From 8e6df3b5c270c569b40794871fcb74b27fcb4e33 Mon Sep 17 00:00:00 2001 From: yaojingang Date: Tue, 16 Jun 2026 23:10:54 +0800 Subject: [PATCH] Refresh human evidence validation locks --- reports/benchmark_reproducibility.json | 20 ++-- reports/benchmark_reproducibility.md | 14 +-- reports/evidence_consistency.json | 28 ++--- reports/review-studio.html | 10 +- reports/review-studio.json | 156 +++++++++++++++---------- reports/review-viewer.json | 24 ++-- reports/skill-interpretation.html | 2 +- reports/skill-interpretation.json | 24 ++-- reports/skill-overview.html | 2 +- reports/skill-overview.json | 24 ++-- 10 files changed, 167 insertions(+), 137 deletions(-) diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index 273bec49..1ad02f25 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,7 +3,7 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "46716b5330ce6f614e192fc0c8d3b576740e54b8", + "commit": "c7d04459c1b62208943217d7d8b2ab5e06561485", "git_status": { "available": true, "dirty": false, @@ -17,8 +17,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "5d043ed0bed71e060e6153381f91dda6d5e6aec888ae7042adde1e6882956824", - "source_contract_sha256": "01c09d5fa7c971a657e4d138499ac8d50095ae1a078c2bff1bd9b70657199c9f", + "evidence_bundle_sha256": "04c59801a47b464dcefeb008a1ddc05f350345733a2623277c24c4669079daee", + "source_contract_sha256": "c2ad60de7b1e3d70021ec9e0169a8f8c8c860ff830a434baba2ce44e2530069e", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", "output_case_count": 5, "failure_disclosure_count": 3, @@ -54,7 +54,7 @@ }, "release_lock": { "ready": true, - "commit": "46716b5330ce6f614e192fc0c8d3b576740e54b8", + "commit": "c7d04459c1b62208943217d7d8b2ab5e06561485", "status_scope": "generation-time status before this report is written", "reason": "clean generation-time HEAD" }, @@ -64,7 +64,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "5d043ed0bed71e060e6153381f91dda6d5e6aec888ae7042adde1e6882956824" + "sha256": "04c59801a47b464dcefeb008a1ddc05f350345733a2623277c24c4669079daee" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -172,15 +172,15 @@ "label": "trust_report", "path": "reports/security_trust_report.json", "exists": true, - "bytes": 126934, - "sha256": "d4e11b70d41acca89f4ccad7c0d480c4718827fa91c598ce18245b9c478374ad" + "bytes": 127560, + "sha256": "97993710ff9f5be7e71cd3e3ce8fa83e08dd15abb71279119d36cc87eba62ee6" }, { "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, - "bytes": 27499, - "sha256": "e43cdd6eca68a0a7fc2de1c7ed875c731a4dcd6f1dcb96edea5426e3a0c59eb9" + "bytes": 27755, + "sha256": "f9abc4467f70f25ede587547326b6dcbe7fae3ace76ba16d8740c4882b2ca236" }, { "label": "registry_audit", @@ -208,7 +208,7 @@ "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14310, - "sha256": "41e3e3df458005c5503ed6481e58c2724a39d125502012586a4f37858ae01cca" + "sha256": "adbeaf74b4c824bc4c7880fc7ae959f1dcdf83ebb686e765b79c02dc6d779cd8" }, { "label": "world_class_evidence_plan", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index d2a621e6..8e80bb5d 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,9 +1,9 @@ # Benchmark Reproducibility Generated at: `2026-06-16` -Commit: `46716b5330ce6f614e192fc0c8d3b576740e54b8` +Commit: `c7d04459c1b62208943217d7d8b2ab5e06561485` Working tree dirty at generation: `false` -Evidence bundle SHA256: `5d043ed0bed71e060e6153381f91dda6d5e6aec888ae7042adde1e6882956824` +Evidence bundle SHA256: `04c59801a47b464dcefeb008a1ddc05f350345733a2623277c24c4669079daee` ## Summary @@ -12,7 +12,7 @@ Evidence bundle SHA256: `5d043ed0bed71e060e6153381f91dda6d5e6aec888ae7042adde1e6 - methodology complete: `true` - required artifacts: `25` - missing artifacts: `0` -- source contract sha256: `01c09d5fa7c9` +- source contract sha256: `c2ad60de7b1e` - archive sha256: `5802e5f52255` - output cases: `5` - disclosed failure cases: `3` @@ -50,7 +50,7 @@ This report proves local benchmark reproducibility only. It keeps external provi - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `25` / `25` -- sha256: `5d043ed0bed71e060e6153381f91dda6d5e6aec888ae7042adde1e6882956824` +- sha256: `04c59801a47b464dcefeb008a1ddc05f350345733a2623277c24c4669079daee` ## Methodology Sections @@ -77,12 +77,12 @@ This report proves local benchmark reproducibility only. It keeps external provi | review_adjudication | `reports/output_review_adjudication.json` | present | `bb8c72a9291e` | | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` | | runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` | -| trust_report | `reports/security_trust_report.json` | present | `d4e11b70d41a` | -| python_compatibility | `reports/python_compatibility.json` | present | `e43cdd6eca68` | +| trust_report | `reports/security_trust_report.json` | present | `97993710ff9f` | +| python_compatibility | `reports/python_compatibility.json` | present | `f9abc4467f70` | | registry_audit | `reports/registry_audit.json` | present | `e75a341d15e4` | | package_verification | `reports/package_verification.json` | present | `a27941fdb865` | | install_simulation | `reports/install_simulation.json` | present | `e29ae26bc97c` | -| skill_os2_audit | `reports/skill_os2_audit.json` | present | `41e3e3df4580` | +| skill_os2_audit | `reports/skill_os2_audit.json` | present | `adbeaf74b4c8` | | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `130161495dc4` | | world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `75569fdccc5b` | | world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `7f502f722ff1` | diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index 75e852a9..cd6e8cbe 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -248,8 +248,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "46716b5330ce6f614e192fc0c8d3b576740e54b8", - "actual": "46716b5330ce6f614e192fc0c8d3b576740e54b8", + "expected": "c7d04459c1b62208943217d7d8b2ab5e06561485", + "actual": "c7d04459c1b62208943217d7d8b2ab5e06561485", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -264,7 +264,7 @@ "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "01c09d5fa7c971a657e4d138499ac8d50095ae1a078c2bff1bd9b70657199c9f", + "source_contract_sha256": "c2ad60de7b1e3d70021ec9e0169a8f8c8c860ff830a434baba2ce44e2530069e", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, @@ -277,7 +277,7 @@ "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "01c09d5fa7c971a657e4d138499ac8d50095ae1a078c2bff1bd9b70657199c9f", + "source_contract_sha256": "c2ad60de7b1e3d70021ec9e0169a8f8c8c860ff830a434baba2ce44e2530069e", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, @@ -394,8 +394,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "46716b5330ce6f614e192fc0c8d3b576740e54b8", - "actual": "46716b5330ce6f614e192fc0c8d3b576740e54b8", + "expected": "c7d04459c1b62208943217d7d8b2ab5e06561485", + "actual": "c7d04459c1b62208943217d7d8b2ab5e06561485", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -410,7 +410,7 @@ "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "01c09d5fa7c971a657e4d138499ac8d50095ae1a078c2bff1bd9b70657199c9f", + "source_contract_sha256": "c2ad60de7b1e3d70021ec9e0169a8f8c8c860ff830a434baba2ce44e2530069e", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, @@ -423,7 +423,7 @@ "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "01c09d5fa7c971a657e4d138499ac8d50095ae1a078c2bff1bd9b70657199c9f", + "source_contract_sha256": "c2ad60de7b1e3d70021ec9e0169a8f8c8c860ff830a434baba2ce44e2530069e", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, @@ -1512,7 +1512,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 136 + "file_count": 137 }, { "path": "evals", @@ -1527,7 +1527,7 @@ "file_count": 229 } ], - "file_count": 433, + "file_count": 434, "folder_count": 4, "distribution": [ { @@ -1552,7 +1552,7 @@ }, { "label": "scripts", - "value": 136 + "value": 137 }, { "label": "evals", @@ -1600,7 +1600,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 136 + "file_count": 137 }, { "path": "evals", @@ -1615,7 +1615,7 @@ "file_count": 229 } ], - "file_count": 433, + "file_count": 434, "folder_count": 4, "distribution": [ { @@ -1640,7 +1640,7 @@ }, { "label": "scripts", - "value": 136 + "value": 137 }, { "label": "evals", diff --git a/reports/review-studio.html b/reports/review-studio.html index f47b32b2..11d56d8d 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -740,12 +740,12 @@

