From 9da8d0e08b00a013166dc6b6058e12622b923d10 Mon Sep 17 00:00:00 2001 From: yaojingang Date: Wed, 17 Jun 2026 00:26:39 +0800 Subject: [PATCH] Refresh evidence after stale lock guard --- registry/index.json | 2 +- registry/packages/yao-meta-skill.json | 2 +- reports/adoption_drift_report.json | 28 +- reports/adoption_drift_report.md | 10 +- reports/benchmark_reproducibility.json | 90 ++-- reports/benchmark_reproducibility.md | 51 +-- reports/compiled_targets.json | 72 ++-- reports/context_budget.json | 4 +- reports/context_budget_summary.json | 2 +- reports/evidence_consistency.json | 164 +++---- reports/evidence_consistency.md | 2 +- reports/install_simulation.json | 18 +- reports/install_simulation.md | 4 +- reports/output_execution_runs.json | 20 +- reports/output_execution_runs.md | 20 +- reports/package_verification.json | 6 +- reports/package_verification.md | 2 +- reports/registry_audit.json | 4 +- reports/registry_audit.md | 2 +- reports/review-studio.html | 30 +- reports/review-studio.json | 446 +++++++++++--------- reports/review-viewer.json | 59 +-- reports/review_annotations.json | 2 +- reports/review_waivers.json | 4 +- reports/review_waivers.md | 2 +- reports/runtime_permission_probes.json | 10 +- reports/skill-interpretation.html | 2 +- reports/skill-interpretation.json | 59 +-- reports/skill-os-2-review.md | 4 +- reports/skill-overview.html | 2 +- reports/skill-overview.json | 59 +-- reports/skill_atlas.json | 4 +- reports/skill_os2_audit.json | 6 +- reports/skill_os2_audit.md | 4 +- reports/skill_os2_coverage.json | 16 +- reports/skill_os2_coverage.md | 14 +- reports/skillops/daily/2026-06-16.json | 2 +- reports/skillops/daily/2026-06-16.md | 2 +- 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/upgrade_check.json | 8 +- reports/world_class_evidence_intake.json | 2 +- reports/world_class_evidence_ledger.json | 20 +- reports/world_class_evidence_ledger.md | 12 +- reports/world_class_evidence_plan.json | 4 +- reports/world_class_evidence_plan.md | 2 +- reports/world_class_evidence_preflight.html | 8 +- reports/world_class_evidence_preflight.json | 12 +- reports/world_class_evidence_preflight.md | 4 +- reports/world_class_operator_runbook.html | 8 +- reports/world_class_operator_runbook.json | 17 +- reports/world_class_operator_runbook.md | 7 +- reports/world_class_submission_review.json | 18 +- reports/world_class_submission_review.md | 2 +- skill_atlas/catalog.json | 4 +- 57 files changed, 722 insertions(+), 652 deletions(-) diff --git a/registry/index.json b/registry/index.json index b8b583c3..c9a785a4 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69" + "package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index 7b84f164..ebed657c 100644 --- a/registry/packages/yao-meta-skill.json +++ b/registry/packages/yao-meta-skill.json @@ -16,7 +16,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", + "package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b" }, "compatibility": { diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json index cc4b39cf..a423e3d0 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": "2026-06-16T16:15:39Z", + "generated_at": "2026-06-17", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -25,14 +25,14 @@ }, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -41,7 +41,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -53,31 +53,31 @@ { "skill": "yao-meta-skill", "events": 1, - "adoption_events": 1, - "accepted": 1, + "adoption_events": 0, + "accepted": 0, "edited": 0, "rejected": 0, "missed": 0, - "adoption_rate": 100.0 + "adoption_rate": 0 } ], "next_iteration_candidates": [], "recent_events": [ { "command": "unknown", - "event": "skill_activation", + "event": "review_event", "skill": "yao-meta-skill", "source": "manual", "version": "1.1.0", - "activation_type": "explicit", - "outcome": "accepted", + "activation_type": "manual", + "outcome": "reviewed", "failure_type": "none", - "timestamp": "2026-06-13T10:00:00Z" + "timestamp": "2026-06-13T12:00:00Z" } ], "failures": [], "artifacts": { - "events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl", + "events_jsonl": "reports/telemetry_events.jsonl", "json": "reports/adoption_drift_report.json", "markdown": "reports/adoption_drift_report.md" } diff --git a/reports/adoption_drift_report.md b/reports/adoption_drift_report.md index 206372c9..91b31983 100644 --- a/reports/adoption_drift_report.md +++ b/reports/adoption_drift_report.md @@ -5,9 +5,9 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs, ## Summary - Events: `1` -- Adoption samples: `1` -- Activation events: `1` -- Adoption rate: `100.0` +- Adoption samples: `0` +- Activation events: `0` +- Adoption rate: `0` - Missed trigger signals: `0` - Bad output signals: `0` - Script error signals: `0` @@ -25,7 +25,7 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs, | Skill | Events | Adoption Samples | Accepted | Edited | Rejected | Missed | Adoption Rate | | --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | -| `yao-meta-skill` | 1 | 1 | 1 | 0 | 0 | 0 | 100.0 | +| `yao-meta-skill` | 1 | 0 | 0 | 0 | 0 | 0 | 0 | ## Next Iteration Candidates @@ -33,4 +33,4 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs, ## Recent Metadata Events -- `2026-06-13T10:00:00Z` `yao-meta-skill` event=`skill_activation` source=`manual` command=`unknown` activation=`explicit` outcome=`accepted` failure=`none` +- `2026-06-13T12:00:00Z` `yao-meta-skill` event=`review_event` source=`manual` command=`unknown` activation=`manual` outcome=`reviewed` failure=`none` diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index c0c5880a..ae66b9bd 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,23 +3,36 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", + "commit": "67058cecebd13cd6e6fa54c009300cc145e8e999", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 56, + "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/benchmark_reproducibility.json", + " M reports/benchmark_reproducibility.md", + " M reports/compiled_targets.json", + " M reports/context_budget.json", + " M reports/context_budget_summary.json", + " M reports/evidence_consistency.json", + " M reports/evidence_consistency.md", + " M reports/install_simulation.json" + ], "scope": "generation-time status before this report is written" }, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f", + "evidence_bundle_sha256": "733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379", "source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", - "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", + "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -34,29 +47,30 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 56 }, "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 (7/13 pass, 6 blocked)" + "world-class source checks are not all accepted (6/13 pass, 7 blocked)" ], "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks." }, "release_lock": { - "ready": true, - "commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", + "ready": false, + "commit": "67058cecebd13cd6e6fa54c009300cc145e8e999", "status_scope": "generation-time status before this report is written", - "reason": "clean generation-time HEAD" + "reason": "working tree was dirty at generation time" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -64,7 +78,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f" + "sha256": "733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -137,8 +151,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7965, - "sha256": "6334c2f0261c2c978ebcb518cdac4ddf409f41e3732b08998c8e4b80529e446d" + "bytes": 7967, + "sha256": "6450488d6ac4f80b0160161d5385bbf2f6aec2856076621a81027ae5c89fa38a" }, { "label": "blind_review", @@ -187,84 +201,84 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "dfd07c1825de99435bd661e2663ae74251bbe03cb5ddda66d268efb6a872eb31" + "sha256": "8683ab3f627c2fe16c77dabe34798d2fb6942bb05c636cc35e4f6edd617c79d5" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "a27941fdb8651371fc7abc69247e15cf8e2863d5805b0538d67c326d4095148f" + "sha256": "1372317d59e9ff19cfa4f69bfcfb5ddb9a9770f5628d9454a8f165e363c5b95b" }, { "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, - "bytes": 8758, - "sha256": "5269d6e6364aaa39e935cbf02df7569a6a88d2653120bc6e3e34d3684a73639d" + "bytes": 8604, + "sha256": "3a707c08d4b0df167b835215f0f7696568a5a1e4099854d8a02647cdcd5b8b37" }, { "label": "skill_os2_audit", "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14310, - "sha256": "390d0bb42652e9f84fcab195de1da3c9cda213c254fd9319d31c54dd8429aee7" + "sha256": "453a86240e7fe1a703615ba3ce9a97d940e9c552ee9e39d5cccbf7c3481dd507" }, { "label": "world_class_evidence_plan", "path": "reports/world_class_evidence_plan.json", "exists": true, "bytes": 20828, - "sha256": "9b74155fb9bfe44ba838d64b1a31768b83978b154bdd8eaa606f494c816f189f" + "sha256": "0a836a86ad6c648d8c442a16cae7cdb17d3640a0ba6ec69c1290825ede6d152a" }, { "label": "world_class_evidence_ledger", "path": "reports/world_class_evidence_ledger.json", "exists": true, - "bytes": 22285, - "sha256": "f6e1a69b0359c28c88e9e9e69ff66763c721ac8a112a43a673ce98cd9d3bce41" + "bytes": 22288, + "sha256": "fe81833eab69292525975b347177bc7fcda6410f493fc60bd840a20e86ca0039" }, { "label": "world_class_evidence_intake", "path": "reports/world_class_evidence_intake.json", "exists": true, "bytes": 19319, - "sha256": "46f801051ec075725059e4e2682ef2162fd892b5e7255c8d5121d7b24dcc7f2c" + "sha256": "4506c836338c65a3a01b15b1f26a1fdd0a8ef520a1e5f1574ee89ce9d3bbeb29" }, { "label": "world_class_evidence_preflight", "path": "reports/world_class_evidence_preflight.json", "exists": true, - "bytes": 41202, - "sha256": "b7fd72d7e75486612f65a9bb73b1ab59106103ebf3ad10dd446cd80903088454" + "bytes": 41208, + "sha256": "725d10a6f951ab1e64f4e6a1cfa907404b51f598a753b5a0351e1381fef7cd9e" }, { "label": "world_class_submission_review", "path": "reports/world_class_submission_review.json", "exists": true, - "bytes": 13655, - "sha256": "9fbd4cd437986fca9a043cbab24aec7d575aaf166a8d9365c79c56f093cab5b8" + "bytes": 13658, + "sha256": "7693638c2e8369a8a179b3420c11090668f8f104f452dc370082dc9ebafe882d" }, { "label": "world_class_operator_runbook", "path": "reports/world_class_operator_runbook.json", "exists": true, - "bytes": 24835, - "sha256": "2d32a2e917b7215afe7a7a93ca8bacffa540a245953aa39e2ee47eea1b169d17" + "bytes": 24899, + "sha256": "f90d59c3e5866da33138869c1c5299350a43389d81e84ba466df794befb494fa" }, { "label": "world_class_operator_runbook_markdown", "path": "reports/world_class_operator_runbook.md", "exists": true, - "bytes": 15424, - "sha256": "00d8ebabb91e14a06cacdb212f448668aa1e47b72587448e30681fc53acaad9a" + "bytes": 15479, + "sha256": "be79ee0f70a3ceed473c481562c5fddaee6cfb36c960ba15ae10c846d5809650" }, { "label": "world_class_operator_runbook_html", "path": "reports/world_class_operator_runbook.html", "exists": true, - "bytes": 21348, - "sha256": "ca72c65b437b2211d08b9d463c9a33a7993b4e388bb75f62757ead4dfcf81a49" + "bytes": 21409, + "sha256": "9a7be02a6990245c9dd1f72ced5928d80a3aaebea4647737c2aaf0b0a2f798df" }, { "label": "world_class_claim_guard", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 4cfbf271..bfbade65 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,29 +1,29 @@ # Benchmark Reproducibility Generated at: `2026-06-17` -Commit: `b6ded57f9cc65b1dd7dbbac9c394647dadc131d7` -Working tree dirty at generation: `false` -Evidence bundle SHA256: `c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f` +Commit: `67058cecebd13cd6e6fa54c009300cc145e8e999` +Working tree dirty at generation: `true` +Evidence bundle SHA256: `733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379` ## Summary - reproducibility ready: `true` -- release lock ready: `true` +- release lock ready: `false` - methodology complete: `true` - required artifacts: `25` - missing artifacts: `0` - source contract sha256: `9cb9a19e7745` -- archive sha256: `5802e5f52255` +- archive sha256: `419593870964` - output cases: `5` - disclosed failure cases: `3` - reproduction commands: `23` - provider evidence complete: `false` - human review complete: `false` - world-class ready: `false` -- world-class source checks: `7` pass / `13` total; `6` blocked +- world-class source checks: `6` pass / `13` total; `7` blocked - public claim ready: `false` -- public claim blockers: `4` -- changed files at generation: `0` +- public claim blockers: `5` +- changed files at generation: `56` 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 is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below. @@ -35,22 +35,23 @@ This report proves local benchmark reproducibility only. It keeps external provi | Blocker | | --- | +| release lock is not clean or commit is unavailable | | provider-backed model holdout evidence is incomplete | | human blind-review adjudication is incomplete | | world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) | -| world-class source checks are not all accepted (7/13 pass, 6 blocked) | +| world-class source checks are not all accepted (6/13 pass, 7 blocked) | ## Release Lock -- ready: `true` -- reason: clean generation-time HEAD +- ready: `false` +- reason: working tree was 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: `c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f` +- sha256: `733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379` ## Methodology Sections @@ -72,25 +73,25 @@ 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 | `6334c2f0261c` | +| output_execution | `reports/output_execution_runs.json` | present | `6450488d6ac4` | | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` | | review_adjudication | `reports/output_review_adjudication.json` | present | `bb8c72a9291e` | | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` | | runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` | | trust_report | `reports/security_trust_report.json` | present | `5b05d1110b96` | | python_compatibility | `reports/python_compatibility.json` | present | `8b48340618cc` | -| registry_audit | `reports/registry_audit.json` | present | `dfd07c1825de` | -| package_verification | `reports/package_verification.json` | present | `a27941fdb865` | -| install_simulation | `reports/install_simulation.json` | present | `5269d6e6364a` | -| skill_os2_audit | `reports/skill_os2_audit.json` | present | `390d0bb42652` | -| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `9b74155fb9bf` | -| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `f6e1a69b0359` | -| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `46f801051ec0` | -| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `b7fd72d7e754` | -| world_class_submission_review | `reports/world_class_submission_review.json` | present | `9fbd4cd43798` | -| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `2d32a2e917b7` | -| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `00d8ebabb91e` | -| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `ca72c65b437b` | +| registry_audit | `reports/registry_audit.json` | present | `8683ab3f627c` | +| package_verification | `reports/package_verification.json` | present | `1372317d59e9` | +| install_simulation | `reports/install_simulation.json` | present | `3a707c08d4b0` | +| skill_os2_audit | `reports/skill_os2_audit.json` | present | `453a86240e7f` | +| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `0a836a86ad6c` | +| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `fe81833eab69` | +| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `4506c836338c` | +| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `725d10a6f951` | +| world_class_submission_review | `reports/world_class_submission_review.json` | present | `7693638c2e83` | +| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `f90d59c3e586` | +| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `be79ee0f70a3` | +| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `9a7be02a6990` | | world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `abe7f7d60c00` | ## Reproduction Commands diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json index 78d28a9b..b579ffda 100644 --- a/reports/compiled_targets.json +++ b/reports/compiled_targets.