diff --git a/registry/index.json b/registry/index.json index 88983285..792ea56e 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8" + "package_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index 77273e04..5e5f1a07 100644 --- a/registry/packages/yao-meta-skill.json +++ b/registry/packages/yao-meta-skill.json @@ -16,8 +16,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8" + "package_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f" }, "compatibility": { "openai": "pass", @@ -48,7 +48,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json index 4d9a463b..4a1b75cc 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": "2026-06-15T14:58:53Z", + "generated_at": "2026-06-15T16:51:01Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index fe6ef095..8f905dbc 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,23 +3,36 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "b9b0ad18cf57af32f669bb1ffaaae8edf18553ad", + "commit": "bf1499d9b8ef137420dfc25b56d332005721da59", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 28, + "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/adoption_drift_report.json", + " M reports/benchmark_reproducibility.json", + " M reports/benchmark_reproducibility.md", + " M reports/context_budget.json", + " M reports/context_budget.md", + " M reports/context_budget_summary.json", + " M reports/evidence_consistency.json", + " M reports/output_execution_runs.json", + " M reports/output_execution_runs.md", + " M reports/package_verification.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": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "8e612a6cb7fbac70b9538d8c1f77713e1ce1806aad777502654b5489b54ce334", - "source_contract_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "evidence_bundle_sha256": "a76544029263cb74d648e507a64bc91f1222fadeed84f128dc62ed3faafd4b4c", + "source_contract_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -37,14 +50,15 @@ "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": 28 }, "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)", @@ -53,10 +67,10 @@ "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": "b9b0ad18cf57af32f669bb1ffaaae8edf18553ad", + "ready": false, + "commit": "bf1499d9b8ef137420dfc25b56d332005721da59", "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": 24, "missing_count": 0, "missing_paths": [], - "sha256": "8e612a6cb7fbac70b9538d8c1f77713e1ce1806aad777502654b5489b54ce334" + "sha256": "a76544029263cb74d648e507a64bc91f1222fadeed84f128dc62ed3faafd4b4c" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -137,8 +151,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7966, - "sha256": "3d79a1bf2d0c9ce23b36a1cf59c94e4943cd68ef4a7a70a8b43b66f25190a551" + "bytes": 7967, + "sha256": "0e4a474685833f04094d42f56dd84af5722185ece221fa6b63ec0996e84921d0" }, { "label": "blind_review", @@ -173,28 +187,28 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 109099, - "sha256": "0b11eb520b7275c36de490ba81e7c96e40ba9dd6baafd74fb4b1abd396042e33" + "sha256": "4fd98fe60dcdd1a0b8c6d0e6569bd21b5a07d695a0987a2f771d4e7b25fdec46" }, { "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, "bytes": 22887, - "sha256": "471c481ff9f9daf9aec60f81f2f6f40df7f077a4f5c8a8434ea69b56e0a6c84d" + "sha256": "be0b8550a4404d85a044b3ae612b39d94e8b493723e7aaf02386cace291b8262" }, { "label": "registry_audit", "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "944ae2224089a684a7495706685005d148b1ce8eea2efd1c18f318f1ffc59032" + "sha256": "7c901c1abbfa4ef1e8216f5ff4426fd41f929034722914d35d5d9995c6b215e7" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "c7a048b6bb2f6b13e88f473137c6b469fe7d25e99c67ca4018b9cf0f7308f312" + "sha256": "0ffbc5dcb848ab2965a6e01708d7c39d243c98b8fa387ecef5280d04f112da6e" }, { "label": "install_simulation", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index db83eec9..8f86293c 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,19 +1,19 @@ # Benchmark Reproducibility Generated at: `2026-06-16` -Commit: `b9b0ad18cf57af32f669bb1ffaaae8edf18553ad` -Working tree dirty at generation: `false` -Evidence bundle SHA256: `8e612a6cb7fbac70b9538d8c1f77713e1ce1806aad777502654b5489b54ce334` +Commit: `bf1499d9b8ef137420dfc25b56d332005721da59` +Working tree dirty at generation: `true` +Evidence bundle SHA256: `a76544029263cb74d648e507a64bc91f1222fadeed84f128dc62ed3faafd4b4c` ## Summary - reproducibility ready: `true` -- release lock ready: `true` +- release lock ready: `false` - methodology complete: `true` - required artifacts: `24` - missing artifacts: `0` -- source contract sha256: `002cb9e43ee2` -- archive sha256: `eddf1d422b1a` +- source contract sha256: `caa815571f7c` +- archive sha256: `6721f9af9fc9` - output cases: `5` - disclosed failure cases: `3` - reproduction commands: `22` @@ -22,8 +22,8 @@ Evidence bundle SHA256: `8e612a6cb7fbac70b9538d8c1f77713e1ce1806aad777502654b548 - world-class ready: `false` - 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: `28` 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. @@ -35,6 +35,7 @@ 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) | @@ -42,15 +43,15 @@ This report proves local benchmark reproducibility only. It keeps external provi ## 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: `24` / `24` -- sha256: `8e612a6cb7fbac70b9538d8c1f77713e1ce1806aad777502654b5489b54ce334` +- sha256: `a76544029263cb74d648e507a64bc91f1222fadeed84f128dc62ed3faafd4b4c` ## Methodology Sections @@ -72,15 +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 | `3d79a1bf2d0c` | +| output_execution | `reports/output_execution_runs.json` | present | `0e4a47468583` | | 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 | `0b11eb520b72` | -| python_compatibility | `reports/python_compatibility.json` | present | `471c481ff9f9` | -| registry_audit | `reports/registry_audit.json` | present | `944ae2224089` | -| package_verification | `reports/package_verification.json` | present | `c7a048b6bb2f` | +| trust_report | `reports/security_trust_report.json` | present | `4fd98fe60dcd` | +| python_compatibility | `reports/python_compatibility.json` | present | `be0b8550a440` | +| registry_audit | `reports/registry_audit.json` | present | `7c901c1abbfa` | +| package_verification | `reports/package_verification.json` | present | `0ffbc5dcb848` | | install_simulation | `reports/install_simulation.json` | present | `28ceb014e202` | | 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/context_budget.json b/reports/context_budget.json index 837b8d3b..38af6f23 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -6,15 +6,15 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 767, - "other_text_tokens": 1357572, + "other_text_tokens": 1370410, "estimated_initial_load_tokens": 960, - "estimated_total_text_tokens": 1358339, - "deferred_resource_tokens": 431562, + "estimated_total_text_tokens": 1371177, + "deferred_resource_tokens": 434418, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 382351, + "estimated_tokens": 385207, "file_count": 110 }, { @@ -31,7 +31,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 382351, + "estimated_tokens": 385207, "file_count": 110 } ], @@ -54,14 +54,14 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 382351, + "estimated_tokens": 385207, "file_count": 110, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } ], "summary": "Large deferred resources are indexed and backed by evidence." }, - "relevant_file_count": 562, + "relevant_file_count": 563, "unused_resource_dirs": [], "quality_signal_points": 130, "quality_density": 135.4 diff --git a/reports/context_budget.md b/reports/context_budget.md index 1672df59..5c5c2d07 100644 --- a/reports/context_budget.md +++ b/reports/context_budget.md @@ -2,7 +2,7 @@ | Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status | | --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- | -| root | `.` | `production` | 1000 | 960 | 767 | 431562 | `governed` | scripts:382351 | 135.4 | - | ok | +| root | `.` | `production` | 1000 | 960 | 767 | 434418 | `governed` | scripts:385207 | 135.4 | - | ok | | complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok | | governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok | diff --git a/reports/context_budget_summary.json b/reports/context_budget_summary.json index d721e9bf..dd3484c8 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -8,11 +8,11 @@ "budget_limit": 1000, "initial_tokens": 960, "skill_body_tokens": 767, - "deferred_resource_tokens": 431562, + "deferred_resource_tokens": 434418, "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 382351, + "estimated_tokens": 385207, "file_count": 110 } ], @@ -35,7 +35,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 382351, + "estimated_tokens": 385207, "file_count": 110, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index 84596a1f..a7575c69 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -43,8 +43,8 @@ "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" ], @@ -54,8 +54,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "b9b0ad18cf57af32f669bb1ffaaae8edf18553ad", - "actual": "b9b0ad18cf57af32f669bb1ffaaae8edf18553ad", + "expected": "bf1499d9b8ef137420dfc25b56d332005721da59", + "actual": "bf1499d9b8ef137420dfc25b56d332005721da59", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -67,30 +67,30 @@ "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": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "source_contract_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "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": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "source_contract_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "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", @@ -200,8 +200,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "b9b0ad18cf57af32f669bb1ffaaae8edf18553ad", - "actual": "b9b0ad18cf57af32f669bb1ffaaae8edf18553ad", + "expected": "bf1499d9b8ef137420dfc25b56d332005721da59", + "actual": "bf1499d9b8ef137420dfc25b56d332005721da59", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -213,30 +213,30 @@ "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": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "source_contract_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "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": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "source_contract_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "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", @@ -1663,11 +1663,11 @@ "SKILL.md": true, "manifest.json": true, "agents/interface.yaml": true, - "dist/manifest.json": true, - "dist/targets/openai/adapter.json": true, "evidence/world_class/README.md": true, "security/permission_policy.json": true, - "reports/world_class_evidence_ledger.json": true + "reports/world_class_evidence_ledger.json": true, + "dist/manifest.json": true, + "dist/targets/openai/adapter.json": true }, "prohibited_surfaces": [] }, @@ -1684,11 +1684,11 @@ "SKILL.md": true, "manifest.json": true, "agents/interface.yaml": true, - "dist/manifest.json": true, - "dist/targets/openai/adapter.json": true, "evidence/world_class/README.md": true, "security/permission_policy.json": true, - "reports/world_class_evidence_ledger.json": true + "reports/world_class_evidence_ledger.json": true, + "dist/manifest.json": true, + "dist/targets/openai/adapter.json": true }, "prohibited_surfaces": [] }, diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 7a6ce3e2..57cb2181 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": 27.02, + "duration_ms": 26.46, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 25.98, + "duration_ms": 26.34, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 25.78, + "duration_ms": 26.22, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.05, + "duration_ms": 26.54, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.11, + "duration_ms": 26.72, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.39, + "duration_ms": 26.47, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.01, + "duration_ms": 27.05, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.1, + "duration_ms": 26.35, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.37, + "duration_ms": 26.32, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.29, + "duration_ms": 26.65, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index cc0e9188..67724765 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 | 27.02 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 25.98 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 25.78 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.05 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 29.11 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 27.39 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.01 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.1 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.37 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.29 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 26.46 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 26.34 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 26.22 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 26.54 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 26.72 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.47 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 27.05 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.35 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.32 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.65 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/package_verification.json b/reports/package_verification.json index dafd06bc..01c0bea9 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": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "archive_entry_count": 617, "failure_count": 0, "warning_count": 0 diff --git a/reports/package_verification.md b/reports/package_verification.md index 3b2fed6c..fa31c474 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: `eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8` +- Archive SHA256: `6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f` - Failures: `0` - Warnings: `0` diff --git a/reports/python_compatibility.json b/reports/python_compatibility.json index 71bd68da..0eeeda29 100644 --- a/reports/python_compatibility.json +++ b/reports/python_compatibility.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-16", "root": ".", "summary": { "target_python": "3.11", diff --git a/reports/python_compatibility.md b/reports/python_compatibility.md index 5381d245..7a40edff 100644 --- a/reports/python_compatibility.md +++ b/reports/python_compatibility.md @@ -1,6 +1,6 @@ # Python Compatibility -Generated at: `2026-06-15` +Generated at: `2026-06-16` ## Summary diff --git a/reports/registry_audit.json b/reports/registry_audit.json index 1ef84c1b..76454a24 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,8 +21,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8" + "package_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f" }, "compatibility": { "openai": "pass", @@ -53,7 +53,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8" + "package_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index 137a1d61..5c8adc66 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,8 +6,8 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8` -- Archive SHA256: `eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8` +- Package SHA256: `caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921` +- Archive SHA256: `6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f` - Install simulated: `True` ## Compatibility diff --git a/reports/review-studio.html b/reports/review-studio.html index 54cd505b..c5798e3c 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -676,12 +676,12 @@

