diff --git a/registry/index.json b/registry/index.json index a5a1b546..cea3e43c 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc" + "package_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index 2efe37c7..f2ef3851 100644 --- a/registry/packages/yao-meta-skill.json +++ b/registry/packages/yao-meta-skill.json @@ -16,7 +16,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "package_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { diff --git a/reports/adaptation_proposals.json b/reports/adaptation_proposals.json index 594c30d5..55deb9b3 100644 --- a/reports/adaptation_proposals.json +++ b/reports/adaptation_proposals.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17", + "generated_at": "2026-06-16T20:58:28Z", "skill_dir": ".", "source_patterns": "reports/user_patterns.json", "pattern_count": 5, diff --git a/reports/adaptation_proposals.md b/reports/adaptation_proposals.md index 974c14dc..9f165538 100644 --- a/reports/adaptation_proposals.md +++ b/reports/adaptation_proposals.md @@ -1,6 +1,6 @@ # Adaptation Proposals -- Generated at: `2026-06-17` +- Generated at: `2026-06-16T20:58:28Z` - Pattern report: `reports/user_patterns.json` - Proposal only: `true` - Writes repository files: `false` diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json index c0941ae7..37100b8e 100644 --- a/reports/adoption_drift_report.json +++ b/reports/adoption_drift_report.json @@ -1,7 +1,7 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-16T20:48:23Z", + "generated_at": "2026-06-16T20:58:58Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", diff --git a/reports/architecture_maintainability.json b/reports/architecture_maintainability.json index db54c9f5..df659b1f 100644 --- a/reports/architecture_maintainability.json +++ b/reports/architecture_maintainability.json @@ -4,10 +4,10 @@ "generated_at": "2026-06-13", "skill_dir": ".", "summary": { - "python_file_count": 227, - "script_file_count": 151, + "python_file_count": 228, + "script_file_count": 152, "test_file_count": 76, - "internal_module_count": 67, + "internal_module_count": 68, "cli_script_count": 86, "command_handler_count": 68, "entrypoint_command_handler_count": 18, @@ -18,7 +18,7 @@ "block_line_threshold": 1500, "largest_file_lines": 696, "watchlist_count": 0, - "early_watchlist_count": 2, + "early_watchlist_count": 3, "hotspot_count": 0, "blocker_count": 0, "decision": "pass" @@ -40,6 +40,14 @@ "early_watch": true, "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." }, + { + "path": "tests/verify_evidence_consistency.py", + "lines": 609, + "kind": "test", + "severity": "pass", + "early_watch": true, + "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." + }, { "path": "tests/verify_output_review_adjudication.py", "lines": 599, @@ -80,6 +88,14 @@ "early_watch": false, "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." }, + { + "path": "scripts/render_evidence_consistency.py", + "lines": 579, + "kind": "cli-script", + "severity": "pass", + "early_watch": false, + "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." + }, { "path": "tests/verify_world_class_evidence_ledger.py", "lines": 579, @@ -96,14 +112,6 @@ "early_watch": false, "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." }, - { - "path": "scripts/render_evidence_consistency.py", - "lines": 571, - "kind": "cli-script", - "severity": "pass", - "early_watch": false, - "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." - }, { "path": "scripts/render_review_studio.py", "lines": 568, @@ -111,14 +119,6 @@ "severity": "pass", "early_watch": false, "recommendation": "Move data loading and large section renderers into focused review_studio_* modules." - }, - { - "path": "scripts/adjudicate_output_review.py", - "lines": 566, - "kind": "cli-script", - "severity": "pass", - "early_watch": false, - "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." } ], "watchlist": [], @@ -138,6 +138,14 @@ "severity": "pass", "early_watch": true, "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." + }, + { + "path": "tests/verify_evidence_consistency.py", + "lines": 609, + "kind": "test", + "severity": "pass", + "early_watch": true, + "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." } ], "hotspots": [], diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md index 651b320c..328f1a53 100644 --- a/reports/architecture_maintainability.md +++ b/reports/architecture_maintainability.md @@ -5,17 +5,17 @@ Generated at: `2026-06-13` ## Summary - decision: `pass` -- python files: `227` -- scripts: `151` +- python files: `228` +- scripts: `152` - tests: `76` -- internal modules: `67` +- internal modules: `68` - CLI scripts: `86` - Yao CLI command handlers: `68` - entrypoint command handlers: `18` - command modules: `6` - largest file lines: `696` - early watch threshold lines: `600` -- early watchlist: `2` +- early watchlist: `3` - watch threshold lines: `720` - watchlist: `0` - hotspots: `0` @@ -37,6 +37,7 @@ No near-threshold files found. | --- | ---: | --- | --- | | `tests/verify_yao_cli.py` | `696` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | | `tests/verify_world_class_evidence_intake.py` | `690` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | +| `tests/verify_evidence_consistency.py` | `609` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | ## Largest Files @@ -44,16 +45,16 @@ No near-threshold files found. | --- | ---: | --- | --- | | `tests/verify_yao_cli.py` | `696` | `test` | `pass` | | `tests/verify_world_class_evidence_intake.py` | `690` | `test` | `pass` | +| `tests/verify_evidence_consistency.py` | `609` | `test` | `pass` | | `tests/verify_output_review_adjudication.py` | `599` | `test` | `pass` | | `scripts/render_skill_overview.py` | `588` | `cli-script` | `pass` | | `scripts/build_skill_atlas.py` | `586` | `cli-script` | `pass` | | `scripts/optimize_description.py` | `585` | `cli-script` | `pass` | | `scripts/trust_check.py` | `582` | `cli-script` | `pass` | +| `scripts/render_evidence_consistency.py` | `579` | `cli-script` | `pass` | | `tests/verify_world_class_evidence_ledger.py` | `579` | `test` | `pass` | | `scripts/world_class_submission_kit_rendering.py` | `576` | `internal-module` | `pass` | -| `scripts/render_evidence_consistency.py` | `571` | `cli-script` | `pass` | | `scripts/render_review_studio.py` | `568` | `cli-script` | `pass` | -| `scripts/adjudicate_output_review.py` | `566` | `cli-script` | `pass` | ## Release Rule diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index f89dadfe..ccc28440 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,43 +3,48 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "0f97b66ed83c74eb82198744292b8da166612d78", + "commit": "c30882468f45c7e78bef73e0ada161fd1fbaef79", "git_status": { "available": true, "dirty": true, - "changed_file_count": 17, + "changed_file_count": 64, "generated_dirty": true, - "generated_changed_file_count": 17, - "source_dirty": false, - "source_changed_file_count": 0, + "generated_changed_file_count": 60, + "source_dirty": true, + "source_changed_file_count": 4, "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", " M reports/adaptation_proposals.json", " M reports/adaptation_proposals.md", + " M reports/adoption_drift_report.json", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", + " M reports/compiled_targets.json", " M reports/context_budget.json", - " M reports/evidence_consistency.json", - " M reports/output_execution_runs.json", - " M reports/output_execution_runs.md", - " M reports/review-studio.html", - " M reports/review-studio.json", - " M reports/review-viewer.json", - " M reports/skill-interpretation.json" + " M reports/context_budget.md" + ], + "source_sample": [ + " M scripts/render_evidence_consistency.py", + " M tests/verify_architecture_maintainability.py", + " M tests/verify_evidence_consistency.py", + "?? scripts/evidence_consistency_phase_queue.py" ], - "source_sample": [], "generated_sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", " M reports/adaptation_proposals.json", " M reports/adaptation_proposals.md", + " M reports/adoption_drift_report.json", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", + " M reports/compiled_targets.json", " M reports/context_budget.json", - " M reports/evidence_consistency.json", - " M reports/output_execution_runs.json", - " M reports/output_execution_runs.md", - " M reports/review-studio.html", - " M reports/review-studio.json", - " M reports/review-viewer.json", - " M reports/skill-interpretation.json" + " M reports/context_budget.md" ], "generated_dirty_prefixes": [ "dist/", @@ -53,12 +58,12 @@ }, "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": "70140015193af060a6a111a5f18e5b069a16e8b2a47de84776c564d640830f93", - "source_contract_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "evidence_bundle_sha256": "0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd", + "source_contract_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, @@ -77,18 +82,19 @@ "world_class_source_pass_count": 10, "world_class_source_blocked_count": 9, "public_claim_ready": false, - "public_claim_blocker_count": 4, + "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 17, - "source_tree_dirty": false, - "source_changed_file_count": 0, + "changed_file_count": 64, + "source_tree_dirty": true, + "source_changed_file_count": 4, "generated_tree_dirty": true, - "generated_changed_file_count": 17 + "generated_changed_file_count": 60 }, "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)", @@ -97,12 +103,12 @@ "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": "0f97b66ed83c74eb82198744292b8da166612d78", + "ready": false, + "commit": "c30882468f45c7e78bef73e0ada161fd1fbaef79", "status_scope": "generation-time status before this report is written", - "source_changed_file_count": 0, - "generated_changed_file_count": 17, - "reason": "only generated evidence artifacts were dirty at generation time" + "source_changed_file_count": 4, + "generated_changed_file_count": 60, + "reason": "source files were dirty at generation time" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -110,7 +116,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "70140015193af060a6a111a5f18e5b069a16e8b2a47de84776c564d640830f93" + "sha256": "0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -183,8 +189,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7965, - "sha256": "428b1ecabe160d6185bb8eaece93563d9f4aa6091b484fb7e3552f51c29166af" + "bytes": 7967, + "sha256": "615d4b9ec6fb8d487c98e06ffb8cdbe7d34b08b07a2d9ea069eee3cdd4edc0a9" }, { "label": "blind_review", @@ -218,22 +224,22 @@ "label": "trust_report", "path": "reports/security_trust_report.json", "exists": true, - "bytes": 136375, - "sha256": "08c2d3659e8a3a05ddc4be6da0a533970b09f6017efbe508ed311d189fe69726" + "bytes": 136999, + "sha256": "a44deb1fb680973315225900381bb1d09b71352fca1bed3a99df60393340c6fc" }, { "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, - "bytes": 29848, - "sha256": "4dc6cc6e37038493bdd01df3ecc043c90efefc0a4d4932525adc8f4053c1affc" + "bytes": 29983, + "sha256": "cb95afb7d7cc89ec865364f28ef499acadad39afafb9a1494acc118def9201a0" }, { "label": "registry_audit", "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "c5dd375176e01291baf0bbcb1dc5c7eb65a3ce59c4ebcd655c94b91481983380" + "sha256": "af63529bb20c444d93b81a278be60ff89b2f49245f0c557cf574cc2dfd6d1e2e" }, { "label": "package_verification", @@ -247,14 +253,14 @@ "path": "reports/install_simulation.json", "exists": true, "bytes": 8758, - "sha256": "f71d25a6ac3e731412f435fd722b343e616def12c013a07f87e57ea4a7551a96" + "sha256": "d2bea19ea46f3eff07ad50cd76b82816983c065db59bf0ae35ac1fa418206db0" }, { "label": "skill_os2_audit", "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14466, - "sha256": "432b795c6ccc1db3c2815b97220675a7c27facbe9c8334ed0158627b7f2214b7" + "sha256": "ad57230481ed929c651fcc1087f20ec2e6c036d7cfe85817f7709c030c5b3b32" }, { "label": "world_class_evidence_plan", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 916b1c3c..68d135f2 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,20 +1,20 @@ # Benchmark Reproducibility Generated at: `2026-06-17` -Commit: `0f97b66ed83c74eb82198744292b8da166612d78` +Commit: `c30882468f45c7e78bef73e0ada161fd1fbaef79` Working tree dirty at generation: `true` -Source tree dirty at generation: `false` +Source tree dirty at generation: `true` Generated evidence dirty at generation: `true` -Evidence bundle SHA256: `70140015193af060a6a111a5f18e5b069a16e8b2a47de84776c564d640830f93` +Evidence bundle SHA256: `0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd` ## Summary - reproducibility ready: `true` -- release lock ready: `true` +- release lock ready: `false` - methodology complete: `true` - required artifacts: `25` - missing artifacts: `0` -- source contract sha256: `453ca3f4c546` +- source contract sha256: `5533575c144f` - archive sha256: `7db44f059844` - output cases: `5` - disclosed failure cases: `3` @@ -24,10 +24,10 @@ Evidence bundle SHA256: `70140015193af060a6a111a5f18e5b069a16e8b2a47de84776c564d - world-class ready: `false` - world-class source checks: `10` pass / `19` total; `9` blocked - public claim ready: `false` -- public claim blockers: `4` -- changed files at generation: `17` -- source changed files at generation: `0` -- generated changed files at generation: `17` +- public claim blockers: `5` +- changed files at generation: `64` +- source changed files at generation: `4` +- generated changed files at generation: `60` This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit and dirty samples are generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below. @@ -39,6 +39,7 @@ 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) | @@ -46,15 +47,15 @@ This report proves local benchmark reproducibility only. It keeps external provi ## Release Lock -- ready: `true` -- reason: only generated evidence artifacts were dirty at generation time +- ready: `false` +- reason: source files were dirty at generation time - status scope: generation-time status before this report is written ## Evidence Bundle - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `25` / `25` -- sha256: `70140015193af060a6a111a5f18e5b069a16e8b2a47de84776c564d640830f93` +- sha256: `0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd` ## Methodology Sections @@ -76,17 +77,17 @@ 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 | `428b1ecabe16` | +| output_execution | `reports/output_execution_runs.json` | present | `615d4b9ec6fb` | | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` | | review_adjudication | `reports/output_review_adjudication.json` | present | `91fd88dd9b0f` | | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` | | runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` | -| trust_report | `reports/security_trust_report.json` | present | `08c2d3659e8a` | -| python_compatibility | `reports/python_compatibility.json` | present | `4dc6cc6e3703` | -| registry_audit | `reports/registry_audit.json` | present | `c5dd375176e0` | +| trust_report | `reports/security_trust_report.json` | present | `a44deb1fb680` | +| python_compatibility | `reports/python_compatibility.json` | present | `cb95afb7d7cc` | +| registry_audit | `reports/registry_audit.json` | present | `af63529bb20c` | | package_verification | `reports/package_verification.json` | present | `7aa6c25e8154` | -| install_simulation | `reports/install_simulation.json` | present | `f71d25a6ac3e` | -| skill_os2_audit | `reports/skill_os2_audit.json` | present | `432b795c6ccc` | +| install_simulation | `reports/install_simulation.json` | present | `d2bea19ea46f` | +| skill_os2_audit | `reports/skill_os2_audit.json` | present | `ad57230481ed` | | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `d0ab41774295` | | world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `fc4c3e398ad0` | | world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `1a939bdd1f4a` | diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json index 13db711a..b30ed7df 100644 --- a/reports/compiled_targets.json +++ b/reports/compiled_targets.json @@ -172,6 +172,7 @@ "scripts/emit_telemetry_event.py", "scripts/evidence_consistency_artifact_roles.py", "scripts/evidence_consistency_core.py", + "scripts/evidence_consistency_phase_queue.py", "scripts/evidence_consistency_release.py", "scripts/evidence_consistency_skill_os2_review.py", "scripts/evidence_consistency_world_class.py", @@ -356,7 +357,7 @@ ], "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 } @@ -629,7 +630,7 @@ "strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -640,7 +641,7 @@ }, "scripts": { "strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -885,7 +886,7 @@ "strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -896,7 +897,7 @@ }, "scripts": { "strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -1125,6 +1126,7 @@ "scripts/emit_telemetry_event.py", "scripts/evidence_consistency_artifact_roles.py", "scripts/evidence_consistency_core.py", + "scripts/evidence_consistency_phase_queue.py", "scripts/evidence_consistency_release.py", "scripts/evidence_consistency_skill_os2_review.py", "scripts/evidence_consistency_world_class.py", @@ -1309,7 +1311,7 @@ ], "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 } @@ -1582,7 +1584,7 @@ "strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -1593,7 +1595,7 @@ }, "scripts": { "strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -1838,7 +1840,7 @@ "strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -1849,7 +1851,7 @@ }, "scripts": { "strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -2078,6 +2080,7 @@ "scripts/emit_telemetry_event.py", "scripts/evidence_consistency_artifact_roles.py", "scripts/evidence_consistency_core.py", + "scripts/evidence_consistency_phase_queue.py", "scripts/evidence_consistency_release.py", "scripts/evidence_consistency_skill_os2_review.py", "scripts/evidence_consistency_world_class.py", @@ -2262,7 +2265,7 @@ ], "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 } @@ -2535,7 +2538,7 @@ "strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -2545,7 +2548,7 @@ }, "scripts": { "strategy": "Expose script and permission metadata for downstream clients or installers to enforce.