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "summary": { "target_count": 5, @@ -512,12 +512,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -554,7 +555,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -576,7 +577,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -768,12 +769,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -810,7 +812,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -830,7 +832,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -1430,12 +1432,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -1472,7 +1475,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -1494,7 +1497,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -1686,12 +1689,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -1728,7 +1732,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -1748,7 +1752,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -2348,12 +2352,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -2390,7 +2395,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -2412,7 +2417,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -2597,12 +2602,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -2639,7 +2645,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -2659,7 +2665,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -3250,12 +3256,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -3292,7 +3299,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -3314,7 +3321,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -3499,12 +3506,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -3541,7 +3549,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -3561,7 +3569,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -4152,12 +4160,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -4194,7 +4203,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -4216,7 +4225,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -4405,12 +4414,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -4447,7 +4457,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -4467,7 +4477,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", diff --git a/reports/context_budget.json b/reports/context_budget.json index 64bb91e9..a262c2a3 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": 1078122, + "other_text_tokens": 1078201, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1078919, + "estimated_total_text_tokens": 1078998, "deferred_resource_tokens": 495718, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ diff --git a/reports/context_budget_summary.json b/reports/context_budget_summary.json index d2d7a29f..a90b26ad 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 be02ba8c..970ca19a 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 git dirty state", "status": "pass", - "expected": true, - "actual": true, + "expected": false, + "actual": false, "paths": [ "reports/benchmark_reproducibility.json" ], @@ -218,12 +218,16 @@ "key": "benchmark-clean-worktree-release-lock", "label": "Clean worktree keeps a clean benchmark release lock", "status": "pass", - "expected": true, - "actual": true, + "expected": "checked only when git is available and the current worktree is clean", + "actual": { + "available": true, + "clean": false, + "changed_file_count": 57 + }, "paths": [ "reports/benchmark_reproducibility.json" ], - "detail": "If the current worktree is clean, the committed benchmark report must not still carry a dirty release lock from an earlier generation." + "detail": "Dirty or non-git worktrees cannot prove final release-lock freshness, so this check is advisory until the final clean-lock pass." }, { "key": "skill-ir-evidence-path-contract", @@ -259,8 +263,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", - "actual": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", + "expected": "67058cecebd13cd6e6fa54c009300cc145e8e999", + "actual": "67058cecebd13cd6e6fa54c009300cc145e8e999", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -272,30 +276,30 @@ "label": "overview embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, "source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", - "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", + "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "actual": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, "source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", - "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", + "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -309,13 +313,13 @@ "status": "pass", "expected": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, + "adoption_rate": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "source_types": { "manual": 1 @@ -323,13 +327,13 @@ }, "actual": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, + "adoption_rate": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "source_types": { "manual": 1 @@ -352,8 +356,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -364,8 +368,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -385,7 +389,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 13, - "source_pass_count": 7 + "source_pass_count": 6 }, "actual": { "ready": false, @@ -393,7 +397,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 13, - "source_pass_count": 7 + "source_pass_count": 6 }, "paths": [ "reports/world_class_evidence_ledger.json", @@ -405,8 +409,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", - "actual": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", + "expected": "67058cecebd13cd6e6fa54c009300cc145e8e999", + "actual": "67058cecebd13cd6e6fa54c009300cc145e8e999", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -418,30 +422,30 @@ "label": "interpretation embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, "source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", - "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", + "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "actual": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, "source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", - "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", + "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -455,13 +459,13 @@ "status": "pass", "expected": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, + "adoption_rate": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "source_types": { "manual": 1 @@ -469,13 +473,13 @@ }, "actual": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, + "adoption_rate": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "source_types": { "manual": 1 @@ -498,8 +502,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -510,8 +514,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -531,7 +535,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 13, - "source_pass_count": 7 + "source_pass_count": 6 }, "actual": { "ready": false, @@ -539,7 +543,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 13, - "source_pass_count": 7 + "source_pass_count": 6 }, "paths": [ "reports/world_class_evidence_ledger.json", @@ -1338,7 +1342,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 13, - "source_pass_count": 7, + "source_pass_count": 6, "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": [ @@ -1397,7 +1401,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -1411,7 +1416,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 13, - "source_pass_count": 7, + "source_pass_count": 6, "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": [ @@ -1470,7 +1475,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -1820,15 +1826,15 @@ "expected": { "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false }, "actual": { "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false }, "paths": [ @@ -1844,8 +1850,8 @@ "expected": { "pending_count": 4, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "preflight_counts_as_evidence": false, "credential_value_exposed": false @@ -1853,8 +1859,8 @@ "actual": { "pending_count": 4, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "preflight_counts_as_evidence": false, "credential_value_exposed": false @@ -2108,8 +2114,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "plan_keys": [ "human-adjudication", "native-client-telemetry", @@ -2257,8 +2263,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "plan_keys": [ "human-adjudication", "native-client-telemetry", @@ -2415,8 +2421,8 @@ "`3` warnings", "`54` declared internal modules", "`86 / 86` CLI help smoke checks passing across `140` scripts", - "`658` zip entries", - "archive with `658` entries", + "`677` zip entries", + "archive with `677` entries", "`12` installer permission checks enforced", "`0` permission failures", "`25` required artifacts", diff --git a/reports/evidence_consistency.md b/reports/evidence_consistency.md index 4f793959..26627b69 100644 --- a/reports/evidence_consistency.md +++ b/reports/evidence_consistency.md @@ -20,7 +20,7 @@ This gate compares generated evidence reports against each other. It does not cr | Release evidence flow covers first-class reports | `pass` | Release refresh and clean-lock instructions must regenerate every first-class report before evidence consistency can be trusted. | `AGENTS.md`, `reports/output_execution_runs.json`, `reports/install_simulation.json`, `reports/security_trust_report.json`, `reports/registry_audit.json`, `reports/package_verification.json`, `reports/upgrade_check.json`, `reports/adoption_drift_report.json`, `reports/architecture_maintainability.json`, `reports/python_compatibility.json`, `reports/runtime_permission_probes.json`, `reports/review_waivers.json`, `reports/review_annotations.json`, `reports/skill_atlas.json`, `reports/skill_os2_audit.json`, `reports/skill_os2_coverage.json`, `reports/context_budget.json`, `reports/context_budget_summary.json`, `reports/benchmark_reproducibility.json`, `reports/skill-overview.json`, `reports/skill-interpretation.json`, `reports/review-viewer.json`, `reports/world_class_evidence_preflight.json`, `reports/skillops/daily`, `reports/skillops/weekly`, `reports/review-studio.json`, `reports/evidence_consistency.json` | | Review Studio mirrors context budget governance | `pass` | Review Studio must not keep stale context warnings after context reports prove large deferred resources are governed. | `reports/context_budget.json`, `reports/review-studio.json` | | Benchmark release lock matches git dirty state | `pass` | The benchmark release lock must reflect the generation-time git dirty flag. | `reports/benchmark_reproducibility.json` | -| Clean worktree keeps a clean benchmark release lock | `pass` | If the current worktree is clean, the committed benchmark report must not still carry a dirty release lock from an earlier generation. | `reports/benchmark_reproducibility.json` | +| Clean worktree keeps a clean benchmark release lock | `pass` | Dirty or non-git worktrees cannot prove final release-lock freshness, so this check is advisory until the final clean-lock pass. | `reports/benchmark_reproducibility.json` | | Human-facing reports expose the canonical Skill IR artifact | `pass` | Skill IR is the 2.0 platform-neutral semantic source, so user-facing reports must link to the artifact that actually exists. | `reports/skill-overview.json`, `reports/skill-interpretation.json`, `reports/review-studio.json`, `skill-ir/examples/yao-meta-skill.json` | | overview embeds the benchmark commit | `pass` | Human-facing reports must point to the same benchmark release-lock commit. | `reports/benchmark_reproducibility.json`, `reports/skill-overview.json` | | overview embeds benchmark summary fields | `pass` | Selected summary fields must match exactly across generated reports. | `reports/benchmark_reproducibility.json`, `reports/skill-overview.json` | diff --git a/reports/install_simulation.json b/reports/install_simulation.json index b80aaab5..88dc275b 100644 --- a/reports/install_simulation.json +++ b/reports/install_simulation.json @@ -1,11 +1,11 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", - "package_dir": "tests/tmp_review_studio/dist", - "install_root": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill", - "installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill", + "package_dir": "dist", + "install_root": "dist/install-simulation/simulate-yao-meta-skill", + "installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill", "summary": { "archive_present": true, "archive_entry_count": 677, @@ -26,7 +26,7 @@ { "id": "archive-present", "status": "pass", - "detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip" + "detail": "Package archive exists: dist/yao-meta-skill.zip" }, { "id": "archive-safe-paths", @@ -272,9 +272,9 @@ "failures": [], "warnings": [], "artifacts": { - "archive": "tests/tmp_review_studio/dist/yao-meta-skill.zip", - "package_manifest": "tests/tmp_review_studio/dist/manifest.json", - "json": "tests/tmp_review_studio/install_simulation.json", - "markdown": "tests/tmp_review_studio/install_simulation.md" + "archive": "dist/yao-meta-skill.zip", + "package_manifest": "dist/manifest.json", + "json": "reports/install_simulation.json", + "markdown": "reports/install_simulation.md" } } diff --git a/reports/install_simulation.md b/reports/install_simulation.md index b0d16dae..6750e007 100644 --- a/reports/install_simulation.md +++ b/reports/install_simulation.md @@ -1,7 +1,7 @@ # Install Simulation - OK: `True` -- Package directory: `tests/tmp_review_studio/dist` +- Package directory: `dist` - Archive extracted: `True` - Entrypoint loaded: `True` - Manifest loaded: `True` @@ -16,7 +16,7 @@ | Check | Status | Detail | | --- | --- | --- | -| `archive-present` | `pass` | Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip | +| `archive-present` | `pass` | Package archive exists: dist/yao-meta-skill.zip | | `archive-safe-paths` | `pass` | Archive has no absolute or parent-traversal entries | | `single-top-level` | `pass` | Archive top-level directory is yao-meta-skill | | `entrypoint-load` | `pass` | Installed SKILL.md frontmatter is readable | diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index ff45db38..be42f21a 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": 26.12, + "duration_ms": 27.03, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.28, + "duration_ms": 25.75, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.37, + "duration_ms": 25.71, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.8, + "duration_ms": 27.67, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.59, + "duration_ms": 28.25, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.55, + "duration_ms": 26.51, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.89, + "duration_ms": 34.54, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.9, + "duration_ms": 30.74, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.03, + "duration_ms": 27.88, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.51, + "duration_ms": 26.38, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index 8cb1af25..4776b03b 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 | 26.12 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 28.28 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 29.37 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.8 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 29.59 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 28.55 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.89 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.9 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.03 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.51 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 27.03 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 25.75 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 25.71 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 27.67 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 28.25 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.51 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 34.54 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 30.74 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 27.88 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.38 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/package_verification.json b/reports/package_verification.json index 90f285fa..d73c2fe9 100644 --- a/reports/package_verification.json +++ b/reports/package_verification.json @@ -1,15 +1,15 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-16", + "generated_at": "2026-06-17", "skill_dir": ".", "package_dir": "dist", "summary": { "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", - "archive_entry_count": 658, + "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7", + "archive_entry_count": 677, "failure_count": 0, "warning_count": 0 }, diff --git a/reports/package_verification.md b/reports/package_verification.md index 4f251d50..76ca4ee4 100644 --- a/reports/package_verification.md +++ b/reports/package_verification.md @@ -4,7 +4,7 @@ - Package directory: `dist` - Targets: `4 / 4` adapters present - Archive present: `True` -- Archive SHA256: `5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b` +- Archive SHA256: `4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7` - Failures: `0` - Warnings: `0` diff --git a/reports/registry_audit.json b/reports/registry_audit.json index 01d6a836..c6e2ef99 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,7 +21,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", + "package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b" }, "compatibility": { @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69" + "package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index 5783d3ed..4821a16a 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,7 +6,7 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69` +- Package SHA256: `9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b` - Archive SHA256: `5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b` - Install simulated: `True` diff --git a/reports/review-studio.html b/reports/review-studio.html index 438e1d7c..acc7d1cc 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -740,12 +740,12 @@

