diff --git a/AGENTS.md b/AGENTS.md index c8b59855..56988faf 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -49,8 +49,10 @@ python3 scripts/render_world_class_operator_runbook.py . --generated-at "$GENERA python3 scripts/render_world_class_claim_guard.py . --generated-at "$GENERATED_AT" python3 scripts/render_skill_os2_coverage.py . --generated-at "$GENERATED_AT" python3 scripts/render_skill_overview.py . +python3 scripts/render_skill_interpretation.py . python3 scripts/render_review_viewer.py . python3 scripts/render_review_studio.py . --output-html reports/review-studio.html --output-json reports/review-studio.json +python3 scripts/render_evidence_consistency.py . --generated-at "$GENERATED_AT" ``` For final release evidence, commit source and generated package evidence first, then run the clean-lock reports from a clean worktree: @@ -58,8 +60,10 @@ For final release evidence, commit source and generated package evidence first, ```bash python3 scripts/render_benchmark_reproducibility.py . --generated-at "$GENERATED_AT" python3 scripts/render_skill_overview.py . +python3 scripts/render_skill_interpretation.py . python3 scripts/render_review_viewer.py . python3 scripts/render_review_studio.py . --output-html reports/review-studio.html --output-json reports/review-studio.json +python3 scripts/render_evidence_consistency.py . --generated-at "$GENERATED_AT" ``` If `reports/benchmark_reproducibility.json` reports `release_lock_ready: false`, do not commit that benchmark as release evidence. Restore the transient dirty-lock reports, commit the source/generated evidence that caused the dirty state, and regenerate the clean-lock reports on the resulting clean tree. diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index 6ba2870f..6363283e 100644 --- a/registry/packages/yao-meta-skill.json +++ b/registry/packages/yao-meta-skill.json @@ -17,7 +17,7 @@ "license": "MIT", "checksums": { "package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea", - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5" + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9" }, "compatibility": { "openai": "pass", @@ -48,7 +48,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5", + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index 36ee29c5..63dd2ae6 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,21 +3,24 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf", + "commit": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b", "git_status": { "available": true, "dirty": true, - "changed_file_count": 9, + "changed_file_count": 22, "sample": [ + " M AGENTS.md", + " M registry/packages/yao-meta-skill.json", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", " M reports/evidence_consistency.json", - " M reports/review-studio.html", - " M reports/review-studio.json", - " M reports/review-viewer.json", - " M reports/skill-interpretation.json", - " M reports/skill-os-2-review.md", - " M reports/skill-overview.json" + " M reports/output_execution_runs.json", + " M reports/output_execution_runs.md", + " M reports/package_verification.json", + " M reports/package_verification.md", + " M reports/registry_audit.json", + " M reports/registry_audit.md", + " M reports/review-studio.html" ], "scope": "generation-time status before this report is written" }, @@ -27,9 +30,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8", + "evidence_bundle_sha256": "60f3799e92d774a4f737edfdd3cdf402a427a326b25adf5322c6bc61b3a39e8a", "source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea", - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5", + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -49,7 +52,7 @@ "public_claim_ready": false, "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 9 + "changed_file_count": 22 }, "public_claim": { "ready": false, @@ -65,7 +68,7 @@ }, "release_lock": { "ready": false, - "commit": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf", + "commit": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b", "status_scope": "generation-time status before this report is written", "reason": "working tree was dirty at generation time" }, @@ -75,7 +78,7 @@ "existing_count": 24, "missing_count": 0, "missing_paths": [], - "sha256": "5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8" + "sha256": "60f3799e92d774a4f737edfdd3cdf402a427a326b25adf5322c6bc61b3a39e8a" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -148,8 +151,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7967, - "sha256": "56430f01ba194dc6dc793eb505f92fec7a8c46e1be4b71976a3d641c9b98c7ec" + "bytes": 7966, + "sha256": "bdec10142028387b48df78668ee9b2d51a83f6582f82640ad74751c51f7866c5" }, { "label": "blind_review", @@ -198,14 +201,14 