Refresh extracted consistency release lock

2026-06-16 01:09:34 +08:00
parent a7960d4cfd
commit bc999b9508
9 changed files with 105 additions and 180 deletions
@@ -3,24 +3,21 @@
  "ok": true,
  "generated_at": "2026-06-16",
  "skill_dir": ".",
-  "commit": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
+  "commit": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf",
  "git_status": {
    "available": true,
    "dirty": true,
-    "changed_file_count": 36,
+    "changed_file_count": 9,
    "sample": [
-      " M registry/index.json",
-      " M registry/packages/yao-meta-skill.json",
-      " 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/context_budget.json",
-      " M reports/context_budget.md",
-      " M reports/context_budget_summary.json",
      " M reports/evidence_consistency.json",
-      " M reports/install_simulation.json"
+      " M reports/review-studio.html",
+      " M reports/review-studio.json",
+      " M reports/review-viewer.json",
+      " M reports/skill-interpretation.json",
+      " M reports/skill-os-2-review.md",
+      " M reports/skill-overview.json"
    ],
    "scope": "generation-time status before this report is written"
  },
@@ -52,7 +49,7 @@
    "public_claim_ready": false,
    "public_claim_blocker_count": 5,
    "working_tree_dirty": true,
-    "changed_file_count": 36
+    "changed_file_count": 9
  },
  "public_claim": {
    "ready": false,
@@ -68,7 +65,7 @@
  },
  "release_lock": {
    "ready": false,
-    "commit": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
+    "commit": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf",
    "status_scope": "generation-time status before this report is written",
    "reason": "working tree was dirty at generation time"
  },
@@ -1,7 +1,7 @@
 # Benchmark Reproducibility

 Generated at: `2026-06-16`
-Commit: `391821240ba14f088d0fbe12dd5f1fdca7917a39`
+Commit: `a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf`
 Working tree dirty at generation: `true`
 Evidence bundle SHA256: `5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8`

@@ -23,7 +23,7 @@ Evidence bundle SHA256: `5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24
 - world-class source checks: `6` pass / `13` total; `7` blocked
 - public claim ready: `false`
 - public claim blockers: `5`
- changed files at generation: `36`
+- changed files at generation: `9`

 This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.

@@ -47,8 +47,8 @@
      "key": "benchmark-release-lock-self-consistency",
      "label": "Benchmark release lock matches git dirty state",
      "status": "pass",
-      "expected": false,
-      "actual": false,
+      "expected": true,
+      "actual": true,
      "paths": [
        "reports/benchmark_reproducibility.json"
      ],
@@ -58,8 +58,8 @@
      "key": "overview-benchmark-commit",
      "label": "overview embeds the benchmark commit",
      "status": "pass",
-      "expected": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
-      "actual": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
+      "expected": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf",
+      "actual": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf",
      "paths": [
        "reports/benchmark_reproducibility.json",
        "reports/skill-overview.json"
@@ -71,7 +71,7 @@
      "label": "overview embeds benchmark summary fields",
      "status": "pass",
      "expected": {
-        "release_lock_ready": false,
+        "release_lock_ready": true,
        "required_artifact_count": 24,
        "missing_artifact_count": 0,
        "source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
@@ -81,10 +81,10 @@
        "world_class_source_pass_count": 6,
        "world_class_source_blocked_count": 7,
        "public_claim_ready": false,
-        "public_claim_blocker_count": 5
+        "public_claim_blocker_count": 4
      },
      "actual": {
-        "release_lock_ready": false,
+        "release_lock_ready": true,
        "required_artifact_count": 24,
        "missing_artifact_count": 0,
        "source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
@@ -94,7 +94,7 @@
        "world_class_source_pass_count": 6,
        "world_class_source_blocked_count": 7,
        "public_claim_ready": false,
