docs: refresh review viewer evidence lock

This commit is contained in:
yaojingang
2026-06-14 12:40:28 +08:00
parent 17db8f0498
commit ec9474d0a6
6 changed files with 187 additions and 123 deletions
+9 -9
View File
@@ -3,7 +3,7 @@
"ok": true,
"generated_at": "2026-06-14",
"skill_dir": ".",
"commit": "328be185f6199ff1d7041378c97657b42e7e3c42",
"commit": "17db8f04980942fa5e91899ffc93c1b796df5bb8",
"git_status": {
"available": true,
"dirty": false,
@@ -17,9 +17,9 @@
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "1e0bb8068a01ef836225760c31bdd6fa04dbf4014643f5b4532d5241357c4554",
"source_contract_sha256": "7bd945074bb9066661e3f4f1c2b45a6147d0bdd467cadc3e96af1ce129dc3397",
"archive_sha256": "0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798",
"evidence_bundle_sha256": "ebcc03a915d4cd65f48e88dcf0a62b3f921b041dcc940421543f0d107c0c7870",
"source_contract_sha256": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2",
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 21,
@@ -50,7 +50,7 @@
},
"release_lock": {
"ready": true,
"commit": "328be185f6199ff1d7041378c97657b42e7e3c42",
"commit": "17db8f04980942fa5e91899ffc93c1b796df5bb8",
"status_scope": "generation-time status before this report is written",
"reason": "clean generation-time HEAD"
},
@@ -60,7 +60,7 @@
"existing_count": 24,
"missing_count": 0,
"missing_paths": [],
"sha256": "1e0bb8068a01ef836225760c31bdd6fa04dbf4014643f5b4532d5241357c4554"
"sha256": "ebcc03a915d4cd65f48e88dcf0a62b3f921b041dcc940421543f0d107c0c7870"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -169,7 +169,7 @@
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 98830,
"sha256": "39ddc420a6f8d6e0b991b54311c61ce2f7be8de8e6c7241eda8d0ffe9434bb39"
"sha256": "ffa875d30f2c73a4c876aa99953b09af72c83c3e75ee04129bb05d0a3fab50ba"
},
{
"label": "python_compatibility",
@@ -183,14 +183,14 @@
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "d02dbd2d31655fd27613765d3395212d53ca07c8ef028deeff64732ca5059dbc"
"sha256": "a9b53df3dd1baf4e4e6f5725020a6c54b9ff7834cfe5ac0d34134992186acc60"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19325,
"sha256": "e101808a5f8f97126c02fedac757d545fef3e65a7f01d9d1da2774d314af0840"
"sha256": "332f666e2f20e686d42da4f268e8e65c704d386d48bc05c2715f16974c84a5a1"
},
{
"label": "install_simulation",
+8 -8
View File
@@ -1,9 +1,9 @@
# Benchmark Reproducibility
Generated at: `2026-06-14`
Commit: `328be185f6199ff1d7041378c97657b42e7e3c42`
Commit: `17db8f04980942fa5e91899ffc93c1b796df5bb8`
Working tree dirty at generation: `false`
Evidence bundle SHA256: `1e0bb8068a01ef836225760c31bdd6fa04dbf4014643f5b4532d5241357c4554`
Evidence bundle SHA256: `ebcc03a915d4cd65f48e88dcf0a62b3f921b041dcc940421543f0d107c0c7870`
## Summary
@@ -12,8 +12,8 @@ Evidence bundle SHA256: `1e0bb8068a01ef836225760c31bdd6fa04dbf4014643f5b4532d524
- methodology complete: `true`
- required artifacts: `24`
- missing artifacts: `0`
- source contract sha256: `7bd945074bb9`
- archive sha256: `0488c5b84d90`
- source contract sha256: `8a63d5ebc9ac`
- archive sha256: `73cbe952a5a4`
- output cases: `5`
- disclosed failure cases: `3`
- reproduction commands: `21`
@@ -48,7 +48,7 @@ This report proves local benchmark reproducibility only. It keeps external provi
- algorithm: `sha256(path,label,exists,artifact_sha256)`
- artifacts: `24` / `24`
- sha256: `1e0bb8068a01ef836225760c31bdd6fa04dbf4014643f5b4532d5241357c4554`
- sha256: `ebcc03a915d4cd65f48e88dcf0a62b3f921b041dcc940421543f0d107c0c7870`
## Methodology Sections
@@ -75,10 +75,10 @@ This report proves local benchmark reproducibility only. It keeps external provi
| review_adjudication | `reports/output_review_adjudication.json` | present | `240485a721af` |
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
| runtime_conformance | `reports/conformance_matrix.json` | present | `8251329e663d` |
| trust_report | `reports/security_trust_report.json` | present | `39ddc420a6f8` |
| trust_report | `reports/security_trust_report.json` | present | `ffa875d30f2c` |
| python_compatibility | `reports/python_compatibility.json` | present | `ae16e17266e4` |
| registry_audit | `reports/registry_audit.json` | present | `d02dbd2d3165` |
| package_verification | `reports/package_verification.json` | present | `e101808a5f8f` |