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

Blueprint21/21

2.0 coverage; extensions partial 0, planned 0; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

136 scripts scanned; secrets found

Py Compat0

212 files scanned for Python 3.11

Arch Debt0

704 largest lines; 0 watchlist; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock true

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

180 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

658 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

+
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

Blueprint21/21

2.0 coverage; extensions partial 0, planned 0; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

137 scripts scanned; secrets found

Py Compat0

214 files scanned for Python 3.11

Arch Debt0

696 largest lines; 0 watchlist; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock true

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

180 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

658 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

审查闸门

-
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

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

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 990/1000; deferred 491281/120000; top deferred scripts 431183; resource governance governed; quality density 131.3

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 136 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 212 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

209 Python files; 0 hotspots; 0 watchlist files; 0 blockers; largest 704 lines; 68 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

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

reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md 证据
+
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

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

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 990/1000; deferred 492676/120000; top deferred scripts 432578; resource governance governed; quality density 131.3

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 137 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 214 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

211 Python files; 0 hotspots; 0 watchlist files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

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

reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md 证据
@@ -812,17 +812,17 @@
-

上下文

initial load 990/1000; deferred 491281/120000; top deferred scripts 431183; resource governance governed; quality density 131.3

+

上下文

initial load 990/1000; deferred 492676/120000; top deferred scripts 432578; resource governance governed; quality density 131.3

编译证据

Review reports/compiled_targets.md before packaging to inspect target adapter modes, generated files, preserved semantics, warnings, and unsupported features.

-

信任报告

Secret
0
脚本数
136
网络脚本
3
Help 失败
0
包体哈希
01c09d5fa7c971a657e4d138499ac8d50095ae1a078c2bff1bd9b70657199c9f
+

信任报告

Secret
0
脚本数
137
网络脚本
3
Help 失败
0
包体哈希
c2ad60de7b1e3d70021ec9e0169a8f8c8c860ff830a434baba2ce44e2530069e

