Refresh clean privacy guard release locks

2026-06-17 00:09:52 +08:00
parent 4a5880bea1
commit 500f8cc34e
8 changed files with 66 additions and 73 deletions
@@ -3,19 +3,17 @@
  "ok": true,
  "generated_at": "2026-06-17",
  "skill_dir": ".",
-  "commit": "f3957bfc06b84e766ae56377baa73a7062509a59",
+  "commit": "4a5880bea1a07966e0d914c453d22cf6132c5781",
  "git_status": {
    "available": true,
-    "dirty": true,
-    "changed_file_count": 1,
-    "sample": [
-      " M reports/context_budget.json"
-    ],
+    "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": 25,
    "missing_artifact_count": 0,
@@ -39,15 +37,14 @@
    "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": 1
+    "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)",
@@ -56,10 +53,10 @@
    "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": "f3957bfc06b84e766ae56377baa73a7062509a59",
+    "ready": true,
+    "commit": "4a5880bea1a07966e0d914c453d22cf6132c5781",
    "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)",
@@ -1,14 +1,14 @@
 # Benchmark Reproducibility

 Generated at: `2026-06-17`
-Commit: `f3957bfc06b84e766ae56377baa73a7062509a59`
-Working tree dirty at generation: `true`
+Commit: `4a5880bea1a07966e0d914c453d22cf6132c5781`
+Working tree dirty at generation: `false`
 Evidence bundle SHA256: `62e7b774ed1b2bd66e28986ad09ffecb9da8ae4d9008641cfe63dcfe354f0c91`

 ## Summary

 - reproducibility ready: `true`
- release lock ready: `false`
+- release lock ready: `true`
 - methodology complete: `true`
 - required artifacts: `25`
 - missing artifacts: `0`
@@ -22,8 +22,8 @@ Evidence bundle SHA256: `62e7b774ed1b2bd66e28986ad09ffecb9da8ae4d9008641cfe63dcf
 - world-class ready: `false`
 - world-class source checks: `6` pass / `13` total; `7` blocked
 - public claim ready: `false`
- public claim blockers: `5`
- changed files at generation: `1`
+- public claim blockers: `4`
+- changed files at generation: `0`

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

@@ -35,7 +35,6 @@ 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) |
@@ -43,8 +42,8 @@ This report proves local benchmark reproducibility only. It keeps external provi

 ## Release Lock

- ready: `false`
- reason: working tree was dirty at generation time
+- ready: `true`
+- reason: clean generation-time HEAD
 - status scope: generation-time status before this report is written

 ## Evidence Bundle
@@ -207,8 +207,8 @@
      "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"
      ],
@@ -248,8 +248,8 @@
      "key": "overview-benchmark-commit",
      "label": "overview embeds the benchmark commit",
      "status": "pass",
-      "expected": "f3957bfc06b84e766ae56377baa73a7062509a59",
-      "actual": "f3957bfc06b84e766ae56377baa73a7062509a59",
+      "expected": "4a5880bea1a07966e0d914c453d22cf6132c5781",
+      "actual": "4a5880bea1a07966e0d914c453d22cf6132c5781",
      "paths": [
        "reports/benchmark_reproducibility.json",
        "reports/skill-overview.json"
@@ -261,7 +261,7 @@
      "label": "overview embeds benchmark summary fields",
      "status": "pass",
      "expected": {
-        "release_lock_ready": false,
+        "release_lock_ready": true,
        "required_artifact_count": 25,
        "missing_artifact_count": 0,
        "source_contract_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627",
@@ -271,10 +271,10 @@
        "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": 25,
        "missing_artifact_count": 0,
        "source_contract_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627",
@@ -284,7 +284,7 @@
        "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",
@@ -394,8 +394,8 @@
      "key": "interpretation-benchmark-commit",
      "label": "interpretation embeds the benchmark commit",
      "status": "pass",
-      "expected": "f3957bfc06b84e766ae56377baa73a7062509a59",
-      "actual": "f3957bfc06b84e766ae56377baa73a7062509a59",
+      "expected": "4a5880bea1a07966e0d914c453d22cf6132c5781",
+      "actual": "4a5880bea1a07966e0d914c453d22cf6132c5781",
      "paths": [
        "reports/benchmark_reproducibility.json",
        "reports/skill-interpretation.json"
@@ -407,7 +407,7 @@
      "label": "interpretation embeds benchmark summary fields",
      "status": "pass",
      "expected": {
-        "release_lock_ready": false,
+        "release_lock_ready": true,
        "required_artifact_count": 25,
        "missing_artifact_count": 0,
        "source_contract_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627",
@@ -417,10 +417,10 @@
        "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": 25,
        "missing_artifact_count": 0,
        "source_contract_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627",
@@ -430,7 +430,7 @@
        "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",
@@ -740,7 +740,7 @@