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -2784,7 +2787,7 @@ "strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -2794,7 +2797,7 @@ }, "scripts": { "strategy": "Expose script and permission metadata for downstream clients or installers to enforce.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -3015,6 +3018,7 @@ "scripts/emit_telemetry_event.py", "scripts/evidence_consistency_artifact_roles.py", "scripts/evidence_consistency_core.py", + "scripts/evidence_consistency_phase_queue.py", "scripts/evidence_consistency_release.py", "scripts/evidence_consistency_skill_os2_review.py", "scripts/evidence_consistency_world_class.py", @@ -3199,7 +3203,7 @@ ], "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 } @@ -3472,7 +3476,7 @@ "strategy": "Keep optional directories as relative resources next to SKILL.md.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -3483,7 +3487,7 @@ }, "scripts": { "strategy": "Scripts remain local optional resources and should advertise --help when executable.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -3721,7 +3725,7 @@ "strategy": "Keep optional directories as relative resources next to SKILL.md.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -3732,7 +3736,7 @@ }, "scripts": { "strategy": "Scripts remain local optional resources and should advertise --help when executable.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -3952,6 +3956,7 @@ "scripts/emit_telemetry_event.py", "scripts/evidence_consistency_artifact_roles.py", "scripts/evidence_consistency_core.py", + "scripts/evidence_consistency_phase_queue.py", "scripts/evidence_consistency_release.py", "scripts/evidence_consistency_skill_os2_review.py", "scripts/evidence_consistency_world_class.py", @@ -4136,7 +4141,7 @@ ], "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 } @@ -4409,7 +4414,7 @@ "strategy": "Install as project or user scoped skill source, preserving relative references and scripts.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -4420,7 +4425,7 @@ }, "scripts": { "strategy": "Scripts require workspace trust and operator/client approval outside this compiler.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -4662,7 +4667,7 @@ "strategy": "Install as project or user scoped skill source, preserving relative references and scripts.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -4673,7 +4678,7 @@ }, "scripts": { "strategy": "Scripts require workspace trust and operator/client approval outside this compiler.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { diff --git a/reports/context_budget.json b/reports/context_budget.json index f4d96f3d..22efedac 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -6,16 +6,16 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1118744, + "other_text_tokens": 1121236, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1119541, - "deferred_resource_tokens": 511351, + "estimated_total_text_tokens": 1122033, + "deferred_resource_tokens": 512782, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 450048, - "file_count": 151 + "estimated_tokens": 451479, + "file_count": 152 }, { "path": "references", @@ -36,8 +36,8 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 450048, - "file_count": 151 + "estimated_tokens": 451479, + "file_count": 152 } ], "deferred_resource_governance": { @@ -59,14 +59,14 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 450048, - "file_count": 151, + "estimated_tokens": 451479, + "file_count": 152, "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": 708, + "relevant_file_count": 710, "unused_resource_dirs": [], "quality_signal_points": 130, "quality_density": 131.3 diff --git a/reports/context_budget.md b/reports/context_budget.md index 702b4753..6e25ea2e 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 | 511351 | `governed` | scripts:450048 | 131.3 | - | ok | +| root | `.` | `production` | 1000 | 990 | 797 | 512782 | `governed` | scripts:451479 | 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 14b3acc6..b4fc88de 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -8,12 +8,12 @@ "budget_limit": 1000, "initial_tokens": 990, "skill_body_tokens": 797, - "deferred_resource_tokens": 511351, + "deferred_resource_tokens": 512782, "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 450048, - "file_count": 151 + "estimated_tokens": 451479, + "file_count": 152 } ], "deferred_resource_governance": { @@ -35,8 +35,8 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 450048, - "file_count": 151, + "estimated_tokens": 451479, + "file_count": 152, "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 fb9bc2c3..4c960794 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -4,14 +4,14 @@ "generated_at": "2026-06-17", "skill_dir": ".", "summary": { - "check_count": 36, - "pass_count": 36, + "check_count": 37, + "pass_count": 37, "warn_count": 0, "fail_count": 0, "decision": "consistent" }, "status_counts": { - "pass": 36, + "pass": 37, "warn": 0, "fail": 0 }, @@ -189,12 +189,12 @@ "status": "pass", "expected": { "status": "pass", - "detail": "initial load 990/1000; deferred 511351/120000; top deferred scripts 450048; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 512782/120000; top deferred scripts 451479; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "actual": { "status": "pass", - "detail": "initial load 990/1000; deferred 511351/120000; top deferred scripts 450048; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 512782/120000; top deferred scripts 451479; 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 source dirty state", "status": "pass", - "expected": true, - "actual": true, + "expected": false, + "actual": false, "paths": [ "reports/benchmark_reproducibility.json" ], @@ -222,7 +222,7 @@ "actual": { "available": true, "clean": false, - "changed_file_count": 14 + "changed_file_count": 64 }, "paths": [ "reports/benchmark_reproducibility.json" @@ -263,8 +263,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "0f97b66ed83c74eb82198744292b8da166612d78", - "actual": "0f97b66ed83c74eb82198744292b8da166612d78", + "expected": "c30882468f45c7e78bef73e0ada161fd1fbaef79", + "actual": "c30882468f45c7e78bef73e0ada161fd1fbaef79", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -276,30 +276,30 @@ "label": "overview embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "source_contract_sha256": "e1d05a0ec120c6955b331e25941b0ee8a7ffcc0d0d6e22b359367a4312644b37", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "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": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "source_contract_sha256": "e1d05a0ec120c6955b331e25941b0ee8a7ffcc0d0d6e22b359367a4312644b37", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -313,13 +313,13 @@ "status": "pass", "expected": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, + "adoption_rate": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "source_types": { "manual": 1 @@ -327,13 +327,13 @@ }, "actual": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, + "adoption_rate": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "source_types": { "manual": 1 @@ -356,8 +356,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -368,8 +368,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -389,7 +389,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 19, - "source_pass_count": 10 + "source_pass_count": 9 }, "actual": { "ready": false, @@ -397,7 +397,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 19, - "source_pass_count": 10 + "source_pass_count": 9 }, "paths": [ "reports/world_class_evidence_ledger.json", @@ -409,8 +409,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "0f97b66ed83c74eb82198744292b8da166612d78", - "actual": "0f97b66ed83c74eb82198744292b8da166612d78", + "expected": "c30882468f45c7e78bef73e0ada161fd1fbaef79", + "actual": "c30882468f45c7e78bef73e0ada161fd1fbaef79", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -422,30 +422,30 @@ "label": "interpretation embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "source_contract_sha256": "e1d05a0ec120c6955b331e25941b0ee8a7ffcc0d0d6e22b359367a4312644b37", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "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": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "source_contract_sha256": "e1d05a0ec120c6955b331e25941b0ee8a7ffcc0d0d6e22b359367a4312644b37", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -459,13 +459,13 @@ "status": "pass", "expected": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, + "adoption_rate": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "source_types": { "manual": 1 @@ -473,13 +473,13 @@ }, "actual": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, + "adoption_rate": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "source_types": { "manual": 1 @@ -502,8 +502,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -514,8 +514,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -535,7 +535,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 19, - "source_pass_count": 10 + "source_pass_count": 9 }, "actual": { "ready": false, @@ -543,7 +543,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 19, - "source_pass_count": 10 + "source_pass_count": 9 }, "paths": [ "reports/world_class_evidence_ledger.json", @@ -1342,7 +1342,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 19, - "source_pass_count": 10, + "source_pass_count": 9, "conclusion_zh": "世界级证据尚未完成:4 项待补,0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -1402,7 +1402,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -1416,7 +1417,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 19, - "source_pass_count": 10, + "source_pass_count": 9, "conclusion_zh": "世界级证据尚未完成:4 项待补,0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -1476,7 +1477,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -1527,7 +1529,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 151 + "file_count": 152 }, { "path": "evals", @@ -1542,7 +1544,7 @@ "file_count": 235 } ], - "file_count": 454, + "file_count": 455, "folder_count": 4, "distribution": [ { @@ -1567,7 +1569,7 @@ }, { "label": "scripts", - "value": 151 + "value": 152 }, { "label": "evals", @@ -1615,7 +1617,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 151 + "file_count": 152 }, { "path": "evals", @@ -1630,7 +1632,7 @@ "file_count": 235 } ], - "file_count": 454, + "file_count": 455, "folder_count": 4, "distribution": [ { @@ -1655,7 +1657,7 @@ }, { "label": "scripts", - "value": 151 + "value": 152 }, { "label": "evals", @@ -1826,15 +1828,15 @@ "expected": { "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "public_claim_ready": false }, "actual": { "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, - "world_class_source_pass_count": 10, - "world_class_source_blocked_count": 9, + "world_class_source_pass_count": 9, + "world_class_source_blocked_count": 10, "public_claim_ready": false }, "paths": [ @@ -1850,8 +1852,8 @@ "expected": { "pending_count": 4, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "ready_to_claim_world_class": false, "preflight_counts_as_evidence": false, "credential_value_exposed": false @@ -1859,8 +1861,8 @@ "actual": { "pending_count": 4, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "ready_to_claim_world_class": false, "preflight_counts_as_evidence": false, "credential_value_exposed": false @@ -2029,6 +2031,684 @@ ], "detail": "The Review Studio world-class action card must carry the same submission-ref versus supporting-evidence contract as the preflight handoff." }, + { + "key": "world-class-phase-queue-consistency", + "label": "World-class phase queues mirror repair rows", + "status": "pass", + "expected": { + "summary": { + "phase_queue_count": 2, + "phase_queue_blocked_count": 2, + "phase_queue_row_count": 14, + "phase_queue_next_phase": "unblock-access", + "phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer", + "phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "phase_queue_counts_as_completion": false + }, + "top_level_phase_queue": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 4, + "row_count": 4, + "owners": [ + "Browser/Chrome/IDE/provider client integrator", + "human reviewer", + "operator with provider credentials", + "target client or installer integrator" + ], + "evidence_keys": [ + "human-adjudication", + "native-client-telemetry", + "native-permission-enforcement", + "provider-holdout" + ], + "next_action_id": "human-adjudication-precheck-human-reviewer", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 10, + "row_count": 10, + "owners": [ + "Browser/Chrome/IDE/provider client integrator", + "human reviewer", + "operator with provider credentials", + "target client or installer integrator" + ], + "evidence_keys": [ + "human-adjudication", + "native-client-telemetry", + "native-permission-enforcement", + "provider-holdout" + ], + "next_action_id": "human-adjudication-source-check-blind_review_attested", + "verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ], + "item_phase_queues": { + "provider-holdout": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "operator with provider credentials" + ], + "evidence_keys": [ + "provider-holdout" + ], + "next_action_id": "provider-holdout-precheck-openai-api-key", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 2, + "row_count": 2, + "owners": [ + "operator with provider credentials" + ], + "evidence_keys": [ + "provider-holdout" + ], + "next_action_id": "provider-holdout-source-check-model_executed_count", + "verification_command": "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60 && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ], + "human-adjudication": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "human reviewer" + ], + "evidence_keys": [ + "human-adjudication" + ], + "next_action_id": "human-adjudication-precheck-human-reviewer", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 5, + "row_count": 5, + "owners": [ + "human reviewer" + ], + "evidence_keys": [ + "human-adjudication" + ], + "next_action_id": "human-adjudication-source-check-blind_review_attested", + "verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ], + "native-permission-enforcement": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "target client or installer integrator" + ], + "evidence_keys": [ + "native-permission-enforcement" + ], + "next_action_id": "native-permission-enforcement-precheck-native-guard", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "target client or installer integrator" + ], + "evidence_keys": [ + "native-permission-enforcement" + ], + "next_action_id": "native-permission-enforcement-source-check-native_enforcement_count", + "verification_command": "python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ], + "native-client-telemetry": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "Browser/Chrome/IDE/provider client integrator" + ], + "evidence_keys": [ + "native-client-telemetry" + ], + "next_action_id": "native-client-telemetry-precheck-external-client", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 2, + "row_count": 2, + "owners": [ + "Browser/Chrome/IDE/provider client integrator" + ], + "evidence_keys": [ + "native-client-telemetry" + ], + "next_action_id": "native-client-telemetry-source-check-adoption_sample_count", + "verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ] + }, + "phase_queue_counts_as_completion": false, + "review_studio_phase_queues": { + "provider-holdout": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "operator