| registry_audit | `reports/registry_audit.json` | present | `a9b53df3dd1b` |
| package_verification | `reports/package_verification.json` | present | `332f666e2f20` |
| install_simulation | `reports/install_simulation.json` | present | `8f987e805c92` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `6bb2dcb0e1e5` |
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `164803bb1cea` |
+6 -6
View File
@@ -505,12 +505,12 @@
<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>3 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>20/20</strong><p>2.0 coverage; 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>97 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>159 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>888 largest lines; 34 CLI handlers</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>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>73 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>576 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>3 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>20/20</strong><p>2.0 coverage; 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>97 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>159 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>891 largest lines; 34 CLI handlers</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>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>73 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>576 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>
<h2>审查闸门</h2>
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>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</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 960/1000; deferred 388240/120000; top deferred scripts 340504; resource governance governed; quality density 135.4</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 97 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 159 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>156 Python files; 0 hotspots; 0 blockers; largest 888 lines; 34 CLI handlers</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low</p><footer>reports/adoption_drift_report.json <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>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</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 960/1000; deferred 388370/120000; top deferred scripts 340634; resource governance governed; quality density 135.4</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 97 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 159 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>156 Python files; 0 hotspots; 0 blockers; largest 891 lines; 34 CLI handlers</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low</p><footer>reports/adoption_drift_report.json <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
</section>
<div class="twocol">
@@ -572,12 +572,12 @@
</section>
<section class="twocol">
<div class="panel"><h2>上下文</h2><p>initial load 960/1000; deferred 388240/120000; top deferred scripts 340504; resource governance governed; quality density 135.4</p></div>
<div class="panel"><h2>上下文</h2><p>initial load 960/1000; deferred 388370/120000; top deferred scripts 340634; resource governance governed; quality density 135.4</p></div>
<div class="panel"><h2>编译证据</h2><p>Review reports/compiled_targets.md before packaging to inspect target adapter modes, generated files, preserved semantics, warnings, and unsupported features.</p></div>
</section>
<section id="trust" class="twocol">
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>97</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>7bd945074bb9066661e3f4f1c2b45a6147d0bdd467cadc3e96af1ce129dc3397</code></dd></div></dl></div>
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>97</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2</code></dd></div></dl></div>
<div class="panel"><h2>安全边界</h2><p>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。</p></div>
</section>
@@ -656,12 +656,12 @@
<section id="registry" class="twocol">
<div class="panel"><h2>注册审计</h2><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p></div>
<div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible, vscode</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798</code></dd></div></dl></div>
