_count: `0` -- release_lock_ready: `False` +- release_lock_ready: `True` - evidence_consistency_ok: `True` - public_world_class_ready: `False` - world_class_pending_count: `4` diff --git a/reports/world_class_evidence_preflight.json b/reports/world_class_evidence_preflight.json index 1a1a1f4..22c57f1 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": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "summary": { "evidence_item_count": 4, diff --git a/reports/world_class_evidence_preflight.md b/reports/world_class_evidence_preflight.md index cb7ce7b..958e56f 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: `2026-06-13` +Generated at: `2026-06-17` ## Summary