diff --git a/registry/index.json b/registry/index.json index 611cd1f..e82fd8f 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" + "package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index aac73e6..ca8b6f6 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": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" + "package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482" }, "compatibility": { "openai": "pass", @@ -48,7 +48,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" diff --git a/reports/architecture_maintainability.json b/reports/architecture_maintainability.json index 4267177..469f18b 100644 --- a/reports/architecture_maintainability.json +++ b/reports/architecture_maintainability.json @@ -15,7 +15,7 @@ "warn_line_threshold": 900, "watch_line_threshold": 720, "block_line_threshold": 1500, - "largest_file_lines": 836, + "largest_file_lines": 837, "watchlist_count": 8, "hotspot_count": 0, "blocker_count": 0, @@ -24,7 +24,7 @@ "largest_files": [ { "path": "tests/verify_review_studio.py", - "lines": 836, + "lines": 837, "kind": "test", "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." @@ -110,7 +110,7 @@ "watchlist": [ { "path": "tests/verify_review_studio.py", - "lines": 836, + "lines": 837, "kind": "test", "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md index 6fabd89..df9f363 100644 --- a/reports/architecture_maintainability.md +++ b/reports/architecture_maintainability.md @@ -13,7 +13,7 @@ Generated at: `2026-06-16` - Yao CLI command handlers: `68` - entrypoint command handlers: `18` - command modules: `6` -- largest file lines: `836` +- largest file lines: `837` - watch threshold lines: `720` - watchlist: `8` - hotspots: `0` @@ -29,7 +29,7 @@ No file-size hotspots found. | File | Lines | Kind | Recommended next split | | --- | ---: | --- | --- | -| `tests/verify_review_studio.py` | `836` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | +| `tests/verify_review_studio.py` | `837` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | | `scripts/skill_report_model.py` | `800` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | | `tests/verify_yao_cli.py` | `785` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | | `scripts/render_evidence_consistency.py` | `766` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | @@ -42,7 +42,7 @@ No file-size hotspots found. | File | Lines | Kind | Severity | | --- | ---: | --- | --- | -| `tests/verify_review_studio.py` | `836` | `test` | `pass` | +| `tests/verify_review_studio.py` | `837` | `test` | `pass` | | `scripts/skill_report_model.py` | `800` | `internal-module` | `pass` | | `tests/verify_yao_cli.py` | `785` | `test` | `pass` | | `scripts/render_evidence_consistency.py` | `766` | `cli-script` | `pass` | diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index 88431af..9590cab 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": "499214b052869193d96cdd7e73f537a57eb7bb8d", + "commit": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 32, + "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", + " 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" + ], "scope": "generation-time status before this report is written" }, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8", - "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "evidence_bundle_sha256": "813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a", + "source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -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": 32 }, "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": "499214b052869193d96cdd7e73f537a57eb7bb8d", + "ready": false, + "commit": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da", "status_scope": "generation-time status before this report is written", - "reason": "clean generation-time HEAD" + "reason": "working tree was dirty at generation time" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -64,7 +78,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8" + "sha256": "813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -138,7 +152,7 @@ "path": "reports/output_execution_runs.json", "exists": true, "bytes": 7966, - "sha256": "fd065f84dd529c38c2a7078d99f185fb23d08e3734fbdf7faab1c897f8129818" + "sha256": "93a5679326b29eb9d79c3ada70679f0070be6a8aed6e50d0452c854b48efa475" }, { "label": "blind_review", @@ -173,7 +187,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 120363, - "sha256": "e6353c1589c371823d9f4944a9be8fa46f154d004668d678c3529c92143a8436" + "sha256": "bea31eb462ca6e8021e68181ce3c4d34eaa0122dd34476b697ba59d38391cf36" }, { "label": "python_compatibility", @@ -187,14 +201,14 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "879a11cef5138fedb93365e40253d650137c7bae0f810803242640a9c6d273c1" + "sha256": "c6d5cf3c3ec415480b7cc72623b1977c5a98e64707a7dbd13ba239dfd44159fe" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "45b51edb26bc22e7ab349bf8b050830d219a6971156a9c003538a99e91e47f55" + "sha256": "dd90aae6ad68c21bd0db241b033aa00038278fd6396e75fc42f86064911ce51b" }, { "label": "install_simulation", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 07d9247..16dcac6 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,19 +1,19 @@ # Benchmark Reproducibility Generated at: `2026-06-16` -Commit: `499214b052869193d96cdd7e73f537a57eb7bb8d` -Working tree dirty at generation: `false` -Evidence bundle SHA256: `7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8` +Commit: `ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da` +Working tree dirty at generation: `true` +Evidence bundle SHA256: `813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a` ## Summary - reproducibility ready: `true` -- release lock ready: `true` +- release lock ready: `false` - methodology complete: `true` - required artifacts: `25` - missing artifacts: `0` -- source contract sha256: `1e466c4508d6` -- archive sha256: `88dc8d392047` +- source contract sha256: `363354808bdd` +- archive sha256: `a5a62aeb079b` - output cases: `5` - disclosed failure cases: `3` - reproduction commands: `23` @@ -22,8 +22,8 @@ Evidence bundle SHA256: `7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae - 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: `32` 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: `25` / `25` -- sha256: `7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8` +- sha256: `813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a` ## 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 | `fd065f84dd52` | +| output_execution | `reports/output_execution_runs.json` | present | `93a5679326b2` | | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` | | review_adjudication | `reports/output_review_adjudication.json` | present | `bb8c72a9291e` | | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` | | runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` | -| trust_report | `reports/security_trust_report.json` | present | `e6353c1589c3` | +| trust_report | `reports/security_trust_report.json` | present | `bea31eb462ca` | | python_compatibility | `reports/python_compatibility.json` | present | `6843f5283fd7` | -| registry_audit | `reports/registry_audit.json` | present | `879a11cef513` | -| package_verification | `reports/package_verification.json` | present | `45b51edb26bc` | +| registry_audit | `reports/registry_audit.json` | present | `c6d5cf3c3ec4` | +| package_verification | `reports/package_verification.json` | present | `dd90aae6ad68` | | install_simulation | `reports/install_simulation.json` | present | `1c3fdea61d50` | | skill_os2_audit | `reports/skill_os2_audit.json` | present | `c0e499f9f051` | | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `130161495dc4` | diff --git a/reports/context_budget.json b/reports/context_budget.json index 76b3031..80e62ef 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": 797, - "other_text_tokens": 1050165, + "other_text_tokens": 1050110, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1050962, - "deferred_resource_tokens": 486314, + "estimated_total_text_tokens": 1050907, + "deferred_resource_tokens": 486227, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 426187, + "estimated_tokens": 426100, "file_count": 125 }, { @@ -36,7 +36,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 426187, + "estimated_tokens": 426100, "file_count": 125 } ], @@ -59,7 +59,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 426187, + "estimated_tokens": 426100, "file_count": 125, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } diff --git a/reports/context_budget.md b/reports/context_budget.md index 8d72382..71aaa7b 100644 --- a/reports/context_budget.md +++ b/reports/context_budget.md @@ -2,7 +2,7 @@ | Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status | | --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- | -| root | `.