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

Blueprint20/21

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

140 scripts scanned; secrets found

Py Compat0

218 files scanned for Python 3.11

Arch Debt0

696 largest lines; 0 watchlist; 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

658 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

+
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

5 blockers; local reproducible true

Blueprint21/21

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

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

140 scripts scanned; secrets found

Py Compat0

218 files scanned for Python 3.11

Arch Debt0

696 largest lines; 0 watchlist; 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

677 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 495718/120000; top deferred scripts 435620; 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; 140 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 218 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

215 Python files; 0 hotspots; 0 watchlist 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 7/13 pass; 6 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 495718/120000; top deferred scripts 435620; 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; 140 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 218 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

215 Python files; 0 hotspots; 0 watchlist 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 6/13 pass; 7 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
@@ -755,12 +755,12 @@

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 7/13 pass; 6 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 6/13 pass; 7 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。

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
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
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.
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
2 blocked / 2 pass
下一步
Record real A/B choices in the decision template, then regenerate adjudication.
阻断检查
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
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/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.
  • The decision importer rejects raw prompt, output, transcript, message, and answer-key fields.
  • Keep the answer key separate until after decisions are recorded.
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
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.
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
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.
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。

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
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
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.
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
2 blocked / 2 pass
下一步
Record real A/B choices in the decision template, then regenerate adjudication.
阻断检查
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
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/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.
  • The decision importer rejects raw prompt, output, transcript, message, and answer-key fields.
  • Keep the answer key separate until after decisions are recorded.
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
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.
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
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.
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.
@@ -842,14 +842,14 @@
-

运营回路

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

-

漂移信号

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

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock 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
-

日常运维

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

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
Writes Source Files
Auto Patch Enabled
+

日常运维

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

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
Writes Source Files
Auto Patch Enabled
@@ -861,13 +861,13 @@

批准台账

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

批准候选

-
可批准 · needs-reviewer-decision

Output Lab

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

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

审查条件

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

World-Class Evidence

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

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

审查条件

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

Output Lab

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

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

审查条件

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

World-Class Evidence

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

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

审查条件

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

世界证据

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

-
待补证 · external

Provider Holdout

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

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

执行步骤

  • Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.
  • export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}
  • python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions

完成定义

  • reports/output_execution_runs.json summary.model_executed_count > 0
  • reports/output_execution_runs.json summary.timing_observed_count > 0
  • reports/output_execution_runs.json summary.token_observed_count > 0
  • reports/skill_os2_audit.json item provider-holdout status becomes pass

证据来源

  • reports/output_execution_runs.json
  • reports/output_execution_runs.md
  • reports/skill_os2_audit.json
  • evidence/world_class/intake.schema.json
  • evidence/world_class/templates/provider-holdout.intake.json
  • reports/world_class_evidence_intake.json
  • reports/world_class_evidence_intake.md

隐私约束

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

源证据检查

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

Human Adjudication

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

负责人
human reviewer
当前状态
0/5 decisions; pending 5
下一步
Record real A/B choices in the decision template, then regenerate adjudication.
观测值
pair_count: 5; judgment_count: 0; pending_count: 5; invalid_decision_count: 0; answer_revealed_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 case_id, winner_variant, confidence, and reason only.
  • python3 scripts/yao.py output-review-import --input <reviewer-decisions.json> --run-adjudication
  • python3 scripts/yao.py output-review
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions

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/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.
  • The decision importer rejects raw prompt, output, transcript, message, and answer-key fields.
  • 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 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.
待补证 · external

Native Permission Enforcement

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

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

执行步骤

  • Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.
  • Update the generated target adapter only when the guard is actually enforced by that target.
  • python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip
  • python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation
  • python3 scripts/yao.py runtime-permissions . --package-dir dist
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions

完成定义

  • reports/runtime_permission_probes.json summary.native_enforcement_count > 0
  • reports/runtime_permission_probes.json summary.failure_count == 0
  • reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence
  • reports/skill_os2_audit.json item native-permission-enforcement status becomes pass

证据来源

  • dist/targets/*/adapter.json
  • reports/runtime_permission_probes.json
  • reports/runtime_permission_probes.md
  • reports/install_simulation.json
  • reports/install_simulation.md
  • security/permission_policy.json
  • evidence/world_class/intake.schema.json
  • evidence/world_class/templates/native-permission-enforcement.intake.json
  • reports/world_class_evidence_intake.json
  • reports/world_class_evidence_intake.md

隐私约束

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

源证据检查

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

Native Client Telemetry

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

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

执行步骤

  • python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/
  • Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.
  • python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
  • python3 scripts/yao.py skill-atlas --workspace-root .
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions

完成定义

  • reports/adoption_drift_report.json summary.source_types.external > 0
  • reports/adoption_drift_report.json summary.adoption_sample_count > 0
  • reports/skill_os2_audit.json item native-client-telemetry status becomes pass

证据来源

  • reports/adoption_drift_report.json
  • reports/adoption_drift_report.md
  • reports/telemetry_hook_recipes.json
  • scripts/telemetry_native_host.py
  • evidence/world_class/intake.schema.json
  • evidence/world_class/templates/native-client-telemetry.intake.json
  • reports/world_class_evidence_intake.json
  • reports/world_class_evidence_intake.md

隐私约束

  • Telemetry must remain metadata-only and local-first.
  • Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.