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "d6b523cc5cbb2d69c35989913e7e68dd4dc2bb04d3bcff88bbcb56fbe8be5084" + "sha256": "5d720a3d1a51c6ba512aa9504fb215b157b5e3132abc416e893aa2cda30b8a4c" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "ae8ac3872be3299b3d2dc18a29128346a3ecbb579987b1b08156e305237b5119" + "sha256": "cd65875d5b972e75a36d96c13f8f9ff7681c4a0f769add4d7802c609da73f08d" }, { "label": "install_simulation", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index f0c1a86b..a5cd0442 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,9 +1,9 @@ # Benchmark Reproducibility Generated at: `2026-06-16` -Commit: `a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf` +Commit: `bc999b9508da329c8ce09f98cffa6f02aae5bb2b` Working tree dirty at generation: `true` -Evidence bundle SHA256: `5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8` +Evidence bundle SHA256: `60f3799e92d774a4f737edfdd3cdf402a427a326b25adf5322c6bc61b3a39e8a` ## Summary @@ -13,7 +13,7 @@ Evidence bundle SHA256: `5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24 - required artifacts: `24` - missing artifacts: `0` - source contract sha256: `9fde13846a41` -- archive sha256: `83ece575ef74` +- archive sha256: `2fd9a3f8c7c4` - output cases: `5` - disclosed failure cases: `3` - reproduction commands: `22` @@ -23,7 +23,7 @@ Evidence bundle SHA256: `5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24 - world-class source checks: `6` pass / `13` total; `7` blocked - public claim ready: `false` - public claim blockers: `5` -- changed files at generation: `9` +- changed files at generation: `22` 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. @@ -51,7 +51,7 @@ This report proves local benchmark reproducibility only. It keeps external provi - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `24` / `24` -- sha256: `5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8` +- sha256: `60f3799e92d774a4f737edfdd3cdf402a427a326b25adf5322c6bc61b3a39e8a` ## Methodology Sections @@ -73,15 +73,15 @@ 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 | `56430f01ba19` | +| output_execution | `reports/output_execution_runs.json` | present | `bdec10142028` | | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` | | review_adjudication | `reports/output_review_adjudication.json` | present | `240485a721af` | | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` | | runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` | | trust_report | `reports/security_trust_report.json` | present | `a3a6d4e6809e` | | python_compatibility | `reports/python_compatibility.json` | present | `e53158aa045e` | -| registry_audit | `reports/registry_audit.json` | present | `d6b523cc5cbb` | -| package_verification | `reports/package_verification.json` | present | `ae8ac3872be3` | +| registry_audit | `reports/registry_audit.json` | present | `5d720a3d1a51` | +| package_verification | `reports/package_verification.json` | present | `cd65875d5b97` | | install_simulation | `reports/install_simulation.json` | present | `3e27a6f7678e` | | skill_os2_audit | `reports/skill_os2_audit.json` | present | `57536bc67370` | | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `76a3f8e2b12b` | diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index bb9f3623..3b42dbc7 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -47,8 +47,8 @@ "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" ], @@ -58,8 +58,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf", - "actual": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf", + "expected": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b", + "actual": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -71,7 +71,7 @@ "label": "overview embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 24, "missing_artifact_count": 0, "source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea", @@ -81,10 +81,10 @@ "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": 24, "missing_artifact_count": 0, "source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea", @@ -94,7 +94,7 @@ "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", @@ -204,8 +204,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf", - "actual": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf", + "expected": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b", + "actual": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -217,7 +217,7 @@ "label": "interpretation embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 24, "missing_artifact_count": 0, "source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea", @@ -227,10 +227,10 @@ "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": 24, "missing_artifact_count": 0, "source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea", @@ -240,7 +240,7 @@ "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", diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 2f5bbfa4..78bc16b9 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": 26.79, + "duration_ms": 28.59, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.31, + "duration_ms": 28.37, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.66, + "duration_ms": 27.45, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.21, + "duration_ms": 29.67, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.62, + "duration_ms": 30.1, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.34, + "duration_ms": 30.07, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.51, + "duration_ms": 27.43, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.37, + "duration_ms": 27.52, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.44, + "duration_ms": 27.47, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.21, + "duration_ms": 27.12, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index 0b1f8aa1..df9d94f5 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 | 26.79 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 27.31 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 26.66 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 26.21 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 26.62 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.34 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.51 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.37 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.44 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.21 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 28.59 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 28.37 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 27.45 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.67 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 30.1 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 30.07 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 27.43 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 27.52 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 27.47 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 27.12 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/package_verification.json b/reports/package_verification.json index 796fc70f..43d78451 100644 --- a/reports/package_verification.json +++ b/reports/package_verification.json @@ -8,7 +8,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5", + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9", "archive_entry_count": 618, "failure_count": 0, "warning_count": 0 diff --git a/reports/package_verification.md b/reports/package_verification.md index 088c4db6..8a654c30 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: `83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5` +- Archive SHA256: `2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9` - Failures: `0` - Warnings: `0` diff --git a/reports/python_compatibility.json b/reports/python_compatibility.json index f731c0b8..b7a6d032 100644 --- a/reports/python_compatibility.json +++ b/reports/python_compatibility.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16", + "generated_at": "2026-06-13", "root": ".", "summary": { "target_python": "3.11", diff --git a/reports/python_compatibility.md b/reports/python_compatibility.md index 8cb1d252..362aca7d 100644 --- a/reports/python_compatibility.md +++ b/reports/python_compatibility.md @@ -1,6 +1,6 @@ # Python Compatibility -Generated at: `2026-06-16` +Generated at: `2026-06-13` ## Summary diff --git a/reports/registry_audit.json b/reports/registry_audit.json index 4007ecc1..25910348 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -22,7 +22,7 @@ "license": "MIT", "checksums": { "package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea", - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5" + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9" }, "compatibility": { "openai": "pass", @@ -53,7 +53,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5", + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" diff --git a/reports/registry_audit.md b/reports/registry_audit.md index 28f79aa9..c643b1d4 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -7,7 +7,7 @@ - Owner: `Yao Team` - License: `MIT` - Package SHA256: `9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea` -- Archive SHA256: `83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5` +- Archive SHA256: `2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9` - Install simulated: `True` ## Compatibility diff --git a/reports/review-studio.html b/reports/review-studio.html index 4c46c3c7..3f0d0b50 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -676,7 +676,7 @@