with provider credentials" + ], + "evidence_keys": [ + "provider-holdout" + ], + "next_action_id": "provider-holdout-precheck-openai-api-key", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 2, + "row_count": 2, + "owners": [ + "operator with provider credentials" + ], + "evidence_keys": [ + "provider-holdout" + ], + "next_action_id": "provider-holdout-source-check-model_executed_count", + "verification_command": "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60 && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ], + "human-adjudication": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "human reviewer" + ], + "evidence_keys": [ + "human-adjudication" + ], + "next_action_id": "human-adjudication-precheck-human-reviewer", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 5, + "row_count": 5, + "owners": [ + "human reviewer" + ], + "evidence_keys": [ + "human-adjudication" + ], + "next_action_id": "human-adjudication-source-check-blind_review_attested", + "verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ], + "native-permission-enforcement": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "target client or installer integrator" + ], + "evidence_keys": [ + "native-permission-enforcement" + ], + "next_action_id": "native-permission-enforcement-precheck-native-guard", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "target client or installer integrator" + ], + "evidence_keys": [ + "native-permission-enforcement" + ], + "next_action_id": "native-permission-enforcement-source-check-native_enforcement_count", + "verification_command": "python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ], + "native-client-telemetry": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "Browser/Chrome/IDE/provider client integrator" + ], + "evidence_keys": [ + "native-client-telemetry" + ], + "next_action_id": "native-client-telemetry-precheck-external-client", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 2, + "row_count": 2, + "owners": [ + "Browser/Chrome/IDE/provider client integrator" + ], + "evidence_keys": [ + "native-client-telemetry" + ], + "next_action_id": "native-client-telemetry-source-check-adoption_sample_count", + "verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ] + } + }, + "actual": { + "summary": { + "phase_queue_count": 2, + "phase_queue_blocked_count": 2, + "phase_queue_row_count": 14, + "phase_queue_next_phase": "unblock-access", + "phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer", + "phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "phase_queue_counts_as_completion": false + }, + "top_level_phase_queue": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 4, + "row_count": 4, + "owners": [ + "Browser/Chrome/IDE/provider client integrator", + "human reviewer", + "operator with provider credentials", + "target client or installer integrator" + ], + "evidence_keys": [ + "human-adjudication", + "native-client-telemetry", + "native-permission-enforcement", + "provider-holdout" + ], + "next_action_id": "human-adjudication-precheck-human-reviewer", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 10, + "row_count": 10, + "owners": [ + "Browser/Chrome/IDE/provider client integrator", + "human reviewer", + "operator with provider credentials", + "target client or installer integrator" + ], + "evidence_keys": [ + "human-adjudication", + "native-client-telemetry", + "native-permission-enforcement", + "provider-holdout" + ], + "next_action_id": "human-adjudication-source-check-blind_review_attested", + "verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ], + "item_phase_queues": { + "provider-holdout": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "operator with provider credentials" + ], + "evidence_keys": [ + "provider-holdout" + ], + "next_action_id": "provider-holdout-precheck-openai-api-key", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 2, + "row_count": 2, + "owners": [ + "operator with provider credentials" + ], + "evidence_keys": [ + "provider-holdout" + ], + "next_action_id": "provider-holdout-source-check-model_executed_count", + "verification_command": "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60 && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ], + "human-adjudication": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "human reviewer" + ], + "evidence_keys": [ + "human-adjudication" + ], + "next_action_id": "human-adjudication-precheck-human-reviewer", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 5, + "row_count": 5, + "owners": [ + "human reviewer" + ], + "evidence_keys": [ + "human-adjudication" + ], + "next_action_id": "human-adjudication-source-check-blind_review_attested", + "verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ], + "native-permission-enforcement": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "target client or installer integrator" + ], + "evidence_keys": [ + "native-permission-enforcement" + ], + "next_action_id": "native-permission-enforcement-precheck-native-guard", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "target client or installer integrator" + ], + "evidence_keys": [ + "native-permission-enforcement" + ], + "next_action_id": "native-permission-enforcement-source-check-native_enforcement_count", + "verification_command": "python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ], + "native-client-telemetry": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "Browser/Chrome/IDE/provider client integrator" + ], + "evidence_keys": [ + "native-client-telemetry" + ], + "next_action_id": "native-client-telemetry-precheck-external-client", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 2, + "row_count": 2, + "owners": [ + "Browser/Chrome/IDE/provider client integrator" + ], + "evidence_keys": [ + "native-client-telemetry" + ], + "next_action_id": "native-client-telemetry-source-check-adoption_sample_count", + "verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ] + }, + "review_studio_phase_queues": { + "provider-holdout": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "operator with provider credentials" + ], + "evidence_keys": [ + "provider-holdout" + ], + "next_action_id": "provider-holdout-precheck-openai-api-key", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 2, + "row_count": 2, + "owners": [ + "operator with provider credentials" + ], + "evidence_keys": [ + "provider-holdout" + ], + "next_action_id": "provider-holdout-source-check-model_executed_count", + "verification_command": "python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60 && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ], + "human-adjudication": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "human reviewer" + ], + "evidence_keys": [ + "human-adjudication" + ], + "next_action_id": "human-adjudication-precheck-human-reviewer", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 5, + "row_count": 5, + "owners": [ + "human reviewer" + ], + "evidence_keys": [ + "human-adjudication" + ], + "next_action_id": "human-adjudication-source-check-blind_review_attested", + "verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ], + "native-permission-enforcement": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "target client or installer integrator" + ], + "evidence_keys": [ + "native-permission-enforcement" + ], + "next_action_id": "native-permission-enforcement-precheck-native-guard", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "target client or installer integrator" + ], + "evidence_keys": [ + "native-permission-enforcement" + ], + "next_action_id": "native-permission-enforcement-source-check-native_enforcement_count", + "verification_command": "python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ], + "native-client-telemetry": [ + { + "phase": "unblock-access", + "priority": 20, + "status": "blocked", + "blocked_count": 1, + "row_count": 1, + "owners": [ + "Browser/Chrome/IDE/provider client integrator" + ], + "evidence_keys": [ + "native-client-telemetry" + ], + "next_action_id": "native-client-telemetry-precheck-external-client", + "verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + }, + { + "phase": "collect-source", + "priority": 40, + "status": "blocked", + "blocked_count": 2, + "row_count": 2, + "owners": [ + "Browser/Chrome/IDE/provider client integrator" + ], + "evidence_keys": [ + "native-client-telemetry" + ], + "next_action_id": "native-client-telemetry-source-check-adoption_sample_count", + "verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions", + "counts_as_completion": false + } + ] + }, + "phase_queue_counts_as_completion": false + }, + "paths": [ + "reports/world_class_evidence_preflight.json", + "reports/review-studio.json" + ], + "detail": "Phase queues must be derived from repair rows in preflight and mirrored into Review Studio without counting queue guidance as completion evidence." + }, { "key": "review-studio-no-overclaim", "label": "Review Studio does not overclaim pending world-class evidence", @@ -2114,8 +2794,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "plan_keys": [ "human-adjudication", "native-client-telemetry", @@ -2263,8 +2943,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 19, - "source_pass_count": 10, - "source_blocked_count": 9, + "source_pass_count": 9, + "source_blocked_count": 10, "plan_keys": [ "human-adjudication", "native-client-telemetry", @@ -2419,8 +3099,8 @@ "score `91`", "`16` gates", "`3` warnings", - "`65` declared internal modules", - "`86 / 86` CLI help smoke checks passing across `151` scripts", + "`66` declared internal modules", + "`86 / 86` CLI help smoke checks passing across `152` scripts", "`689` zip entries", "archive with `689` entries", "`12` installer permission checks enforced", diff --git a/reports/evidence_consistency.md b/reports/evidence_consistency.md index a711e77c..9baa139d 100644 --- a/reports/evidence_consistency.md +++ b/reports/evidence_consistency.md @@ -5,8 +5,8 @@ Generated at: `2026-06-17` ## Summary - decision: `consistent` -- checks: `36` -- pass: `36` +- checks: `37` +- pass: `37` - warn: `0` - fail: `0` @@ -48,6 +48,7 @@ This gate compares generated evidence reports against each other. It does not cr | Preflight mirrors ledger without accepting evidence | `pass` | Collection preflight may help operators gather evidence, but it must not print secrets or change world-class readiness. | `reports/world_class_evidence_ledger.json`, `reports/world_class_evidence_preflight.json` | | Preflight exposes a safe submission-kit handoff | `pass` | Preflight must give operators the exact draft, SHA-prefill, intake, review, ledger, and claim-guard commands without letting drafts, prefill, or submissions count as accepted evidence. | `reports/world_class_evidence_preflight.json`, `reports/world_class_evidence_preflight.html` | | Review Studio mirrors preflight artifact roles | `pass` | The Review Studio world-class action card must carry the same submission-ref versus supporting-evidence contract as the preflight handoff. | `reports/world_class_evidence_preflight.json`, `reports/review-studio.json` | +| World-class phase queues mirror repair rows | `pass` | Phase queues must be derived from repair rows in preflight and mirrored into Review Studio without counting queue guidance as completion evidence. | `reports/world_class_evidence_preflight.json`, `reports/review-studio.json` | | Review Studio does not overclaim pending world-class evidence | `pass` | When world-class evidence is pending, Review Studio must stay in a review or warning posture. | `reports/world_class_evidence_ledger.json`, `reports/review-studio.json` | | Claim guard covers package and runtime claim surfaces | `pass` | The overclaim guard must scan package manifests, adapter metadata, security policy, and ledger surfaces before public readiness can be trusted. | `reports/world_class_claim_guard.json`, `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` | | World-class evidence workflows cover every pending ledger entry | `pass` | Every pending world-class evidence key must have matching plan, intake, submission review, operator runbook, and Review Studio actions without counting planned work as completion. | `reports/world_class_evidence_ledger.json`, `reports/world_class_evidence_plan.json`, `reports/world_class_evidence_intake.json`, `reports/world_class_submission_review.json`, `reports/world_class_operator_runbook.json`, `reports/review-studio.json` | diff --git a/reports/install_simulation.json b/reports/install_simulation.json index c35e725d..07a823e5 100644 --- a/reports/install_simulation.json +++ b/reports/install_simulation.json @@ -8,7 +8,7 @@ "installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill", "summary": { "archive_present": true, - "archive_entry_count": 690, + "archive_entry_count": 691, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 103c3576..f4927be0 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": 35.1, + "duration_ms": 31.72, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 45.06, + "duration_ms": 28.31, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 40.46, + "duration_ms": 28.59, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 36.35, + "duration_ms": 27.92, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 34.09, + "duration_ms": 28.16, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 37.27, + "duration_ms": 28.43, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 36.32, + "duration_ms": 28.62, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 36.26, + "duration_ms": 27.78, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.5, + "duration_ms": 27.76, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.55, + "duration_ms": 27.99, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index 4d169baa..19e65aa1 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 | 35.1 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 45.06 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 40.46 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 36.35 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 34.09 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 37.27 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 36.32 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 36.26 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 30.5 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 31.55 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 31.72 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 28.31 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 28.59 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 27.92 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 28.16 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 28.43 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 28.62 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 27.78 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 27.76 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 27.99 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/python_compatibility.json b/reports/python_compatibility.json index e2ddc932..f6400285 100644 --- a/reports/python_compatibility.json +++ b/reports/python_compatibility.json @@ -5,7 +5,7 @@ "root": ".", "summary": { "target_python": "3.11", - "file_count": 230, + "file_count": 231, "issue_count": 0, "syntax_error_count": 0, "fstring_311_violation_count": 0, @@ -178,6 +178,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/evidence_consistency_phase_queue.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/evidence_consistency_release.py", "ok": true, diff --git a/reports/python_compatibility.md b/reports/python_compatibility.md index 2977432f..6c208df8 100644 --- a/reports/python_compatibility.md +++ b/reports/python_compatibility.md @@ -6,7 +6,7 @@ Generated at: `2026-06-13` - decision: `pass` - target python: `3.11` -- files scanned: `230` +- files scanned: `231` - issues: `0` - syntax errors: `0` - f-string 3.11 violations: `0` diff --git a/reports/registry_audit.json b/reports/registry_audit.json index 201eec31..500e300b 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,7 +21,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "package_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc" + "package_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index b3699255..4a927c09 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,7 +6,7 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc` +- Package SHA256: `5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d` - Archive SHA256: `7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2` - Install simulated: `True` diff --git a/reports/review-studio.html b/reports/review-studio.html index 8d4309ef..6963892a 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -772,12 +772,12 @@