-        "public_claim_blocker_count": 5
+        "public_claim_blocker_count": 4
      },
      "paths": [
        "reports/benchmark_reproducibility.json",
@@ -204,8 +204,8 @@
      "key": "interpretation-benchmark-commit",
      "label": "interpretation embeds the benchmark commit",
      "status": "pass",
-      "expected": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
-      "actual": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
+      "expected": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf",
+      "actual": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf",
      "paths": [
        "reports/benchmark_reproducibility.json",
        "reports/skill-interpretation.json"
@@ -217,7 +217,7 @@
      "label": "interpretation embeds benchmark summary fields",
      "status": "pass",
      "expected": {
-        "release_lock_ready": false,
+        "release_lock_ready": true,
        "required_artifact_count": 24,
        "missing_artifact_count": 0,
        "source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
@@ -227,10 +227,10 @@
        "world_class_source_pass_count": 6,
        "world_class_source_blocked_count": 7,
        "public_claim_ready": false,
-        "public_claim_blocker_count": 5
+        "public_claim_blocker_count": 4
      },
      "actual": {
-        "release_lock_ready": false,
+        "release_lock_ready": true,
        "required_artifact_count": 24,
        "missing_artifact_count": 0,
        "source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
@@ -240,7 +240,7 @@
        "world_class_source_pass_count": 6,
        "world_class_source_blocked_count": 7,
        "public_claim_ready": false,
-        "public_claim_blocker_count": 5
+        "public_claim_blocker_count": 4
      },
      "paths": [
        "reports/benchmark_reproducibility.json",
@@ -2025,9 +2025,9 @@
      "label": "Skill OS 2.0 review summary mirrors current evidence",
      "status": "pass",
      "expected": [
-        "score `89`",
+        "score `91`",
        "`16` gates",
-        "`4` warnings",
+        "`3` warnings",
        "`29` declared internal modules",
        "`82 / 82` CLI help smoke checks passing across `111` scripts",
        "`618` zip entries",
@@ -4,11 +4,11 @@
  "skill_dir": ".",
  "summary": {
    "decision": "review",
-    "world_class_score": 89,
+    "world_class_score": 91,
    "gate_count": 16,
    "blocker_count": 0,
-    "warning_count": 4,
-    "action_count": 4,
+    "warning_count": 3,
+    "action_count": 3,
    "annotation_count": 0,
    "open_annotation_count": 0,
    "open_annotation_blocker_count": 0,
@@ -42,8 +42,8 @@
    {
      "key": "context-budget",
      "label": "上下文",
-      "status": "warn",
-      "detail": "initial load 960/1000; deferred 436837/120000; top deferred scripts 387626; resource governance needs-review; quality density 135.4",
+      "status": "pass",
+      "detail": "initial load 960/1000; deferred 436837/120000; top deferred scripts 387626; resource governance governed; quality density 135.4",
      "evidence": "reports/context_budget.json",
      "link": "context_budget.md"
    },
@@ -115,7 +115,7 @@
      "key": "review-waivers",
      "label": "人工批准",
      "status": "warn",
-      "detail": "0 active waivers; 2 warning gates still need reviewer decision",
+      "detail": "0 active waivers; 1 warning gates still need reviewer decision",
      "evidence": "reports/review_waivers.json",
      "link": "review_waivers.md"
    },
@@ -154,19 +154,11 @@
      "evidence": "reports/output_quality_scorecard.json",
      "link": "output_quality_scorecard.md"
    },
-    {
-      "key": "context-budget",
-      "label": "上下文",
-      "status": "warn",
-      "detail": "initial load 960/1000; deferred 436837/120000; top deferred scripts 387626; resource governance needs-review; quality density 135.4",
-      "evidence": "reports/context_budget.json",
-      "link": "context_budget.md"
-    },
    {
      "key": "review-waivers",
      "label": "人工批准",
      "status": "warn",
-      "detail": "0 active waivers; 2 warning gates still need reviewer decision",
+      "detail": "0 active waivers; 1 warning gates still need reviewer decision",
      "evidence": "reports/review_waivers.json",
      "link": "review_waivers.md"
