From 00a8265b81dc32c1716dd5f8981981b164653e53 Mon Sep 17 00:00:00 2001 From: yaojingang Date: Wed, 17 Jun 2026 03:13:45 +0800 Subject: [PATCH] Refresh clean-lock evidence after source anchors --- reports/benchmark_reproducibility.json | 58 +++++++---------- reports/benchmark_reproducibility.md | 33 +++++----- reports/evidence_consistency.json | 14 ++-- reports/review-studio.html | 10 +-- reports/review-studio.json | 90 +++++++++++--------------- reports/review-viewer.json | 18 +++--- reports/skill-interpretation.json | 18 +++--- reports/skill-overview.json | 18 +++--- 8 files changed, 115 insertions(+), 144 deletions(-) diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index a9331956..7162ec39 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,35 +3,22 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "d709f043a2c286646a5c72d7345faaed932200de", + "commit": "360f05503df3d7543d74417bcaf3f6a749a23477", "git_status": { "available": true, - "dirty": true, - "changed_file_count": 32, - "sample": [ - " M registry/index.json", - " M registry/packages/yao-meta-skill.json", - " M reports/adoption_drift_report.json", - " M reports/architecture_maintainability.json", - " M reports/architecture_maintainability.md", - " M reports/benchmark_reproducibility.json", - " M reports/benchmark_reproducibility.md", - " M reports/compiled_targets.json", - " M reports/context_budget.json", - " M reports/evidence_consistency.json", - " M reports/install_simulation.json", - " M reports/install_simulation.md" - ], + "dirty": false, + "changed_file_count": 0, + "sample": [], "scope": "generation-time status before this report is written" }, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec", - "source_contract_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7", + "evidence_bundle_sha256": "89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9", + "source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995", "archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e", "output_case_count": 5, "failure_disclosure_count": 3, @@ -50,15 +37,14 @@ "world_class_source_pass_count": 9, "world_class_source_blocked_count": 8, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 32 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, "public_claim": { "ready": false, "scope": "public benchmark or world-class readiness claim", "blockers": [ - "release lock is not clean or commit is unavailable", "provider-backed model holdout evidence is incomplete", "human blind-review adjudication is incomplete", "world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)", @@ -67,10 +53,10 @@ "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks." }, "release_lock": { - "ready": false, - "commit": "d709f043a2c286646a5c72d7345faaed932200de", + "ready": true, + "commit": "360f05503df3d7543d74417bcaf3f6a749a23477", "status_scope": "generation-time status before this report is written", - "reason": "working tree was dirty at generation time" + "reason": "clean generation-time HEAD" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -78,7 +64,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec" + "sha256": "89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -151,8 +137,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7963, - "sha256": "ce151bc7d860840d0308731c3cf0342cae0610489d4205b452bbd4e47cc607ef" + "bytes": 7964, + "sha256": "282122e93b08d73b0c199715c51bc619a95af47d315047fc41dceb31f56a3293" }, { "label": "blind_review", @@ -187,21 +173,21 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 133860, - "sha256": "f110df76d439c01b2d9b4ea82561d6c5277ff407f7ef616504e3923438d4d96b" + "sha256": "d865e5cc97a3b92e1332366c5c780354afb46038ba1c6ef152a61cc8407a19bc" }, { "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, "bytes": 29196, - "sha256": "636583616dbcc15fe06d582ff0eda17c08a3d37eae618b03e1ca9c666c5276d2" + "sha256": "f8e498d295db139c49e2ea51bd2cbdd52db61fa2b0bd008ef74135601d691895" }, { "label": "registry_audit", "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "c28991bdf087bb31370774c1dcce9987ed41eac46b2415eecda092692b9dd915" + "sha256": "88c94a496b941ef0538a7bab550c85d2fc07487edf35e4cd39bde14b1475108c" }, { "label": "package_verification", @@ -214,15 +200,15 @@ "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, - "bytes": 8758, - "sha256": "c91884a915384363d4ea0339de5c9a3e37ede4356ad1069edf0ae6f880366cc7" + "bytes": 8604, + "sha256": "044b2cf73dd4559a2a0b2f6cbb5560677d409d4716d135261fac6399012d1abb" }, { "label": "skill_os2_audit", "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14310, - "sha256": "4f193d15332d6ae7c6df397b0c777219fc9627b61c176ca70f66e43b4e94d08e" + "sha256": "e63bc60e69cdc0e613983edea2a66f6c80d0e4da92efd6f90203c390b813350d" }, { "label": "world_class_evidence_plan", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index bae787d4..eb6557e3 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,18 +1,18 @@ # Benchmark Reproducibility Generated at: `2026-06-17` -Commit: `d709f043a2c286646a5c72d7345faaed932200de` -Working tree dirty at generation: `true` -Evidence bundle SHA256: `16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec` +Commit: `360f05503df3d7543d74417bcaf3f6a749a23477` +Working tree dirty at generation: `false` +Evidence bundle SHA256: `89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9` ## Summary - reproducibility ready: `true` -- release lock ready: `false` +- release lock ready: `true` - methodology complete: `true` - required artifacts: `25` - missing artifacts: `0` -- source contract sha256: `83ea6e60852f` +- source contract sha256: `e9d5b26e20c8` - archive sha256: `563d37a1085a` - output cases: `5` - disclosed failure cases: `3` @@ -22,8 +22,8 @@ Evidence bundle SHA256: `16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc9 - world-class ready: `false` - world-class source checks: `9` pass / `17` total; `8` blocked - public claim ready: `false` -- public claim blockers: `5` -- changed files at generation: `32` +- public claim blockers: `4` +- changed files at generation: `0` This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below. @@ -35,7 +35,6 @@ This report proves local benchmark reproducibility only. It keeps external provi | Blocker | | --- | -| release lock is not clean or commit is unavailable | | provider-backed model holdout evidence is incomplete | | human blind-review adjudication is incomplete | | world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) | @@ -43,15 +42,15 @@ This report proves local benchmark reproducibility only. It keeps external provi ## Release Lock -- ready: `false` -- reason: working tree was dirty at generation time +- ready: `true` +- reason: clean generation-time HEAD - status scope: generation-time status before this report is written ## Evidence Bundle - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `25` / `25` -- sha256: `16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec` +- sha256: `89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9` ## Methodology Sections @@ -73,17 +72,17 @@ This report proves local benchmark reproducibility only. It keeps external provi | output_cases | `evals/output/cases.jsonl` | present | `a6ae96857116` | | output_schema | `evals/output/schema.json` | present | `8ee340c95064` | | output_scorecard | `reports/output_quality_scorecard.json` | present | `0806258a8e08` | -| output_execution | `reports/output_execution_runs.json` | present | `ce151bc7d860` | +| output_execution | `reports/output_execution_runs.json` | present | `282122e93b08` | | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` | | review_adjudication | `reports/output_review_adjudication.json` | present | `2ed79f8bc7a3` | | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` | | runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` | -| trust_report | `reports/security_trust_report.json` | present | `f110df76d439` | -| python_compatibility | `reports/python_compatibility.json` | present | `636583616dbc` | -| registry_audit | `reports/registry_audit.json` | present | `c28991bdf087` | +| trust_report | `reports/security_trust_report.json` | present | `d865e5cc97a3` | +| python_compatibility | `reports/python_compatibility.json` | present | `f8e498d295db` | +| registry_audit | `reports/registry_audit.json` | present | `88c94a496b94` | | package_verification | `reports/package_verification.json` | present | `f9c6cdf1a7e0` | -| install_simulation | `reports/install_simulation.json` | present | `c91884a91538` | -| skill_os2_audit | `reports/skill_os2_audit.json` | present | `4f193d15332d` | +| install_simulation | `reports/install_simulation.json` | present | `044b2cf73dd4` | +| skill_os2_audit | `reports/skill_os2_audit.json` | present | `e63bc60e69cd` | | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `d9781994f88c` | | world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `dc7fba17bf81` | | world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `e57fba2812b3` | diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index 39592ecb..2ccd88ca 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -189,12 +189,12 @@ "status": "pass", "expected": { "status": "pass", - "detail": "initial load 990/1000; deferred 498644/120000; top deferred scripts 437614; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 498646/120000; top deferred scripts 437616; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "actual": { "status": "pass", - "detail": "initial load 990/1000; deferred 498644/120000; top deferred scripts 437614; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 498646/120000; top deferred scripts 437616; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "paths": [ @@ -222,7 +222,7 @@ "actual": { "available": true, "clean": false, - "changed_file_count": 9 + "changed_file_count": 7 }, "paths": [ "reports/benchmark_reproducibility.json" @@ -263,8 +263,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "d709f043a2c286646a5c72d7345faaed932200de", - "actual": "d709f043a2c286646a5c72d7345faaed932200de", + "expected": "360f05503df3d7543d74417bcaf3f6a749a23477", + "actual": "360f05503df3d7543d74417bcaf3f6a749a23477", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -409,8 +409,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "d709f043a2c286646a5c72d7345faaed932200de", - "actual": "d709f043a2c286646a5c72d7345faaed932200de", + "expected": "360f05503df3d7543d74417bcaf3f6a749a23477", + "actual": "360f05503df3d7543d74417bcaf3f6a749a23477", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" diff --git a/reports/review-studio.html b/reports/review-studio.html index f4adf052..1f2c4aed 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