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

151 scripts scanned; secrets found

Py Compat0

230 files scanned for Python 3.11

Arch Debt0

696 largest lines; 0 watchlist; 2 early; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock true

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

182 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

689 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

152 scripts scanned; secrets found

Py Compat0

231 files scanned for Python 3.11

Arch Debt0

696 largest lines; 0 watchlist; 3 early; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock false

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

182 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

689 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 511351/120000; top deferred scripts 450048; 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; 151 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 230 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

227 Python files; 0 hotspots; 0 watchlist files; 2 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

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

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

权限探针

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

reports/runtime_permission_probes.json 证据
通过

组合治理

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

reports/skill_atlas.json 证据
通过

运营回路

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

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

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 10/19 pass; 9 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

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

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

发布路线

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

reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md 证据
+
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 512782/120000; top deferred scripts 451479; 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; 152 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 231 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

228 Python files; 0 hotspots; 0 watchlist files; 3 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

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

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

权限探针

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

reports/runtime_permission_probes.json 证据
通过

组合治理

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

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock 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 10/19 pass; 9 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

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

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

发布路线

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

@@ -844,17 +844,17 @@
-

上下文

initial load 990/1000; deferred 511351/120000; top deferred scripts 450048; resource governance governed; quality density 131.3

+

上下文

initial load 990/1000; deferred 512782/120000; top deferred scripts 451479; 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
151
网络脚本
3
Help 失败
0
包体哈希
453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc
+

信任报告

Secret
0
脚本数
152
网络脚本
3
Help 失败
0
包体哈希
5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d

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。

-

Python 兼容

目标 Python
3.11
文件数
230
问题数
0
语法错误
0
F-string 3.11
0
+

Python 兼容

目标 Python
3.11
文件数
231
问题数
0
语法错误
0
F-string 3.11
0

解释器边界

CI 和发布审查以 Python 3.11 兼容为底线;本地更高版本允许的新语法不能绕过兼容门禁。

@@ -874,14 +874,14 @@
-

运营回路

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

+

运营回路

1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock 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
100
漏触发
0
Bad Output Count
0
风险带
low
-

日常运维

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

周度队列

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

日常运维

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

周度队列

决策
curator-review
Week Id
2026-W25
日报数
2
唯一机会
5
待批准复核
1
提案复核
4
Top Score
88
发布锁
Writes Source Files
Auto Patch Enabled
@@ -914,8 +914,8 @@
-