安全边界

高风险 secret、远程 inline execution、缺失依赖策略或无法解释的脚本接口应阻断 governed release。

-

Python 兼容

目标 Python
3.11
文件数
212
问题数
0
语法错误
0
F-string 3.11
0
+

Python 兼容

目标 Python
3.11
文件数
214
问题数
0
语法错误
0
F-string 3.11
0

解释器边界

CI 和发布审查以 Python 3.11 兼容为底线；本地更高版本允许的新语法不能绕过兼容门禁。

diff --git a/reports/review-studio.json b/reports/review-studio.json index 3cc3151e..de82d33c 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -44,7 +44,7 @@ "key": "context-budget", "label": "上下文", "status": "pass", - "detail": "initial load 990/1000; deferred 491281/120000; top deferred scripts 431183; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 492676/120000; top deferred scripts 432578; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json", "link": "context_budget.md" }, @@ -60,7 +60,7 @@ "key": "trust-report", "label": "信任报告", "status": "pass", - "detail": "0 secrets; 136 scripts; 3 network-capable scripts; 0 help smoke failures", + "detail": "0 secrets; 137 scripts; 3 network-capable scripts; 0 help smoke failures", "evidence": "reports/security_trust_report.json", "link": "security_trust_report.md" }, @@ -68,7 +68,7 @@ "key": "python-compat", "label": "Python 兼容", "status": "pass", - "detail": "Python 3.11; 212 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards", + "detail": "Python 3.11; 214 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards", "evidence": "reports/python_compatibility.json", "link": "python_compatibility.md" }, @@ -76,7 +76,7 @@ "key": "architecture-maintainability", "label": "架构维护", "status": "pass", - "detail": "209 Python files; 0 hotspots; 0 watchlist files; 0 blockers; largest 704 lines; 68 CLI handlers; 18 in entrypoint", + "detail": "211 Python files; 0 hotspots; 0 watchlist files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint", "evidence": "reports/architecture_maintainability.json", "link": "architecture_maintainability.md" }, @@ -1484,7 +1484,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 136 + "file_count": 137 }, { "path": "evals", @@ -1499,7 +1499,7 @@ "file_count": 229 } ], - "file_count": 433, + "file_count": 434, "folder_count": 4, "distribution": [ { @@ -1524,7 +1524,7 @@ }, { "label": "scripts", - "value": 136 + "value": 137 }, { "label": "evals", @@ -1654,7 +1654,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 136 + "file_count": 137 }, { "path": "evals", @@ -1972,8 +1972,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "5d043ed0bed71e060e6153381f91dda6d5e6aec888ae7042adde1e6882956824", - "source_contract_sha256": "01c09d5fa7c971a657e4d138499ac8d50095ae1a078c2bff1bd9b70657199c9f", + "evidence_bundle_sha256": "04c59801a47b464dcefeb008a1ddc05f350345733a2623277c24c4669079daee", + "source_contract_sha256": "c2ad60de7b1e3d70021ec9e0169a8f8c8c860ff830a434baba2ce44e2530069e", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1996,7 +1996,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "46716b5330ce6f614e192fc0c8d3b576740e54b8", + "commit": "c7d04459c1b62208943217d7d8b2ab5e06561485", "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.", @@ -2080,9 +2080,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 227, - "script_count": 136, - "internal_module_count": 50, + "scanned_files": 228, + "script_count": 137, + "internal_module_count": 51, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -2100,8 +2100,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 227, - "package_sha256": "01c09d5fa7c971a657e4d138499ac8d50095ae1a078c2bff1bd9b70657199c9f" + "package_hash_file_count": 228, + "package_sha256": "c2ad60de7b1e3d70021ec9e0169a8f8c8c860ff830a434baba2ce44e2530069e" }, "skill_atlas": { "skill_count": 12, @@ -5659,7 +5659,7 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "46716b5330ce6f614e192fc0c8d3b576740e54b8", + "commit": "c7d04459c1b62208943217d7d8b2ab5e06561485", "git_status": { "available": true, "dirty": false, @@ -5673,8 +5673,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "5d043ed0bed71e060e6153381f91dda6d5e6aec888ae7042adde1e6882956824", - "source_contract_sha256": "01c09d5fa7c971a657e4d138499ac8d50095ae1a078c2bff1bd9b70657199c9f", + "evidence_bundle_sha256": "04c59801a47b464dcefeb008a1ddc05f350345733a2623277c24c4669079daee", + "source_contract_sha256": "c2ad60de7b1e3d70021ec9e0169a8f8c8c860ff830a434baba2ce44e2530069e", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", "output_case_count": 5, "failure_disclosure_count": 3, @@ -5710,7 +5710,7 @@ }, "release_lock": { "ready": true, - "commit": "46716b5330ce6f614e192fc0c8d3b576740e54b8", + "commit": "c7d04459c1b62208943217d7d8b2ab5e06561485", "status_scope": "generation-time status before this report is written", "reason": "clean generation-time HEAD" }, @@ -5720,7 +5720,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "5d043ed0bed71e060e6153381f91dda6d5e6aec888ae7042adde1e6882956824" + "sha256": "04c59801a47b464dcefeb008a1ddc05f350345733a2623277c24c4669079daee" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5828,15 +5828,15 @@ "label": "trust_report", "path": "reports/security_trust_report.json", "exists": true, - "bytes": 126934, - "sha256": "d4e11b70d41acca89f4ccad7c0d480c4718827fa91c598ce18245b9c478374ad" + "bytes": 127560, + "sha256": "97993710ff9f5be7e71cd3e3ce8fa83e08dd15abb71279119d36cc87eba62ee6" }, { "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, - "bytes": 27499, - "sha256": "e43cdd6eca68a0a7fc2de1c7ed875c731a4dcd6f1dcb96edea5426e3a0c59eb9" + "bytes": 27755, + "sha256": "f9abc4467f70f25ede587547326b6dcbe7fae3ace76ba16d8740c4882b2ca236" }, { "label": "registry_audit", @@ -5864,7 +5864,7 @@ "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14310, - "sha256": "41e3e3df458005c5503ed6481e58c2724a39d125502012586a4f37858ae01cca" + "sha256": "adbeaf74b4c824bc4c7880fc7ae959f1dcdf83ebb686e765b79c02dc6d779cd8" }, { "label": "world_class_evidence_plan", @@ -6196,7 +6196,7 @@ "label": "Trust Security", "status": "pass", "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.", - "current": "136 scripts; secrets 0; help failures 0", + "current": "137 scripts; secrets 0; help failures 0", "command": "python3 scripts/yao.py trust .", "test": "python3 tests/verify_trust_check.py", "evidence": [ @@ -12083,9 +12083,9 @@ "ok": true, "skill_dir": ".", "summary": { - "scanned_files": 227, - "script_count": 136, - "internal_module_count": 50, + "scanned_files": 228, + "script_count": 137, + "internal_module_count": 51, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -12103,8 +12103,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 227, - "package_sha256": "01c09d5fa7c971a657e4d138499ac8d50095ae1a078c2bff1bd9b70657199c9f" + "package_hash_file_count": 228, + "package_sha256": "c2ad60de7b1e3d70021ec9e0169a8f8c8c860ff830a434baba2ce44e2530069e" }, "failures": [], "warnings": [], @@ -13793,6 +13793,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/world_class_human_evidence.py", + "interface": "internal-module", + "interface_declared": true, + "interface_reason": "Imported by world_class_evidence_contract.py to validate blind A/B human adjudication evidence from decision rows.", + "has_argparse": false, + "has_main_guard": false, + "uses_input": false, + "uses_network": false, + "uses_file_write": false, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/world_class_preflight_layout.py", "interface": "internal-module", @@ -14066,7 +14080,7 @@ "checked_count": 86, "passed_count": 86, "failed_count": 0, - "skipped_count": 50, + "skipped_count": 51, "failed_scripts": [], "results": [ { @@ -15067,6 +15081,10 @@ "path": "scripts/world_class_evidence_contract.py", "reason": "internal module" }, + { + "path": "scripts/world_class_human_evidence.py", + "reason": "internal module" + }, { "path": "scripts/world_class_preflight_layout.py", "reason": "internal module" @@ -15326,7 +15344,7 @@ "root": ".", "summary": { "target_python": "3.11", - "file_count": 212, + "file_count": 214, "issue_count": 0, "syntax_error_count": 0, "fstring_311_violation_count": 0, @@ -16075,6 +16093,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/world_class_human_evidence.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/world_class_preflight_layout.py", "ok": true, @@ -16603,6 +16627,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "tests/world_class_human_fixtures.