源证据检查

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

Provider Holdout

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

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

执行步骤

  • Set OPENAI_API_KEY in the operator shell before running provider evidence; never commit or print the value.
  • export YAO_OUTPUT_EVAL_MODEL=${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini}
  • python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions

完成定义

  • reports/output_execution_runs.json summary.model_executed_count > 0
  • reports/output_execution_runs.json summary.timing_observed_count > 0
  • reports/output_execution_runs.json summary.token_observed_count > 0
  • reports/skill_os2_audit.json item provider-holdout status becomes pass

证据来源

  • reports/output_execution_runs.json
  • reports/output_execution_runs.md
  • reports/skill_os2_audit.json
  • evidence/world_class/intake.schema.json
  • evidence/world_class/templates/provider-holdout.intake.json
  • reports/world_class_evidence_intake.json
  • reports/world_class_evidence_intake.md

隐私约束

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

源证据检查

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

Human Adjudication

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

负责人
human reviewer
当前状态
0/5 decisions; pending 5
下一步
Record real A/B choices in the decision template, then regenerate adjudication.
观测值
pair_count: 5; judgment_count: 0; pending_count: 5; invalid_decision_count: 0; answer_revealed_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 case_id, winner_variant, confidence, and reason only.
  • python3 scripts/yao.py output-review-import --input <reviewer-decisions.json> --run-adjudication
  • python3 scripts/yao.py output-review
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions

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/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.
  • The decision importer rejects raw prompt, output, transcript, message, and answer-key fields.
  • 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 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.
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.
@@ -877,17 +877,17 @@
-

蓝图覆盖

项目数
21
模块数
8
建议 PR
13
通过数
20
Warn Count
1
缺失数
0
Extension Track Count
4
Extension Covered Count
4
Extension Partial Count
0
Extension Planned Count
0
Adaptive Extension Ready
本地蓝图
世界级
待补证据
4
+

蓝图覆盖

项目数
21
模块数
8
建议 PR
13
通过数
21
Warn Count
0
缺失数
0
Extension Track Count
4
Extension Covered Count
4
Extension Partial Count
0
Extension Planned Count
0
Adaptive Extension Ready
本地蓝图
世界级
待补证据
4

覆盖边界

蓝图覆盖只证明 2.0 模块、建议 PR、脚本、报告和测试在本地闭环;public world-class 仍以 world-class evidence ledger 的真人和外部证据为准。

-

公开声明

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

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 (7/13 pass, 6 blocked)
+

公开声明

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

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 (6/13 pass, 7 blocked)
-

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 7/13 pass; 6 blocked; overclaim guard true

+

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 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
Ready To Claim World Class
@@ -908,7 +908,7 @@

发布路线

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

-

包体验证

目标数
4
Adapter
4
归档存在
Zip 条目
658
失败数
0
警告数
0
归档哈希
5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b
+