` | `production` | 1000 | 990 | 797 | 486314 | `governed` | scripts:426187 | 131.3 | - | ok | +| root | `.` | `production` | 1000 | 990 | 797 | 486227 | `governed` | scripts:426100 | 131.3 | - | ok | | complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok | | governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok | diff --git a/reports/context_budget_summary.json b/reports/context_budget_summary.json index bcef6ce..488d0e9 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -8,11 +8,11 @@ "budget_limit": 1000, "initial_tokens": 990, "skill_body_tokens": 797, - "deferred_resource_tokens": 486314, + "deferred_resource_tokens": 486227, "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 426187, + "estimated_tokens": 426100, "file_count": 125 } ], @@ -35,7 +35,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 426187, + "estimated_tokens": 426100, "file_count": 125, "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 d21cd09..7cd7aac 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -189,12 +189,12 @@ "status": "pass", "expected": { "status": "pass", - "detail": "initial load 990/1000; deferred 486314/120000; top deferred scripts 426187; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 486227/120000; top deferred scripts 426100; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "actual": { "status": "pass", - "detail": "initial load 990/1000; deferred 486314/120000; top deferred scripts 426187; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 486227/120000; top deferred scripts 426100; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "paths": [ @@ -207,8 +207,8 @@ "key": "benchmark-release-lock-self-consistency", "label": "Benchmark release lock matches git dirty state", "status": "pass", - "expected": true, - "actual": true, + "expected": false, + "actual": false, "paths": [ "reports/benchmark_reproducibility.json" ], @@ -248,8 +248,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "499214b052869193d96cdd7e73f537a57eb7bb8d", - "actual": "499214b052869193d96cdd7e73f537a57eb7bb8d", + "expected": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da", + "actual": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -261,30 +261,30 @@ "label": "overview embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "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": 25, "missing_artifact_count": 0, - "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "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", @@ -394,8 +394,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "499214b052869193d96cdd7e73f537a57eb7bb8d", - "actual": "499214b052869193d96cdd7e73f537a57eb7bb8d", + "expected": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da", + "actual": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -407,30 +407,30 @@ "label": "interpretation embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "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": 25, "missing_artifact_count": 0, - "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "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", diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 2b2c026..3a619d8 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": 32.31, + "duration_ms": 31.35, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 35.69, + "duration_ms": 31.06, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 37.25, + "duration_ms": 31.69, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 34.3, + "duration_ms": 33.39, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.89, + "duration_ms": 31.94, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 33.18, + "duration_ms": 32.09, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 33.42, + "duration_ms": 31.3, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 33.85, + "duration_ms": 31.15, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 34.38, + "duration_ms": 31.77, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 34.62, + "duration_ms": 33.75, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index 975c9fd..e319057 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 | 32.31 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 35.69 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 37.25 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 34.3 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 32.89 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 33.18 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 33.42 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 33.85 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 34.38 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 34.62 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 31.35 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 31.06 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 31.69 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 33.39 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 31.94 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 32.09 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 31.3 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 31.15 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 31.77 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 33.75 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/package_verification.json b/reports/package_verification.json index 43df8ed..2ce0684 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": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 diff --git a/reports/package_verification.md b/reports/package_verification.md index e590c59..20f3414 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: `88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288` +- Archive SHA256: `a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482` - Failures: `0` - Warnings: `0` diff --git a/reports/registry_audit.json b/reports/registry_audit.json index 595c43d..503534b 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,8 +21,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" + "package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482" }, "compatibility": { "openai": "pass", @@ -53,7 +53,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "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": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" + "package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index 234da30..87ab404 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,8 +6,8 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642` -- Archive SHA256: `88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288` +- Package SHA256: `363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453` +- Archive SHA256: `a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482` - Install simulated: `True` ## Compatibility diff --git a/reports/review-studio.html b/reports/review-studio.html index fd0a6f1..db25bdd 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -740,12 +740,12 @@