    },
@@ -243,53 +235,6 @@
      "verification_command": "python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review",
      "evidence_steps": []
    },
-    {
-      "gate_key": "context-budget",
-      "label": "上下文",
-      "status": "warn",
-      "priority": "warning",
-      "summary": "压缩或拆分高成本 deferred resources，保留最小可路由上下文。",
-      "why": "初始加载可以安全，但后续 references、scripts、evals 体量过大时，reviewer 仍需要看到维护和读取成本。",
-      "source_fix": "SKILL.md + references/ + scripts/ + evals/",
-      "source_refs": [
-        {
-          "path": "SKILL.md",
-          "label": "entrypoint",
-          "kind": "source",
-          "line": 9,
-          "exists": true,
-          "link": "../SKILL.md"
-        },
-        {
-          "path": "reports/context_budget.md",
-          "label": "context budget",
-          "kind": "report",
-          "line": 1,
-          "exists": true,
-          "link": "context_budget.md"
-        },
-        {
-          "path": "scripts/resource_boundary_check.py",
-          "label": "resource boundary checker",
-          "kind": "source",
-          "line": 44,
-          "exists": true,
-          "link": "../scripts/resource_boundary_check.py"
-        },
-        {
-          "path": "references/skill-engineering-method.md",
-          "label": "skill engineering method",
-          "kind": "method",
-          "line": 208,
-          "exists": true,
-          "link": "../references/skill-engineering-method.md"
-        }
-      ],
-      "evidence": "reports/context_budget.json",
-      "evidence_link": "context_budget.md",
-      "verification_command": "python3 scripts/render_context_reports.py",
-      "evidence_steps": []
-    },
    {
      "gate_key": "review-waivers",
      "label": "人工批准",
@@ -1731,13 +1676,13 @@
        "ok": true,
        "summary": {
          "reproducibility_ready": true,
-          "release_lock_ready": false,
+          "release_lock_ready": true,
          "methodology_complete": true,
          "required_artifact_count": 24,
          "missing_artifact_count": 0,
-          "evidence_bundle_sha256": "d4d58b9557d03656a800aad0acee41d5434db006ebbbff2645fbbab80962cc27",
-          "source_contract_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
-          "archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
+          "evidence_bundle_sha256": "5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8",
+          "source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
+          "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
          "output_case_count": 5,
          "failure_disclosure_count": 3,
          "command_count": 22,
@@ -1755,11 +1700,11 @@
          "world_class_source_pass_count": 6,
          "world_class_source_blocked_count": 7,
          "public_claim_ready": false,
-          "public_claim_blocker_count": 5,
-          "working_tree_dirty": true,
-          "changed_file_count": 20
+          "public_claim_blocker_count": 4,
+          "working_tree_dirty": false,
+          "changed_file_count": 0
        },
-        "commit": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
+        "commit": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf",
        "missing_artifacts": [],
        "limitations": [
          "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
@@ -4401,7 +4346,7 @@
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
-          "duration_ms": 26.59,
+          "duration_ms": 26.79,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
@@ -4429,7 +4374,7 @@
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
-          "duration_ms": 26.1,
+          "duration_ms": 27.31,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
@@ -4452,7 +4397,7 @@
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
-          "duration_ms": 26.12,
+          "duration_ms": 26.66,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
@@ -4480,7 +4425,7 @@
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
-          "duration_ms": 28.36,
+          "duration_ms": 26.21,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
@@ -4503,7 +4448,7 @@
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
-          "duration_ms": 29.38,