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "tests/yao_cli_helpers.py", "ok": true, @@ -16628,10 +16658,10 @@ "generated_at": "2026-06-16", "skill_dir": ".", "summary": { - "python_file_count": 209, - "script_file_count": 136, - "test_file_count": 73, - "internal_module_count": 52, + "python_file_count": 211, + "script_file_count": 137, + "test_file_count": 74, + "internal_module_count": 53, "cli_script_count": 86, "command_handler_count": 68, "entrypoint_command_handler_count": 18, @@ -16639,27 +16669,13 @@ "warn_line_threshold": 900, "watch_line_threshold": 720, "block_line_threshold": 1500, - "largest_file_lines": 704, + "largest_file_lines": 696, "watchlist_count": 0, "hotspot_count": 0, "blocker_count": 0, "decision": "pass" }, "largest_files": [ - { - "path": "tests/verify_world_class_evidence_intake.py", - "lines": 704, - "kind": "test", - "severity": "pass", - "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." - }, - { - "path": "scripts/world_class_evidence_contract.py", - "lines": 699, - "kind": "internal-module", - "severity": "pass", - "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." - }, { "path": "tests/verify_yao_cli.py", "lines": 696, @@ -16723,12 +16739,26 @@ "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." }, + { + "path": "scripts/world_class_evidence_contract.py", + "lines": 620, + "kind": "internal-module", + "severity": "pass", + "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." + }, { "path": "scripts/render_benchmark_reproducibility.py", "lines": 595, "kind": "cli-script", "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." + }, + { + "path": "scripts/optimize_description.py", + "lines": 585, + "kind": "cli-script", + "severity": "pass", + "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." } ], "watchlist": [], @@ -16747,16 +16777,16 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1060977, + "other_text_tokens": 1063452, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1061774, - "deferred_resource_tokens": 491281, + "estimated_total_text_tokens": 1064249, + "deferred_resource_tokens": 492676, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 431183, - "file_count": 136 + "estimated_tokens": 432578, + "file_count": 137 }, { "path": "references", @@ -16777,8 +16807,8 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 431183, - "file_count": 136 + "estimated_tokens": 432578, + "file_count": 137 } ], "deferred_resource_governance": { @@ -16800,14 +16830,14 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 431183, - "file_count": 136, + "estimated_tokens": 432578, + "file_count": 137, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } ], "summary": "Large deferred resources are indexed and backed by evidence." }, - "relevant_file_count": 665, + "relevant_file_count": 669, "unused_resource_dirs": [], "quality_signal_points": 130, "quality_density": 131.3 diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 66fbb2af..c1d7d001 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -513,7 +513,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 136 + "file_count": 137 }, { "path": "evals", @@ -528,7 +528,7 @@ "file_count": 229 } ], - "file_count": 433, + "file_count": 434, "folder_count": 4, "distribution": [ { @@ -553,7 +553,7 @@ }, { "label": "scripts", - "value": 136 + "value": 137 }, { "label": "evals", @@ -683,7 +683,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 136 + "file_count": 137 }, { "path": "evals", @@ -1001,8 +1001,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "5d043ed0bed71e060e6153381f91dda6d5e6aec888ae7042adde1e6882956824", - "source_contract_sha256": "01c09d5fa7c971a657e4d138499ac8d50095ae1a078c2bff1bd9b70657199c9f", + "evidence_bundle_sha256": "04c59801a47b464dcefeb008a1ddc05f350345733a2623277c24c4669079daee", + "source_contract_sha256": "c2ad60de7b1e3d70021ec9e0169a8f8c8c860ff830a434baba2ce44e2530069e", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1025,7 +1025,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "46716b5330ce6f614e192fc0c8d3b576740e54b8", + "commit": "c7d04459c1b62208943217d7d8b2ab5e06561485", "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.", @@ -1109,9 +1109,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 227, - "script_count": 136, - "internal_module_count": 50, + "scanned_files": 228, + "script_count": 137, + "internal_module_count": 51, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -1129,8 +1129,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 227, - "package_sha256": "01c09d5fa7c971a657e4d138499ac8d50095ae1a078c2bff1bd9b70657199c9f" + "package_hash_file_count": 228, + "package_sha256": "c2ad60de7b1e3d70021ec9e0169a8f8c8c860ff830a434baba2ce44e2530069e" }, "skill_atlas": { "skill_count": 12, diff --git a/reports/skill-interpretation.html b/reports/skill-interpretation.html index b57ff820..29ae099e 100644 --- a/reports/skill-interpretation.html +++ b/reports/skill-interpretation.html @@ -921,7 +921,7 @@