<div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible, vscode</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496</code></dd></div></dl></div>
</section>
<section id="release" class="twocol">
<div class="panel"><h2>发布路线</h2><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p></div>
<div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd></dd></div><div><dt>Zip 条目</dt><dd>576</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798</code></dd></div></dl></div>
<div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd></dd></div><div><dt>Zip 条目</dt><dd>576</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496</code></dd></div></dl></div>
</section>
<section class="twocol">
+40 -40
View File
@@ -43,7 +43,7 @@
"key": "context-budget",
"label": "上下文",
"status": "pass",
"detail": "initial load 960/1000; deferred 388240/120000; top deferred scripts 340504; resource governance governed; quality density 135.4",
"detail": "initial load 960/1000; deferred 388370/120000; top deferred scripts 340634; resource governance governed; quality density 135.4",
"evidence": "reports/context_budget.json",
"link": "context_budget.md"
},
@@ -75,7 +75,7 @@
"key": "architecture-maintainability",
"label": "架构维护",
"status": "pass",
"detail": "156 Python files; 0 hotspots; 0 blockers; largest 888 lines; 34 CLI handlers",
"detail": "156 Python files; 0 hotspots; 0 blockers; largest 891 lines; 34 CLI handlers",
"evidence": "reports/architecture_maintainability.json",
"link": "architecture_maintainability.md"
},
@@ -1336,9 +1336,9 @@
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "1e0bb8068a01ef836225760c31bdd6fa04dbf4014643f5b4532d5241357c4554",
"source_contract_sha256": "7bd945074bb9066661e3f4f1c2b45a6147d0bdd467cadc3e96af1ce129dc3397",
"archive_sha256": "0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798",
"evidence_bundle_sha256": "ebcc03a915d4cd65f48e88dcf0a62b3f921b041dcc940421543f0d107c0c7870",
"source_contract_sha256": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2",
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 21,
@@ -1357,7 +1357,7 @@
"working_tree_dirty": false,
"changed_file_count": 0
},
"commit": "328be185f6199ff1d7041378c97657b42e7e3c42",
"commit": "17db8f04980942fa5e91899ffc93c1b796df5bb8",
"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.",
@@ -1462,7 +1462,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 181,
"package_sha256": "7bd945074bb9066661e3f4f1c2b45a6147d0bdd467cadc3e96af1ce129dc3397"
"package_sha256": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2"
},
"skill_atlas": {
"skill_count": 12,
@@ -1500,8 +1500,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "7bd945074bb9066661e3f4f1c2b45a6147d0bdd467cadc3e96af1ce129dc3397",
"archive_sha256": "0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798"
"package_sha256": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2",
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496"
},
"compatibility": {
"openai": "pass",
@@ -1532,7 +1532,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798",
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1548,7 +1548,7 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798",
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496",
"archive_entry_count": 576,
"failure_count": 0,
"warning_count": 0
@@ -1627,12 +1627,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798"
"to": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "7bd945074bb9066661e3f4f1c2b45a6147d0bdd467cadc3e96af1ce129dc3397"
"to": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2"
}
]
},
@@ -4764,7 +4764,7 @@
"ok": true,
"generated_at": "2026-06-14",
"skill_dir": ".",
"commit": "328be185f6199ff1d7041378c97657b42e7e3c42",
"commit": "17db8f04980942fa5e91899ffc93c1b796df5bb8",
"git_status": {
"available": true,
"dirty": false,
@@ -4778,9 +4778,9 @@
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "1e0bb8068a01ef836225760c31bdd6fa04dbf4014643f5b4532d5241357c4554",
"source_contract_sha256": "7bd945074bb9066661e3f4f1c2b45a6147d0bdd467cadc3e96af1ce129dc3397",
"archive_sha256": "0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798",
"evidence_bundle_sha256": "ebcc03a915d4cd65f48e88dcf0a62b3f921b041dcc940421543f0d107c0c7870",
