Refresh clean-lock evidence after source anchors

This commit is contained in:
yaojingang
2026-06-17 03:13:45 +08:00
parent 360f05503d
commit 00a8265b81
8 changed files with 115 additions and 144 deletions
+22 -36
View File
@@ -3,35 +3,22 @@
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "d709f043a2c286646a5c72d7345faaed932200de",
"commit": "360f05503df3d7543d74417bcaf3f6a749a23477",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 32,
"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/compiled_targets.json",
" M reports/context_budget.json",
" M reports/evidence_consistency.json",
" M reports/install_simulation.json",
" M reports/install_simulation.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": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec",
"source_contract_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7",
"evidence_bundle_sha256": "89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9",
"source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
"archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -50,15 +37,14 @@
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 8,
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 32
"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)",
@@ -67,10 +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": "d709f043a2c286646a5c72d7345faaed932200de",
"ready": true,
"commit": "360f05503df3d7543d74417bcaf3f6a749a23477",
"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)",
@@ -78,7 +64,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec"
"sha256": "89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -151,8 +137,8 @@
"label": "output_execution",
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7963,
"sha256": "ce151bc7d860840d0308731c3cf0342cae0610489d4205b452bbd4e47cc607ef"
"bytes": 7964,
"sha256": "282122e93b08d73b0c199715c51bc619a95af47d315047fc41dceb31f56a3293"
},
{
"label": "blind_review",
@@ -187,21 +173,21 @@
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 133860,
"sha256": "f110df76d439c01b2d9b4ea82561d6c5277ff407f7ef616504e3923438d4d96b"
"sha256": "d865e5cc97a3b92e1332366c5c780354afb46038ba1c6ef152a61cc8407a19bc"
},
{
"label": "python_compatibility",
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 29196,
"sha256": "636583616dbcc15fe06d582ff0eda17c08a3d37eae618b03e1ca9c666c5276d2"
"sha256": "f8e498d295db139c49e2ea51bd2cbdd52db61fa2b0bd008ef74135601d691895"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "c28991bdf087bb31370774c1dcce9987ed41eac46b2415eecda092692b9dd915"
"sha256": "88c94a496b941ef0538a7bab550c85d2fc07487edf35e4cd39bde14b1475108c"
},
{
"label": "package_verification",
@@ -214,15 +200,15 @@
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8758,
"sha256": "c91884a915384363d4ea0339de5c9a3e37ede4356ad1069edf0ae6f880366cc7"
"bytes": 8604,
"sha256": "044b2cf73dd4559a2a0b2f6cbb5560677d409d4716d135261fac6399012d1abb"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14310,
"sha256": "4f193d15332d6ae7c6df397b0c777219fc9627b61c176ca70f66e43b4e94d08e"
"sha256": "e63bc60e69cdc0e613983edea2a66f6c80d0e4da92efd6f90203c390b813350d"
},
{
"label": "world_class_evidence_plan",
+16 -17
View File
@@ -1,18 +1,18 @@
# Benchmark Reproducibility
Generated at: `2026-06-17`
Commit: `d709f043a2c286646a5c72d7345faaed932200de`
Working tree dirty at generation: `true`
Evidence bundle SHA256: `16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec`
Commit: `360f05503df3d7543d74417bcaf3f6a749a23477`
Working tree dirty at generation: `false`
Evidence bundle SHA256: `89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9`
## Summary
- reproducibility ready: `true`
- release lock ready: `false`
- release lock ready: `true`
- methodology complete: `true`
- required artifacts: `25`
- missing artifacts: `0`
- source contract sha256: `83ea6e60852f`
- source contract sha256: `e9d5b26e20c8`
- archive sha256: `563d37a1085a`
- output cases: `5`
- disclosed failure cases: `3`
@@ -22,8 +22,8 @@ Evidence bundle SHA256: `16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc9
- world-class ready: `false`
- world-class source checks: `9` pass / `17` total; `8` blocked
- public claim ready: `false`
- public claim blockers: `5`
- changed files at generation: `32`
- 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) |
@@ -43,15 +42,15 @@ 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
- algorithm: `sha256(path,label,exists,artifact_sha256)`
- artifacts: `25` / `25`
- sha256: `16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec`
- sha256: `89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9`
## Methodology Sections
@@ -73,17 +72,17 @@ This report proves local benchmark reproducibility only. It keeps external provi
| output_cases | `evals/output/cases.jsonl` | present | `a6ae96857116` |
| output_schema | `evals/output/schema.json` | present | `8ee340c95064` |
| output_scorecard | `reports/output_quality_scorecard.json` | present | `0806258a8e08` |
| output_execution | `reports/output_execution_runs.json` | present | `ce151bc7d860` |
| output_execution | `reports/output_execution_runs.json` | present | `282122e93b08` |