让 reviewer 快速确认关键文件、目录和资产分布。Lets reviewers confirm key files, directories, and asset distribution quickly.

-
资产分布Asset Distribution433项433 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
+
资产分布Asset Distribution434项434 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index 1c3e993c..20c64152 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -513,7 +513,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 136 + "file_count": 137 }, { "path": "evals", @@ -528,7 +528,7 @@ "file_count": 229 } ], - "file_count": 433, + "file_count": 434, "folder_count": 4, "distribution": [ { @@ -553,7 +553,7 @@ }, { "label": "scripts", - "value": 136 + "value": 137 }, { "label": "evals", @@ -687,7 +687,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 136 + "file_count": 137 }, { "path": "evals", @@ -1005,8 +1005,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "5d043ed0bed71e060e6153381f91dda6d5e6aec888ae7042adde1e6882956824", - "source_contract_sha256": "01c09d5fa7c971a657e4d138499ac8d50095ae1a078c2bff1bd9b70657199c9f", + "evidence_bundle_sha256": "04c59801a47b464dcefeb008a1ddc05f350345733a2623277c24c4669079daee", + "source_contract_sha256": "c2ad60de7b1e3d70021ec9e0169a8f8c8c860ff830a434baba2ce44e2530069e", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1029,7 +1029,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "46716b5330ce6f614e192fc0c8d3b576740e54b8", + "commit": "c7d04459c1b62208943217d7d8b2ab5e06561485", "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.", @@ -1113,9 +1113,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 227, - "script_count": 136, - "internal_module_count": 50, + "scanned_files": 228, + "script_count": 137, + "internal_module_count": 51, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -1133,8 +1133,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 227, - "package_sha256": "01c09d5fa7c971a657e4d138499ac8d50095ae1a078c2bff1bd9b70657199c9f" + "package_hash_file_count": 228, + "package_sha256": "c2ad60de7b1e3d70021ec9e0169a8f8c8c860ff830a434baba2ce44e2530069e" }, "skill_atlas": { "skill_count": 12, diff --git a/reports/skill-overview.html b/reports/skill-overview.html index 111b1db2..f413f425 100644 --- a/reports/skill-overview.html +++ b/reports/skill-overview.html @@ -921,7 +921,7 @@