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

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

125 scripts scanned; secrets found

Py Compat0

199 files scanned for Python 3.11

Arch Debt0

836 largest lines; 8 watchlist; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock true

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

180 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

652 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

125 scripts scanned; secrets found

Py Compat0

199 files scanned for Python 3.11

Arch Debt0

837 largest lines; 8 watchlist; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock false

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

180 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

652 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

审查闸门

-
通过

意图画布

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

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

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

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 990/1000; deferred 486314/120000; top deferred scripts 426187; resource governance governed; quality density 131.3

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 125 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 199 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

196 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 836 lines; 68 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

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

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

权限探针

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

reports/runtime_permission_probes.json 证据
通过

组合治理

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

reports/skill_atlas.json 证据
通过

运营回路

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

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

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 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 990/1000; deferred 486227/120000; top deferred scripts 426100; resource governance governed; quality density 131.3

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 125 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 199 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

196 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 837 lines; 68 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

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

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

权限探针

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

reports/runtime_permission_probes.json 证据
通过

组合治理

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

reports/skill_atlas.json 证据
通过

运营回路

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

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

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

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

reports/world_class_evidence_ledger.json 证据
通过

注册审计

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

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

发布路线

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

@@ -807,12 +807,12 @@
-

上下文

initial load 990/1000; deferred 486314/120000; top deferred scripts 426187; resource governance governed; quality density 131.3

+

上下文

initial load 990/1000; deferred 486227/120000; top deferred scripts 426100; resource governance governed; quality density 131.3

编译证据

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

-

信任报告

Secret
0
脚本数
125
网络脚本
3
Help 失败
0
包体哈希
1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642
+

信任报告

Secret
0
脚本数
125
网络脚本
3
Help 失败
0
包体哈希
363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453