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
| review_adjudication | `reports/output_review_adjudication.json` | present | `2ed79f8bc7a3` |
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
| runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` |
| trust_report | `reports/security_trust_report.json` | present | `f110df76d439` |
| python_compatibility | `reports/python_compatibility.json` | present | `636583616dbc` |
| registry_audit | `reports/registry_audit.json` | present | `c28991bdf087` |
| trust_report | `reports/security_trust_report.json` | present | `d865e5cc97a3` |
| python_compatibility | `reports/python_compatibility.json` | present | `f8e498d295db` |
| registry_audit | `reports/registry_audit.json` | present | `88c94a496b94` |
| package_verification | `reports/package_verification.json` | present | `f9c6cdf1a7e0` |
| install_simulation | `reports/install_simulation.json` | present | `c91884a91538` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `4f193d15332d` |
| install_simulation | `reports/install_simulation.json` | present | `044b2cf73dd4` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `e63bc60e69cd` |
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `d9781994f88c` |
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `dc7fba17bf81` |
| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `e57fba2812b3` |
+7 -7
View File
@@ -189,12 +189,12 @@
"status": "pass",
"expected": {
"status": "pass",
"detail": "initial load 990/1000; deferred 498644/120000; top deferred scripts 437614; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 498646/120000; top deferred scripts 437616; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json"
},
"actual": {
"status": "pass",
"detail": "initial load 990/1000; deferred 498644/120000; top deferred scripts 437614; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 498646/120000; top deferred scripts 437616; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json"
},
"paths": [
@@ -222,7 +222,7 @@
"actual": {
"available": true,
"clean": false,
"changed_file_count": 9
"changed_file_count": 7
},
"paths": [
"reports/benchmark_reproducibility.json"
@@ -263,8 +263,8 @@
"key": "overview-benchmark-commit",
"label": "overview embeds the benchmark commit",
"status": "pass",
"expected": "d709f043a2c286646a5c72d7345faaed932200de",
"actual": "d709f043a2c286646a5c72d7345faaed932200de",
"expected": "360f05503df3d7543d74417bcaf3f6a749a23477",
"actual": "360f05503df3d7543d74417bcaf3f6a749a23477",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-overview.json"
@@ -409,8 +409,8 @@
"key": "interpretation-benchmark-commit",
"label": "interpretation embeds the benchmark commit",
"status": "pass",
"expected": "d709f043a2c286646a5c72d7345faaed932200de",
"actual": "d709f043a2c286646a5c72d7345faaed932200de",
"expected": "360f05503df3d7543d74417bcaf3f6a749a23477",
"actual": "360f05503df3d7543d74417bcaf3f6a749a23477",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-interpretation.json"
+5 -5
View File
@@ -740,12 +740,12 @@
<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>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>147 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>225 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>696 largest lines; 0 watchlist; 2 early; 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 true</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>182 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>685 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>147 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>225 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>696 largest lines; 0 watchlist; 2 early; 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 true</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>182 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>685 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 990/1000; deferred 498644/120000; top deferred scripts 437614; resource governance governed; quality density 131.3</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; 147 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; 225 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>222 Python files; 0 hotspots; 0 watchlist files; 2 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint</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 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <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; source checks 9/17 pass; 8 blocked; 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 990/1000; deferred 498646/120000; top deferred scripts 437616; resource governance governed; quality density 131.3</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; 147 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; 225 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>222 Python files; 0 hotspots; 0 watchlist files; 2 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint</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 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <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; source checks 9/17 pass; 8 blocked; 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>
