Refresh clean world-class CLI test lock
This commit is contained in:
yaojingang
@@ -3,19 +3,17 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16",
|
||||
"skill_dir": ".",
|
||||
"commit": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
|
||||
"commit": "4f339c536676c48037194b95ff0a1e157041c453",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": true,
|
||||
"changed_file_count": 1,
|
||||
"sample": [
|
||||
" M reports/context_budget.json"
|
||||
],
|
||||
"dirty": false,
|
||||
"changed_file_count": 0,
|
||||
"sample": [],
|
||||
"scope": "generation-time status before this report is written"
|
||||
},
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
@@ -39,15 +37,14 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 1
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
},
|
||||
"public_claim": {
|
||||
"ready": false,
|
||||
"scope": "public benchmark or world-class readiness claim",
|
||||
"blockers": [
|
||||
"release lock is not clean or commit is unavailable",
|
||||
"provider-backed model holdout evidence is incomplete",
|
||||
"human blind-review adjudication is incomplete",
|
||||
"world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
|
||||
@@ -56,10 +53,10 @@
|
||||
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
|
||||
},
|
||||
"release_lock": {
|
||||
"ready": false,
|
||||
"commit": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
|
||||
"ready": true,
|
||||
"commit": "4f339c536676c48037194b95ff0a1e157041c453",
|
||||
"status_scope": "generation-time status before this report is written",
|
||||
"reason": "working tree was dirty at generation time"
|
||||
"reason": "clean generation-time HEAD"
|
||||
},
|
||||
"evidence_bundle": {
|
||||
"algorithm": "sha256(path,label,exists,artifact_sha256)",
|
||||
|
||||
@@ -1,14 +1,14 @@
|
||||
# Benchmark Reproducibility
|
||||
|
||||
Generated at: `2026-06-16`
|
||||
Commit: `7df231b6d229c49a4980eb4e8a97e5dc940bbed6`
|
||||
Working tree dirty at generation: `true`
|
||||
Commit: `4f339c536676c48037194b95ff0a1e157041c453`
|
||||
Working tree dirty at generation: `false`
|
||||
Evidence bundle SHA256: `e29fb9204676313a6abe14b1a33dfe8c40f88659227570762fff51396ff99a3a`
|
||||
|
||||
## Summary
|
||||
|
||||
- reproducibility ready: `true`
|
||||
- release lock ready: `false`
|
||||
- release lock ready: `true`
|
||||
- methodology complete: `true`
|
||||
- required artifacts: `25`
|
||||
- missing artifacts: `0`
|
||||
@@ -22,8 +22,8 @@ Evidence bundle SHA256: `e29fb9204676313a6abe14b1a33dfe8c40f88659227570762fff513
|
||||
- world-class ready: `false`
|
||||
- world-class source checks: `6` pass / `13` total; `7` blocked
|
||||
- public claim ready: `false`
|
||||
- public claim blockers: `5`
|
||||
- changed files at generation: `1`
|
||||
- public claim blockers: `4`
|
||||
- changed files at generation: `0`
|
||||
|
||||
This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
|
||||
|
||||
@@ -35,7 +35,6 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
|
||||
| Blocker |
|
||||
| --- |
|
||||
| release lock is not clean or commit is unavailable |
|
||||
| provider-backed model holdout evidence is incomplete |
|
||||
| human blind-review adjudication is incomplete |
|
||||
| world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) |
|
||||
@@ -43,8 +42,8 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
|
||||
## Release Lock
|
||||
|
||||
- ready: `false`
|
||||
- reason: working tree was dirty at generation time
|
||||
- ready: `true`
|
||||
- reason: clean generation-time HEAD
|
||||
- status scope: generation-time status before this report is written
|
||||
|
||||
## Evidence Bundle
|
||||
|
||||
@@ -207,8 +207,8 @@
|
||||
"key": "benchmark-release-lock-self-consistency",
|
||||
"label": "Benchmark release lock matches git dirty state",
|
||||
"status": "pass",
|
||||
"expected": false,
|
||||
"actual": false,
|
||||
"expected": true,
|
||||
"actual": true,
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json"
|
||||
],
|
||||
@@ -248,8 +248,8 @@
|
||||
"key": "overview-benchmark-commit",
|
||||
"label": "overview embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
|
||||
"actual": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
|
||||
"expected": "4f339c536676c48037194b95ff0a1e157041c453",
|
||||
"actual": "4f339c536676c48037194b95ff0a1e157041c453",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-overview.json"
|
||||
@@ -261,7 +261,7 @@
|
||||
"label": "overview embeds benchmark summary fields",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "1e5b2ced62c29f6d23ad88f576df6f278bfc0582382c11f834f56b64a686ed80",
|
||||
@@ -271,10 +271,10 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5
|
||||
"public_claim_blocker_count": 4
|
||||
},
|
||||
"actual": {
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "1e5b2ced62c29f6d23ad88f576df6f278bfc0582382c11f834f56b64a686ed80",
|
||||
@@ -284,7 +284,7 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5
|
||||
"public_claim_blocker_count": 4
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
@@ -394,8 +394,8 @@
|
||||