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。

@@ -837,14 +837,14 @@
-

运营回路

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

+

运营回路

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

漂移信号

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

日常运维

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

周度队列

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

日常运维

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

周度队列

决策
curator-review
Week Id
2026-W25
日报数
1
唯一机会
5
待批准复核
1
提案复核
4
Top Score
88
发布锁
否
Writes Source Files
否
Auto Patch Enabled
否
@@ -877,8 +877,8 @@
-

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

  • 阻断provider-backed model holdout evidence is incomplete
  • 阻断human blind-review adjudication is incomplete
  • 阻断world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)
  • 阻断world-class source checks are not all accepted (6/13 pass, 7 blocked)
+

公开声明

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

声明阻断

  • 阻断release lock is not clean or commit is unavailable
  • 阻断provider-backed model holdout evidence is incomplete
  • 阻断human blind-review adjudication is incomplete
  • 阻断world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)
  • 阻断world-class source checks are not all accepted (6/13 pass, 7 blocked)
@@ -898,12 +898,12 @@

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
88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288
+

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
a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482

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
652
失败数
0
警告数
0
归档哈希
88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288
+

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
652
失败数
0
警告数
0
归档哈希
a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482
diff --git a/reports/review-studio.json b/reports/review-studio.json index 81658c1..06bc9a7 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 990/1000; deferred 486314/120000; top deferred scripts 426187; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 486227/120000; top deferred scripts 426100; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json", "link": "context_budget.md" }, @@ -75,7 +75,7 @@ "key": "architecture-maintainability", "label": "架构维护", "status": "pass", - "detail": "196 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 836 lines; 68 CLI handlers; 18 in entrypoint", + "detail": "196 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 837 lines; 68 CLI handlers; 18 in entrypoint", "evidence": "reports/architecture_maintainability.json", "link": "architecture_maintainability.md" }, @@ -107,7 +107,7 @@ "key": "operations-loop", "label": "运营回路", "status": "pass", - "detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true", + "detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false", "evidence": "reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly", "link": "adoption_drift_report.md" }, @@ -1922,13 +1922,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8", - "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "evidence_bundle_sha256": "813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a", + "source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1946,11 +1946,11 @@ "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": 32 }, - "commit": "499214b052869193d96cdd7e73f537a57eb7bb8d", + "commit": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da", "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.", @@ -2055,7 +2055,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" + "package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453" }, "skill_atlas": { "skill_count": 12, @@ -2093,8 +2093,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" + "package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482" }, "compatibility": { "openai": "pass", @@ -2125,7 +2125,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -2141,7 +2141,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -2220,12 +2220,12 @@ { "field": "archive_sha256", "from": "", - "to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" + "to": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" + "to": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453" } ] }, @@ -4642,7 +4642,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.31, + "duration_ms": 31.35, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4670,7 +4670,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 35.69, + "duration_ms": 31.06, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4693,7 +4693,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 37.25, + "duration_ms": 31.69, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4721,7 +4721,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 34.3, + "duration_ms": 33.39, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4744,7 +4744,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.89, + "duration_ms": 31.94, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4772,7 +4772,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 33.18, + "duration_ms": 32.09, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4795,7 +4795,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 33.42, + "duration_ms": 31.3, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4822,7 +4822,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 33.85, + "duration_ms": 31.15, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4845,7 +4845,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 34.38, + "duration_ms": 31.77, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4874,7 +4874,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 34.62, + "duration_ms": 33.75, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5600,23 +5600,36 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "499214b052869193d96cdd7e73f537a57eb7bb8d", + "commit": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 32, + "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", + " 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" + ], "scope": "generation-time status before this report is written" }, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8", - "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "evidence_bundle_sha256": "813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a", + "source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -5634,14 +5647,15 @@ "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": 32 }, "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)", @@ -5650,10 +5664,10 @@ "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": "499214b052869193d96cdd7e73f537a57eb7bb8d", + "ready": false, + "commit": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da", "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)", @@ -5661,7 +5675,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8" + "sha256": "813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5735,7 +5749,7 @@ "path": "reports/output_execution_runs.json", "exists": true, "bytes": 7966, - "sha256": "fd065f84dd529c38c2a7078d99f185fb23d08e3734fbdf7faab1c897f8129818" + "sha256": "93a5679326b29eb9d79c3ada70679f0070be6a8aed6e50d0452c854b48efa475" }, { "label": "blind_review", @@ -5770,7 +5784,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 120363, - "sha256": "e6353c1589c371823d9f4944a9be8fa46f154d004668d678c3529c92143a8436" + "sha256": "bea31eb462ca6e8021e68181ce3c4d34eaa0122dd34476b697ba59d38391cf36" }, { "label": "python_compatibility", @@ -5784,14 +5798,14 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "879a11cef5138fedb93365e40253d650137c7bae0f810803242640a9c6d273c1" + "sha256": "c6d5cf3c3ec415480b7cc72623b1977c5a98e64707a7dbd13ba239dfd44159fe" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "45b51edb26bc22e7ab349bf8b050830d219a6971156a9c003538a99e91e47f55" + "sha256": "dd90aae6ad68c21bd0db241b033aa00038278fd6396e75fc42f86064911ce51b" }, { "label": "install_simulation", @@ -12045,7 +12059,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" + "package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453" }, "failures": [], "warnings": [], @@ -16304,7 +16318,7 @@ "warn_line_threshold": 900, "watch_line_threshold": 720, "block_line_threshold": 1500, - "largest_file_lines": 836, + "largest_file_lines": 837, "watchlist_count": 8, "hotspot_count": 0, "blocker_count": 0, @@ -16313,7 +16327,7 @@ "largest_files": [ { "path": "tests/verify_review_studio.py", - "lines": 836, + "lines": 837, "kind": "test", "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." @@ -16399,7 +16413,7 @@ "watchlist": [ { "path": "tests/verify_review_studio.py", - "lines": 836, + "lines": 837, "kind": "test", "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." @@ -16469,15 +16483,15 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1050165, + "other_text_tokens": 1050110, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1050962, - "deferred_resource_tokens": 486314, + "estimated_total_text_tokens": 1050907, + "deferred_resource_tokens": 486227, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 426187, + "estimated_tokens": 426100, "file_count": 125 }, { @@ -16499,7 +16513,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 426187, + "estimated_tokens": 426100, "file_count": 125 } ], @@ -16522,7 +16536,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 426187, + "estimated_tokens": 426100, "file_count": 125, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } @@ -18516,7 +18530,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -18533,7 +18547,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -18982,7 +18996,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true }, "actions": [ @@ -19031,7 +19045,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -19051,7 +19065,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -19303,7 +19317,7 @@ "no_route_opportunity_count": 0 }, "release_state": { - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4 @@ -23413,8 +23427,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" + "package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482" }, "compatibility": { "openai": "pass", @@ -23445,7 +23459,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -23470,7 +23484,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" + "package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453" } ] }, @@ -23493,7 +23507,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -24501,12 +24515,12 @@ { "field": "archive_sha256", "from": "", - "to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" + "to": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" + "to": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453" } ] }, diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 1cfda2f..08be6a7 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -997,13 +997,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8", - "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "evidence_bundle_sha256": "813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a", + "source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1021,11 +1021,11 @@ "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": 32 }, - "commit": "499214b052869193d96cdd7e73f537a57eb7bb8d", + "commit": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da", "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.", @@ -1130,7 +1130,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" + "package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453" }, "skill_atlas": { "skill_count": 