<section>
@@ -812,7 +812,7 @@
</section>
<section class="twocol">
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 498644/120000; top deferred scripts 437614; resource governance governed; quality density 131.3</p></div>
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 498646/120000; top deferred scripts 437616; resource governance governed; quality density 131.3</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>
@@ -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></dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>可公开声明</dt><dd></dd></div><div><dt>声明阻断</dt><dd>5</dd></div><div><dt>Provider 证据</dt><dd></dd></div><div><dt>人审完成</dt><dd></dd></div><div><dt>世界级就绪</dt><dd></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 (9/17 pass, 8 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></dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>可公开声明</dt><dd></dd></div><div><dt>声明阻断</dt><dd>4</dd></div><div><dt>Provider 证据</dt><dd></dd></div><div><dt>人审完成</dt><dd></dd></div><div><dt>世界级就绪</dt><dd></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 (9/17 pass, 8 blocked)</span></li></ul></div>
</section>
<section class="twocol">
+38 -52
View File
@@ -44,7 +44,7 @@
"key": "context-budget",
"label": "上下文",
"status": "pass",
"detail": "initial load 990/1000; deferred 498644/120000; top deferred scripts 437614; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 498646/120000; top deferred scripts 437616; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json",
"link": "context_budget.md"
},
@@ -1981,12 +1981,12 @@
"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,
"evidence_bundle_sha256": "16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec",
"source_contract_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7",
"evidence_bundle_sha256": "89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9",
"source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
"archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -2005,11 +2005,11 @@
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 8,
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 32
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
},
"commit": "d709f043a2c286646a5c72d7345faaed932200de",
"commit": "360f05503df3d7543d74417bcaf3f6a749a23477",
"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.",
@@ -2114,7 +2114,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 239,
"package_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7"
"package_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995"
},
"skill_atlas": {
"skill_count": 12,
@@ -2189,7 +2189,7 @@
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
},
"generated_at": "2026-06-13"
"generated_at": "2026-06-17"
},
"failures": [],
"warnings": []
@@ -5740,35 +5740,22 @@
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "d709f043a2c286646a5c72d7345faaed932200de",
"commit": "360f05503df3d7543d74417bcaf3f6a749a23477",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 32,
"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/compiled_targets.json",
" M reports/context_budget.json",
" M reports/evidence_consistency.json",
" M reports/install_simulation.json",
" M reports/install_simulation.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": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec",
"source_contract_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7",
"evidence_bundle_sha256": "89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9",
"source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
"archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -5787,15 +5774,14 @@
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 8,
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 32
"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)",
@@ -5804,10 +5790,10 @@
"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": "d709f043a2c286646a5c72d7345faaed932200de",
"ready": true,
"commit": "360f05503df3d7543d74417bcaf3f6a749a23477",
"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)",
@@ -5815,7 +5801,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec"
"sha256": "89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -5888,8 +5874,8 @@
"label": "output_execution",
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7963,
"sha256": "ce151bc7d860840d0308731c3cf0342cae0610489d4205b452bbd4e47cc607ef"
"bytes": 7964,
"sha256": "282122e93b08d73b0c199715c51bc619a95af47d315047fc41dceb31f56a3293"
},
{
"label": "blind_review",
@@ -5924,21 +5910,21 @@
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 133860,
"sha256": "f110df76d439c01b2d9b4ea82561d6c5277ff407f7ef616504e3923438d4d96b"
"sha256": "d865e5cc97a3b92e1332366c5c780354afb46038ba1c6ef152a61cc8407a19bc"
},
{
"label": "python_compatibility",
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 29196,
"sha256": "636583616dbcc15fe06d582ff0eda17c08a3d37eae618b03e1ca9c666c5276d2"
"sha256": "f8e498d295db139c49e2ea51bd2cbdd52db61fa2b0bd008ef74135601d691895"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "c28991bdf087bb31370774c1dcce9987ed41eac46b2415eecda092692b9dd915"