"source_contract_sha256": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2",
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 21,
@@ -4811,7 +4811,7 @@
},
"release_lock": {
"ready": true,
"commit": "328be185f6199ff1d7041378c97657b42e7e3c42",
"commit": "17db8f04980942fa5e91899ffc93c1b796df5bb8",
"status_scope": "generation-time status before this report is written",
"reason": "clean generation-time HEAD"
},
@@ -4821,7 +4821,7 @@
"existing_count": 24,
"missing_count": 0,
"missing_paths": [],
"sha256": "1e0bb8068a01ef836225760c31bdd6fa04dbf4014643f5b4532d5241357c4554"
"sha256": "ebcc03a915d4cd65f48e88dcf0a62b3f921b041dcc940421543f0d107c0c7870"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -4930,7 +4930,7 @@
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 98830,
"sha256": "39ddc420a6f8d6e0b991b54311c61ce2f7be8de8e6c7241eda8d0ffe9434bb39"
"sha256": "ffa875d30f2c73a4c876aa99953b09af72c83c3e75ee04129bb05d0a3fab50ba"
},
{
"label": "python_compatibility",
@@ -4944,14 +4944,14 @@
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "d02dbd2d31655fd27613765d3395212d53ca07c8ef028deeff64732ca5059dbc"
"sha256": "a9b53df3dd1baf4e4e6f5725020a6c54b9ff7834cfe5ac0d34134992186acc60"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19325,
"sha256": "e101808a5f8f97126c02fedac757d545fef3e65a7f01d9d1da2774d314af0840"
"sha256": "332f666e2f20e686d42da4f268e8e65c704d386d48bc05c2715f16974c84a5a1"
},
{
"label": "install_simulation",
@@ -10653,7 +10653,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 181,
"package_sha256": "7bd945074bb9066661e3f4f1c2b45a6147d0bdd467cadc3e96af1ce129dc3397"
"package_sha256": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2"
},
"failures": [],
"warnings": [],
@@ -14101,7 +14101,7 @@
"command_handler_count": 34,
"warn_line_threshold": 900,
"block_line_threshold": 1500,
"largest_file_lines": 888,
"largest_file_lines": 891,
"hotspot_count": 0,
"blocker_count": 0,
"decision": "pass"
@@ -14109,14 +14109,14 @@
"largest_files": [
{
"path": "tests/verify_yao_cli.py",
"lines": 888,
"lines": 891,
"kind": "test",
"severity": "pass",
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/yao.py",
"lines": 874,
"lines": 881,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Split command handlers by domain while keeping scripts/yao.py as the thin CLI orchestrator."
@@ -14207,15 +14207,15 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 767,
"other_text_tokens": 1204831,
"other_text_tokens": 1205660,
"estimated_initial_load_tokens": 960,
"estimated_total_text_tokens": 1205598,
"deferred_resource_tokens": 388240,
"estimated_total_text_tokens": 1206427,
"deferred_resource_tokens": 388370,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 340504,
"estimated_tokens": 340634,
"file_count": 97
},
{
@@ -14232,7 +14232,7 @@
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 340504,
"estimated_tokens": 340634,
"file_count": 97
}
],
@@ -14255,14 +14255,14 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 340504,
"estimated_tokens": 340634,
"file_count": 97,
"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": 510,
"relevant_file_count": 511,
"unused_resource_dirs": [],
"quality_signal_points": 130,
"quality_density": 135.4
@@ -17748,8 +17748,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "7bd945074bb9066661e3f4f1c2b45a6147d0bdd467cadc3e96af1ce129dc3397",
"archive_sha256": "0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798"
"package_sha256": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2",
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496"
},
"compatibility": {
"openai": "pass",
@@ -17780,7 +17780,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798",
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -17805,7 +17805,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "7bd945074bb9066661e3f4f1c2b45a6147d0bdd467cadc3e96af1ce129dc3397"
"package_sha256": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2"
}
]
},
@@ -17828,7 +17828,7 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798",
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496",
"archive_entry_count": 576,
"failure_count": 0,
"warning_count": 0
@@ -18836,12 +18836,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798"