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

Blueprint21/21

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

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

110 scripts scanned; secrets found

Py Compat0

176 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

617 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

110 scripts scanned; secrets found

Py Compat0

176 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

617 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 960/1000; deferred 431562/120000; top deferred scripts 382351; resource governance governed; quality density 135.4

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; 110 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 176 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

173 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 899 lines; 64 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

reports/adoption_drift_report.json 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
+
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 960/1000; deferred 434418/120000; top deferred scripts 385207; resource governance governed; quality density 135.4

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; 110 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 176 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

173 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 899 lines; 64 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

reports/adoption_drift_report.json 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

@@ -743,12 +743,12 @@
-

上下文

initial load 960/1000; deferred 431562/120000; top deferred scripts 382351; resource governance governed; quality density 135.4

+

上下文

initial load 960/1000; deferred 434418/120000; top deferred scripts 385207; resource governance governed; quality density 135.4

编译证据

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

-

信任报告

Secret
0
脚本数
110
网络脚本
3
Help 失败
0
包体哈希
002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8
+

信任报告

Secret
0
脚本数
110
网络脚本
3
Help 失败
0
包体哈希
caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921

安全边界

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

@@ -785,7 +785,7 @@

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 2027-06-15 --evidence reports/output_review_adjudication.md
不可批准 · cannot-waive

World-Class Evidence

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

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

审查条件

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

Output Lab

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

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

审查条件

  • Reviewer confirms this release does not claim provider-backed or human-adjudicated output superiority.
  • Reviewer names the release scope and expiry date.
  • Reviewer links output_review_adjudication or output_execution evidence.
建议命令python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-16 --evidence reports/output_review_adjudication.md
不可批准 · cannot-waive

World-Class Evidence

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

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

审查条件

  • Do not use a waiver to claim public world-class readiness.
  • Either submit accepted ledger evidence or state that this release does not claim world-class completion.
  • Keep claim guard active until ledger summary.ready_to_claim_world_class is true.
建议命令python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-claim-guard .
@@ -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
eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8
+

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
6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f

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
617
失败数
0
警告数
0
归档哈希
eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8
+