12, @@ -1168,8 +1168,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" + "package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482" }, "compatibility": { "openai": "pass", @@ -1200,7 +1200,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1216,7 +1216,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -1295,12 +1295,12 @@ { "field": "archive_sha256", "from": "", - "to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" + "to": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" + "to": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453" } ] }, diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index 6708cb3..a192a44 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": 216, - "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" + "package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453" }, "failures": [], "warnings": [], diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index 7f7560e..f3d4915 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: `216` -- Package SHA256: `1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642` +- Package SHA256: `363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453` ## Failures diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index b0a9048..37cd57b 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -1001,13 +1001,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8", - "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "evidence_bundle_sha256": "813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a", + "source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1025,11 +1025,11 @@ "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": 32 }, - "commit": "499214b052869193d96cdd7e73f537a57eb7bb8d", + "commit": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da", "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.", @@ -1134,7 +1134,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" + "package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453" }, "skill_atlas": { "skill_count": 12, @@ -1172,8 +1172,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" + "package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482" }, "compatibility": { "openai": "pass", @@ -1204,7 +1204,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1220,7 +1220,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -1299,12 +1299,12 @@ { "field": "archive_sha256", "from": "", - "to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" + "to": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" + "to": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453" } ] }, diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 6776b32..84358ce 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.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": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8", - "source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "evidence_bundle_sha256": "813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a", + "source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -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": 32 }, - "commit": "499214b052869193d96cdd7e73f537a57eb7bb8d", + "commit": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da", "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": 216, - "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" + "package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453" }, "skill_atlas": { "skill_count": 12, @@ -1167,8 +1167,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642", - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" + "package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482" }, "compatibility": { "openai": "pass", @@ -1199,7 +1199,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "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": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288", + "archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -1294,12 +1294,12 @@ { "field": "archive_sha256", "from": "", - "to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" + "to": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" + "to": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453" } ] }, diff --git a/reports/skillops/daily/2026-06-16.json b/reports/skillops/daily/2026-06-16.json index a35cbc8..386b061 100644 --- a/reports/skillops/daily/2026-06-16.json +++ b/reports/skillops/daily/2026-06-16.json @@ -14,7 +14,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -31,7 +31,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -480,7 +480,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true }, "actions": [ diff --git a/reports/skillops/daily/2026-06-16.md b/reports/skillops/daily/2026-06-16.md index 105c41c..d0fbea0 100644 --- a/reports/skillops/daily/2026-06-16.md +++ b/reports/skillops/daily/2026-06-16.md @@ -14,7 +14,7 @@ Generated at: `2026-06-16` - local blueprint ready: `true` - public world-class ready: `false` - world-class pending: `4` -- release lock ready: `true` +- release lock ready: `false` - evidence consistency ok: `true` This report is an operations cockpit for explicit-source SkillOps. It does not scan private logs, write source files, apply patches, or count as world-class external or human evidence. diff --git a/reports/skillops/weekly/2026-W25.json b/reports/skillops/weekly/2026-W25.json index 998d23e..65c79eb 100644 --- a/reports/skillops/weekly/2026-W25.json +++ b/reports/skillops/weekly/2026-W25.json @@ -15,7 +15,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -35,7 +35,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -287,7 +287,7 @@ "no_route_opportunity_count": 0 }, "release_state": { - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4 diff --git