"to": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "7bd945074bb9066661e3f4f1c2b45a6147d0bdd467cadc3e96af1ce129dc3397"
"to": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2"
}
]
},
+113 -49
View File
@@ -17,9 +17,10 @@
"reports/output_quality_scorecard.md",
"reports/output_execution_runs.md",
"reports/output_blind_review_pack.md",
"reports/output_blind_answer_key.json",
"reports/output_review_kit.md",
"reports/output_review_adjudication.md",
"reports/benchmark_reproducibility.md",
"reports/output_blind_answer_key.json",
"reports/conformance_matrix.md",
"reports/security_trust_report.md",
"reports/runtime_permission_probes.md",
@@ -79,7 +80,7 @@
"label": "可维护性",
"score": 100,
"reasons": [
"SKILL.md 约 350 个词/字。",
"SKILL.md 约 356 个词/字。",
"入口文件保持克制,可维护性较好。",
"references/ 已承载扩展指导。",
"scripts/ 已承载确定性逻辑。",
@@ -100,7 +101,7 @@
"label": "上下文成本",
"score": 42,
"reasons": [
"入口约 350 个词/字,references 约 15394 个词/字。",
"入口约 356 个词/字,references 约 15566 个词/字。",
"分数越高代表上下文成本越低。",
"上下文成本偏高,建议压缩入口或拆分 references。"
]
@@ -204,7 +205,7 @@
"已生成 Output Review Adjudication,可记录盲评决策、一致率和待评审项。"
],
"gaps": [
"上下文成本需要补强:入口约 350 个词/字,references 约 15394 个词/字。"
"上下文成本需要补强:入口约 356 个词/字,references 约 15566 个词/字。"
],
"recommendations": [
"先改触发边界,再扩展工作流。",
@@ -269,7 +270,7 @@
"name": "包体膨胀风险",
"impact": 2,
"probability": 1,
"signal": "SKILL.md 约 350 个词/字。",
"signal": "SKILL.md 约 356 个词/字。",
"response": "先补证据和边界,再增加包体复杂度。"
},
{
@@ -437,7 +438,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 90
"file_count": 97
},
{
"path": "evals",
@@ -449,10 +450,10 @@
"path": "reports",
"label": "Generated evidence and overview artifacts",
"kind": "folder",
"file_count": 195
"file_count": 203
}
],
"file_count": 349,
"file_count": 364,
"folder_count": 4,
"distribution": [
{
@@ -477,7 +478,7 @@
},
{
"label": "scripts",
"value": 90
"value": 97
},
{
"label": "evals",
@@ -485,7 +486,7 @@
},
{
"label": "reports",
"value": 195
"value": 203
}
]
},
@@ -606,7 +607,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 90
"file_count": 97
},
{
"path": "evals",
@@ -618,7 +619,7 @@
"path": "reports",
"label": "Generated evidence and overview artifacts",
"kind": "folder",
"file_count": 195
"file_count": 203
}
],
"strengths": [
@@ -866,6 +867,31 @@
"pair_count": 5,
"answer_key_separate": true
},
"output_review_kit": {
"ok": true,
"summary": {
"case_count": 5,
"ready_for_adjudication_count": 0,
"pending_decision_count": 5,
"invalid_decision_count": 0,
"reviewer_metadata_present": false,
"answer_key_hidden": true,
"answer_key_path_exposed": false,
"ready_to_run_adjudication": false,
"failure_count": 0
},
"artifacts": {
"reviewer_kit_json": "reports/output_review_kit.json",
"reviewer_kit_markdown": "reports/output_review_kit.md",
"reviewer_kit_html": "reports/output_review_kit.html",
"blind_pack_json": "reports/output_blind_review_pack.json",
"blind_pack_markdown": "reports/output_blind_review_pack.md",
"decisions": "reports/output_review_decisions.json",
"adjudication_json": "reports/output_review_adjudication.json",
"adjudication_markdown": "reports/output_review_adjudication.md"
},
"failures": []
},
"output_review_adjudication": {
"ok": true,
"summary": {
@@ -893,12 +919,16 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"methodology_complete": true,
"required_artifact_count": 20,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "ebcc03a915d4cd65f48e88dcf0a62b3f921b041dcc940421543f0d107c0c7870",
"source_contract_sha256": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2",
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 19,
"command_count": 21,
"command_executed_count": 10,
"timing_observed_count": 10,
"model_executed_count": 0,
@@ -909,12 +939,15 @@
"world_class_open_gap_count": 4,
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"working_tree_dirty": true,
"changed_file_count": 30
"public_claim_ready": false,
"public_claim_blocker_count": 3,
"working_tree_dirty": false,
"changed_file_count": 0
},
"commit": "c5e7b05faae8536b420c5120c1d3a59456c96e51",
"commit": "17db8f04980942fa5e91899ffc93c1b796df5bb8",
"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.",
"Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.",
"Pending blind-review decisions are visible but do not count as human adjudication.",
"World-class readiness remains false until external and human evidence gaps close."
