Refresh downstream reports for artifact roles

This commit is contained in:
yaojingang
2026-06-16 07:12:08 +08:00
parent e81337c7db
commit 220f68a066
6 changed files with 48 additions and 62 deletions
+14 -14
View File
@@ -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": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
"actual": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
"expected": "28c83c6976717daff13667d775bbbc1dbc377dc0",
"actual": "28c83c6976717daff13667d775bbbc1dbc377dc0",
"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": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
@@ -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": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
@@ -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": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
"actual": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
"expected": "28c83c6976717daff13667d775bbbc1dbc377dc0",
"actual": "28c83c6976717daff13667d775bbbc1dbc377dc0",
"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": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
@@ -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": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
@@ -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",
+3 -3
View File
@@ -711,7 +711,7 @@
<section>
<h2>核心指标</h2>
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>5 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>121 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>193 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>899 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>646 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>121 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>193 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>899 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>646 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>
@@ -848,8 +848,8 @@
</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 (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></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 (6/13 pass, 7 blocked)</span></li></ul></div>
</section>
<section class="twocol">
+16 -30
View File
@@ -1812,7 +1812,7 @@
"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,
@@ -1836,11 +1836,11 @@
"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": 22
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
},
"commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
"commit": "28c83c6976717daff13667d775bbbc1dbc377dc0",
"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.",
@@ -5446,30 +5446,17 @@
"ok": true,
"generated_at": "2026-06-16",
"skill_dir": ".",
"commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
"commit": "28c83c6976717daff13667d775bbbc1dbc377dc0",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 22,
"sample": [
" M evidence/world_class/README.md",
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" M reports/context_budget.json",
" M reports/context_budget.md",
" M reports/context_budget_summary.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md",
" M reports/package_verification.json",
" M reports/package_verification.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,
@@ -5493,15 +5480,14 @@
"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": 22
"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)",
@@ -5510,10 +5496,10 @@
"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": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
"ready": true,
"commit": "28c83c6976717daff13667d775bbbc1dbc377dc0",
"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)",
+5 -5
View File
@@ -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": 22
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
},
"commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
"commit": "28c83c6976717daff13667d775bbbc1dbc377dc0",
"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.",
+5 -5
View File
@@ -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": 22
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
},
"commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
"commit": "28c83c6976717daff13667d775bbbc1dbc377dc0",
"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.",
+5 -5
View File
@@ -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": 22
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
},
"commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
"commit": "28c83c6976717daff13667d775bbbc1dbc377dc0",
"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.",