包体验证

目标数
4
Adapter
4
归档存在
Zip 条目
677
失败数
0
警告数
0
归档哈希
4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7
diff --git a/reports/review-studio.json b/reports/review-studio.json index 0911cf8a..2a15841c 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 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true", + "detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false", "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 7/13 pass; 6 blocked; overclaim guard true", + "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 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 7/13 pass; 6 blocked; overclaim guard true", + "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true", "evidence": "reports/world_class_evidence_ledger.json", "link": "world_class_evidence_ledger.md" } @@ -817,12 +817,12 @@ "category": "external", "status": "pending", "readiness": "awaiting-submission", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "next_action": "Install a real client against the native host and import production metadata-only events.", "submission_path": "evidence/world_class/submissions/native-client-telemetry.json", "template_path": "evidence/world_class/templates/native-client-telemetry.intake.json", - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "blocked_checks": [ { "label": "External events", @@ -831,6 +831,14 @@ "expected": ">0", "status": "blocked", "next_action": "Import at least one metadata-only event from a real client." + }, + { + "label": "Adoption sample", + "field": "adoption_sample_count", + "actual": 0, + "expected": ">0", + "status": "blocked", + "next_action": "Telemetry must include adoption outcome evidence." } ], "commands": [ @@ -1375,7 +1383,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 13, - "source_pass_count": 7, + "source_pass_count": 6, "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": [ @@ -1434,7 +1442,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -1959,13 +1968,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f", + "evidence_bundle_sha256": "733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379", "source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", - "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", + "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1980,14 +1989,14 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 56 }, - "commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", + "commit": "67058cecebd13cd6e6fa54c009300cc145e8e999", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -2130,7 +2139,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", + "package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b" }, "compatibility": { @@ -2178,8 +2187,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", - "archive_entry_count": 658, + "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7", + "archive_entry_count": 677, "failure_count": 0, "warning_count": 0 }, @@ -2262,7 +2271,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69" + "to": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b" } ] }, @@ -2279,14 +2288,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -2295,7 +2304,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -2562,7 +2571,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -2615,8 +2624,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -2966,7 +2975,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -3003,7 +3012,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -3024,8 +3033,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -3041,8 +3050,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", @@ -4692,7 +4701,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.12, + "duration_ms": 27.03, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4720,7 +4729,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.28, + "duration_ms": 25.75, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4743,7 +4752,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.37, + "duration_ms": 25.71, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4771,7 +4780,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.8, + "duration_ms": 27.67, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4794,7 +4803,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.59, + "duration_ms": 28.25, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4822,7 +4831,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.55, + "duration_ms": 26.51, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4845,7 +4854,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.89, + "duration_ms": 34.54, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4872,7 +4881,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.9, + "duration_ms": 30.74, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4895,7 +4904,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.03, + "duration_ms": 27.88, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4924,7 +4933,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.51, + "duration_ms": 26.38, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5650,23 +5659,36 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", + "commit": "67058cecebd13cd6e6fa54c009300cc145e8e999", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 56, + "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/benchmark_reproducibility.json", + " M reports/benchmark_reproducibility.md", + " M reports/compiled_targets.json", + " M reports/context_budget.json", + " M reports/context_budget_summary.json", + " M reports/evidence_consistency.json", + " M reports/evidence_consistency.md", + " M reports/install_simulation.json" + ], "scope": "generation-time status before this report is written" }, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f", + "evidence_bundle_sha256": "733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379", "source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", - "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", + "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -5681,29 +5703,30 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 56 }, "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 (7/13 pass, 6 blocked)" + "world-class source checks are not all accepted (6/13 pass, 7 blocked)" ], "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks." }, "release_lock": { - "ready": true, - "commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", + "ready": false, + "commit": "67058cecebd13cd6e6fa54c009300cc145e8e999", "status_scope": "generation-time status before this report is written", - "reason": "clean generation-time HEAD" + "reason": "working tree was dirty at generation time" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -5711,7 +5734,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f" + "sha256": "733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5784,8 +5807,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7965, - "sha256": "6334c2f0261c2c978ebcb518cdac4ddf409f41e3732b08998c8e4b80529e446d" + "bytes": 7967, + "sha256": "6450488d6ac4f80b0160161d5385bbf2f6aec2856076621a81027ae5c89fa38a" }, { "label": "blind_review", @@ -5834,84 +5857,84 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "dfd07c1825de99435bd661e2663ae74251bbe03cb5ddda66d268efb6a872eb31" + "sha256": "8683ab3f627c2fe16c77dabe34798d2fb6942bb05c636cc35e4f6edd617c79d5" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "a27941fdb8651371fc7abc69247e15cf8e2863d5805b0538d67c326d4095148f" + "sha256": "1372317d59e9ff19cfa4f69bfcfb5ddb9a9770f5628d9454a8f165e363c5b95b" }, { "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, - "bytes": 8758, - "sha256": "5269d6e6364aaa39e935cbf02df7569a6a88d2653120bc6e3e34d3684a73639d" + "bytes": 8604, + "sha256": "3a707c08d4b0df167b835215f0f7696568a5a1e4099854d8a02647cdcd5b8b37" }, { "label": "skill_os2_audit", "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14310, - "sha256": "390d0bb42652e9f84fcab195de1da3c9cda213c254fd9319d31c54dd8429aee7" + "sha256": "453a86240e7fe1a703615ba3ce9a97d940e9c552ee9e39d5cccbf7c3481dd507" }, { "label": "world_class_evidence_plan", "path": "reports/world_class_evidence_plan.json", "exists": true, "bytes": 20828, - "sha256": "9b74155fb9bfe44ba838d64b1a31768b83978b154bdd8eaa606f494c816f189f" + "sha256": "0a836a86ad6c648d8c442a16cae7cdb17d3640a0ba6ec69c1290825ede6d152a" }, { "label": "world_class_evidence_ledger", "path": "reports/world_class_evidence_ledger.json", "exists": true, - "bytes": 22285, - "sha256": "f6e1a69b0359c28c88e9e9e69ff66763c721ac8a112a43a673ce98cd9d3bce41" + "bytes": 22288, + "sha256": "fe81833eab69292525975b347177bc7fcda6410f493fc60bd840a20e86ca0039" }, { "label": "world_class_evidence_intake", "path": "reports/world_class_evidence_intake.json", "exists": true, "bytes": 19319, - "sha256": "46f801051ec075725059e4e2682ef2162fd892b5e7255c8d5121d7b24dcc7f2c" + "sha256": "4506c836338c65a3a01b15b1f26a1fdd0a8ef520a1e5f1574ee89ce9d3bbeb29" }, { "label": "world_class_evidence_preflight", "path": "reports/world_class_evidence_preflight.json", "exists": true, - "bytes": 41202, - "sha256": "b7fd72d7e75486612f65a9bb73b1ab59106103ebf3ad10dd446cd80903088454" + "bytes": 41208, + "sha256": "725d10a6f951ab1e64f4e6a1cfa907404b51f598a753b5a0351e1381fef7cd9e" }, { "label": "world_class_submission_review", "path": "reports/world_class_submission_review.json", "exists": true, - "bytes": 13655, - "sha256": "9fbd4cd437986fca9a043cbab24aec7d575aaf166a8d9365c79c56f093cab5b8" + "bytes": 13658, + "sha256": "7693638c2e8369a8a179b3420c11090668f8f104f452dc370082dc9ebafe882d" }, { "label": "world_class_operator_runbook", "path": "reports/world_class_operator_runbook.json", "exists": true, - "bytes": 24835, - "sha256": "2d32a2e917b7215afe7a7a93ca8bacffa540a245953aa39e2ee47eea1b169d17" + "bytes": 24899, + "sha256": "f90d59c3e5866da33138869c1c5299350a43389d81e84ba466df794befb494fa" }, { "label": "world_class_operator_runbook_markdown", "path": "reports/world_class_operator_runbook.md", "exists": true, - "bytes": 15424, - "sha256": "00d8ebabb91e14a06cacdb212f448668aa1e47b72587448e30681fc53acaad9a" + "bytes": 15479, + "sha256": "be79ee0f70a3ceed473c481562c5fddaee6cfb36c960ba15ae10c846d5809650" }, { "label": "world_class_operator_runbook_html", "path": "reports/world_class_operator_runbook.html", "exists": true, - "bytes": 21348, - "sha256": "ca72c65b437b2211d08b9d463c9a33a7993b4e388bb75f62757ead4dfcf81a49" + "bytes": 21409, + "sha256": "9a7be02a6990245c9dd1f72ced5928d80a3aaebea4647737c2aaf0b0a2f798df" }, { "label": "world_class_claim_guard", @@ -6064,22 +6087,22 @@ "item_count": 21, "module_count": 8, "recommended_pr_count": 13, - "pass_count": 20, - "warn_count": 1, + "pass_count": 21, + "warn_count": 0, "missing_count": 0, "extension_track_count": 4, "extension_partial_count": 0, "extension_planned_count": 0, "extension_covered_count": 4, "adaptive_extension_ready": true, - "local_blueprint_ready": false, + "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_evidence_pending_count": 4, - "decision": "continue-implementation" + "decision": "local-blueprint-covered-evidence-pending" }, "status_counts": { - "pass": 20, - "warn": 1, + "pass": 21, + "warn": 0, "missing": 0 }, "extension_status_counts": { @@ -6261,7 +6284,7 @@ "label": "Registry Distribution", "status": "pass", "objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.", - "current": "archive entries 658; install failures 0", + "current": "archive entries 677; install failures 0", "command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .", "test": "python3 tests/verify_registry_audit.py", "evidence": [ @@ -6668,7 +6691,7 @@ "key": "evidence-consistency", "category": "recommended-pr", "label": "Evidence Consistency", - "status": "warn", + "status": "pass", "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.", "current": "36 consistency checks", "command": "make ci-test", @@ -6869,7 +6892,7 @@ "compiled_targets": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "summary": { "target_count": 5, @@ -7380,12 +7403,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -7422,7 +7446,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -7444,7 +7468,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -7636,12 +7660,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -7678,7 +7703,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -7698,7 +7723,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -8298,12 +8323,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -8340,7 +8366,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -8362,7 +8388,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -8554,12 +8580,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -8596,7 +8623,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -8616,7 +8643,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -9216,12 +9243,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -9258,7 +9286,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -9280,7 +9308,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -9465,12 +9493,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -9507,7 +9536,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -9527,7 +9556,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -10118,12 +10147,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -10160,7 +10190,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -10182,7 +10212,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -10367,12 +10397,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -10409,7 +10440,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -10429,7 +10460,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -11020,12 +11051,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -11062,7 +11094,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -11084,7 +11116,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -11273,12 +11305,13 @@ }, "subprocess": { "required": true, - "script_count": 10, + "script_count": 11, "scripts": [ "scripts/apply_adaptation.py", "scripts/ci_test.py", "scripts/render_benchmark_reproducibility.py", "scripts/render_eval_dashboard.py", + "scripts/render_evidence_consistency.py", "scripts/run_eval_suite.py", "scripts/run_output_execution.py", "scripts/sync_local_install.py", @@ -11315,7 +11348,7 @@ "secret_findings": 0, "network_script_count": 3, "file_write_script_count": 73, - "subprocess_script_count": 10, + "subprocess_script_count": 11, "interactive_script_count": 0, "help_smoke_failed_count": 0 } @@ -11335,7 +11368,7 @@ "capability_counts": { "network": 3, "file_write": 73, - "subprocess": 10, + "subprocess": 11, "interactive": 0 }, "evidence": "reports/security_trust_report.json", @@ -11683,7 +11716,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "package_dir": "tests/tmp_review_studio/dist", + "package_dir": "dist", "expected_capabilities": [ "file_write", "network", @@ -11723,7 +11756,7 @@ { "target": "openai", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json", + "adapter": "dist/targets/openai/adapter.json", "permission_model": "metadata-only", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -11820,7 +11853,7 @@ { "target": "claude", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json", + "adapter": "dist/targets/claude/adapter.json", "permission_model": "neutral-source-plus-adapter", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -11902,7 +11935,7 @@ { "target": "generic", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json", + "adapter": "dist/targets/generic/adapter.json", "permission_model": "agent-skills-compatible-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -11984,7 +12017,7 @@ { "target": "vscode", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json", + "adapter": "dist/targets/vscode/adapter.json", "permission_model": "vscode-workspace-trust-plus-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -16847,9 +16880,9 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1078122, + "other_text_tokens": 1078201, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1078919, + "estimated_total_text_tokens": 1078998, "deferred_resource_tokens": 495718, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ @@ -17980,8 +18013,8 @@ "report": "reports/adoption_drift_report.json", "risk_band": "low", "event_count": 1, - "adoption_sample_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "adoption_rate": 0, "candidate_count": 0 } }, @@ -18812,7 +18845,7 @@ "adoption_drift": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-16T16:15:39Z", + "generated_at": "2026-06-17", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -18836,14 +18869,14 @@ }, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -18852,7 +18885,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -18864,31 +18897,31 @@ { "skill": "yao-meta-skill", "events": 1, - "adoption_events": 1, - "accepted": 1, + "adoption_events": 0, + "accepted": 0, "edited": 0, "rejected": 0, "missed": 0, - "adoption_rate": 100.0 + "adoption_rate": 0 } ], "next_iteration_candidates": [], "recent_events": [ { "command": "unknown", - "event": "skill_activation", + "event": "review_event", "skill": "yao-meta-skill", "source": "manual", "version": "1.1.0", - "activation_type": "explicit", - "outcome": "accepted", + "activation_type": "manual", + "outcome": "reviewed", "failure_type": "none", - "timestamp": "2026-06-13T10:00:00Z" + "timestamp": "2026-06-13T12:00:00Z" } ], "failures": [], "artifacts": { - "events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl", + "events_jsonl": "reports/telemetry_events.jsonl", "json": "reports/adoption_drift_report.json", "markdown": "reports/adoption_drift_report.md" } @@ -18909,7 +18942,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -18926,7 +18959,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -19375,7 +19408,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true }, "actions": [ @@ -19424,7 +19457,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -19444,7 +19477,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -19697,7 +19730,7 @@ "no_route_opportunity_count": 0 }, "release_state": { - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4 @@ -19732,7 +19765,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "summary": { "waiver_count": 0, "active_count": 0, @@ -19822,7 +19855,7 @@ "Reviewer links output_review_adjudication or output_execution evidence." ], "suggested_evidence": "reports/output_review_adjudication.md", - "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md", + "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-17 --evidence reports/output_review_adjudication.md", "world_class_boundary": "Does not count as provider, human, or public world-class completion evidence." }, { @@ -19852,7 +19885,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "source": "tests/tmp_review_studio/empty_review_annotations_input.json", + "source": "reports/review_annotations_input.json", "summary": { "annotation_count": 0, "open_count": 0, @@ -20288,8 +20321,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -20305,8 +20338,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -20682,7 +20715,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -20719,7 +20752,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -20740,8 +20773,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -20757,8 +20790,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", @@ -21110,7 +21143,7 @@ "source_accepted": false, "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -21194,8 +21227,8 @@ "collection_ready_count": 1, "collection_blocked_count": 3, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "pending_count": 4, "ready_to_claim_world_class": false, "credential_value_exposed": false, @@ -21715,8 +21748,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -22071,8 +22104,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -22155,8 +22188,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "review_counts_submission_as_completion": false, "summary": { "review_item_count": 4, @@ -22168,8 +22201,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "review_counts_submission_as_completion": false, "decision": "awaiting-submissions" @@ -22443,7 +22476,7 @@ "intake_errors": [], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -22464,8 +22497,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -22481,8 +22514,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "success_checks": [ "reports/adoption_drift_report.json summary.source_types.external > 0", "reports/adoption_drift_report.json summary.adoption_sample_count > 0", @@ -22519,8 +22552,8 @@ "valid_packet_source_incomplete_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "runbook_counts_as_completion": false, "decision": "collect-evidence" @@ -22915,7 +22948,7 @@ "review_state": "awaiting-submission", "source_accepted": false, "objective": "Import production metadata-only events from a real external client into the local drift loop.", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "execution_runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.", @@ -22963,7 +22996,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -22984,8 +23017,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -23000,9 +23033,10 @@ "next_action": "Telemetry must stay metadata-only." } ], - "blocked_source_check_count": 1, + "blocked_source_check_count": 2, "next_source_actions": [ - "Import at least one metadata-only event from a real client." + "Import at least one metadata-only event from a real client.", + "Telemetry must include adoption outcome evidence." ], "submission_state": { "status": "missing", @@ -23841,7 +23875,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", + "package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b" }, "compatibility": { @@ -23898,7 +23932,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69" + "package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b" } ] }, @@ -23914,15 +23948,15 @@ "package_verification": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-16", + "generated_at": "2026-06-17", "skill_dir": ".", "package_dir": "dist", "summary": { "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", - "archive_entry_count": 658, + "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7", + "archive_entry_count": 677, "failure_count": 0, "warning_count": 0 }, @@ -24580,11 +24614,11 @@ "install_simulation": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", - "package_dir": "tests/tmp_review_studio/dist", - "install_root": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill", - "installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill", + "package_dir": "dist", + "install_root": "dist/install-simulation/simulate-yao-meta-skill", + "installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill", "summary": { "archive_present": true, "archive_entry_count": 677, @@ -24605,7 +24639,7 @@ { "id": "archive-present", "status": "pass", - "detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip" + "detail": "Package archive exists: dist/yao-meta-skill.zip" }, { "id": "archive-safe-paths", @@ -24851,16 +24885,16 @@ "failures": [], "warnings": [], "artifacts": { - "archive": "tests/tmp_review_studio/dist/yao-meta-skill.zip", - "package_manifest": "tests/tmp_review_studio/dist/manifest.json", - "json": "tests/tmp_review_studio/install_simulation.json", - "markdown": "tests/tmp_review_studio/install_simulation.md" + "archive": "dist/yao-meta-skill.zip", + "package_manifest": "dist/manifest.json", + "json": "reports/install_simulation.json", + "markdown": "reports/install_simulation.md" } }, "upgrade_check": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "previous": { "name": "yao-meta-skill", "version": "1.0.0", @@ -24934,7 +24968,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69" + "to": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b" } ] }, @@ -24949,8 +24983,8 @@ "artifacts": { "previous_package": "registry/examples/yao-meta-skill-1.0.0.json", "current_package": "reports/registry_audit.json", - "json": "tests/tmp_review_studio/upgrade_check.json", - "markdown": "tests/tmp_review_studio/upgrade_check.md" + "json": "reports/upgrade_check.json", + "markdown": "reports/upgrade_check.md" } }, "manifest": { diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 583b73e3..2361dabc 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": 13, - "source_pass_count": 7, + "source_pass_count": 6, "conclusion_zh": "世界级证据尚未完成:4 项待补,0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -471,7 +471,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -996,13 +997,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f", + "evidence_bundle_sha256": "733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379", "source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", - "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", + "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1017,14 +1018,14 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 56 }, - "commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", + "commit": "67058cecebd13cd6e6fa54c009300cc145e8e999", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -1167,7 +1168,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", + "package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b" }, "compatibility": { @@ -1215,8 +1216,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", - "archive_entry_count": 658, + "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7", + "archive_entry_count": 677, "failure_count": 0, "warning_count": 0 }, @@ -1299,7 +1300,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69" + "to": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b" } ] }, @@ -1316,14 +1317,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -1332,7 +1333,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -1599,7 +1600,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -1652,8 +1653,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -2003,7 +2004,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -2040,7 +2041,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -2061,8 +2062,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -2078,8 +2079,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", diff --git a/reports/review_annotations.json b/reports/review_annotations.json index 66f2b1d9..76fadc1f 100644 --- a/reports/review_annotations.json +++ b/reports/review_annotations.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "source": "tests/tmp_review_studio/empty_review_annotations_input.json", + "source": "reports/review_annotations_input.json", "summary": { "annotation_count": 0, "open_count": 0, diff --git a/reports/review_waivers.json b/reports/review_waivers.json index a994e852..1ec9a128 100644 --- a/reports/review_waivers.json +++ b/reports/review_waivers.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "summary": { "waiver_count": 0, "active_count": 0, @@ -92,7 +92,7 @@ "Reviewer links output_review_adjudication or output_execution evidence." ], "suggested_evidence": "reports/output_review_adjudication.md", - "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md", + "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-17 --evidence reports/output_review_adjudication.md", "world_class_boundary": "Does not count as provider, human, or public world-class completion evidence." }, { diff --git a/reports/review_waivers.md b/reports/review_waivers.md index df7cc049..90ddd5bd 100644 --- a/reports/review_waivers.md +++ b/reports/review_waivers.md @@ -38,7 +38,7 @@ - waiver allowed: `true` - risk: review pending 5; model-executed 0; output failures 0 - evidence: `reports/output_review_adjudication.md` -- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md` +- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-17 --evidence reports/output_review_adjudication.md` - world-class boundary: Does not count as provider, human, or public world-class completion evidence. #### Required Review diff --git a/reports/runtime_permission_probes.json b/reports/runtime_permission_probes.json index 59c9a1a4..9c2ffd6e 100644 --- a/reports/runtime_permission_probes.json +++ b/reports/runtime_permission_probes.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "package_dir": "tests/tmp_review_studio/dist", + "package_dir": "dist", "expected_capabilities": [ "file_write", "network", @@ -42,7 +42,7 @@ { "target": "openai", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json", + "adapter": "dist/targets/openai/adapter.json", "permission_model": "metadata-only", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -139,7 +139,7 @@ { "target": "claude", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json", + "adapter": "dist/targets/claude/adapter.json", "permission_model": "neutral-source-plus-adapter", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -221,7 +221,7 @@ { "target": "generic", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json", + "adapter": "dist/targets/generic/adapter.json", "permission_model": "agent-skills-compatible-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -303,7 +303,7 @@ { "target": "vscode", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json", + "adapter": "dist/targets/vscode/adapter.json", "permission_model": "vscode-workspace-trust-plus-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, diff --git a/reports/skill-interpretation.html b/reports/skill-interpretation.html index d3c8e099..0c4638fd 100644 --- a/reports/skill-interpretation.html +++ b/reports/skill-interpretation.html @@ -910,7 +910,7 @@ -