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
617
失败数
0
警告数
0
归档哈希
6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f
diff --git a/reports/review-studio.json b/reports/review-studio.json index db2b7a0d..29375d6d 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -43,7 +43,7 @@ "key": "context-budget", "label": "上下文", "status": "pass", - "detail": "initial load 960/1000; deferred 431562/120000; top deferred scripts 382351; resource governance governed; quality density 135.4", + "detail": "initial load 960/1000; deferred 434418/120000; top deferred scripts 385207; resource governance governed; quality density 135.4", "evidence": "reports/context_budget.json", "link": "context_budget.md" }, @@ -1676,11 +1676,11 @@ "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, - "evidence_bundle_sha256": "8e612a6cb7fbac70b9538d8c1f77713e1ce1806aad777502654b5489b54ce334", + "evidence_bundle_sha256": "973e79957defbf5b70acff7de4f500e1618fb32636719d0ebe18c2210e6b5f3f", "source_contract_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", "output_case_count": 5, @@ -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": 11 }, - "commit": "b9b0ad18cf57af32f669bb1ffaaae8edf18553ad", + "commit": "bf1499d9b8ef137420dfc25b56d332005721da59", "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.", @@ -1809,7 +1809,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 197, - "package_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8" + "package_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921" }, "skill_atlas": { "skill_count": 12, @@ -1847,8 +1847,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8" + "package_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f" }, "compatibility": { "openai": "pass", @@ -1879,7 +1879,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "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": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "archive_entry_count": 617, "failure_count": 0, "warning_count": 0 @@ -1974,12 +1974,12 @@ { "field": "archive_sha256", "from": "", - "to": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8" + "to": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8" + "to": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921" } ] }, @@ -4346,7 +4346,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.02, + "duration_ms": 27.36, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4374,7 +4374,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 25.98, + "duration_ms": 26.68, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4397,7 +4397,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 25.78, + "duration_ms": 25.7, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4425,7 +4425,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.05, + "duration_ms": 28.11, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4448,7 +4448,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.11, + "duration_ms": 30.55, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4476,7 +4476,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.39, + "duration_ms": 28.2, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4499,7 +4499,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.01, + "duration_ms": 26.04, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4526,7 +4526,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.1, + "duration_ms": 26.72, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4549,7 +4549,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.37, + "duration_ms": 26.6, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4578,7 +4578,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.29, + "duration_ms": 26.01, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5299,21 +5299,33 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "b9b0ad18cf57af32f669bb1ffaaae8edf18553ad", + "commit": "bf1499d9b8ef137420dfc25b56d332005721da59", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 11, + "sample": [ + " M reports/adoption_drift_report.json", + " M reports/context_budget.json", + " M reports/context_budget.md", + " M reports/context_budget_summary.json", + " M reports/output_execution_runs.json", + " M reports/output_execution_runs.md", + " M reports/python_compatibility.json", + " M reports/python_compatibility.md", + " M reports/review_waivers.json", + " M reports/review_waivers.md", + " M scripts/render_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, - "evidence_bundle_sha256": "8e612a6cb7fbac70b9538d8c1f77713e1ce1806aad777502654b5489b54ce334", + "evidence_bundle_sha256": "973e79957defbf5b70acff7de4f500e1618fb32636719d0ebe18c2210e6b5f3f", "source_contract_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", "output_case_count": 5, @@ -5333,14 +5345,15 @@ "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": 11 }, "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 +5362,10 @@ "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": "b9b0ad18cf57af32f669bb1ffaaae8edf18553ad", + "ready": false, + "commit": "bf1499d9b8ef137420dfc25b56d332005721da59", "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)", @@ -5360,7 +5373,7 @@ "existing_count": 24, "missing_count": 0, "missing_paths": [], - "sha256": "8e612a6cb7fbac70b9538d8c1f77713e1ce1806aad777502654b5489b54ce334" + "sha256": "973e79957defbf5b70acff7de4f500e1618fb32636719d0ebe18c2210e6b5f3f" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5433,8 +5446,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7966, - "sha256": "3d79a1bf2d0c9ce23b36a1cf59c94e4943cd68ef4a7a70a8b43b66f25190a551" + "bytes": 7967, + "sha256": "6ac52b821a85dc924f2a3b0cdad440fdfee36222604f8f13b66aaa9387581f45" }, { "label": "blind_review", @@ -5476,7 +5489,7 @@ "path": "reports/python_compatibility.json", "exists": true, "bytes": 