    <section>
      <h2>核心指标</h2>
-      <div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>5 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>140 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>218 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>696 largest lines; 0 watchlist; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock false</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>180 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>658 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
+      <div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>4 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>140 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>218 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>696 largest lines; 0 watchlist; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock false</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>180 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>658 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
    </section>

    <section>
@@ -882,8 +882,8 @@
    </section>

    <section class="twocol">
-      <div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>5</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
-      <div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>release lock is not clean or commit is unavailable</span></li><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
+      <div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>4</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
+      <div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
    </section>

    <section class="twocol">
@@ -1968,7 +1968,7 @@
        "ok": true,
        "summary": {
          "reproducibility_ready": true,
-          "release_lock_ready": false,
+          "release_lock_ready": true,
          "methodology_complete": true,
          "required_artifact_count": 25,
          "missing_artifact_count": 0,
@@ -1992,11 +1992,11 @@
          "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": 1
+          "public_claim_blocker_count": 4,
+          "working_tree_dirty": false,
+          "changed_file_count": 0
        },
-        "commit": "f3957bfc06b84e766ae56377baa73a7062509a59",
+        "commit": "4a5880bea1a07966e0d914c453d22cf6132c5781",
        "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.",
@@ -5659,19 +5659,17 @@
      "ok": true,
      "generated_at": "2026-06-17",
      "skill_dir": ".",
-      "commit": "f3957bfc06b84e766ae56377baa73a7062509a59",
+      "commit": "4a5880bea1a07966e0d914c453d22cf6132c5781",
      "git_status": {
        "available": true,
-        "dirty": true,
-        "changed_file_count": 1,
-        "sample": [
-          " M reports/context_budget.json"
-        ],
+        "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": 25,
        "missing_artifact_count": 0,
@@ -5695,15 +5693,14 @@
        "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": 1
+        "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)",
@@ -5712,10 +5709,10 @@
        "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": "f3957bfc06b84e766ae56377baa73a7062509a59",
+        "ready": true,
+        "commit": "4a5880bea1a07966e0d914c453d22cf6132c5781",
        "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)",
@@ -997,7 +997,7 @@
      "ok": true,
      "summary": {
        "reproducibility_ready": true,
-        "release_lock_ready": false,
+        "release_lock_ready": true,
        "methodology_complete": true,
        "required_artifact_count": 25,
        "missing_artifact_count": 0,
@@ -1021,11 +1021,11 @@
        "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": 1
+        "public_claim_blocker_count": 4,
+        "working_tree_dirty": false,
+        "changed_file_count": 0
      },
-      "commit": "f3957bfc06b84e766ae56377baa73a7062509a59",
+      "commit": "4a5880bea1a07966e0d914c453d22cf6132c5781",
      "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.",
@@ -1001,7 +1001,7 @@
    "ok": true,
    "summary": {
      "reproducibility_ready": true,
-      "release_lock_ready": false,
+      "release_lock_ready": true,
      "methodology_complete": true,
      "required_artifact_count": 25,
      "missing_artifact_count": 0,
@@ -1025,11 +1025,11 @@
      "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": 1
+      "public_claim_blocker_count": 4,
+      "working_tree_dirty": false,
+      "changed_file_count": 0
    },
-    "commit": "f3957bfc06b84e766ae56377baa73a7062509a59",
+    "commit": "4a5880bea1a07966e0d914c453d22cf6132c5781",
    "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.",
@@ -996,7 +996,7 @@
    "ok": true,
    "summary": {
      "reproducibility_ready": true,
-      "release_lock_ready": false,
+      "release_lock_ready": true,
      "methodology_complete": true,
      "required_artifact_count": 25,
      "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": 1
+      "public_claim_blocker_count": 4,
+      "working_tree_dirty": false,
+      "changed_file_count": 0
    },
-    "commit": "f3957bfc06b84e766ae56377baa73a7062509a59",
+    "commit": "4a5880bea1a07966e0d914c453d22cf6132c5781",
    "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.",