公开声明

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

声明阻断

+

公开声明

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

声明阻断

diff --git a/reports/review-studio.json b/reports/review-studio.json index edbf8bd0..66a118fb 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -44,7 +44,7 @@ "key": "context-budget", "label": "上下文", "status": "pass", - "detail": "initial load 990/1000; deferred 511351/120000; top deferred scripts 450048; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 512782/120000; top deferred scripts 451479; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json", "link": "context_budget.md" }, @@ -60,7 +60,7 @@ "key": "trust-report", "label": "信任报告", "status": "pass", - "detail": "0 secrets; 151 scripts; 3 network-capable scripts; 0 help smoke failures", + "detail": "0 secrets; 152 scripts; 3 network-capable scripts; 0 help smoke failures", "evidence": "reports/security_trust_report.json", "link": "security_trust_report.md" }, @@ -68,7 +68,7 @@ "key": "python-compat", "label": "Python 兼容", "status": "pass", - "detail": "Python 3.11; 230 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards", + "detail": "Python 3.11; 231 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards", "evidence": "reports/python_compatibility.json", "link": "python_compatibility.md" }, @@ -76,7 +76,7 @@ "key": "architecture-maintainability", "label": "架构维护", "status": "pass", - "detail": "227 Python files; 0 hotspots; 0 watchlist files; 2 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint", + "detail": "228 Python files; 0 hotspots; 0 watchlist files; 3 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint", "evidence": "reports/architecture_maintainability.json", "link": "architecture_maintainability.md" }, @@ -108,7 +108,7 @@ "key": "operations-loop", "label": "运营回路", "status": "pass", - "detail": "1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true", + "detail": "1 metadata events; adoption 100.0; 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" }, @@ -1871,7 +1871,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 151 + "file_count": 152 }, { "path": "evals", @@ -1886,7 +1886,7 @@ "file_count": 235 } ], - "file_count": 454, + "file_count": 455, "folder_count": 4, "distribution": [ { @@ -1911,7 +1911,7 @@ }, { "label": "scripts", - "value": 151 + "value": 152 }, { "label": "evals", @@ -2041,7 +2041,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 151 + "file_count": 152 }, { "path": "evals", @@ -2363,12 +2363,12 @@ "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": "70140015193af060a6a111a5f18e5b069a16e8b2a47de84776c564d640830f93", - "source_contract_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "evidence_bundle_sha256": "0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd", + "source_contract_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, @@ -2387,15 +2387,15 @@ "world_class_source_pass_count": 10, "world_class_source_blocked_count": 9, "public_claim_ready": false, - "public_claim_blocker_count": 4, + "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 17, - "source_tree_dirty": false, - "source_changed_file_count": 0, + "changed_file_count": 64, + "source_tree_dirty": true, + "source_changed_file_count": 4, "generated_tree_dirty": true, - "generated_changed_file_count": 17 + "generated_changed_file_count": 60 }, - "commit": "0f97b66ed83c74eb82198744292b8da166612d78", + "commit": "c30882468f45c7e78bef73e0ada161fd1fbaef79", "missing_artifacts": [], "limitations": [ "The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.", @@ -2479,9 +2479,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 243, - "script_count": 151, - "internal_module_count": 65, + "scanned_files": 244, + "script_count": 152, + "internal_module_count": 66, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -2499,8 +2499,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 243, - "package_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc" + "package_hash_file_count": 244, + "package_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d" }, "skill_atlas": { "skill_count": 12, @@ -2538,7 +2538,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "package_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { @@ -2598,7 +2598,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 690, + "archive_entry_count": 691, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -2670,7 +2670,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc" + "to": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d" } ] }, @@ -5184,7 +5184,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 35.1, + "duration_ms": 31.72, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5212,7 +5212,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 45.06, + "duration_ms": 28.31, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5235,7 +5235,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 40.46, + "duration_ms": 28.59, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5263,7 +5263,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 36.35, + "duration_ms": 27.92, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5286,7 +5286,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 34.09, + "duration_ms": 28.16, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5314,7 +5314,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 37.27, + "duration_ms": 28.43, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5337,7 +5337,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 36.32, + "duration_ms": 28.62, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5364,7 +5364,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 36.26, + "duration_ms": 27.78, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5387,7 +5387,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.5, + "duration_ms": 27.76, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5416,7 +5416,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.55, + "duration_ms": 27.99, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -6197,43 +6197,48 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "0f97b66ed83c74eb82198744292b8da166612d78", + "commit": "c30882468f45c7e78bef73e0ada161fd1fbaef79", "git_status": { "available": true, "dirty": true, - "changed_file_count": 17, + "changed_file_count": 64, "generated_dirty": true, - "generated_changed_file_count": 17, - "source_dirty": false, - "source_changed_file_count": 0, + "generated_changed_file_count": 60, + "source_dirty": true, + "source_changed_file_count": 4, "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", " M reports/adaptation_proposals.json", " M reports/adaptation_proposals.md", + " M reports/adoption_drift_report.json", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", + " M reports/compiled_targets.json", " M reports/context_budget.json", - " M reports/evidence_consistency.json", - " M reports/output_execution_runs.json", - " M reports/output_execution_runs.md", - " M reports/review-studio.html", - " M reports/review-studio.json", - " M reports/review-viewer.json", - " M reports/skill-interpretation.json" + " M reports/context_budget.md" + ], + "source_sample": [ + " M scripts/render_evidence_consistency.py", + " M tests/verify_architecture_maintainability.py", + " M tests/verify_evidence_consistency.py", + "?? scripts/evidence_consistency_phase_queue.py" ], - "source_sample": [], "generated_sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", " M reports/adaptation_proposals.json", " M reports/adaptation_proposals.md", + " M reports/adoption_drift_report.json", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", + " M reports/compiled_targets.json", " M reports/context_budget.json", - " M reports/evidence_consistency.json", - " M reports/output_execution_runs.json", - " M reports/output_execution_runs.md", - " M reports/review-studio.html", - " M reports/review-studio.json", - " M reports/review-viewer.json", - " M reports/skill-interpretation.json" + " M reports/context_budget.md" ], "generated_dirty_prefixes": [ "dist/", @@ -6247,12 +6252,12 @@ }, "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": "70140015193af060a6a111a5f18e5b069a16e8b2a47de84776c564d640830f93", - "source_contract_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "evidence_bundle_sha256": "0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd", + "source_contract_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, @@ -6271,18 +6276,19 @@ "world_class_source_pass_count": 10, "world_class_source_blocked_count": 9, "public_claim_ready": false, - "public_claim_blocker_count": 4, + "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 17, - "source_tree_dirty": false, - "source_changed_file_count": 0, + "changed_file_count": 64, + "source_tree_dirty": true, + "source_changed_file_count": 4, "generated_tree_dirty": true, - "generated_changed_file_count": 17 + "generated_changed_file_count": 60 }, "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)", @@ -6291,12 +6297,12 @@ "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": "0f97b66ed83c74eb82198744292b8da166612d78", + "ready": false, + "commit": "c30882468f45c7e78bef73e0ada161fd1fbaef79", "status_scope": "generation-time status before this report is written", - "source_changed_file_count": 0, - "generated_changed_file_count": 17, - "reason": "only generated evidence artifacts were dirty at generation time" + "source_changed_file_count": 4, + "generated_changed_file_count": 60, + "reason": "source files were dirty at generation time" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -6304,7 +6310,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "70140015193af060a6a111a5f18e5b069a16e8b2a47de84776c564d640830f93" + "sha256": "0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -6377,8 +6383,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7965, - "sha256": "428b1ecabe160d6185bb8eaece93563d9f4aa6091b484fb7e3552f51c29166af" + "bytes": 7967, + "sha256": "615d4b9ec6fb8d487c98e06ffb8cdbe7d34b08b07a2d9ea069eee3cdd4edc0a9" }, { "label": "blind_review", @@ -6412,22 +6418,22 @@ "label": "trust_report", "path": "reports/security_trust_report.json", "exists": true, - "bytes": 136375, - "sha256": "08c2d3659e8a3a05ddc4be6da0a533970b09f6017efbe508ed311d189fe69726" + "bytes": 136999, + "sha256": "a44deb1fb680973315225900381bb1d09b71352fca1bed3a99df60393340c6fc" }, { "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, - "bytes": 29848, - "sha256": "4dc6cc6e37038493bdd01df3ecc043c90efefc0a4d4932525adc8f4053c1affc" + "bytes": 29983, + "sha256": "cb95afb7d7cc89ec865364f28ef499acadad39afafb9a1494acc118def9201a0" }, { "label": "registry_audit", "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "c5dd375176e01291baf0bbcb1dc5c7eb65a3ce59c4ebcd655c94b91481983380" + "sha256": "af63529bb20c444d93b81a278be60ff89b2f49245f0c557cf574cc2dfd6d1e2e" }, { "label": "package_verification", @@ -6441,14 +6447,14 @@ "path": "reports/install_simulation.json", "exists": true, "bytes": 8758, - "sha256": "f71d25a6ac3e731412f435fd722b343e616def12c013a07f87e57ea4a7551a96" + "sha256": "d2bea19ea46f3eff07ad50cd76b82816983c065db59bf0ae35ac1fa418206db0" }, { "label": "skill_os2_audit", "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14466, - "sha256": "432b795c6ccc1db3c2815b97220675a7c27facbe9c8334ed0158627b7f2214b7" + "sha256": "ad57230481ed929c651fcc1087f20ec2e6c036d7cfe85817f7709c030c5b3b32" }, { "label": "world_class_evidence_plan", @@ -6780,7 +6786,7 @@ "label": "Trust Security", "status": "pass", "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.", - "current": "151 scripts; secrets 0; help failures 0", + "current": "152 scripts; secrets 0; help failures 0", "command": "python3 scripts/yao.py trust .", "test": "python3 tests/verify_trust_check.py", "evidence": [ @@ -7263,7 +7269,7 @@ "label": "Evidence Consistency", "status": "pass", "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.", - "current": "36 consistency checks", + "current": "37 consistency checks", "command": "make ci-test", "test": "tests/verify_evidence_consistency.py", "evidence": [ @@ -7633,6 +7639,7 @@ "scripts/emit_telemetry_event.py", "scripts/evidence_consistency_artifact_roles.py", "scripts/evidence_consistency_core.py", + "scripts/evidence_consistency_phase_queue.py", "scripts/evidence_consistency_release.py", "scripts/evidence_consistency_skill_os2_review.py", "scripts/evidence_consistency_world_class.py", @@ -7817,7 +7824,7 @@ ], "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 } @@ -8090,7 +8097,7 @@ "strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -8101,7 +8108,7 @@ }, "scripts": { "strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -8346,7 +8353,7 @@ "strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -8357,7 +8364,7 @@ }, "scripts": { "strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -8586,6 +8593,7 @@ "scripts/emit_telemetry_event.py", "scripts/evidence_consistency_artifact_roles.py", "scripts/evidence_consistency_core.py", + "scripts/evidence_consistency_phase_queue.py", "scripts/evidence_consistency_release.py", "scripts/evidence_consistency_skill_os2_review.py", "scripts/evidence_consistency_world_class.py", @@ -8770,7 +8778,7 @@ ], "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 } @@ -9043,7 +9051,7 @@ "strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -9054,7 +9062,7 @@ }, "scripts": { "strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -9299,7 +9307,7 @@ "strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -9310,7 +9318,7 @@ }, "scripts": { "strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -9539,6 +9547,7 @@ "scripts/emit_telemetry_event.py", "scripts/evidence_consistency_artifact_roles.py", "scripts/evidence_consistency_core.py", + "scripts/evidence_consistency_phase_queue.py", "scripts/evidence_consistency_release.py", "scripts/evidence_consistency_skill_os2_review.py", "scripts/evidence_consistency_world_class.py", @@ -9723,7 +9732,7 @@ ], "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 } @@ -9996,7 +10005,7 @@ "strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -10006,7 +10015,7 @@ }, "scripts": { "strategy": "Expose script and permission metadata for downstream clients or installers to enforce.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -10245,7 +10254,7 @@ "strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -10255,7 +10264,7 @@ }, "scripts": { "strategy": "Expose script and permission metadata for downstream clients or installers to enforce.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -10476,6 +10485,7 @@ "scripts/emit_telemetry_event.py", "scripts/evidence_consistency_artifact_roles.py", "scripts/evidence_consistency_core.py", + "scripts/evidence_consistency_phase_queue.py", "scripts/evidence_consistency_release.py", "scripts/evidence_consistency_skill_os2_review.py", "scripts/evidence_consistency_world_class.py", @@ -10660,7 +10670,7 @@ ], "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 } @@ -10933,7 +10943,7 @@ "strategy": "Keep optional directories as relative resources next to SKILL.md.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -10944,7 +10954,7 @@ }, "scripts": { "strategy": "Scripts remain local optional resources and should advertise --help when executable.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -11182,7 +11192,7 @@ "strategy": "Keep optional directories as relative resources next to SKILL.md.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -11193,7 +11203,7 @@ }, "scripts": { "strategy": "Scripts remain local optional resources and should advertise --help when executable.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -11413,6 +11423,7 @@ "scripts/emit_telemetry_event.py", "scripts/evidence_consistency_artifact_roles.py", "scripts/evidence_consistency_core.py", + "scripts/evidence_consistency_phase_queue.py", "scripts/evidence_consistency_release.py", "scripts/evidence_consistency_skill_os2_review.py", "scripts/evidence_consistency_world_class.py", @@ -11597,7 +11608,7 @@ ], "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 } @@ -11870,7 +11881,7 @@ "strategy": "Install as project or user scoped skill source, preserving relative references and scripts.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -11881,7 +11892,7 @@ }, "scripts": { "strategy": "Scripts require workspace trust and operator/client approval outside this compiler.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -12123,7 +12134,7 @@ "strategy": "Install as project or user scoped skill source, preserving relative references and scripts.", "counts": { "references": 35, - "scripts": 151, + "scripts": 152, "assets": 6, "reports": 43 }, @@ -12134,7 +12145,7 @@ }, "scripts": { "strategy": "Scripts require workspace trust and operator/client approval outside this compiler.", - "script_count": 151, + "script_count": 152, "help_smoke_failed_count": 0 }, "permissions": { @@ -12842,9 +12853,9 @@ "ok": true, "skill_dir": ".", "summary": { - "scanned_files": 243, - "script_count": 151, - "internal_module_count": 65, + "scanned_files": 244, + "script_count": 152, + "internal_module_count": 66, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -12862,8 +12873,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 243, - "package_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc" + "package_hash_file_count": 244, + "package_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d" }, "failures": [], "warnings": [], @@ -13196,6 +13207,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/evidence_consistency_phase_queue.py", + "interface": "internal-module", + "interface_declared": true, + "interface_reason": "Imported by render_evidence_consistency.py to prevent preflight and Review Studio phase-queue drift.", + "has_argparse": false, + "has_main_guard": false, + "uses_input": false, + "uses_network": false, + "uses_file_write": false, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/evidence_consistency_release.py", "interface": "internal-module", @@ -15035,7 +15060,7 @@ "checked_count": 86, "passed_count": 86, "failed_count": 0, - "skipped_count": 65, + "skipped_count": 66, "failed_scripts": [], "results": [ { @@ -15940,6 +15965,10 @@ "path": "scripts/evidence_consistency_core.py", "reason": "internal module" }, + { + "path": "scripts/evidence_consistency_phase_queue.py", + "reason": "internal module" + }, { "path": "scripts/evidence_consistency_release.py", "reason": "internal module" @@ -16357,7 +16386,7 @@ "root": ".", "summary": { "target_python": "3.11", - "file_count": 230, + "file_count": 231, "issue_count": 0, "syntax_error_count": 0, "fstring_311_violation_count": 0, @@ -16530,6 +16559,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/evidence_consistency_phase_queue.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/evidence_consistency_release.py", "ok": true, @@ -17767,10 +17802,10 @@ "generated_at": "2026-06-13", "skill_dir": ".", "summary": { - "python_file_count": 227, - "script_file_count": 151, + "python_file_count": 228, + "script_file_count": 152, "test_file_count": 76, - "internal_module_count": 67, + "internal_module_count": 68, "cli_script_count": 86, "command_handler_count": 68, "entrypoint_command_handler_count": 18, @@ -17781,7 +17816,7 @@ "block_line_threshold": 1500, "largest_file_lines": 696, "watchlist_count": 0, - "early_watchlist_count": 2, + "early_watchlist_count": 3, "hotspot_count": 0, "blocker_count": 0, "decision": "pass" @@ -17803,6 +17838,14 @@ "early_watch": true, "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." }, + { + "path": "tests/verify_evidence_consistency.py", + "lines": 609, + "kind": "test", + "severity": "pass", + "early_watch": true, + "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." + }, { "path": "tests/verify_output_review_adjudication.py", "lines": 599, @@ -17843,6 +17886,14 @@ "early_watch": false, "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." }, + { + "path": "scripts/render_evidence_consistency.py", + "lines": 579, + "kind": "cli-script", + "severity": "pass", + "early_watch": false, + "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." + }, { "path": "tests/verify_world_class_evidence_ledger.py", "lines": 579, @@ -17859,14 +17910,6 @@ "early_watch": false, "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." }, - { - "path": "scripts/render_evidence_consistency.py", - "lines": 571, - "kind": "cli-script", - "severity": "pass", - "early_watch": false, - "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." - }, { "path": "scripts/render_review_studio.py", "lines": 568, @@ -17874,14 +17917,6 @@ "severity": "pass", "early_watch": false, "recommendation": "Move data loading and large section renderers into focused review_studio_* modules." - }, - { - "path": "scripts/adjudicate_output_review.py", - "lines": 566, - "kind": "cli-script", - "severity": "pass", - "early_watch": false, - "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." } ], "watchlist": [], @@ -17901,6 +17936,14 @@ "severity": "pass", "early_watch": true, "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." + }, + { + "path": "tests/verify_evidence_consistency.py", + "lines": 609, + "kind": "test", + "severity": "pass", + "early_watch": true, + "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." } ], "hotspots": [], @@ -17918,16 +17961,16 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1118744, + "other_text_tokens": 1121236, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1119541, - "deferred_resource_tokens": 511351, + "estimated_total_text_tokens": 1122033, + "deferred_resource_tokens": 512782, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 450048, - "file_count": 151 + "estimated_tokens": 451479, + "file_count": 152 }, { "path": "references", @@ -17948,8 +17991,8 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 450048, - "file_count": 151 + "estimated_tokens": 451479, + "file_count": 152 } ], "deferred_resource_governance": { @@ -17971,14 +18014,14 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 450048, - "file_count": 151, + "estimated_tokens": 451479, + "file_count": 152, "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": 708, + "relevant_file_count": 710, "unused_resource_dirs": [], "quality_signal_points": 130, "quality_density": 131.3 @@ -18865,6 +18908,7 @@ "scripts/emit_telemetry_event.py", "scripts/evidence_consistency_artifact_roles.py", "scripts/evidence_consistency_core.py", + "scripts/evidence_consistency_phase_queue.py", "scripts/evidence_consistency_release.py", "scripts/evidence_consistency_skill_os2_review.py", "scripts/evidence_consistency_world_class.py", @@ -19895,7 +19939,7 @@ "adoption_drift": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-16T20:47:11Z", + "generated_at": "2026-06-16T20:58:58Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -19992,7 +20036,7 @@ "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, @@ -20009,7 +20053,7 @@ "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, @@ -20458,7 +20502,7 @@ "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": [ @@ -20493,7 +20537,7 @@ "weekly_curator": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17", + "generated_at": "2026-06-16T20:58:28Z", "skill_dir": ".", "decision": "curator-review", "week_id": "2026-W25", @@ -20507,7 +20551,7 @@ "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, @@ -20527,7 +20571,7 @@ "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, @@ -20780,7 +20824,7 @@ "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 @@ -20958,7 +21002,7 @@ "adaptation_proposals": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17", + "generated_at": "2026-06-16T20:58:28Z", "skill_dir": ".", "source_patterns": "reports/user_patterns.json", "pattern_count": 5, @@ -26322,7 +26366,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "package_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { @@ -26379,7 +26423,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc" + "package_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d" } ] }, @@ -27068,7 +27112,7 @@ "installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill", "summary": { "archive_present": true, - "archive_entry_count": 690, + "archive_entry_count": 691, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -27415,7 +27459,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc" + "to": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d" } ] }, diff --git a/reports/review-viewer.json b/reports/review-viewer.json index d435b8c1..26160646 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -513,7 +513,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 151 + "file_count": 152 }, { "path": "evals", @@ -528,7 +528,7 @@ "file_count": 235 } ], - "file_count": 454, + "file_count": 455, "folder_count": 4, "distribution": [ { @@ -553,7 +553,7 @@ }, { "label": "scripts", - "value": 151 + "value": 152 }, { "label": "evals", @@ -683,7 +683,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 151 + "file_count": 152 }, { "path": "evals", @@ -1005,12 +1005,12 @@ "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": "70140015193af060a6a111a5f18e5b069a16e8b2a47de84776c564d640830f93", - "source_contract_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "evidence_bundle_sha256": "0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd", + "source_contract_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1029,15 +1029,15 @@ "world_class_source_pass_count": 10, "world_class_source_blocked_count": 9, "public_claim_ready": false, - "public_claim_blocker_count": 4, + "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 17, - "source_tree_dirty": false, - "source_changed_file_count": 0, + "changed_file_count": 64, + "source_tree_dirty": true, + "source_changed_file_count": 4, "generated_tree_dirty": true, - "generated_changed_file_count": 17 + "generated_changed_file_count": 60 }, - "commit": "0f97b66ed83c74eb82198744292b8da166612d78", + "commit": "c30882468f45c7e78bef73e0ada161fd1fbaef79", "missing_artifacts": [], "limitations": [ "The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.", @@ -1121,9 +1121,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 243, - "script_count": 151, - "internal_module_count": 65, + "scanned_files": 244, + "script_count": 152, + "internal_module_count": 66, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -1141,8 +1141,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 243, - "package_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc" + "package_hash_file_count": 244, + "package_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d" }, "skill_atlas": { "skill_count": 12, @@ -1180,7 +1180,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "package_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { @@ -1240,7 +1240,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 690, + "archive_entry_count": 691, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1312,7 +1312,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc" + "to": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d" } ] }, diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index 3e3072ec..efee356a 100644 --- a/reports/security_trust_report.json +++ b/reports/security_trust_report.json @@ -2,9 +2,9 @@ "ok": true, "skill_dir": ".", "summary": { - "scanned_files": 243, - "script_count": 151, - "internal_module_count": 65, + "scanned_files": 244, + "script_count": 152, + "internal_module_count": 66, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -22,8 +22,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 243, - "package_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc" + "package_hash_file_count": 244, + "package_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d" }, "failures": [], "warnings": [], @@ -356,6 +356,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/evidence_consistency_phase_queue.py", + "interface": "internal-module", + "interface_declared": true, + "interface_reason": "Imported by render_evidence_consistency.py to prevent preflight and Review Studio phase-queue drift.", + "has_argparse": false, + "has_main_guard": false, + "uses_input": false, + "uses_network": false, + "uses_file_write": false, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/evidence_consistency_release.py", "interface": "internal-module", @@ -2195,7 +2209,7 @@ "checked_count": 86, "passed_count": 86, "failed_count": 0, - "skipped_count": 65, + "skipped_count": 66, "failed_scripts": [], "results": [ { @@ -3100,6 +3114,10 @@ "path": "scripts/evidence_consistency_core.py", "reason": "internal module" }, + { + "path": "scripts/evidence_consistency_phase_queue.py", + "reason": "internal module" + }, { "path": "scripts/evidence_consistency_release.py", "reason": "internal module" diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index fe13108d..5596f95b 100644 --- a/reports/security_trust_report.md +++ b/reports/security_trust_report.md @@ -1,9 +1,9 @@ # Security Trust Report - OK: `True` -- Scanned files: `243` -- Scripts: `151` -- Internal script modules: `65` +- Scanned files: `244` +- Scripts: `152` +- Internal script modules: `66` - Secret findings: `0` - Network-capable scripts: `3` - Network policy covered scripts: `3` @@ -15,8 +15,8 @@ - CLI help smoke failures: `0` - Interactive scripts: `0` - Package hash scope: `source-contract-without-generated-reports` -- Package hash files: `243` -- Package SHA256: `453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc` +- Package hash files: `244` +- Package SHA256: `5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d` ## Failures @@ -85,6 +85,7 @@ | scripts/emit_telemetry_event.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | | scripts/evidence_consistency_artifact_roles.py | internal-module | True | False | False | False | False | False | False | Imported by render_evidence_consistency.py to compare preflight and Review Studio artifact-role contracts. | | scripts/evidence_consistency_core.py | internal-module | True | False | False | False | False | False | False | Imported by render_evidence_consistency.py for shared report loading, comparison, and Markdown rendering helpers. | +| scripts/evidence_consistency_phase_queue.py | internal-module | True | False | False | False | False | False | False | Imported by render_evidence_consistency.py to prevent preflight and Review Studio phase-queue drift. | | scripts/evidence_consistency_release.py | internal-module | True | False | False | False | False | False | False | Imported by render_evidence_consistency.py to verify release evidence refresh instructions. | | scripts/evidence_consistency_skill_os2_review.py | internal-module | True | False | False | False | False | False | False | Imported by render_evidence_consistency.py to keep Skill OS 2.0 review summary drift checks out of the main consistency renderer. | | scripts/evidence_consistency_world_class.py | internal-module | True | False | False | False | False | False | False | Imported by render_evidence_consistency.py to isolate world-class evidence workflow consistency checks. | diff --git a/reports/skill-interpretation.html b/reports/skill-interpretation.html index 128f2bc2..558d3e19 100644 --- a/reports/skill-interpretation.html +++ b/reports/skill-interpretation.html @@ -940,7 +940,7 @@