@@ -935,7 +968,15 @@
"metadata_fallback_count": 4,
"residual_risk_count": 4,
"required_capability_count": 3,
"failure_count": 0
"failure_count": 0,
"installer_enforcement_source_status": "present",
"installer_enforcement_target_count": 4,
"installer_enforcement_pass_count": 4,
"installer_permission_enforced_count": 12,
"installer_permission_failure_count": 0,
"installer_permission_capability_count": 3,
"world_class_native_evidence_ready": false,
"installer_enforcement_ready": true
},
"expected_capabilities": [
"file_write",
@@ -987,9 +1028,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 174,
"script_count": 90,
"internal_module_count": 17,
"scanned_files": 181,
"script_count": 97,
"internal_module_count": 20,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -997,18 +1038,18 @@
"network_script_count": 3,
"network_policy_covered_count": 3,
"network_policy_missing_count": 0,
"file_write_script_count": 60,
"file_write_script_count": 64,
"permission_required_count": 3,
"permission_approved_count": 3,
"permission_missing_count": 0,
"permission_invalid_count": 0,
"permission_expired_count": 0,
"help_smoke_checked_count": 73,
"help_smoke_checked_count": 77,
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 174,
"package_sha256": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9"
"package_hash_file_count": 181,
"package_sha256": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2"
},
"skill_atlas": {
"skill_count": 12,
@@ -1046,8 +1087,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9",
"archive_sha256": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d"
"package_sha256": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2",
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496"
},
"compatibility": {
"openai": "pass",
@@ -1078,7 +1119,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d",
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1094,8 +1135,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d",
"archive_entry_count": 558,
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496",
"archive_entry_count": 576,
"failure_count": 0,
"warning_count": 0
},
@@ -1106,7 +1147,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 558,
"archive_entry_count": 576,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1116,7 +1157,7 @@
"installer_permission_failure_count": 0,
"permission_target_count": 4,
"permission_capability_count": 3,
"install_root_is_temp": true,
"install_root_is_temp": false,
"failure_count": 0,
"warning_count": 0
},
@@ -1173,12 +1214,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d"
"to": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9"
"to": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2"
}
]
},
@@ -1298,7 +1339,10 @@
"summary": {
"audit_decision": "continue-iteration",
"world_class_ready": false,
"audit_world_class_ready": false,
"ready_to_claim_world_class": false,
"ledger_completion_required": true,
"evidence_requirement_count": 4,
"task_count": 4,
"human_task_count": 1,
"external_task_count": 3,
@@ -1318,7 +1362,7 @@
"YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
"Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
"python3 scripts/yao.py world-class-intake ."
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
],
"success_checks": [
"reports/output_execution_runs.json summary.model_executed_count > 0",
@@ -1350,13 +1394,14 @@
"current": "0/5 decisions; pending 5",
"objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
"runbook": [
"python3 scripts/yao.py output-review-kit --write-template",
"Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.",
"python3 scripts/adjudicate_output_review.py --write-template",
"Open reports/output_blind_review_pack.md and choose A or B for each pair without opening the answer key.",
"Edit reports/output_review_decisions.json with winner_variant values and reviewer metadata.",
"python3 scripts/yao.py output-review",
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
"Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.",
"python3 scripts/yao.py world-class-intake ."