"key": "interpretation-benchmark-commit",
|
||||
"label": "interpretation embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
|
||||
"actual": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
|
||||
"expected": "4f339c536676c48037194b95ff0a1e157041c453",
|
||||
"actual": "4f339c536676c48037194b95ff0a1e157041c453",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-interpretation.json"
|
||||
@@ -407,7 +407,7 @@
|
||||
"label": "interpretation embeds benchmark summary fields",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "1e5b2ced62c29f6d23ad88f576df6f278bfc0582382c11f834f56b64a686ed80",
|
||||
@@ -417,10 +417,10 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5
|
||||
"public_claim_blocker_count": 4
|
||||
},
|
||||
"actual": {
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "1e5b2ced62c29f6d23ad88f576df6f278bfc0582382c11f834f56b64a686ed80",
|
||||
@@ -430,7 +430,7 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5
|
||||
"public_claim_blocker_count": 4
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
|
||||
@@ -740,12 +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>122 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>196 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>870 largest lines; 9 watchlist; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock false</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>180 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>649 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>122 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>196 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>870 largest lines; 9 watchlist; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock 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>180 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>649 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 484804/120000; top deferred scripts 424826; 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; 122 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; 196 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>193 Python files; 0 hotspots; 9 watchlist files; 0 blockers; largest 870 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 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false</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 6/13 pass; 7 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 484804/120000; top deferred scripts 424826; 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; 122 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; 196 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>193 Python files; 0 hotspots; 9 watchlist files; 0 blockers; largest 870 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 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 6/13 pass; 7 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>
|
||||
|
||||
<div class="twocol">
|
||||
@@ -837,14 +837,14 @@
|
||||
</section>
|
||||
|
||||
<section id="telemetry" class="twocol">
|
||||
<div class="panel"><h2>运营回路</h2><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false</p></div>
|
||||
<div class="panel"><h2>运营回路</h2><p>1 metadata events; adoption 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></div>
|
||||
<div class="panel"><h2>漂移信号</h2><dl class='kv-grid'><div><dt>事件数</dt><dd>1</dd></div><div><dt>采用率</dt><dd>0</dd></div><div><dt>漏触发</dt><dd>0</dd></div><div><dt>Bad Output Count</dt><dd>0</dd></div><div><dt>风险带</dt><dd>low</dd></div></dl></div>
|
||||
</section>
|
||||
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>日常运维</h2><dl class='kv-grid'><div><dt>决策</dt><dd>proposal-review</dd></div><div><dt>提案数</dt><dd>5</dd></div><div><dt>Approval Count</dt><dd>0</dd></div><div><dt>Pending Review Count</dt><dd>0</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>世界级</dt><dd>否</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>1</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>日常运维</h2><dl class='kv-grid'><div><dt>决策</dt><dd>proposal-review</dd></div><div><dt>提案数</dt><dd>5</dd></div><div><dt>Approval Count</dt><dd>0</dd></div><div><dt>Pending Review Count</dt><dd>0</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>世界级</dt><dd>否</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>1</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
|
||||
</section>
|
||||
|
||||
|
||||
@@ -877,8 +877,8 @@
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>5</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>release lock is not clean or commit is unavailable</span></li><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
|
||||
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>4</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
|
||||
+23
-26
@@ -107,7 +107,7 @@
|
||||
"key": "operations-loop",
|
||||
"label": "运营回路",
|
||||
"status": "pass",
|
||||
"detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false",
|
||||
"detail": "1 metadata events; adoption 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",
|
||||
"evidence": "reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly",
|
||||