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 Checks7 / 13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
外部证据External evidence

原生权限Native Permission

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

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

原生遥测Native Telemetry

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

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

世界证据World Evidence

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

证据待补Evidence pending
待补证据Pending4仍需外部或人工证据接受。External or human evidence still needs acceptance.
已接受Accepted0已通过 source check 与提交契约。Passed source checks and submission contract.
源检查Source Checks6 / 13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
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
diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index d22b8fbe..a5e6fa96 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": 13, - "source_pass_count": 7, + "source_pass_count": 6, "conclusion_zh": "世界级证据尚未完成:4 项待补,0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -471,7 +471,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -1000,13 +1001,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f", + "evidence_bundle_sha256": "733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379", "source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", - "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", + "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1021,14 +1022,14 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 56 }, - "commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", + "commit": "67058cecebd13cd6e6fa54c009300cc145e8e999", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -1171,7 +1172,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", + "package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b" }, "compatibility": { @@ -1219,8 +1220,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", - "archive_entry_count": 658, + "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7", + "archive_entry_count": 677, "failure_count": 0, "warning_count": 0 }, @@ -1303,7 +1304,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69" + "to": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b" } ] }, @@ -1320,14 +1321,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -1336,7 +1337,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -1603,7 +1604,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -1656,8 +1657,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -2007,7 +2008,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -2044,7 +2045,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -2065,8 +2066,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -2082,8 +2083,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", diff --git a/reports/skill-os-2-review.md b/reports/skill-os-2-review.md index a0122cd6..86afeafc 100644 --- a/reports/skill-os-2-review.md +++ b/reports/skill-os-2-review.md @@ -138,8 +138,8 @@ Next move: add real client or installer permission enforcement integration. | Runtime Permission Probes | `4 / 4` target adapters probed, `0` native-enforcement adapters, `4` explicit metadata fallbacks, `4` residual risks retained for reviewer visibility | | Skill Atlas | `12` scanned skills, `1` actionable root skill, `1` telemetry report, `0` actionable route collisions, `0` actionable owner gaps, `0` actionable stale skills, `0` actionable drift signals, `24` scoped non-actionable issue signals retained for visibility | | Registry Audit | package metadata generated with version, owner, license, source checksum, archive checksum, Skill IR provenance, and compatibility matrix | -| Package Verification | `4 / 4` target adapters present, archive verified, `658` zip entries, `0` failures, `0` warnings | -| Install Simulation | archive with `658` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings | +| Package Verification | `4 / 4` target adapters present, archive verified, `677` zip entries, `0` failures, `0` warnings | +| Install Simulation | archive with `677` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings | | Local Install Sync Preflight | `make sync-local-install` and `make sync-active-install` rebuild the package first, then sync only after install simulation passes with `12` enforced installer permission checks and `0` permission failures | | Upgrade Check | current package declares `minor` over the 1.0.0 baseline, recommended bump is `minor`, and release notes include added targets plus checksum changes | | Adoption Drift | `1` metadata-only review event, `1` adoption sample, adoption `100`, risk band `low`; optional `yao.py` CLI capture, external client `telemetry-emit`, `5` `telemetry-hooks` recipes, Browser/Chrome native messaging host, and validated external JSONL import are available but off by default for reproducible release evidence; raw `reports/telemetry_events.jsonl` is gitignored and blocked from zip packages | diff --git a/reports/skill-overview.html b/reports/skill-overview.html index c456d933..c6d5f214 100644 --- a/reports/skill-overview.html +++ b/reports/skill-overview.html @@ -910,7 +910,7 @@ -

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 Checks7 / 13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
外部证据External evidence