+          "duration_ms": 26.62,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
@@ -4531,7 +4476,7 @@
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
-          "duration_ms": 28.48,
+          "duration_ms": 26.34,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
@@ -4581,7 +4526,7 @@
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
-          "duration_ms": 25.88,
+          "duration_ms": 26.37,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
@@ -4604,7 +4549,7 @@
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
-          "duration_ms": 25.99,
+          "duration_ms": 26.44,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
@@ -4633,7 +4578,7 @@
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
-          "duration_ms": 26.23,
+          "duration_ms": 26.21,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
@@ -5354,36 +5299,23 @@
      "ok": true,
      "generated_at": "2026-06-16",
      "skill_dir": ".",
-      "commit": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
+      "commit": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf",
      "git_status": {
        "available": true,
-        "dirty": true,
-        "changed_file_count": 20,
-        "sample": [
-          " 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/context_budget.json",
-          " M reports/context_budget.md",
-          " M reports/context_budget_summary.json",
-          " M reports/output_execution_runs.json",
-          " M reports/output_execution_runs.md",
-          " M reports/python_compatibility.json",
-          " M reports/python_compatibility.md"
-        ],
+        "dirty": false,
+        "changed_file_count": 0,
+        "sample": [],
        "scope": "generation-time status before this report is written"
      },
      "summary": {
        "reproducibility_ready": true,
-        "release_lock_ready": false,
+        "release_lock_ready": true,
        "methodology_complete": true,
        "required_artifact_count": 24,
        "missing_artifact_count": 0,
-        "evidence_bundle_sha256": "d4d58b9557d03656a800aad0acee41d5434db006ebbbff2645fbbab80962cc27",
-        "source_contract_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
-        "archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
+        "evidence_bundle_sha256": "5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8",
+        "source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
+        "archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
        "output_case_count": 5,
        "failure_disclosure_count": 3,
        "command_count": 22,
@@ -5401,15 +5333,14 @@
        "world_class_source_pass_count": 6,
        "world_class_source_blocked_count": 7,
        "public_claim_ready": false,
-        "public_claim_blocker_count": 5,
-        "working_tree_dirty": true,
-        "changed_file_count": 20
+        "public_claim_blocker_count": 4,
+        "working_tree_dirty": false,
+        "changed_file_count": 0
      },
      "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)",
@@ -5418,10 +5349,10 @@
        "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
      },
      "release_lock": {
-        "ready": false,
-        "commit": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
+        "ready": true,
+        "commit": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf",
        "status_scope": "generation-time status before this report is written",
-        "reason": "working tree was dirty at generation time"
+        "reason": "clean generation-time HEAD"
      },
      "evidence_bundle": {
        "algorithm": "sha256(path,label,exists,artifact_sha256)",
@@ -5429,7 +5360,7 @@
        "existing_count": 24,
        "missing_count": 0,
        "missing_paths": [],
-        "sha256": "d4d58b9557d03656a800aad0acee41d5434db006ebbbff2645fbbab80962cc27"
+        "sha256": "5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8"
      },
      "methodology": {
        "path": "reports/benchmark_methodology.md",
@@ -5503,7 +5434,7 @@
          "path": "reports/output_execution_runs.json",
          "exists": true,
          "bytes": 7967,
-          "sha256": "2ee3f1028f48673cddeb6242eb30aee3db1eccf26c44499744f3031d6d3520d7"
+          "sha256": "56430f01ba194dc6dc793eb505f92fec7a8c46e1be4b71976a3d641c9b98c7ec"