让 reviewer 快速确认关键文件、目录和资产分布。Lets reviewers confirm key files, directories, and asset distribution quickly.

-
资产分布Asset Distribution454项454 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
+
资产分布Asset Distribution455项455 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index 8c2a413a..e5dca91d 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -513,7 +513,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 151 + "file_count": 152 }, { "path": "evals", @@ -528,7 +528,7 @@ "file_count": 235 } ], - "file_count": 454, + "file_count": 455, "folder_count": 4, "distribution": [ { @@ -553,7 +553,7 @@ }, { "label": "scripts", - "value": 151 + "value": 152 }, { "label": "evals", @@ -687,7 +687,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 151 + "file_count": 152 }, { "path": "evals", @@ -1009,12 +1009,12 @@ "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": "70140015193af060a6a111a5f18e5b069a16e8b2a47de84776c564d640830f93", - "source_contract_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "evidence_bundle_sha256": "0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd", + "source_contract_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1033,15 +1033,15 @@ "world_class_source_pass_count": 10, "world_class_source_blocked_count": 9, "public_claim_ready": false, - "public_claim_blocker_count": 4, + "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 17, - "source_tree_dirty": false, - "source_changed_file_count": 0, + "changed_file_count": 64, + "source_tree_dirty": true, + "source_changed_file_count": 4, "generated_tree_dirty": true, - "generated_changed_file_count": 17 + "generated_changed_file_count": 60 }, - "commit": "0f97b66ed83c74eb82198744292b8da166612d78", + "commit": "c30882468f45c7e78bef73e0ada161fd1fbaef79", "missing_artifacts": [], "limitations": [ "The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.", @@ -1125,9 +1125,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 243, - "script_count": 151, - "internal_module_count": 65, + "scanned_files": 244, + "script_count": 152, + "internal_module_count": 66, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -1145,8 +1145,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 243, - "package_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc" + "package_hash_file_count": 244, + "package_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d" }, "skill_atlas": { "skill_count": 12, @@ -1184,7 +1184,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "package_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { @@ -1244,7 +1244,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 690, + "archive_entry_count": 691, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1316,7 +1316,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc" + "to": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d" } ] }, diff --git a/reports/skill-os-2-review.md b/reports/skill-os-2-review.md index 998d9fa6..0967fb5b 100644 --- a/reports/skill-os-2-review.md +++ b/reports/skill-os-2-review.md @@ -112,7 +112,7 @@ Next move: run provider-backed holdout cases with real credentials and one real ### 3. Review Studio is unified and now has reviewer actions plus annotations -The Review Studio page aggregates intent, trigger, output, context, runtime, trust, permission approvals, runtime permission probes, atlas, operations-loop, reviewer waiver, reviewer annotations, registry, world-class evidence, and release gates. It exposes current warnings directly and emits `review_actions` for each non-pass gate with a source-fix location, structured `source_refs`, reason, evidence path, and verification command. It now also loads `reports/review_annotations.json`, renders reviewer comments tied to gates and source/report paths, and blocks the page decision when any open blocker annotation exists. The current root report is intentionally not a clean pass: decision `review`, score `91`, `16` gates, `0` blockers, `3` warnings, `3` actions, and `0` open annotation blockers. The warnings are useful evidence: the automated Output Eval Lab is strong, but the blind A/B adjudication still has `5` pending reviewer decisions and the world-class ledger still has `4` pending external or human evidence entries, so the package should not claim fully reviewed or world-class status. +The Review Studio page aggregates intent, trigger, output, context, runtime, trust, permission approvals, runtime permission probes, atlas, operations-loop, reviewer waiver, reviewer annotations, registry, world-class evidence, and release gates. It exposes current warnings directly and emits `review_actions` for each non-pass gate with a source-fix location, structured `source_refs`, reason, evidence path, and verification command. It now also loads `reports/review_annotations.json`, renders reviewer comments tied to gates and source/report paths, and blocks the page decision when any open blocker annotation exists. The current root report is intentionally not a clean pass: decision `review`, score `91`, `16` gates, `0` blockers, `3` warnings, `3` actions, and `0` open annotation blockers. The warnings are useful evidence: the automated Output Eval Lab is strong, but blind A/B adjudication still has `5` pending reviewer decisions, warning waivers still need reviewer handling, and the world-class ledger still has `4` pending external or human evidence entries, so the package should not claim fully reviewed or world-class status. Next move: add richer source-line anchors inside generated reports, record real reviewer annotations during the next human review pass, and close the provider, native-permission, real-client telemetry, and human review evidence entries in the world-class ledger. @@ -135,7 +135,7 @@ Next move: add real client or installer permission enforcement integration. | Output Eval | `5` cases, with-skill pass rate `100`, baseline pass rate `0`, with file-backed, near-neighbor, boundary coverage, `10` local command-runner execution runs, `0` recorded fixture runs, `0` provider model-executed runs in root release evidence, `10` estimated token counts, provider runner v0 available, `5` blind A/B review pairs, a generated `reports/output_review_decisions.json` template, `0 / 5` reviewer decisions pending, `0` answer keys revealed, and `5` pending answers hidden | | Runtime Conformance | `5 / 5` targets passing | | Target Compiler | `5 / 5` compiled target contracts generated for OpenAI, Claude, generic, Agent Skills compatible, and VS Code / Copilot outputs, including target permission contracts and target-native behavior contracts | -| Trust | `0` secret findings, `1` pinned dependency file, `65` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `86 / 86` CLI help smoke checks passing across `151` scripts, source-contract hash scope explicit | +| Trust | `0` secret findings, `1` pinned dependency file, `66` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `86 / 86` CLI help smoke checks passing across `152` scripts, source-contract hash scope explicit | | Permission Governance | `3 / 3` required high-permission capabilities approved, `0` missing, `0` invalid, `0` expired | | Runtime Permission Probes | `4 / 4` target adapters probed, `0` native-enforcement adapters, `4` explicit metadata fallbacks, `4` residual risks retained for reviewer visibility | | Skill Atlas | `12` scanned skills, `1` actionable root skill, `1` telemetry report, `0` actionable route collisions, `0` actionable owner gaps, `0` actionable stale skills, `0` actionable drift signals, `24` scoped non-actionable issue signals retained for visibility | @@ -145,7 +145,7 @@ Next move: add real client or installer permission enforcement integration. | Local Install Sync Preflight | `make sync-local-install` and `make sync-active-install` rebuild the package first, then sync only after install simulation passes with `12` enforced installer permission checks and `0` permission failures | | Upgrade Check | current package declares `minor` over the 1.0.0 baseline, recommended bump is `minor`, and release notes include added targets plus checksum changes | | Adoption Drift | `1` metadata-only review event, `1` adoption sample, adoption `100`, risk band `low`; optional `yao.py` CLI capture, external client `telemetry-emit`, `5` `telemetry-hooks` recipes, Browser/Chrome native messaging host, and validated external JSONL import are available but off by default for reproducible release evidence; raw `reports/telemetry_events.jsonl` is gitignored and blocked from zip packages | -| Review Waivers | ledger generated; current release has `1` warning gate that still needs reviewer decision or a time-bounded waiver; blockers remain non-waivable in v0, and world-class evidence gaps must be closed with accepted evidence rather than waived as completed | +| Review Waivers | ledger generated; current release has `1` warning gates that still need reviewer decision or a time-bounded waiver; blockers remain non-waivable in v0, and world-class evidence gaps must be closed with accepted evidence rather than waived as completed | | Review Annotations | ledger generated; current release has `0` reviewer annotations and `0` open annotation blockers | | Review Studio | decision `review`, world-class score `91`, `16` gates, `0` blockers, `3` warnings, `3` review actions, `0` open annotation blockers | | Skill OS 2.0 Audit | `15` audited areas, with local foundation evidence separated from human-required and external-required gaps | @@ -153,7 +153,7 @@ Next move: add real client or installer permission enforcement integration. | World-Class Evidence Ledger | `4` evidence entries remain pending: `1` human-required and `3` external-required; anti-overclaim guards block planned work, metadata fallbacks, pending review, and local command runners from counting as completion | | Benchmark Reproducibility | local reproducibility ready with `25` required artifacts, `0` missing artifacts, `23` reproduction commands, and `3` disclosed failure cases; provider and human evidence remain explicit limitations | | IR-first Packaging | `openai`, `claude`, `generic`, and `vscode` adapters include compiler contracts, permission contracts, target-native behavior contracts, IR provenance, semantic parity checks, and install-scope notes where applicable | -| Context Budget | initial load `990/1000`, under the production budget | +| Context Budget | initial load `990/1000`; deferred `512782/120000`; resource governance governed | | CI | `make ci-test` target count is `82` after the dedicated CLI world-class verifier split | ## Next Highest-Leverage Moves diff --git a/reports/skill-overview.html b/reports/skill-overview.html index 4796f35e..b93d3009 100644 --- a/reports/skill-overview.html +++ b/reports/skill-overview.html @@ -940,7 +940,7 @@

让 reviewer 快速确认关键文件、目录和资产分布。Lets reviewers confirm key files, directories, and asset distribution quickly.