原生权限Native Permission

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

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

原生遥测Native Telemetry

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

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

世界证据World Evidence

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

证据待补Evidence pending
待补证据Pending4仍需外部或人工证据接受。External or human evidence still needs acceptance.
已接受Accepted0已通过 source check 与提交契约。Passed source checks and submission contract.
源检查Source Checks6 / 13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
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
diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 2360c489..67c6ca1d 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": 13, - "source_pass_count": 7, + "source_pass_count": 6, "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": [ @@ -470,7 +470,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -995,13 +996,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "c31f7210165c76ab9b288c6c7d5d228fd46c8c8627cd86ca095cc1033607e34f", + "evidence_bundle_sha256": "733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379", "source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", - "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", + "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1016,14 +1017,14 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 56 }, - "commit": "b6ded57f9cc65b1dd7dbbac9c394647dadc131d7", + "commit": "67058cecebd13cd6e6fa54c009300cc145e8e999", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -1166,7 +1167,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69", + "package_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b" }, "compatibility": { @@ -1214,8 +1215,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", - "archive_entry_count": 658, + "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7", + "archive_entry_count": 677, "failure_count": 0, "warning_count": 0 }, @@ -1298,7 +1299,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69" + "to": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b" } ] }, @@ -1315,14 +1316,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -1331,7 +1332,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -1598,7 +1599,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -1651,8 +1652,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -2002,7 +2003,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -2039,7 +2040,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -2060,8 +2061,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -2077,8 +2078,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", diff --git a/reports/skill_atlas.json b/reports/skill_atlas.json index e067385c..73f13deb 100644 --- a/reports/skill_atlas.json +++ b/reports/skill_atlas.json @@ -273,8 +273,8 @@ "report": "reports/adoption_drift_report.json", "risk_band": "low", "event_count": 1, - "adoption_sample_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "adoption_rate": 0, "candidate_count": 0 } }, diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json index 7fbbae21..763f23ab 100644 --- a/reports/skill_os2_audit.json +++ b/reports/skill_os2_audit.json @@ -285,7 +285,7 @@ "key": "registry-distribution", "label": "Registry Distribution", "status": "pass", - "current": "zip entries 658; install failures 0; permission failures 0", + "current": "zip entries 677; install failures 0; permission failures 0", "target": "Package metadata, archive checksum, package verification, and install simulation pass", "evidence": [ { @@ -351,7 +351,7 @@ "key": "native-client-telemetry", "label": "Native Client Telemetry", "status": "external_required", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "target": "A real Browser/Chrome/provider client sends production metadata events", "evidence": [ { @@ -433,7 +433,7 @@ "key": "native-client-telemetry", "label": "Native Client Telemetry", "status": "external_required", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "target": "A real Browser/Chrome/provider client sends production metadata events", "evidence": [ { diff --git a/reports/skill_os2_audit.md b/reports/skill_os2_audit.md index 137bf995..c4b5a069 100644 --- a/reports/skill_os2_audit.md +++ b/reports/skill_os2_audit.md @@ -27,10 +27,10 @@ Generated at: `2026-06-17` | Permission Metadata | pass | 4/4 target probes pass; metadata fallback 4; installer enforcement 4 | Packaged adapters expose explicit permission metadata, residual risks, and installer enforcement evidence when available | Preserve residual-risk notes until real native enforcement exists. | | Native Permission Enforcement | external-required | native-enforced targets 0; installer-enforced targets 4 | At least one target/client enforces approved permissions at runtime | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. | | Skill Atlas | pass | 12 skills; actionable collisions 0 | Workspace catalog, route overlap, stale/owner gaps, drift, and no-route opportunities | Feed real drift data into Atlas once client telemetry is installed. | -| Registry Distribution | pass | zip entries 658; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. | +| Registry Distribution | pass | zip entries 677; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. | | Review Studio | pass | decision review; warnings 3; score 91 | One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations | Resolve human/external warning gates before claiming full release readiness. | | Telemetry Drift | pass | events 1; risk low; recipes 5 | Local-first metadata-only event contract, aggregate drift report, hook recipes, and import path | Keep raw JSONL out of distributed packages and use aggregate reports for Atlas. | -| Native Client Telemetry | external-required | external source events 0; adoption samples 1 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. | +| Native Client Telemetry | external-required | external source events 0; adoption samples 0 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. | ## Open Highest-Leverage Gaps diff --git a/reports/skill_os2_coverage.json b/reports/skill_os2_coverage.json index 7844e0a9..72682f35 100644 --- a/reports/skill_os2_coverage.json +++ b/reports/skill_os2_coverage.json @@ -7,22 +7,22 @@ "item_count": 21, "module_count": 8, "recommended_pr_count": 13, - "pass_count": 20, - "warn_count": 1, + "pass_count": 21, + "warn_count": 0, "missing_count": 0, "extension_track_count": 4, "extension_partial_count": 0, "extension_planned_count": 0, "extension_covered_count": 4, "adaptive_extension_ready": true, - "local_blueprint_ready": false, + "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_evidence_pending_count": 4, - "decision": "continue-implementation" + "decision": "local-blueprint-covered-evidence-pending" }, "status_counts": { - "pass": 20, - "warn": 1, + "pass": 21, + "warn": 0, "missing": 0 }, "extension_status_counts": { @@ -204,7 +204,7 @@ "label": "Registry Distribution", "status": "pass", "objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.", - "current": "archive entries 658; install failures 0", + "current": "archive entries 677; install failures 0", "command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .", "test": "python3 tests/verify_registry_audit.py", "evidence": [ @@ -611,7 +611,7 @@ "key": "evidence-consistency", "category": "recommended-pr", "label": "Evidence Consistency", - "status": "warn", + "status": "pass", "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.", "current": "36 consistency checks", "command": "make ci-test", diff --git a/reports/skill_os2_coverage.md b/reports/skill_os2_coverage.md index 497fdb52..86956b01 100644 --- a/reports/skill_os2_coverage.md +++ b/reports/skill_os2_coverage.md @@ -4,12 +4,12 @@ Generated at: `2026-06-17` ## Summary -- decision: `continue-implementation` -- local blueprint ready: `false` +- decision: `local-blueprint-covered-evidence-pending` +- local blueprint ready: `true` - public world-class ready: `false` -- pass: `20` / `21` +- pass: `21` / `21` - missing: `0` -- warn: `1` +- warn: `0` - reference extensions: `4` - extension covered: `4` - extension partial: `0` @@ -28,7 +28,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, | Runtime Conformance | `pass` | 5/5 targets pass | `python3 scripts/yao.py conformance .` | `python3 tests/verify_conformance_suite.py` | | Trust Security | `pass` | 140 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` | | Skill Atlas | `pass` | 12 scanned skills; actionable collisions 0 | `python3 scripts/yao.py skill-atlas --workspace-root .` | `python3 tests/verify_skill_atlas.py` | -| Registry Distribution | `pass` | archive entries 658; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` | +| Registry Distribution | `pass` | archive entries 677; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` | | Review Studio | `pass` | 16 gates; decision review; warnings 3 | `python3 scripts/yao.py review-studio .` | `python3 tests/verify_review_studio.py` | | Telemetry Drift | `pass` | events 1; recipes 5; risk low | `python3 scripts/yao.py telemetry-hooks . && python3 scripts/yao.py adoption-drift .` | `python3 tests/verify_telemetry_hooks.py` | @@ -48,7 +48,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, | Registry Package Format | `pass` | registry ok True | `make ci-test` | `tests/verify_registry_audit.py` | | Review Studio 2.0 | `pass` | 16 review gates | `make ci-test` | `tests/verify_review_studio.py` | | Migration V2 Docs | `pass` | migration guide present | `make ci-test` | `docs review` | -| Evidence Consistency | `warn` | 36 consistency checks | `make ci-test` | `tests/verify_evidence_consistency.py` | +| Evidence Consistency | `pass` | 36 consistency checks | `make ci-test` | `tests/verify_evidence_consistency.py` | ## Reference Extension Tracks @@ -213,7 +213,7 @@ These extension tracks come from the user-supplied 2.0 reference plan. They are ### Evidence Consistency - objective: Recommended Skill OS 2.0 implementation PR from the upgrade plan. -- status: `warn` +- status: `pass` - existing evidence: `scripts/render_evidence_consistency.py`, `reports/evidence_consistency.json`, `tests/verify_evidence_consistency.py` - next action: Keep this item covered as the implementation evolves. diff --git a/reports/skillops/daily/2026-06-16.json b/reports/skillops/daily/2026-06-16.json index a21b7f6b..ffac52a7 100644 --- a/reports/skillops/daily/2026-06-16.json +++ b/reports/skillops/daily/2026-06-16.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16T16:14:10Z", + "generated_at": "2026-06-16T16:24:58Z", "skill_dir": ".", "decision": "proposal-review", "source_supplied": false, diff --git a/reports/skillops/daily/2026-06-16.md b/reports/skillops/daily/2026-06-16.md index de03fe2f..3471bfa3 100644 --- a/reports/skillops/daily/2026-06-16.md +++ b/reports/skillops/daily/2026-06-16.md @@ -1,6 +1,6 @@ # Daily SkillOps Report -Generated at: `2026-06-16T16:14:10Z` +Generated at: `2026-06-16T16:24:58Z` ## Summary diff --git a/reports/skillops/daily/2026-06-17.json b/reports/skillops/daily/2026-06-17.json index 07080fcd..7ee010c4 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": true, + "release_lock_ready": false, "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": true, + "release_lock_ready": false, "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": true, + "release_lock_ready": false, "evidence_consistency_ok": true }, "actions": [ diff --git a/reports/skillops/daily/2026-06-17.md b/reports/skillops/daily/2026-06-17.md index 65caad51..5d6c937a 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: `true` +- release lock ready: `false` - 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 8f21344c..8c1ed2f4 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": true, + "release_lock_ready": false, "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": true, + "release_lock_ready": false, "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": true, + "release_lock_ready": false, "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 a52113b7..e8b03e0e 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: `True` +- release_lock_ready: `False` - evidence_consistency_ok: `True` - public_world_class_ready: `False` - world_class_pending_count: `4` diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index f92ef125..ab7007ed 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -1,7 +1,7 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "previous": { "name": "yao-meta-skill", "version": "1.0.0", @@ -75,7 +75,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69" + "to": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b" } ] }, @@ -90,7 +90,7 @@ "artifacts": { "previous_package": "registry/examples/yao-meta-skill-1.0.0.json", "current_package": "reports/registry_audit.json", - "json": "tests/tmp_review_studio/upgrade_check.json", - "markdown": "tests/tmp_review_studio/upgrade_check.md" + "json": "reports/upgrade_check.json", + "markdown": "reports/upgrade_check.md" } } diff --git a/reports/world_class_evidence_intake.json b/reports/world_class_evidence_intake.json index 81d92d87..bbfc6f87 100644 --- a/reports/world_class_evidence_intake.json +++ b/reports/world_class_evidence_intake.json @@ -312,7 +312,7 @@ "source_accepted": false, "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false diff --git a/reports/world_class_evidence_ledger.json b/reports/world_class_evidence_ledger.json index d81f6f75..5765d1b3 100644 --- a/reports/world_class_evidence_ledger.json +++ b/reports/world_class_evidence_ledger.json @@ -16,8 +16,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -33,8 +33,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -410,7 +410,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -447,7 +447,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -468,8 +468,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -485,8 +485,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", diff --git a/reports/world_class_evidence_ledger.md b/reports/world_class_evidence_ledger.md index fb22bd0b..6920d900 100644 --- a/reports/world_class_evidence_ledger.md +++ b/reports/world_class_evidence_ledger.md @@ -8,8 +8,8 @@ Generated at: `2026-06-17` - ready to claim world-class: `false` - entries: `4` - source accepted: `0` -- source checks: `7` pass / `13` total -- source blocked: `6` +- source checks: `6` pass / `13` total +- source blocked: `7` - accepted: `0` - pending: `4` - human pending: `1` @@ -30,7 +30,7 @@ This ledger records the current evidence state. It requires both passing source | `provider-holdout` | `pending` | `missing` | `external` | model-executed 0; token-observed 0 | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. | | `human-adjudication` | `pending` | `missing` | `human` | 0/5 decisions; pending 5 | Record real A/B choices in the decision template, then regenerate adjudication. | | `native-permission-enforcement` | `pending` | `missing` | `external` | native-enforced targets 0; installer-enforced targets 4 | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. | -| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 1 | Install a real client against the native host and import production metadata-only events. | +| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 0 | Install a real client against the native host and import production metadata-only events. | ## Provider Holdout @@ -172,8 +172,8 @@ This ledger records the current evidence state. It requires both passing source - objective: Import production metadata-only events from a real external client into the local drift loop. - source status: `external_required` -- observed state: `{"external_source_events": 0, "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false}` -- source checks: `2` pass / `3` total +- observed state: `{"external_source_events": 0, "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false}` +- source checks: `1` pass / `3` total - submission state: `{"status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", "artifact_ref_count": 0, "attested_real_evidence": false, "privacy_contract_satisfied": false, "ledger_reviewer_approved": false, "ledger_reviewer": "", "ledger_reviewed_at": "", "ledger_counts_as_completion": false}` ### Provenance Requirements @@ -197,7 +197,7 @@ This ledger records the current evidence state. It requires both passing source | Check | Current | Expected | Status | | --- | --- | --- | --- | | External events | `0` | `>0` | `blocked` | -| Adoption sample | `1` | `>0` | `pass` | +| Adoption sample | `0` | `>0` | `blocked` | | Raw content blocked | `False` | `false` | `pass` | ### Completion Assertions diff --git a/reports/world_class_evidence_plan.json b/reports/world_class_evidence_plan.json index ff133db6..dc133c76 100644 --- a/reports/world_class_evidence_plan.json +++ b/reports/world_class_evidence_plan.json @@ -146,7 +146,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -309,7 +309,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", diff --git a/reports/world_class_evidence_plan.md b/reports/world_class_evidence_plan.md index b540f1e6..a7bc5eb2 100644 --- a/reports/world_class_evidence_plan.md +++ b/reports/world_class_evidence_plan.md @@ -22,7 +22,7 @@ This report is an execution plan for the remaining world-class evidence gaps. It | `provider-holdout` | `external_required` | `external` | operator with provider credentials | model-executed 0; token-observed 0 | | `human-adjudication` | `human_required` | `human` | human reviewer | 0/5 decisions; pending 5 | | `native-permission-enforcement` | `external_required` | `external` | target client or installer integrator | native-enforced targets 0; installer-enforced targets 4 | -| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 1 | +| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 0 | ## Provider Holdout diff --git a/reports/world_class_evidence_preflight.html b/reports/world_class_evidence_preflight.html index 88f28e2d..6c8d1665 100644 --- a/reports/world_class_evidence_preflight.html +++ b/reports/world_class_evidence_preflight.html @@ -65,7 +65,7 @@ Evidence Collection