"sha256": "88c94a496b941ef0538a7bab550c85d2fc07487edf35e4cd39bde14b1475108c"
},
{
"label": "package_verification",
@@ -5951,15 +5937,15 @@
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8758,
"sha256": "c91884a915384363d4ea0339de5c9a3e37ede4356ad1069edf0ae6f880366cc7"
"bytes": 8604,
"sha256": "044b2cf73dd4559a2a0b2f6cbb5560677d409d4716d135261fac6399012d1abb"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14310,
"sha256": "4f193d15332d6ae7c6df397b0c777219fc9627b61c176ca70f66e43b4e94d08e"
"sha256": "e63bc60e69cdc0e613983edea2a66f6c80d0e4da92efd6f90203c390b813350d"
},
{
"label": "world_class_evidence_plan",
@@ -17296,15 +17282,15 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 797,
"other_text_tokens": 1094713,
"other_text_tokens": 1094791,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1095510,
"deferred_resource_tokens": 498644,
"estimated_total_text_tokens": 1095588,
"deferred_resource_tokens": 498646,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 437614,
"estimated_tokens": 437616,
"file_count": 147
},
{
@@ -17326,7 +17312,7 @@
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 437614,
"estimated_tokens": 437616,
"file_count": 147
}
],
@@ -17349,7 +17335,7 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 437614,
"estimated_tokens": 437616,
"file_count": 147,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
+9 -9
View File
@@ -1000,12 +1000,12 @@
"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,
"evidence_bundle_sha256": "16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec",
"source_contract_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7",
"evidence_bundle_sha256": "89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9",
"source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
"archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -1024,11 +1024,11 @@
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 8,
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 32
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
},
"commit": "d709f043a2c286646a5c72d7345faaed932200de",
"commit": "360f05503df3d7543d74417bcaf3f6a749a23477",
"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.",
@@ -1133,7 +1133,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 239,
"package_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7"
"package_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995"
},
"skill_atlas": {
"skill_count": 12,
@@ -1208,7 +1208,7 @@
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
},
"generated_at": "2026-06-13"
"generated_at": "2026-06-17"
},
"failures": [],
"warnings": []
+9 -9
View File
@@ -1004,12 +1004,12 @@
"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,
"evidence_bundle_sha256": "16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec",
"source_contract_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7",
"evidence_bundle_sha256": "89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9",
"source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
"archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -1028,11 +1028,11 @@
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 8,
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 32
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
},
"commit": "d709f043a2c286646a5c72d7345faaed932200de",
"commit": "360f05503df3d7543d74417bcaf3f6a749a23477",
"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.",
@@ -1137,7 +1137,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 239,
"package_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7"
"package_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995"
},
"skill_atlas": {
"skill_count": 12,
@@ -1212,7 +1212,7 @@
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
},
"generated_at": "2026-06-13"
"generated_at": "2026-06-17"
},
"failures": [],
"warnings": []
+9 -9
View File
@@ -999,12 +999,12 @@
"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,
"evidence_bundle_sha256": "16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec",
"source_contract_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7",
"evidence_bundle_sha256": "89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9",
"source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
"archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -1023,11 +1023,11 @@
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 8,
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 32
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
},
"commit": "d709f043a2c286646a5c72d7345faaed932200de",
"commit": "360f05503df3d7543d74417bcaf3f6a749a23477",
"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.",
@@ -1132,7 +1132,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 239,
"package_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7"
"package_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995"
},
"skill_atlas": {
"skill_count": 12,
@@ -1207,7 +1207,7 @@
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
},
"generated_at": "2026-06-13"
"generated_at": "2026-06-17"
},
"failures": [],
"warnings": []