-
资产分布Asset Distribution454项454 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
+
资产分布Asset Distribution455项455 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
路径Path作用Role类型Type
SKILL.mdSkill 入口文件Skill entrypoint文件file
README.md人类可读使用说明Human-readable usage guide文件file
agents/interface.yaml跨平台接口元数据Neutral interface metadata文件file
manifest.json生命周期与打包元数据Lifecycle and portability metadata文件file
references扩展指导与复用资料Extended guidance and reusable notes目录folder
scripts确定性脚本或本地工具Deterministic helpers or local tooling目录folder
evals触发与质量检查Trigger and quality checks目录folder
reports生成的证据与总结报告Generated evidence and overview artifacts目录folder
diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 152d3280..6a977ee3 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -512,7 +512,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 151 + "file_count": 152 }, { "path": "evals", @@ -527,7 +527,7 @@ "file_count": 235 } ], - "file_count": 454, + "file_count": 455, "folder_count": 4, "distribution": [ { @@ -552,7 +552,7 @@ }, { "label": "scripts", - "value": 151 + "value": 152 }, { "label": "evals", @@ -682,7 +682,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 151 + "file_count": 152 }, { "path": "evals", @@ -1004,12 +1004,12 @@ "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": "70140015193af060a6a111a5f18e5b069a16e8b2a47de84776c564d640830f93", - "source_contract_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "evidence_bundle_sha256": "0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd", + "source_contract_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1028,15 +1028,15 @@ "world_class_source_pass_count": 10, "world_class_source_blocked_count": 9, "public_claim_ready": false, - "public_claim_blocker_count": 4, + "public_claim_blocker_count": 5, "working_tree_dirty": true, - "changed_file_count": 17, - "source_tree_dirty": false, - "source_changed_file_count": 0, + "changed_file_count": 64, + "source_tree_dirty": true, + "source_changed_file_count": 4, "generated_tree_dirty": true, - "generated_changed_file_count": 17 + "generated_changed_file_count": 60 }, - "commit": "0f97b66ed83c74eb82198744292b8da166612d78", + "commit": "c30882468f45c7e78bef73e0ada161fd1fbaef79", "missing_artifacts": [], "limitations": [ "The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.", @@ -1120,9 +1120,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 243, - "script_count": 151, - "internal_module_count": 65, + "scanned_files": 244, + "script_count": 152, + "internal_module_count": 66, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -1140,8 +1140,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 243, - "package_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc" + "package_hash_file_count": 244, + "package_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d" }, "skill_atlas": { "skill_count": 12, @@ -1179,7 +1179,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc", + "package_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d", "archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2" }, "compatibility": { @@ -1239,7 +1239,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 690, + "archive_entry_count": 691, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1311,7 +1311,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc" + "to": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d" } ] }, diff --git a/reports/skill_atlas.json b/reports/skill_atlas.json index a0856b09..38997cae 100644 --- a/reports/skill_atlas.json +++ b/reports/skill_atlas.json @@ -87,6 +87,7 @@ "scripts/emit_telemetry_event.py", "scripts/evidence_consistency_artifact_roles.py", "scripts/evidence_consistency_core.py", + "scripts/evidence_consistency_phase_queue.py", "scripts/evidence_consistency_release.py", "scripts/evidence_consistency_skill_os2_review.py", "scripts/evidence_consistency_world_class.py", diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json index 3f57b0e3..36a609ec 100644 --- a/reports/skill_os2_audit.json +++ b/reports/skill_os2_audit.json @@ -197,7 +197,7 @@ "key": "trust-security", "label": "Trust Security", "status": "pass", - "current": "secrets 0; scripts 151; help failures 0", + "current": "secrets 0; scripts 152; help failures 0", "target": "Secrets, scripts, dependencies, permissions, and package hash are reviewable", "evidence": [ { diff --git a/reports/skill_os2_audit.md b/reports/skill_os2_audit.md index 117b3fc8..4b8d9108 100644 --- a/reports/skill_os2_audit.md +++ b/reports/skill_os2_audit.md @@ -23,7 +23,7 @@ Generated at: `2026-06-13` | Human Adjudication | human-required | 0/5 decisions; pending 5 | Real reviewer decisions, blind-review attestation, and integrity fingerprints recorded before claiming output review completion | Record real A/B choices, reviewer metadata, and blind-review attestation, then regenerate adjudication. | | Benchmark Reproducibility | pass | artifacts 25; missing 0; failures 3 | Public methodology, reproducible commands, required artifacts, and failure disclosure are machine-checkable | Keep the manifest current with every benchmark, package, and release evidence change. | | Runtime Conformance | pass | 5/5 targets pass | Target package structure, metadata, relative paths, and degradation notes pass | Keep target conformance fixtures updated as platform contracts change. | -| Trust Security | pass | secrets 0; scripts 151; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. | +| Trust Security | pass | secrets 0; scripts 152; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. | | Permission Metadata | pass | 4/4 target probes pass; metadata fallback 4; installer enforcement 4 | Packaged adapters expose explicit permission metadata, residual risks, and installer enforcement evidence when available | Preserve residual-risk notes until real native enforcement exists. | | Native Permission Enforcement | external-required | native-enforced targets 0; installer-enforced targets 4 | At least one target/client enforces approved permissions at runtime | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. | | Skill Atlas | pass | 12 skills; actionable collisions 0 | Workspace catalog, route overlap, stale/owner gaps, drift, and no-route opportunities | Feed real drift data into Atlas once client telemetry is installed. | diff --git a/reports/skill_os2_coverage.json b/reports/skill_os2_coverage.json index 6d2fbe1c..e85b45d5 100644 --- a/reports/skill_os2_coverage.json +++ b/reports/skill_os2_coverage.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "summary": { "item_count": 21, @@ -130,7 +130,7 @@ "label": "Trust Security", "status": "pass", "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.", - "current": "151 scripts; secrets 0; help failures 0", + "current": "152 scripts; secrets 0; help failures 0", "command": "python3 scripts/yao.py trust .", "test": "python3 tests/verify_trust_check.py", "evidence": [ @@ -613,7 +613,7 @@ "label": "Evidence Consistency", "status": "pass", "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.", - "current": "36 consistency checks", + "current": "37 consistency checks", "command": "make ci-test", "test": "tests/verify_evidence_consistency.py", "evidence": [ diff --git a/reports/skill_os2_coverage.md b/reports/skill_os2_coverage.md index 612d83d5..c4952332 100644 --- a/reports/skill_os2_coverage.md +++ b/reports/skill_os2_coverage.md @@ -1,6 +1,6 @@ # Skill OS 2.0 Blueprint Coverage -Generated at: `2026-06-13` +Generated at: `2026-06-17` ## Summary @@ -26,7 +26,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, | Skill IR | `pass` | schema 2.0.0; targets 5 | `python3 scripts/yao.py skill-ir .` | `python3 tests/verify_skill_ir.py` | | Output Eval Lab | `pass` | 5 cases; delta 100.0; execution 10 | `python3 scripts/yao.py output-exec . && python3 scripts/yao.py output-review .` | `python3 tests/verify_output_eval_lab.py` | | Runtime Conformance | `pass` | 5/5 targets pass | `python3 scripts/yao.py conformance .` | `python3 tests/verify_conformance_suite.py` | -| Trust Security | `pass` | 151 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` | +| Trust Security | `pass` | 152 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` | | Skill Atlas | `pass` | 12 scanned skills; actionable collisions 0 | `python3 scripts/yao.py skill-atlas --workspace-root .` | `python3 tests/verify_skill_atlas.py` | | Registry Distribution | `pass` | archive entries 689; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` | | Review Studio | `pass` | 16 gates; decision review; warnings 3 | `python3 scripts/yao.py review-studio .` | `python3 tests/verify_review_studio.py` | @@ -48,7 +48,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, | Registry Package Format | `pass` | registry ok True | `make ci-test` | `tests/verify_registry_audit.py` | | Review Studio 2.0 | `pass` | 16 review gates | `make ci-test` | `tests/verify_review_studio.py` | | Migration V2 Docs | `pass` | migration guide present | `make ci-test` | `docs review` | -| Evidence Consistency | `pass` | 36 consistency checks | `make ci-test` | `tests/verify_evidence_consistency.py` | +| Evidence Consistency | `pass` | 37 consistency checks | `make ci-test` | `tests/verify_evidence_consistency.py` | ## Reference Extension Tracks diff --git a/reports/skillops/daily/2026-06-16.json b/reports/skillops/daily/2026-06-16.json index 41db97f9..6421f12e 100644 --- a/reports/skillops/daily/2026-06-16.json +++ b/reports/skillops/daily/2026-06-16.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16T20:46:42Z", + "generated_at": "2026-06-16T20:58:28Z", "skill_dir": ".", "decision": "proposal-review", "source_supplied": false, diff --git a/reports/skillops/daily/2026-06-16.md b/reports/skillops/daily/2026-06-16.md index 3298bbb4..731bfd6f 100644 --- a/reports/skillops/daily/2026-06-16.md +++ b/reports/skillops/daily/2026-06-16.md @@ -1,6 +1,6 @@ # Daily SkillOps Report -Generated at: `2026-06-16T20:46:42Z` +Generated at: `2026-06-16T20:58:28Z` ## Summary diff --git a/reports/skillops/daily/2026-06-17.json b/reports/skillops/daily/2026-06-17.json index 07080fcd..7ee010c4 100644 --- a/reports/skillops/daily/2026-06-17.json +++ b/reports/skillops/daily/2026-06-17.json @@ -14,7 +14,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -31,7 +31,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -480,7 +480,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true }, "actions": [ diff --git a/reports/skillops/daily/2026-06-17.md b/reports/skillops/daily/2026-06-17.md index 65caad51..5d6c937a 100644 --- a/reports/skillops/daily/2026-06-17.md +++ b/reports/skillops/daily/2026-06-17.md @@ -14,7 +14,7 @@ Generated at: `2026-06-17` - local blueprint ready: `true` - public world-class ready: `false` - world-class pending: `4` -- release lock ready: `true` +- release lock ready: `false` - evidence consistency ok: `true` This report is an operations cockpit for explicit-source SkillOps. It does not scan private logs, write source files, apply patches, or count as world-class external or human evidence. diff --git a/reports/skillops/weekly/2026-W25.json b/reports/skillops/weekly/2026-W25.json index 8f21344c..54006e3e 100644 --- a/reports/skillops/weekly/2026-W25.json +++ b/reports/skillops/weekly/2026-W25.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-17", + "generated_at": "2026-06-16T20:58:28Z", "skill_dir": ".", "decision": "curator-review", "week_id": "2026-W25", @@ -15,7 +15,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -35,7 +35,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -288,7 +288,7 @@ "no_route_opportunity_count": 0 }, "release_state": { - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4 diff --git a/reports/skillops/weekly/2026-W25.md b/reports/skillops/weekly/2026-W25.md index a52113b7..d62f42f9 100644 --- a/reports/skillops/weekly/2026-W25.md +++ b/reports/skillops/weekly/2026-W25.md @@ -1,6 +1,6 @@ # Weekly SkillOps Curator Report -Generated at: `2026-06-17` +Generated at: `2026-06-16T20:58:28Z` Week: `2026-W25` ## Summary @@ -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 9ea63fbf..d04efafa 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -75,7 +75,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "453ca3f4c54651bc0edc917049ea0fa28064edca66083769bf11b13f01acb4fc" + "to": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d" } ] }, diff --git a/reports/world_class_claim_guard.json b/reports/world_class_claim_guard.json index fe24ca0b..22da9491 100644 --- a/reports/world_class_claim_guard.json +++ b/reports/world_class_claim_guard.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "summary": { "ledger_ready_to_claim_world_class": false, diff --git a/reports/world_class_claim_guard.md b/reports/world_class_claim_guard.md index 5315b99a..d2d4d668 100644 --- a/reports/world_class_claim_guard.md +++ b/reports/world_class_claim_guard.md @@ -1,6 +1,6 @@ # World-Class Claim Guard -Generated at: `2026-06-13` +Generated at: `2026-06-17` ## Summary diff --git a/reports/world_class_evidence_intake.json b/reports/world_class_evidence_intake.json index 2d99eb6c..09c59584 100644 --- a/reports/world_class_evidence_intake.json +++ b/reports/world_class_evidence_intake.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "summary": { "schema_present": true, diff --git a/reports/world_class_evidence_intake.md b/reports/world_class_evidence_intake.md index be6ef919..fc622f51 100644 --- a/reports/world_class_evidence_intake.md +++ b/reports/world_class_evidence_intake.md @@ -1,6 +1,6 @@ # World-Class Evidence Intake -Generated at: `2026-06-13` +Generated at: `2026-06-17` ## Summary diff --git a/reports/world_class_evidence_ledger.json b/reports/world_class_evidence_ledger.json index 5628fc25..cab44e97 100644 --- a/reports/world_class_evidence_ledger.json +++ b/reports/world_class_evidence_ledger.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "decision": "evidence-pending", "ready_to_claim_world_class": false, diff --git a/reports/world_class_evidence_ledger.md b/reports/world_class_evidence_ledger.md index 67e25450..82aa5c4f 100644 --- a/reports/world_class_evidence_ledger.md +++ b/reports/world_class_evidence_ledger.md @@ -1,6 +1,6 @@ # World-Class Evidence Ledger -Generated at: `2026-06-13` +Generated at: `2026-06-17` ## Summary diff --git a/reports/world_class_evidence_plan.json b/reports/world_class_evidence_plan.json index 6614fab9..bbb6e41e 100644 --- a/reports/world_class_evidence_plan.json +++ b/reports/world_class_evidence_plan.