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

Blueprint21/21

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

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

111 scripts scanned; secrets found

Py Compat0

177 files scanned for Python 3.11

Arch Debt0

899 largest lines; 8 watchlist; 64 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

173 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

618 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

111 scripts scanned; secrets found

Py Compat0

177 files scanned for Python 3.11

Arch Debt0

899 largest lines; 8 watchlist; 64 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

173 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

618 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

@@ -806,8 +806,8 @@
-

公开声明

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

声明阻断

+

公开声明

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

声明阻断

@@ -827,12 +827,12 @@

注册审计

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

-

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5
+

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9

发布路线

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

-

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
618
失败数
0
警告数
0
归档哈希
83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5
+

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
618
失败数
0
警告数
0
归档哈希
2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9
diff --git a/reports/review-studio.json b/reports/review-studio.json index f4a28249..9c69fa47 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -1676,7 +1676,7 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, @@ -1700,11 +1700,11 @@ "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": 2 }, - "commit": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf", + "commit": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b", "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.", @@ -1848,7 +1848,7 @@ "license": "MIT", "checksums": { "package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea", - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5" + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9" }, "compatibility": { "openai": "pass", @@ -1879,7 +1879,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5", + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1895,7 +1895,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5", + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9", "archive_entry_count": 618, "failure_count": 0, "warning_count": 0 @@ -1974,7 +1974,7 @@ { "field": "archive_sha256", "from": "", - "to": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5" + "to": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9" }, { "field": "package_sha256", @@ -4346,7 +4346,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.79, + "duration_ms": 28.59, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4374,7 +4374,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.31, + "duration_ms": 28.37, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4397,7 +4397,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.66, + "duration_ms": 27.45, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4425,7 +4425,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.21, + "duration_ms": 29.67, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4448,7 +4448,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.62, + "duration_ms": 30.1, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4476,7 +4476,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.34, + "duration_ms": 30.07, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4499,7 +4499,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.51, + "duration_ms": 27.43, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4526,7 +4526,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.37, + "duration_ms": 27.52, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4549,7 +4549,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.44, + "duration_ms": 27.47, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4578,7 +4578,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.21, + "duration_ms": 27.12, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5299,17 +5299,20 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf", + "commit": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 2, + "sample": [ + " M AGENTS.md", + " M tests/verify_evidence_consistency.py" + ], "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": 24, "missing_artifact_count": 0, @@ -5333,14 +5336,15 @@ "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": 2 }, "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)", @@ -5349,10 +5353,10 @@ "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": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf", + "ready": false, + "commit": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b", "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)", @@ -5939,7 +5943,7 @@ "label": "Review Studio", "status": "pass", "objective": "One HTML page supports first-pass production review across trigger, output, runtime, trust, release, and evidence actions.", - "current": "16 gates; decision review; warnings 4", + "current": "16 gates; decision review; warnings 3", "command": "python3 scripts/yao.py review-studio .", "test": "python3 tests/verify_review_studio.py", "evidence": [ @@ -20463,7 +20467,7 @@ "license": "MIT", "checksums": { "package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea", - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5" + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9" }, "compatibility": { "openai": "pass", @@ -20494,7 +20498,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5", + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -20542,7 +20546,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5", + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9", "archive_entry_count": 618, "failure_count": 0, "warning_count": 0 @@ -21550,7 +21554,7 @@ { "field": "archive_sha256", "from": "", - "to": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5" + "to": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9" }, { "field": "package_sha256", diff --git a/reports/review-viewer.json b/reports/review-viewer.json index e18272db..4c3e4e6a 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -996,7 +996,7 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, @@ -1020,11 +1020,11 @@ "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": 2 }, - "commit": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf", + "commit": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b", "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.", @@ -1168,7 +1168,7 @@ "license": "MIT", "checksums": { "package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea", - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5" + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9" }, "compatibility": { "openai": "pass", @@ -1199,7 +1199,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5", + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1215,7 +1215,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5", + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9", "archive_entry_count": 618, "failure_count": 0, "warning_count": 0 @@ -1294,7 +1294,7 @@ { "field": "archive_sha256", "from": "", - "to": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5" + "to": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9" }, { "field": "package_sha256", diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index 40282d39..6fb33edd 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -1004,9 +1004,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8", + "evidence_bundle_sha256": "60f3799e92d774a4f737edfdd3cdf402a427a326b25adf5322c6bc61b3a39e8a", "source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea", - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5", + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -1026,9 +1026,9 @@ "public_claim_ready": false, "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 9 + "changed_file_count": 22 }, - "commit": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf", + "commit": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b", "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.", @@ -1172,7 +1172,7 @@ "license": "MIT", "checksums": { "package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea", - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5" + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9" }, "compatibility": { "openai": "pass", @@ -1203,7 +1203,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5", + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1219,7 +1219,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5", + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9", "archive_entry_count": 618, "failure_count": 0, "warning_count": 0 @@ -1298,7 +1298,7 @@ { "field": "archive_sha256", "from": "", - "to": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5" + "to": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9" }, { "field": "package_sha256", diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 93e32078..55979647 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -999,9 +999,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8", + "evidence_bundle_sha256": "60f3799e92d774a4f737edfdd3cdf402a427a326b25adf5322c6bc61b3a39e8a", "source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea", - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5", + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -1021,9 +1021,9 @@ "public_claim_ready": false, "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 9 + "changed_file_count": 22 }, - "commit": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf", + "commit": "bc999b9508da329c8ce09f98cffa6f02aae5bb2b", "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 +1167,7 @@ "license": "MIT", "checksums": { "package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea", - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5" + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9" }, "compatibility": { "openai": "pass", @@ -1198,7 +1198,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5", + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1214,7 +1214,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5", + "archive_sha256": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9", "archive_entry_count": 618, "failure_count": 0, "warning_count": 0 @@ -1293,7 +1293,7 @@ { "field": "archive_sha256", "from": "", - "to": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5" + "to": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9" }, { "field": "package_sha256", diff --git a/reports/skill_os2_coverage.json b/reports/skill_os2_coverage.json index 452e124e..9fa67d6f 100644 --- a/reports/skill_os2_coverage.json +++ b/reports/skill_os2_coverage.json @@ -245,7 +245,7 @@ "label": "Review Studio", "status": "pass", "objective": "One HTML page supports first-pass production review across trigger, output, runtime, trust, release, and evidence actions.", - "current": "16 gates; decision review; warnings 4", + "current": "16 gates; decision review; warnings 3", "command": "python3 scripts/yao.py review-studio .", "test": "python3 tests/verify_review_studio.py", "evidence": [ diff --git a/reports/skill_os2_coverage.md b/reports/skill_os2_coverage.md index 2347d6ba..6adfb26f 100644 --- a/reports/skill_os2_coverage.md +++ b/reports/skill_os2_coverage.md @@ -29,7 +29,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, | Trust Security | `pass` | 111 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 618; 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 4 | `python3 scripts/yao.py review-studio .` | `python3 tests/verify_review_studio.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` | ## Recommended PR Coverage diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index 76f81846..aa4f6c09 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -70,7 +70,7 @@ { "field": "archive_sha256", "from": "", - "to": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5" + "to": "2fd9a3f8c7c4aa72b0bd03e9cfbf0449a0fa9215f949459324895c72c9abf6b9" }, { "field": "package_sha256", diff --git a/tests/verify_evidence_consistency.py b/tests/verify_evidence_consistency.py index 724bd05e..a3eed12b 100644 --- a/tests/verify_evidence_consistency.py +++ b/tests/verify_evidence_consistency.py @@ -95,11 +95,26 @@ def assert_world_class_roadmap_matches_ledger() -> None: assert expected_breakdown in actions, actions +def assert_release_evidence_instructions_cover_first_class_reports() -> None: + agents_text = (ROOT / "AGENTS.md").read_text(encoding="utf-8") + source_refresh_header = "After source changes that affect scripts" + clean_lock_header = "For final release evidence" + assert source_refresh_header in agents_text, agents_text + assert clean_lock_header in agents_text, agents_text + + source_refresh = agents_text.split(source_refresh_header, 1)[1].split(clean_lock_header, 1)[0] + clean_lock = agents_text.split(clean_lock_header, 1)[1].split("If `reports/benchmark_reproducibility.json`", 1)[0] + for block in [source_refresh, clean_lock]: + assert "python3 scripts/render_skill_interpretation.py ." in block, block + assert "python3 scripts/render_evidence_consistency.py . --generated-at \"$GENERATED_AT\"" in block, block + + def main() -> None: shutil.rmtree(TMP, ignore_errors=True) TMP.mkdir(parents=True, exist_ok=True) refresh_embedded_reports() assert_world_class_roadmap_matches_ledger() + assert_release_evidence_instructions_cover_first_class_reports() output_json = TMP / "evidence_consistency.json" output_md = TMP / "evidence_consistency.md" proc = run(