        },
        {
          "label": "blind_review",
@@ -5537,8 +5468,8 @@
          "label": "trust_report",
          "path": "reports/security_trust_report.json",
          "exists": true,
-          "bytes": 109099,
-          "sha256": "491354ae881f6682687a62a98c9a4988bbeef931b24565fdf43e6f3a206fd449"
+          "bytes": 109726,
+          "sha256": "a3a6d4e6809ea0b78b8012e37ad68903a54876a06100434efad38ea6bfe9b2bd"
        },
        {
          "label": "python_compatibility",
@@ -5552,21 +5483,21 @@
          "path": "reports/registry_audit.json",
          "exists": true,
          "bytes": 3183,
-          "sha256": "870c455a5cd209ff8d9e8793861da074e668083d265230d04e38e8ee0ff1323a"
+          "sha256": "d6b523cc5cbb2d69c35989913e7e68dd4dc2bb04d3bcff88bbcb56fbe8be5084"
        },
        {
          "label": "package_verification",
          "path": "reports/package_verification.json",
          "exists": true,
          "bytes": 19338,
-          "sha256": "c4acb824482d992e0e4339b7eeeb8d23d49da12d3414606222f4916c3ed09df6"
+          "sha256": "ae8ac3872be3299b3d2dc18a29128346a3ecbb579987b1b08156e305237b5119"
        },
        {
          "label": "install_simulation",
          "path": "reports/install_simulation.json",
          "exists": true,
          "bytes": 8604,
-          "sha256": "28ceb014e202269bb96628391d056234794b3570ff25de0ef9bdfd7f755fd85f"
+          "sha256": "3e27a6f7678efe9d94528f811a9d3acf20cf41d6328ad5b5fa0be5714c6396a0"
        },
        {
          "label": "skill_os2_audit",
@@ -6008,7 +5939,7 @@
          "label": "Review Studio",
          "status": "pass",
          "objective": "One HTML page supports first-pass production review across trigger, output, runtime, trust, release, and evidence actions.",
-          "current": "16 gates; decision review; warnings 3",
+          "current": "16 gates; decision review; warnings 4",
          "command": "python3 scripts/yao.py review-studio .",
          "test": "python3 tests/verify_review_studio.py",
          "evidence": [
@@ -15488,16 +15419,14 @@
    "context_budget": {
      "ok": true,
      "failures": [],
-      "warnings": [
-        "Deferred resource footprint is high: 436837 estimated tokens across references/scripts/evals. Keep Review Studio warnings visible until the largest resource dirs are split, archived, or justified."
-      ],
+      "warnings": [],
      "stats": {
        "context_budget_tier": "production",
        "context_budget_limit": 1000,
        "skill_body_tokens": 767,
-        "other_text_tokens": 1376303,
+        "other_text_tokens": 1377236,
        "estimated_initial_load_tokens": 960,
-        "estimated_total_text_tokens": 1377070,
+        "estimated_total_text_tokens": 1378003,
        "deferred_resource_tokens": 436837,
        "deferred_resource_warn_threshold": 120000,
        "deferred_resource_dirs": [
@@ -15525,31 +15454,30 @@
          }
        ],
        "deferred_resource_governance": {
-          "status": "needs-review",
+          "status": "governed",
          "large_dir_count": 1,
-          "governed_large_dir_count": 0,
+          "governed_large_dir_count": 1,
          "directories": [
            {
-              "status": "needs-review",
+              "status": "governed",
              "evidence": [
                "reports/security_trust_report.json",
                "reports/architecture_maintainability.json",
                "reports/python_compatibility.json"
              ],
              "reasons": [
+                "trust report covers scripts",
                "architecture report has no script hotspots or blockers",
                "Python compatibility report has no issues"
              ],
-              "missing": [
-                "trust report covers scripts"
-              ],
+              "missing": [],
              "path": "scripts",
              "estimated_tokens": 387626,
              "file_count": 111,
              "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
            }
          ],
-          "summary": "One or more large deferred resource directories still need explicit governance evidence."
+          "summary": "Large deferred resources are indexed and backed by evidence."