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "summary": { "audit_decision": "continue-iteration", diff --git a/reports/world_class_evidence_plan.md b/reports/world_class_evidence_plan.md index 9477dab5..5b43964f 100644 --- a/reports/world_class_evidence_plan.md +++ b/reports/world_class_evidence_plan.md @@ -1,6 +1,6 @@ # World-Class Evidence Plan -Generated at: `2026-06-13` +Generated at: `2026-06-17` ## Summary diff --git a/reports/world_class_evidence_preflight.json b/reports/world_class_evidence_preflight.json index 43025b10..80f304fe 100644 --- a/reports/world_class_evidence_preflight.json +++ b/reports/world_class_evidence_preflight.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "summary": { "evidence_item_count": 4, diff --git a/reports/world_class_evidence_preflight.md b/reports/world_class_evidence_preflight.md index 1764251c..d7343ba0 100644 --- a/reports/world_class_evidence_preflight.md +++ b/reports/world_class_evidence_preflight.md @@ -1,6 +1,6 @@ # World-Class Evidence Preflight -Generated at: `2026-06-13` +Generated at: `2026-06-17` ## Summary diff --git a/reports/world_class_operator_runbook.json b/reports/world_class_operator_runbook.json index 7596531a..24e2bd73 100644 --- a/reports/world_class_operator_runbook.json +++ b/reports/world_class_operator_runbook.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "summary": { "evidence_item_count": 4, diff --git a/reports/world_class_operator_runbook.md b/reports/world_class_operator_runbook.md index 7bcee261..833c4d2e 100644 --- a/reports/world_class_operator_runbook.md +++ b/reports/world_class_operator_runbook.md @@ -1,6 +1,6 @@ # World-Class Operator Runbook -Generated at: `2026-06-13` +Generated at: `2026-06-17` ## Summary diff --git a/reports/world_class_submission_review.json b/reports/world_class_submission_review.json index 70449e25..3c09e53d 100644 --- a/reports/world_class_submission_review.json +++ b/reports/world_class_submission_review.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-17", "skill_dir": ".", "decision": "awaiting-submissions", "ready_to_claim_world_class": false, diff --git a/reports/world_class_submission_review.md b/reports/world_class_submission_review.md index b54fcbb7..2dda5c01 100644 --- a/reports/world_class_submission_review.md +++ b/reports/world_class_submission_review.md @@ -1,6 +1,6 @@ # World-Class Submission Review -Generated at: `2026-06-13` +Generated at: `2026-06-17` ## Summary diff --git a/scripts/evidence_consistency_phase_queue.py b/scripts/evidence_consistency_phase_queue.py new file mode 100644 index 00000000..1e957c7f --- /dev/null +++ b/scripts/evidence_consistency_phase_queue.py @@ -0,0 +1,129 @@ +#!/usr/bin/env python3 +"""Compare world-class phase queues across generated reports.""" + +from typing import Any + +from evidence_consistency_world_class import world_class_review_action_steps +from world_class_phase_queue import build_phase_queue, summarize_phase_queue + + +SCRIPT_INTERFACE = "internal-module" +SCRIPT_INTERFACE_REASON = "Imported by render_evidence_consistency.py to prevent preflight and Review Studio phase-queue drift." + + +def phase_queue_signature(queue: list[dict[str, Any]]) -> list[dict[str, Any]]: + signature: list[dict[str, Any]] = [] + for item in queue: + if not isinstance(item, dict): + continue + signature.append( + { + "phase": item.get("phase"), + "priority": item.get("priority"), + "status": item.get("status"), + "blocked_count": item.get("blocked_count"), + "row_count": item.get("row_count"), + "owners": sorted(str(owner) for owner in item.get("owners", [])), + "evidence_keys": sorted(str(key) for key in item.get("evidence_keys", [])), + "next_action_id": item.get("next_action_id"), + "verification_command": item.get("verification_command"), + "counts_as_completion": item.get("counts_as_completion"), + } + ) + return signature + + +def summary_signature(summary: dict[str, Any]) -> dict[str, Any]: + keys = [ + "phase_queue_count", + "phase_queue_blocked_count", + "phase_queue_row_count", + "phase_queue_next_phase", + "phase_queue_next_action_id", + "phase_queue_next_command", + "phase_queue_counts_as_completion", + ] + return {key: summary.get(key) for key in keys} + + +def keyed_preflight_items(world_class_preflight: dict[str, Any]) -> dict[str, dict[str, Any]]: + items = world_class_preflight.get("items", []) if isinstance(world_class_preflight, dict) else [] + keyed: dict[str, dict[str, Any]] = {} + for item in items: + if not isinstance(item, dict): + continue + key = str(item.get("evidence_key", "")).strip() + if key: + keyed[key] = item + return keyed + + +def keyed_phase_queue_signatures_from_repair_rows(items: dict[str, dict[str, Any]]) -> dict[str, list[dict[str, Any]]]: + signatures: dict[str, list[dict[str, Any]]] = {} + for key, item in items.items(): + rows = item.get("repair_checklist", []) if isinstance(item.get("repair_checklist", []), list) else [] + signatures[key] = phase_queue_signature(build_phase_queue(rows)) + return signatures + + +def keyed_phase_queue_signatures_from_items(items: dict[str, dict[str, Any]], queue_key: str) -> dict[str, list[dict[str, Any]]]: + signatures: dict[str, list[dict[str, Any]]] = {} + for key, item in items.items(): + queue = item.get(queue_key, []) if isinstance(item.get(queue_key, []), list) else [] + signatures[key] = phase_queue_signature(queue) + return signatures + + +def build_phase_queue_consistency_check( + *, + world_class_preflight: dict[str, Any], + review_studio: dict[str, Any], + report_paths: dict[str, str], +) -> dict[str, Any]: + repair_rows = ( + world_class_preflight.get("repair_checklist", []) + if isinstance(world_class_preflight.get("repair_checklist", []), list) + else [] + ) + expected_queue = build_phase_queue(repair_rows) + expected_summary = summarize_phase_queue(expected_queue) + preflight_items = keyed_preflight_items(world_class_preflight) + review_steps = world_class_review_action_steps(review_studio) + expected = { + "summary": summary_signature(expected_summary), + "top_level_phase_queue": phase_queue_signature(expected_queue), + "item_phase_queues": keyed_phase_queue_signatures_from_repair_rows(preflight_items), + "phase_queue_counts_as_completion": False, + } + actual = { + "summary": summary_signature( + world_class_preflight.get("summary", {}) + if isinstance(world_class_preflight.get("summary", {}), dict) + else {} + ), + "top_level_phase_queue": phase_queue_signature( + world_class_preflight.get("phase_queue", []) + if isinstance(world_class_preflight.get("phase_queue", []), list) + else [] + ), + "item_phase_queues": keyed_phase_queue_signatures_from_items(preflight_items, "phase_queue"), + "review_studio_phase_queues": keyed_phase_queue_signatures_from_items(review_steps, "phase_queue"), + "phase_queue_counts_as_completion": any( + item.get("counts_as_completion") is True + for item in world_class_preflight.get("phase_queue", []) + if isinstance(item, dict) + ), + } + expected["review_studio_phase_queues"] = expected["item_phase_queues"] + return { + "key": "world-class-phase-queue-consistency", + "label": "World-class phase queues mirror repair rows", + "status": "pass" if expected == actual else "fail", + "expected": expected, + "actual": actual, + "paths": [report_paths["world_class_preflight"], report_paths["review_studio"]], + "detail": ( + "Phase queues must be derived from repair rows in preflight and mirrored into Review Studio " + "without counting queue guidance as completion evidence." + ), + } diff --git a/scripts/render_evidence_consistency.py b/scripts/render_evidence_consistency.py index 94513489..1b09c201 100644 --- a/scripts/render_evidence_consistency.py +++ b/scripts/render_evidence_consistency.py @@ -27,6 +27,7 @@ from evidence_consistency_core import ( report_contract, scanned_surface_paths, ) +from evidence_consistency_phase_queue import build_phase_queue_consistency_check from evidence_consistency_release import build_release_evidence_flow_check from evidence_consistency_skill_os2_review import build_skill_os2_review_current_evidence_check from evidence_consistency_world_class import build_world_class_workflow_check @@ -400,6 +401,13 @@ def build_report(skill_dir: Path, generated_at: str) -> dict[str, Any]: report_paths=REQUIRED_REPORTS, ) ) + checks.append( + build_phase_queue_consistency_check( + world_class_preflight=world_class_preflight, + review_studio=review_studio, + report_paths=REQUIRED_REPORTS, + ) + ) public_ready = bool(ledger_summary.get("ready_to_claim_world_class")) if isinstance(ledger_summary, dict) else False compare_values( diff --git a/skill-ir/examples/yao-meta-skill.json b/skill-ir/examples/yao-meta-skill.json index 31558701..da3e3c70 100644 --- a/skill-ir/examples/yao-meta-skill.json +++ b/skill-ir/examples/yao-meta-skill.json @@ -135,6 +135,7 @@ "scripts/emit_telemetry_event.py", "scripts/evidence_consistency_artifact_roles.py", "scripts/evidence_consistency_core.py", + "scripts/evidence_consistency_phase_queue.py", "scripts/evidence_consistency_release.py", "scripts/evidence_consistency_skill_os2_review.py", "scripts/evidence_consistency_world_class.py", diff --git a/skill_atlas/catalog.json b/skill_atlas/catalog.json index 0a6af4de..695cbb87 100644 --- a/skill_atlas/catalog.json +++ b/skill_atlas/catalog.json @@ -43,6 +43,7 @@ "scripts/emit_telemetry_event.py", "scripts/evidence_consistency_artifact_roles.py", "scripts/evidence_consistency_core.py", + "scripts/evidence_consistency_phase_queue.py", "scripts/evidence_consistency_release.py", "scripts/evidence_consistency_skill_os2_review.py", "scripts/evidence_consistency_world_class.py", diff --git a/tests/verify_architecture_maintainability.py b/tests/verify_architecture_maintainability.py index 653f0a2d..a8f96f25 100644 --- a/tests/verify_architecture_maintainability.py +++ b/tests/verify_architecture_maintainability.py @@ -78,7 +78,7 @@ def main() -> None: assert "No file-size hotspots found." in markdown, markdown assert "No near-threshold files found." in markdown, markdown assert "## Early Watchlist" in markdown, markdown - assert "- early watchlist: `2`" in markdown, markdown + assert f"- early watchlist: `{payload['summary']['early_watchlist_count']}`" in markdown, markdown early_watch_markdown = markdown.split("## Early Watchlist", 1)[1].split("## Largest Files", 1)[0] assert "scripts/render_review_viewer.py" not in markdown, markdown assert "scripts/render_skill_os2_coverage.py" not in markdown, markdown diff --git a/tests/verify_evidence_consistency.py b/tests/verify_evidence_consistency.py index f73f2959..4a14d54d 100644 --- a/tests/verify_evidence_consistency.py +++ b/tests/verify_evidence_consistency.py @@ -182,6 +182,22 @@ def main() -> None: assert checks["review-studio-preflight-artifact-role-handoff"]["status"] == "pass", checks[ "review-studio-preflight-artifact-role-handoff" ] + assert checks["world-class-phase-queue-consistency"]["status"] == "pass", checks[ + "world-class-phase-queue-consistency" + ] + phase_queue_actual = checks["world-class-phase-queue-consistency"]["actual"] + assert phase_queue_actual["summary"]["phase_queue_count"] == 2, phase_queue_actual + assert phase_queue_actual["summary"]["phase_queue_row_count"] == 13, phase_queue_actual + assert phase_queue_actual["phase_queue_counts_as_completion"] is False, phase_queue_actual + assert set(phase_queue_actual["item_phase_queues"]) == { + "provider-holdout", + "human-adjudication", + "native-permission-enforcement", + "native-client-telemetry", + }, phase_queue_actual + assert phase_queue_actual["review_studio_phase_queues"] == phase_queue_actual["item_phase_queues"], ( + phase_queue_actual + ) role_handoff = checks["review-studio-preflight-artifact-role-handoff"]["actual"] assert role_handoff["provider-holdout"]["role_source"] == "world-class-submission-kit", role_handoff assert role_handoff["provider-holdout"]["submission_ref_total_count"] == 1, role_handoff @@ -337,6 +353,34 @@ def main() -> None: preflight_handoff_drift_checks["preflight-submission-kit-handoff"] ) + phase_queue_drift_root = TMP / "phase-queue-drift-skill" + copy_reports(phase_queue_drift_root) + phase_queue_path = phase_queue_drift_root / "reports" / "world_class_evidence_preflight.json" + phase_queue_payload = json.loads(phase_queue_path.read_text(encoding="utf-8")) + phase_queue_payload["summary"]["phase_queue_row_count"] = 1 + phase_queue_payload["phase_queue"][0]["counts_as_completion"] = True + phase_queue_payload["items"][0]["phase_queue"][0]["row_count"] = 999 + phase_queue_path.write_text(json.dumps(phase_queue_payload, ensure_ascii=False, indent=2) + "\n", encoding="utf-8") + phase_queue_drift_proc = run( + [ + sys.executable, + str(SCRIPT), + str(phase_queue_drift_root), + "--output-json", + str(TMP / "phase_queue_drift.json"), + "--output-md", + str(TMP / "phase_queue_drift.md"), + "--generated-at", + "2026-06-15", + ] + ) + assert phase_queue_drift_proc.returncode == 2, phase_queue_drift_proc.stdout + phase_queue_drift_payload = json.loads(phase_queue_drift_proc.stdout) + phase_queue_drift_checks = {item["key"]: item for item in phase_queue_drift_payload["checks"]} + assert phase_queue_drift_checks["world-class-phase-queue-consistency"]["status"] == "fail", ( + phase_queue_drift_checks["world-class-phase-queue-consistency"] + ) + release_flow_drift_root = TMP / "release-flow-drift-skill" copy_reports(release_flow_drift_root) agents_path = release_flow_drift_root / "AGENTS.md" @@ -370,7 +414,8 @@ def main() -> None: context_path = context_drift_root / "reports" / "context_budget.json" context_payload = json.loads(context_path.read_text(encoding="utf-8")) context_payload["warnings"] = ["Deferred resource footprint is high: stale test warning."] - context_payload["stats"]["deferred_resource_governance"]["status"] = "needs-review" + context_payload["stats"]["deferred_resource_tokens"] = 1 + context_payload["stats"]["deferred_resource_governance"]["status"] = "pass" context_path.write_text(json.dumps(context_payload, ensure_ascii=False, indent=2) + "\n", encoding="utf-8") context_drift_proc = run( [
路径Path作用Role类型Type
SKILL.mdSkill 入口文件Skill entrypoint文件file
README.md人类可读使用说明Human-readable usage guide文件file
agents/interface.yaml跨平台接口元数据Neutral interface metadata文件file
manifest.json生命周期与打包元数据Lifecycle and portability metadata文件file
references扩展指导与复用资料Extended guidance and reusable notes目录folder
scripts确定性脚本或本地工具Deterministic helpers or local tooling目录folder
evals触发与质量检查Trigger and quality checks目录folder
reports生成的证据与总结报告Generated evidence and overview artifacts目录folder