22887, - "sha256": "471c481ff9f9daf9aec60f81f2f6f40df7f077a4f5c8a8434ea69b56e0a6c84d" + "sha256": "be0b8550a4404d85a044b3ae612b39d94e8b493723e7aaf02386cace291b8262" }, { "label": "registry_audit", @@ -11412,7 +11425,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 197, - "package_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8" + "package_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921" }, "failures": [], "warnings": [], @@ -14134,7 +14147,7 @@ "python_compatibility": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-16", "root": ".", "summary": { "target_python": "3.11", @@ -15400,15 +15413,15 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 767, - "other_text_tokens": 1357572, + "other_text_tokens": 1370082, "estimated_initial_load_tokens": 960, - "estimated_total_text_tokens": 1358339, - "deferred_resource_tokens": 431562, + "estimated_total_text_tokens": 1370849, + "deferred_resource_tokens": 434418, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 382351, + "estimated_tokens": 385207, "file_count": 110 }, { @@ -15425,7 +15438,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 382351, + "estimated_tokens": 385207, "file_count": 110 } ], @@ -15448,14 +15461,14 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 382351, + "estimated_tokens": 385207, "file_count": 110, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } ], "summary": "Large deferred resources are indexed and backed by evidence." }, - "relevant_file_count": 562, + "relevant_file_count": 563, "unused_resource_dirs": [], "quality_signal_points": 130, "quality_density": 135.4 @@ -17323,7 +17336,7 @@ "adoption_drift": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-15T14:58:53Z", + "generated_at": "2026-06-15T16:50:03Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -17408,7 +17421,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "generated_at": "2026-06-15", + "generated_at": "2026-06-16", "summary": { "waiver_count": 0, "active_count": 0, @@ -17458,7 +17471,7 @@ "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 2027-06-15 --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 2027-06-16 --evidence reports/output_review_adjudication.md", "world_class_boundary": "Does not count as provider, human, or public world-class completion evidence." }, { @@ -20438,8 +20451,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8" + "package_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f" }, "compatibility": { "openai": "pass", @@ -20470,7 +20483,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -20495,7 +20508,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8" + "package_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921" } ] }, @@ -20518,7 +20531,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "archive_entry_count": 617, "failure_count": 0, "warning_count": 0 @@ -21526,12 +21539,12 @@ { "field": "archive_sha256", "from": "", - "to": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8" + "to": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8" + "to": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921" } ] }, diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 9b0c5205..f16c42cd 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -996,13 +996,13 @@ "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, - "evidence_bundle_sha256": "8e612a6cb7fbac70b9538d8c1f77713e1ce1806aad777502654b5489b54ce334", - "source_contract_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "evidence_bundle_sha256": "a76544029263cb74d648e507a64bc91f1222fadeed84f128dc62ed3faafd4b4c", + "source_contract_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -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": 28 }, - "commit": "b9b0ad18cf57af32f669bb1ffaaae8edf18553ad", + "commit": "bf1499d9b8ef137420dfc25b56d332005721da59", "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.", @@ -1129,7 +1129,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 197, - "package_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8" + "package_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921" }, "skill_atlas": { "skill_count": 12, @@ -1167,8 +1167,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8" + "package_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f" }, "compatibility": { "openai": "pass", @@ -1199,7 +1199,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "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": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "archive_entry_count": 617, "failure_count": 0, "warning_count": 0 @@ -1294,12 +1294,12 @@ { "field": "archive_sha256", "from": "", - "to": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8" + "to": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8" + "to": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921" } ] }, diff --git a/reports/review_waivers.json b/reports/review_waivers.json index 3acbd17e..aa2558e7 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": "2026-06-15", + "generated_at": "2026-06-16", "summary": { "waiver_count": 0, "active_count": 0, @@ -52,7 +52,7 @@ "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 2027-06-15 --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 2027-06-16 --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 2fcb0546..6c8d594c 100644 --- a/reports/review_waivers.md +++ b/reports/review_waivers.md @@ -35,7 +35,7 @@ - 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 2027-06-15 --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 2027-06-16 --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/security_trust_report.json b/reports/security_trust_report.json index 9200a159..3052a649 100644 --- a/reports/security_trust_report.json +++ b/reports/security_trust_report.json @@ -23,7 +23,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 197, - "package_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8" + "package_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921" }, "failures": [], "warnings": [], diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index df74b5af..bb00c2ff 100644 --- a/reports/security_trust_report.md +++ b/reports/security_trust_report.md @@ -16,7 +16,7 @@ - Interactive scripts: `0` - Package hash scope: `source-contract-without-generated-reports` - Package hash files: `197` -- Package SHA256: `002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8` +- Package SHA256: `caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921` ## Failures diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index 1ffb97e0..61089de4 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -1000,13 +1000,13 @@ "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, - "evidence_bundle_sha256": "8e612a6cb7fbac70b9538d8c1f77713e1ce1806aad777502654b5489b54ce334", - "source_contract_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "evidence_bundle_sha256": "a76544029263cb74d648e507a64bc91f1222fadeed84f128dc62ed3faafd4b4c", + "source_contract_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -1024,11 +1024,11 @@ "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": 28 }, - "commit": "b9b0ad18cf57af32f669bb1ffaaae8edf18553ad", + "commit": "bf1499d9b8ef137420dfc25b56d332005721da59", "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.", @@ -1133,7 +1133,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 197, - "package_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8" + "package_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921" }, "skill_atlas": { "skill_count": 12, @@ -1171,8 +1171,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8" + "package_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f" }, "compatibility": { "openai": "pass", @@ -1203,7 +1203,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "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": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "archive_entry_count": 617, "failure_count": 0, "warning_count": 0 @@ -1298,12 +1298,12 @@ { "field": "archive_sha256", "from": "", - "to": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8" + "to": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8" + "to": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921" } ] }, diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 9625ad1f..ca2d5db1 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -995,13 +995,13 @@ "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, - "evidence_bundle_sha256": "8e612a6cb7fbac70b9538d8c1f77713e1ce1806aad777502654b5489b54ce334", - "source_contract_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "evidence_bundle_sha256": "a76544029263cb74d648e507a64bc91f1222fadeed84f128dc62ed3faafd4b4c", + "source_contract_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -1019,11 +1019,11 @@ "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": 28 }, - "commit": "b9b0ad18cf57af32f669bb1ffaaae8edf18553ad", + "commit": "bf1499d9b8ef137420dfc25b56d332005721da59", "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.", @@ -1128,7 +1128,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 197, - "package_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8" + "package_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921" }, "skill_atlas": { "skill_count": 12, @@ -1166,8 +1166,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8", - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8" + "package_sha256": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f" }, "compatibility": { "openai": "pass", @@ -1198,7 +1198,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "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": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8", + "archive_sha256": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f", "archive_entry_count": 617, "failure_count": 0, "warning_count": 0 @@ -1293,12 +1293,12 @@ { "field": "archive_sha256", "from": "", - "to": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8" + "to": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8" + "to": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921" } ] }, diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index b3d52557..e2579987 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -70,12 +70,12 @@ { "field": "archive_sha256", "from": "", - "to": "eddf1d422b1ad8d50dc0b49f0525c33010e4fe7db31a4c605dcd68c33adf56e8" + "to": "6721f9af9fc9784b0491f8e73dd92db8a38b3629fc08170ddd3269f2a3c9b48f" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "002cb9e43ee22c7ba2a59422e4e123fb801242506a1a189b9a8bc8ad7d71f7f8" + "to": "caa815571f7c86fa95447cd7407875eb452cac255c45360db63b017699425921" } ] }, diff --git a/scripts/render_evidence_consistency.py b/scripts/render_evidence_consistency.py index 2f9d7115..d6d33941 100644 --- a/scripts/render_evidence_consistency.py +++ b/scripts/render_evidence_consistency.py @@ -437,12 +437,17 @@ def build_report(skill_dir: Path, generated_at: str) -> dict[str, Any]: "SKILL.md", "manifest.json", "agents/interface.yaml", - "dist/manifest.json", - "dist/targets/openai/adapter.json", "evidence/world_class/README.md", "security/permission_policy.json", "reports/world_class_evidence_ledger.json", ] + optional_claim_surfaces = [ + "dist/manifest.json", + "dist/targets/openai/adapter.json", + ] + required_claim_surfaces.extend( + path for path in optional_claim_surfaces if (skill_dir / path).exists() + ) prohibited_claim_surface_prefixes = [ "dist/install-simulation/", "evidence/world_class/submissions/",