        },
        "relevant_file_count": 565,
        "unused_resource_dirs": [],
@@ -17419,7 +17347,7 @@
    "adoption_drift": {
      "ok": true,
      "schema_version": "2.0",
-      "generated_at": "2026-06-15T17:03:40Z",
+      "generated_at": "2026-06-15T17:08:05Z",
      "skill_dir": ".",
      "privacy_contract": {
        "storage": "local-first",
@@ -996,7 +996,7 @@
      "ok": true,
      "summary": {
        "reproducibility_ready": true,
-        "release_lock_ready": false,
+        "release_lock_ready": true,
        "methodology_complete": true,
        "required_artifact_count": 24,
        "missing_artifact_count": 0,
@@ -1020,11 +1020,11 @@
        "world_class_source_pass_count": 6,
        "world_class_source_blocked_count": 7,
        "public_claim_ready": false,
-        "public_claim_blocker_count": 5,
-        "working_tree_dirty": true,
-        "changed_file_count": 36
+        "public_claim_blocker_count": 4,
+        "working_tree_dirty": false,
+        "changed_file_count": 0
      },
-      "commit": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
+      "commit": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf",
      "missing_artifacts": [],
      "limitations": [
        "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
@@ -1026,9 +1026,9 @@
      "public_claim_ready": false,
      "public_claim_blocker_count": 5,
      "working_tree_dirty": true,
-      "changed_file_count": 36
+      "changed_file_count": 9
    },
-    "commit": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
+    "commit": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf",
    "missing_artifacts": [],
    "limitations": [
      "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
@@ -37,7 +37,7 @@ Yao Meta Skill is no longer only a Meta Skill factory. The current working tree
 - Local Install Sync Preflight v0 so source-to-local and source-to-active install syncs rebuild the package first, run install simulation, enforce installer permission coverage, and refuse to copy files before any destructive sync when the package is not install-ready.
 - Atlas Scope Policy v0 so examples, evolution snapshots, embedded generated skills, and validator fixtures remain visible in the full portfolio report without polluting release-actionable gates.
 - Review Annotations v0 for reviewer comments tied to Review Studio gates, source/report paths, and optional line numbers; open blocker annotations now block the Review Studio decision.
- Review Studio now avoids over-claiming release readiness when blind A/B adjudication, context-budget pressure, waiver handling, and world-class evidence are still pending: the root Meta Skill is in `review` with score `89`, no blockers, four warnings, and explicit actions for Output Lab reviewer adjudication, context-budget follow-up, waiver handling, and world-class evidence completion.
+- Review Studio now avoids over-claiming release readiness when blind A/B adjudication, waiver handling, and world-class evidence are still pending: the root Meta Skill is in `review` with score `91`, no blockers, three warnings, and explicit actions for Output Lab reviewer adjudication, waiver handling, and world-class evidence completion.
 - Review Studio Output Lab actions now link directly to `reports/output_review_decisions.json`, so pending blind A/B reviewer decisions have a concrete template instead of only a general adjudication warning.
 - Output Review Adjudication now preserves blind-review integrity by hiding expected winners for pending or invalid reviewer decisions; answer keys are revealed only after a valid A/B decision exists for that case.
 - Provider Output Eval Runner v0 so `python3 scripts/yao.py output-exec --provider-runner openai` can collect real provider-backed model evidence through a reviewed OpenAI Responses API compatible runner instead of ad hoc shell glue.
@@ -91,7 +91,7 @@ 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 `89`, `16` gates, `0` blockers, `4` warnings, `4` 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, the context budget is close to its limit, 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 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.

 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.

@@ -126,7 +126,7 @@ Next move: add real client or installer permission enforcement integration.
 | Adoption Drift | `1` metadata-only review event, `0` adoption samples, adoption `0`, 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 Annotations | ledger generated; current release has `0` reviewer annotations and `0` open annotation blockers |
-| Review Studio | decision `review`, world-class score `89`, `16` gates, `0` blockers, `4` warnings, `4` review actions, `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 |
 | World-Class Evidence Plan | `4` remaining evidence tasks: `1` human-required and `3` external-required, all with runbooks, success checks, and privacy contracts |
 | 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 |
@@ -1021,9 +1021,9 @@
      "public_claim_ready": false,
      "public_claim_blocker_count": 5,
      "working_tree_dirty": true,
-      "changed_file_count": 36
+      "changed_file_count": 9
    },
-    "commit": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
+    "commit": "a7960d4cfd2d9a17cbaebcee7b823f0db13df0cf",
    "missing_artifacts": [],
    "limitations": [
      "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",