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
],
"success_checks": [
"reports/output_review_adjudication.json summary.pending_count == 0",
@@ -1366,6 +1411,7 @@
],
"evidence_artifacts": [
"reports/output_blind_review_pack.md",
"reports/output_review_kit.md",
"reports/output_review_decisions.json",
"reports/output_review_adjudication.json",
"reports/output_review_adjudication.md",
@@ -1386,26 +1432,30 @@
"status": "external_required",
"category": "external",
"owner": "target client or installer integrator",
"current": "native-enforced targets 0",
"objective": "Prove at least one target or installer enforces approved high-permission capabilities at runtime.",
"current": "native-enforced targets 0; installer-enforced targets 4",
"objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
"runbook": [
"Implement or connect a real target client/installer guard that blocks undeclared network, file_write, or subprocess capabilities.",
"Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.",
"Update the generated target adapter only when the guard is actually enforced by that target.",
"python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip",
"python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation",
"python3 scripts/yao.py runtime-permissions . --package-dir dist",
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
"Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.",
"python3 scripts/yao.py world-class-intake ."
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
],
"success_checks": [
"reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
"reports/runtime_permission_probes.json summary.failure_count == 0",
"reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence",
"reports/skill_os2_audit.json item native-permission-enforcement status becomes pass"
],
"evidence_artifacts": [
"dist/targets/*/adapter.json",
"reports/runtime_permission_probes.json",
"reports/runtime_permission_probes.md",
"reports/install_simulation.json",
"reports/install_simulation.md",
"security/permission_policy.json",
"evidence/world_class/intake.schema.json",
"evidence/world_class/templates/native-permission-enforcement.intake.json",
@@ -1416,7 +1466,7 @@
"Do not mark native_enforcement true for metadata-only fallbacks.",
"Keep residual risks visible for targets that still rely on operator enforcement."
],
"audit_next_action": "Integrate a real client or installer runtime guard before claiming native permission enforcement."
"audit_next_action": "Integrate a real target-client or external installer runtime guard before claiming native permission enforcement."
},
{
"key": "native-client-telemetry",
@@ -1433,7 +1483,7 @@
"python3 scripts/yao.py skill-atlas --workspace-root .",
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
"Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.",
"python3 scripts/yao.py world-class-intake ."
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
],
"success_checks": [
"reports/adoption_drift_report.json summary.source_types.external > 0",
@@ -1467,6 +1517,7 @@
"ok": true,
"summary": {
"ledger_entry_count": 4,
"source_accepted_count": 0,
"accepted_count": 0,
"pending_count": 4,
"human_pending_count": 1,
@@ -1475,6 +1526,7 @@
"missing_submission_count": 4,
"invalid_submission_count": 0,
"submitted_but_pending_count": 0,
"source_accepted_without_valid_submission_count": 0,
"overclaim_guard_active": true,
"ready_to_claim_world_class": false,
"decision": "evidence-pending"
@@ -1487,6 +1539,7 @@
"owner": "operator with provider credentials",
"status": "pending",
"source_status": "external_required",
"source_accepted": false,
"current": "model-executed 0; token-observed 0",
"objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
"provenance_requirements": [
@@ -1542,6 +1595,7 @@
"owner": "human reviewer",
"status": "pending",
"source_status": "human_required",
"source_accepted": false,
"current": "0/5 decisions; pending 5",
"objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
"provenance_requirements": [
@@ -1557,6 +1611,7 @@
],
"evidence_artifacts": [
"reports/output_blind_review_pack.md",
"reports/output_review_kit.md",
"reports/output_review_decisions.json",
"reports/output_review_adjudication.json",
"reports/output_review_adjudication.md",
@@ -1600,22 +1655,26 @@
"owner": "target client or installer integrator",
"status": "pending",
"source_status": "external_required",
"current": "native-enforced targets 0",
"objective": "Prove at least one target or installer enforces approved high-permission capabilities at runtime.",