"link": "adoption_drift_report.md"
|
||||
},
|
||||
@@ -1922,7 +1922,7 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
@@ -1946,11 +1946,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 1
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
},
|
||||
"commit": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
|
||||
"commit": "4f339c536676c48037194b95ff0a1e157041c453",
|
||||
"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.",
|
||||
@@ -5560,19 +5560,17 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16",
|
||||
"skill_dir": ".",
|
||||
"commit": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
|
||||
"commit": "4f339c536676c48037194b95ff0a1e157041c453",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": true,
|
||||
"changed_file_count": 1,
|
||||
"sample": [
|
||||
" M reports/context_budget.json"
|
||||
],
|
||||
"dirty": false,
|
||||
"changed_file_count": 0,
|
||||
"sample": [],
|
||||
"scope": "generation-time status before this report is written"
|
||||
},
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
@@ -5596,15 +5594,14 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 1
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
},
|
||||
"public_claim": {
|
||||
"ready": false,
|
||||
"scope": "public benchmark or world-class readiness claim",
|
||||
"blockers": [
|
||||
"release lock is not clean or commit is unavailable",
|
||||
"provider-backed model holdout evidence is incomplete",
|
||||
"human blind-review adjudication is incomplete",
|
||||
"world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
|
||||
@@ -5613,10 +5610,10 @@
|
||||
"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": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
|
||||
"ready": true,
|
||||
"commit": "4f339c536676c48037194b95ff0a1e157041c453",
|
||||
"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)",
|
||||
@@ -18411,7 +18408,7 @@
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
@@ -18428,7 +18425,7 @@
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
@@ -18877,7 +18874,7 @@
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true
|
||||
},
|
||||
"actions": [
|
||||
@@ -18926,7 +18923,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -18946,7 +18943,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -19198,7 +19195,7 @@
|
||||
"no_route_opportunity_count": 0
|
||||
},
|
||||
"release_state": {
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4
|
||||
|
||||
@@ -997,7 +997,7 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
@@ -1021,11 +1021,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 1
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
},
|
||||
"commit": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
|
||||
"commit": "4f339c536676c48037194b95ff0a1e157041c453",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
|
||||
|
||||
@@ -1001,7 +1001,7 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
@@ -1025,11 +1025,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 1
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
},
|
||||
"commit": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
|
||||
"commit": "4f339c536676c48037194b95ff0a1e157041c453",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
|
||||
|
||||
@@ -996,7 +996,7 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
@@ -1020,11 +1020,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 1
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
},
|
||||
"commit": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
|
||||
"commit": "4f339c536676c48037194b95ff0a1e157041c453",
|
||||
"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.",
|
||||
|
||||
@@ -14,7 +14,7 @@
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
@@ -31,7 +31,7 @@
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
@@ -480,7 +480,7 @@
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true
|
||||
},
|
||||
"actions": [
|
||||
|
||||
@@ -14,7 +14,7 @@ Generated at: `2026-06-16`
|
||||
- local blueprint ready: `true`
|
||||
- public world-class ready: `false`
|
||||
- world-class pending: `4`
|
||||
- release lock ready: `false`
|
||||
- release lock ready: `true`
|
||||
- evidence consistency ok: `true`
|
||||
|
||||
This report is an operations cockpit for explicit-source SkillOps. It does not scan private logs, write source files, apply patches, or count as world-class external or human evidence.
|
||||
|
||||
@@ -15,7 +15,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -35,7 +35,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -287,7 +287,7 @@
|
||||
"no_route_opportunity_count": 0
|
||||
},
|
||||
"release_state": {
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4
|
||||
|
||||
@@ -13,7 +13,7 @@ Week: `2026-W25`
|
||||
- top_score: `88`
|
||||
- skill_count: `12`
|
||||
- actionable_portfolio_issue_count: `0`
|
||||
- release_lock_ready: `False`
|
||||
- release_lock_ready: `True`
|
||||
- evidence_consistency_ok: `True`
|
||||
- public_world_class_ready: `False`
|
||||
- world_class_pending_count: `4`
|
||||
|
||||
Reference in New Issue
Block a user