让 reviewer 快速确认关键文件、目录和资产分布。Lets reviewers confirm key files, directories, and asset distribution quickly.

-
资产分布Asset Distribution433项433 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
+
资产分布Asset Distribution434项434 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
路径Path作用Role类型Type
SKILL.mdSkill 入口文件Skill entrypoint文件file
README.md人类可读使用说明Human-readable usage guide文件file
agents/interface.yaml跨平台接口元数据Neutral interface metadata文件file
manifest.json生命周期与打包元数据Lifecycle and portability metadata文件file
references扩展指导与复用资料Extended guidance and reusable notes目录folder
scripts确定性脚本或本地工具Deterministic helpers or local tooling目录folder
evals触发与质量检查Trigger and quality checks目录folder
reports生成的证据与总结报告Generated evidence and overview artifacts目录folder
diff --git a/reports/skill-overview.json b/reports/skill-overview.json index c8be5550..c1972afc 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -512,7 +512,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 136 + "file_count": 137 }, { "path": "evals", @@ -527,7 +527,7 @@ "file_count": 229 } ], - "file_count": 433, + "file_count": 434, "folder_count": 4, "distribution": [ { @@ -552,7 +552,7 @@ }, { "label": "scripts", - "value": 136 + "value": 137 }, { "label": "evals", @@ -682,7 +682,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 136 + "file_count": 137 }, { "path": "evals", @@ -1000,8 +1000,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "5d043ed0bed71e060e6153381f91dda6d5e6aec888ae7042adde1e6882956824", - "source_contract_sha256": "01c09d5fa7c971a657e4d138499ac8d50095ae1a078c2bff1bd9b70657199c9f", + "evidence_bundle_sha256": "04c59801a47b464dcefeb008a1ddc05f350345733a2623277c24c4669079daee", + "source_contract_sha256": "c2ad60de7b1e3d70021ec9e0169a8f8c8c860ff830a434baba2ce44e2530069e", "archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1024,7 +1024,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "46716b5330ce6f614e192fc0c8d3b576740e54b8", + "commit": "c7d04459c1b62208943217d7d8b2ab5e06561485", "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.", @@ -1108,9 +1108,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 227, - "script_count": 136, - "internal_module_count": 50, + "scanned_files": 228, + "script_count": 137, + "internal_module_count": 51, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -1128,8 +1128,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 227, - "package_sha256": "01c09d5fa7c971a657e4d138499ac8d50095ae1a078c2bff1bd9b70657199c9f" + "package_hash_file_count": 228, + "package_sha256": "c2ad60de7b1e3d70021ec9e0169a8f8c8c860ff830a434baba2ce44e2530069e" }, "skill_atlas": { "skill_count": 12,
路径Path作用Role类型Type
SKILL.mdSkill 入口文件Skill entrypoint文件file
README.md人类可读使用说明Human-readable usage guide文件file
agents/interface.yaml跨平台接口元数据Neutral interface metadata文件file
manifest.json生命周期与打包元数据Lifecycle and portability metadata文件file
references扩展指导与复用资料Extended guidance and reusable notes目录folder
scripts确定性脚本或本地工具Deterministic helpers or local tooling目录folder
evals触发与质量检查Trigger and quality checks目录folder
reports生成的证据与总结报告Generated evidence and overview artifacts目录folder