a/reports/skillops/weekly/2026-W25.md b/reports/skillops/weekly/2026-W25.md index 4d75fc3..1fd6a71 100644 --- a/reports/skillops/weekly/2026-W25.md +++ b/reports/skillops/weekly/2026-W25.md @@ -13,7 +13,7 @@ Week: `2026-W25` - top_score: `88` - skill_count: `12` - actionable_portfolio_issue_count: `0` -- release_lock_ready: `True` +- release_lock_ready: `False` - evidence_consistency_ok: `True` - public_world_class_ready: `False` - world_class_pending_count: `4` diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index 721b7ab..f1693f0 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -70,12 +70,12 @@ { "field": "archive_sha256", "from": "", - "to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288" + "to": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642" + "to": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453" } ] }, diff --git a/scripts/render_review_waivers.py b/scripts/render_review_waivers.py index d049e60..eb13cff 100644 --- a/scripts/render_review_waivers.py +++ b/scripts/render_review_waivers.py @@ -6,26 +6,10 @@ from datetime import date, timedelta from pathlib import Path from typing import Any +from review_studio_gates import REVIEW_STUDIO_GATE_KEYS + ROOT = Path(__file__).resolve().parent.parent -REVIEW_STUDIO_GATE_KEYS = { - "intent-canvas", - "trigger-lab", - "output-lab", - "context-budget", - "runtime-matrix", - "trust-report", - "python-compat", - "architecture-maintainability", - "permission-gates", - "permission-runtime", - "skill-atlas", - "operations-loop", - "review-waivers", - "world-class-evidence", - "registry-audit", - "release-notes", -} NON_WAIVABLE_GATE_KEYS = {"review-waivers", "world-class-evidence"} WAIVERABLE_GATE_KEYS = REVIEW_STUDIO_GATE_KEYS - NON_WAIVABLE_GATE_KEYS KNOWN_GATE_KEYS = WAIVERABLE_GATE_KEYS diff --git a/scripts/review_studio_gates.py b/scripts/review_studio_gates.py index 60b7acd..e197926 100644 --- a/scripts/review_studio_gates.py +++ b/scripts/review_studio_gates.py @@ -20,6 +20,26 @@ SCRIPT_INTERFACE_REASON = "Imported by render_review_studio.py to keep Review St ROOT = Path(__file__).resolve().parent.parent +GATE_WEIGHTS = { + "trigger-lab": 15, + "output-lab": 20, + "context-budget": 10, + "runtime-matrix": 10, + "trust-report": 10, + "python-compat": 10, + "architecture-maintainability": 10, + "permission-gates": 10, + "permission-runtime": 10, + "skill-atlas": 10, + "operations-loop": 10, + "review-waivers": 10, + "world-class-evidence": 10, + "registry-audit": 10, + "release-notes": 10, + "intent-canvas": 10, +} +REVIEW_STUDIO_GATE_KEYS = frozenset(GATE_WEIGHTS) + def _load_json(path: Path) -> dict[str, Any]: if not path.exists(): @@ -653,28 +673,10 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An def weighted_score(gates: list[dict[str, str]]) -> int: - weights = { - "trigger-lab": 15, - "output-lab": 20, - "context-budget": 10, - "runtime-matrix": 10, - "trust-report": 10, - "python-compat": 10, - "architecture-maintainability": 10, - "permission-gates": 10, - "permission-runtime": 10, - "skill-atlas": 10, - "operations-loop": 10, - "review-waivers": 10, - "world-class-evidence": 10, - "registry-audit": 10, - "release-notes": 10, - "intent-canvas": 10, - } earned = 0.0 total = 0.0 for item in gates: - weight = weights.get(item["key"], 5) + weight = GATE_WEIGHTS.get(item["key"], 5) total += weight if item["status"] == "pass": earned += weight diff --git a/tests/verify_review_studio.py b/tests/verify_review_studio.py index f43c9b9..c44171d 100644 --- a/tests/verify_review_studio.py +++ b/tests/verify_review_studio.py @@ -308,7 +308,8 @@ def main() -> None: "world-class-evidence", }, payload gate_keys = {item["key"] for item in payload["gates"]} - assert {"intent-canvas", "trigger-lab", "output-lab", "context-budget", "runtime-matrix", "trust-report", "python-compat", "architecture-maintainability", "permission-gates", "permission-runtime", "skill-atlas", "operations-loop", "review-waivers", "world-class-evidence", "registry-audit", "release-notes"} <= gate_keys, payload + assert gate_keys == review_gates.REVIEW_STUDIO_GATE_KEYS, payload + assert set(review_gates.GATE_WEIGHTS) == review_gates.REVIEW_STUDIO_GATE_KEYS, review_gates.GATE_WEIGHTS output_gate = next(item for item in payload["gates"] if item["key"] == "output-lab") assert output_gate["status"] == "warn", output_gate assert "5/5 cases" in output_gate["detail"], output_gate diff --git a/tests/verify_review_waivers.py b/tests/verify_review_waivers.py index e74b9a9..b7050a7 100644 --- a/tests/verify_review_waivers.py +++ b/tests/verify_review_waivers.py @@ -11,6 +11,7 @@ SCRIPT = ROOT / "scripts" / "render_review_waivers.py" sys.path.insert(0, str(ROOT / "scripts")) import render_review_waivers as review_waivers # noqa: E402 +import review_studio_gates as review_gates # noqa: E402 def run(*args: str, check: bool = True) -> subprocess.CompletedProcess: @@ -24,7 +25,7 @@ def run(*args: str, check: bool = True) -> subprocess.CompletedProcess: def main() -> None: - assert review_waivers.REVIEW_STUDIO_GATE_KEYS == { + expected_gate_keys = { "intent-canvas", "trigger-lab", "output-lab", @@ -41,7 +42,10 @@ def main() -> None: "world-class-evidence", "registry-audit", "release-notes", - }, review_waivers.REVIEW_STUDIO_GATE_KEYS + } + assert review_gates.REVIEW_STUDIO_GATE_KEYS == expected_gate_keys, review_gates.REVIEW_STUDIO_GATE_KEYS + assert set(review_gates.GATE_WEIGHTS) == expected_gate_keys, review_gates.GATE_WEIGHTS + assert review_waivers.REVIEW_STUDIO_GATE_KEYS == review_gates.REVIEW_STUDIO_GATE_KEYS assert review_waivers.NON_WAIVABLE_GATE_KEYS == {"review-waivers", "world-class-evidence"} assert "python-compat" in review_waivers.WAIVERABLE_GATE_KEYS assert "architecture-maintainability" in review_waivers.WAIVERABLE_GATE_KEYS