World-Class Evidence Preflight

This operator view shows which external and human evidence is still blocked, which commands prepare editable submission drafts, and why preflight never counts as accepted evidence.

-
Decisioncollection-preflight-blocked
Pending4
Ready1
Blocked3
Source7/13
+
Decisioncollection-preflight-blocked
Pending4
Ready1
Blocked3
Source6/13
@@ -611,15 +611,15 @@
-
+
adoption_sample_count Adoption sample
-
Current
1
+
Current
0
Expected
>0
-
Status
pass
+
Status
blocked
Action
Telemetry must include adoption outcome evidence.
diff --git a/reports/world_class_evidence_preflight.json b/reports/world_class_evidence_preflight.json index bf6bf821..600a442f 100644 --- a/reports/world_class_evidence_preflight.json +++ b/reports/world_class_evidence_preflight.json @@ -14,8 +14,8 @@ "collection_ready_count": 1, "collection_blocked_count": 3, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "pending_count": 4, "ready_to_claim_world_class": false, "credential_value_exposed": false, @@ -535,8 +535,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -891,8 +891,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, diff --git a/reports/world_class_evidence_preflight.md b/reports/world_class_evidence_preflight.md index d6431496..52a3d2ac 100644 --- a/reports/world_class_evidence_preflight.md +++ b/reports/world_class_evidence_preflight.md @@ -10,7 +10,7 @@ Generated at: `2026-06-17` - credential value exposed: `false` - collection ready: `1` - collection blocked: `3` -- source checks: `7` pass / `13` total +- source checks: `6` pass / `13` total This preflight report checks whether an operator can start collecting the remaining external or human evidence. It never accepts evidence, prints secret values, or changes the world-class ledger. @@ -150,7 +150,7 @@ Generate the submission kit after the real provider, human, native-permission, o | Check | Current | Expected | Status | Next action | | --- | --- | --- | --- | --- | | External events | `0` | `>0` | `blocked` | Import at least one metadata-only event from a real client. | -| Adoption sample | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. | +| Adoption sample | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. | | Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. | ## Boundary diff --git a/reports/world_class_operator_runbook.html b/reports/world_class_operator_runbook.html index 9fa92ced..a3b8b9fa 100644 --- a/reports/world_class_operator_runbook.html +++ b/reports/world_class_operator_runbook.html @@ -57,7 +57,7 @@ Evidence Operations

World-Class Operator Runbook

A single operating page for collecting the remaining human and external evidence. It coordinates action, but does not accept evidence or change the ledger.

-
Pending4
Awaiting4
Ready0
Source7/13
Blocked6
Invalid0
+
Pending4
Awaiting4
Ready0
Source6/13
Blocked7
Invalid0

Fast Path

  1. Run the real external or human work for one evidence item.
  2. Generate and fill the matching submission draft.
  3. Validate intake and inspect the submission review queue.
  4. Refresh the ledger and run the claim guard before making any completion claim.

Evidence Items

@@ -120,7 +120,7 @@
Owner
Browser/Chrome/IDE/provider client integrator
Ledger
pending
-
Blocked
1
+
Blocked
2
Submission
evidence/world_class/submissions/native-client-telemetry.json

Source Runbook

  • python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/
  • Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.
  • python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
  • python3 scripts/yao.py skill-atlas --workspace-root .
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
@@ -130,8 +130,8 @@

Success Checks

  • reports/adoption_drift_report.json summary.source_types.external > 0
  • reports/adoption_drift_report.json summary.adoption_sample_count > 0
  • reports/skill_os2_audit.json item native-client-telemetry status becomes pass

Privacy

  • 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.
-

Next Source Actions

  • Import at least one metadata-only event from a real client.
-

Source Evidence Snapshot

  • 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.
+

Next Source Actions

  • Import at least one metadata-only event from a real client.
  • Telemetry must include adoption outcome evidence.
+

Source Evidence Snapshot

  • 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.

Boundary

  • Planned work, draft packets, metadata fallback, pending human decisions, and local command runners do not count as completion.
  • Valid intake means ready for submission review; ledger review still requires passing source evidence.
  • The world-class ledger and claim guard remain the source of truth.
diff --git a/reports/world_class_operator_runbook.json b/reports/world_class_operator_runbook.json index 18dec411..2ccccdc6 100644 --- a/reports/world_class_operator_runbook.json +++ b/reports/world_class_operator_runbook.json @@ -12,8 +12,8 @@ "valid_packet_source_incomplete_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "runbook_counts_as_completion": false, "decision": "collect-evidence" @@ -408,7 +408,7 @@ "review_state": "awaiting-submission", "source_accepted": false, "objective": "Import production metadata-only events from a real external client into the local drift loop.", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "execution_runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.", @@ -456,7 +456,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -477,8 +477,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -493,9 +493,10 @@ "next_action": "Telemetry must stay metadata-only." } ], - "blocked_source_check_count": 1, + "blocked_source_check_count": 2, "next_source_actions": [ - "Import at least one metadata-only event from a real client." + "Import at least one metadata-only event from a real client.", + "Telemetry must include adoption outcome evidence." ], "submission_state": { "status": "missing", diff --git a/reports/world_class_operator_runbook.md b/reports/world_class_operator_runbook.md index 17ebd41e..9118e3af 100644 --- a/reports/world_class_operator_runbook.md +++ b/reports/world_class_operator_runbook.md @@ -28,7 +28,7 @@ This runbook coordinates evidence collection only. It does not accept submission | `provider-holdout` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Run provider-backed output-exec with real credentials. | operator with provider credentials | | `human-adjudication` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Record a reviewer choice for every pair. | human reviewer | | `native-permission-enforcement` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Collect real target-client or external runtime guard proof. | target client or installer integrator | -| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator | +| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator | ## Provider Holdout @@ -244,7 +244,7 @@ This runbook coordinates evidence collection only. It does not accept submission - objective: Import production metadata-only events from a real external client into the local drift loop. - blocking reason: No evidence packet has been submitted for review. -- blocked source checks: `1` +- blocked source checks: `2` - submission: `evidence/world_class/submissions/native-client-telemetry.json` - template: `evidence/world_class/templates/native-client-telemetry.intake.json` @@ -297,13 +297,14 @@ This runbook coordinates evidence collection only. It does not accept submission ### Next Source Actions - Import at least one metadata-only event from a real client. +- Telemetry must include adoption outcome evidence. ### Source Evidence Snapshot | Check | Current | Expected | Status | Next action | | --- | --- | --- | --- | --- | | External events | `0` | `>0` | `blocked` | Import at least one metadata-only event from a real client. | -| Adoption sample | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. | +| Adoption sample | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. | | Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. | ## Boundary diff --git a/reports/world_class_submission_review.json b/reports/world_class_submission_review.json index 5b9f0a2d..57e35727 100644 --- a/reports/world_class_submission_review.json +++ b/reports/world_class_submission_review.json @@ -14,8 +14,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "review_counts_submission_as_completion": false, "summary": { "review_item_count": 4, @@ -27,8 +27,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "review_counts_submission_as_completion": false, "decision": "awaiting-submissions" @@ -302,7 +302,7 @@ "intake_errors": [], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -323,8 +323,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -340,8 +340,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "success_checks": [ "reports/adoption_drift_report.json summary.source_types.external > 0", "reports/adoption_drift_report.json summary.adoption_sample_count > 0", diff --git a/reports/world_class_submission_review.md b/reports/world_class_submission_review.md index 4958147c..4d0deed1 100644 --- a/reports/world_class_submission_review.md +++ b/reports/world_class_submission_review.md @@ -139,7 +139,7 @@ This report is a read-only reviewer queue. It does not accept evidence or make w #### Source Checks - External events: 0 / >0 => blocked -- Adoption sample: 1 / >0 => pass +- Adoption sample: 0 / >0 => blocked - Raw content blocked: False / false => pass #### Completion Assertions diff --git a/skill_atlas/catalog.json b/skill_atlas/catalog.json index eeb2eb26..8d6c0908 100644 --- a/skill_atlas/catalog.json +++ b/skill_atlas/catalog.json @@ -229,8 +229,8 @@ "report": "reports/adoption_drift_report.json", "risk_band": "low", "event_count": 1, - "adoption_sample_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "adoption_rate": 0, "candidate_count": 0 } },