"source_accepted": false,
"current": "native-enforced targets 0; installer-enforced targets 4",
"objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
"provenance_requirements": [
"real target or installer guard",
"native enforcement flag",
"real target client or external installer runtime guard",
"native enforcement flag or externally accepted guard proof",
"residual risk retained for fallback targets"
],
"success_checks": [
"reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
"reports/runtime_permission_probes.json summary.failure_count == 0",
"reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence",
"reports/skill_os2_audit.json item native-permission-enforcement status becomes pass"
],
"evidence_artifacts": [
"dist/targets/*/adapter.json",
"reports/runtime_permission_probes.json",
"reports/runtime_permission_probes.md",
"reports/install_simulation.json",
"reports/install_simulation.md",
"security/permission_policy.json",
"evidence/world_class/intake.schema.json",
"evidence/world_class/templates/native-permission-enforcement.intake.json",
@@ -1629,6 +1688,9 @@
"observed_state": {
"native_enforcement_count": 0,
"metadata_fallback_count": 4,
"installer_enforcement_pass_count": 4,
"installer_permission_failure_count": 0,
"installer_enforcement_ready": true,
"residual_risk_count": 4,
"failure_count": 0,
"accepted": false
@@ -1647,7 +1709,7 @@
"pending_review_counts_as_human_decision": false,
"local_command_runner_counts_as_provider_model": false
},
"next_action": "Integrate a real client or installer runtime guard before claiming native permission enforcement."
"next_action": "Integrate a real target-client or external installer runtime guard before claiming native permission enforcement."
},
{
"key": "native-client-telemetry",
@@ -1656,6 +1718,7 @@
"owner": "Browser/Chrome/IDE/provider client integrator",
"status": "pending",
"source_status": "external_required",
"source_accepted": false,
"current": "external source events 0; adoption samples 0",
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"provenance_requirements": [
@@ -1709,7 +1772,8 @@
"source_plan": {
"json": "reports/world_class_evidence_plan.json",
"markdown": "reports/world_class_evidence_plan.md",
"task_count": 4
"task_count": 4,
"evidence_requirement_count": 4
}
},
"synthesis_highlights": [
+11 -11
View File
@@ -922,9 +922,9 @@
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "1e0bb8068a01ef836225760c31bdd6fa04dbf4014643f5b4532d5241357c4554",
"source_contract_sha256": "7bd945074bb9066661e3f4f1c2b45a6147d0bdd467cadc3e96af1ce129dc3397",
"archive_sha256": "0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798",
"evidence_bundle_sha256": "ebcc03a915d4cd65f48e88dcf0a62b3f921b041dcc940421543f0d107c0c7870",
"source_contract_sha256": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2",
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 21,
@@ -943,7 +943,7 @@
"working_tree_dirty": false,
"changed_file_count": 0
},
"commit": "328be185f6199ff1d7041378c97657b42e7e3c42",
"commit": "17db8f04980942fa5e91899ffc93c1b796df5bb8",
"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.",
@@ -1048,7 +1048,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 181,
"package_sha256": "7bd945074bb9066661e3f4f1c2b45a6147d0bdd467cadc3e96af1ce129dc3397"
"package_sha256": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2"
},
"skill_atlas": {
"skill_count": 12,
@@ -1086,8 +1086,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "7bd945074bb9066661e3f4f1c2b45a6147d0bdd467cadc3e96af1ce129dc3397",
"archive_sha256": "0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798"
"package_sha256": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2",
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496"
},
"compatibility": {
"openai": "pass",
@@ -1118,7 +1118,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798",
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1134,7 +1134,7 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798",
"archive_sha256": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496",
"archive_entry_count": 576,
"failure_count": 0,
"warning_count": 0
@@ -1213,12 +1213,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "0488c5b84d906354c41570de908244ed8af5d55b55f3f01f94bdfdff99851798"
"to": "73cbe952a5a437ab3568fab5ffad102273e4188a6a877c13be755fea1777d496"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "7bd945074bb9066661e3f4f1c2b45a6147d0bdd467cadc3e96af1ce129dc3397"
"to": "8a63d5ebc9ac16b7ace805fa6373f591d993a135e099eacdb209596db70f3bf2"
}
]
},