5 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

147 scripts scanned; secrets found

Py Compat0

225 files scanned for Python 3.11

Arch Debt0

696 largest lines; 0 watchlist; 2 early; 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

182 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

685 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

147 scripts scanned; secrets found

Py Compat0

225 files scanned for Python 3.11

Arch Debt0

696 largest lines; 0 watchlist; 2 early; 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

182 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

685 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 498644/120000; top deferred scripts 437614; 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; 147 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 225 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

222 Python files; 0 hotspots; 0 watchlist files; 2 early watch 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 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true

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 9/17 pass; 8 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 498646/120000; top deferred scripts 437616; 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; 147 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 225 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

222 Python files; 0 hotspots; 0 watchlist files; 2 early watch 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 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true

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 9/17 pass; 8 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
@@ -812,7 +812,7 @@
-

上下文

initial load 990/1000; deferred 498644/120000; top deferred scripts 437614; resource governance governed; quality density 131.3

+

上下文

initial load 990/1000; deferred 498646/120000; top deferred scripts 437616; 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.

@@ -882,8 +882,8 @@
-

公开声明

本地复现
是
发布锁
否
可公开声明
否
声明阻断
5
Provider 证据
否
人审完成
否
世界级就绪
否
-

声明阻断

  • 阻断release lock is not clean or commit is unavailable
  • 阻断provider-backed model holdout evidence is incomplete
  • 阻断human blind-review adjudication is incomplete
  • 阻断world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)
  • 阻断world-class source checks are not all accepted (9/17 pass, 8 blocked)
+

公开声明

本地复现
是
发布锁
是
可公开声明
否
声明阻断
4
Provider 证据
否
人审完成
否
世界级就绪
否
+

声明阻断

  • 阻断provider-backed model holdout evidence is incomplete
  • 阻断human blind-review adjudication is incomplete
  • 阻断world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)
  • 阻断world-class source checks are not all accepted (9/17 pass, 8 blocked)
diff --git a/reports/review-studio.json b/reports/review-studio.json index 0f6efe01..feb643c4 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 498644/120000; top deferred scripts 437614; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 498646/120000; top deferred scripts 437616; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json", "link": "context_budget.md" }, @@ -1981,12 +1981,12 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec", - "source_contract_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7", + "evidence_bundle_sha256": "89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9", + "source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995", "archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e", "output_case_count": 5, "failure_disclosure_count": 3, @@ -2005,11 +2005,11 @@ "world_class_source_pass_count": 9, "world_class_source_blocked_count": 8, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 32 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, - "commit": "d709f043a2c286646a5c72d7345faaed932200de", + "commit": "360f05503df3d7543d74417bcaf3f6a749a23477", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -2114,7 +2114,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 239, - "package_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7" + "package_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995" }, "skill_atlas": { "skill_count": 12, @@ -2189,7 +2189,7 @@ "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-17" }, "failures": [], "warnings": [] @@ -5740,35 +5740,22 @@ "ok": true, "generated_at": "2026-06-17", "skill_dir": ".", - "commit": "d709f043a2c286646a5c72d7345faaed932200de", + "commit": "360f05503df3d7543d74417bcaf3f6a749a23477", "git_status": { "available": true, - "dirty": true, - "changed_file_count": 32, - "sample": [ - " M registry/index.json", - " M registry/packages/yao-meta-skill.json", - " M reports/adoption_drift_report.json", - " M reports/architecture_maintainability.json", - " M reports/architecture_maintainability.md", - " M reports/benchmark_reproducibility.json", - " M reports/benchmark_reproducibility.md", - " M reports/compiled_targets.json", - " M reports/context_budget.json", - " M reports/evidence_consistency.json", - " M reports/install_simulation.json", - " M reports/install_simulation.md" - ], + "dirty": false, + "changed_file_count": 0, + "sample": [], "scope": "generation-time status before this report is written" }, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec", - "source_contract_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7", + "evidence_bundle_sha256": "89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9", + "source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995", "archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e", "output_case_count": 5, "failure_disclosure_count": 3, @@ -5787,15 +5774,14 @@ "world_class_source_pass_count": 9, "world_class_source_blocked_count": 8, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 32 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, "public_claim": { "ready": false, "scope": "public benchmark or world-class readiness claim", "blockers": [ - "release lock is not clean or commit is unavailable", "provider-backed model holdout evidence is incomplete", "human blind-review adjudication is incomplete", "world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)", @@ -5804,10 +5790,10 @@ "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks." }, "release_lock": { - "ready": false, - "commit": "d709f043a2c286646a5c72d7345faaed932200de", + "ready": true, + "commit": "360f05503df3d7543d74417bcaf3f6a749a23477", "status_scope": "generation-time status before this report is written", - "reason": "working tree was dirty at generation time" + "reason": "clean generation-time HEAD" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -5815,7 +5801,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec" + "sha256": "89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5888,8 +5874,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7963, - "sha256": "ce151bc7d860840d0308731c3cf0342cae0610489d4205b452bbd4e47cc607ef" + "bytes": 7964, + "sha256": "282122e93b08d73b0c199715c51bc619a95af47d315047fc41dceb31f56a3293" }, { "label": "blind_review", @@ -5924,21 +5910,21 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 133860, - "sha256": "f110df76d439c01b2d9b4ea82561d6c5277ff407f7ef616504e3923438d4d96b" + "sha256": "d865e5cc97a3b92e1332366c5c780354afb46038ba1c6ef152a61cc8407a19bc" }, { "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, "bytes": 29196, - "sha256": "636583616dbcc15fe06d582ff0eda17c08a3d37eae618b03e1ca9c666c5276d2" + "sha256": "f8e498d295db139c49e2ea51bd2cbdd52db61fa2b0bd008ef74135601d691895" }, { "label": "registry_audit", "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "c28991bdf087bb31370774c1dcce9987ed41eac46b2415eecda092692b9dd915" + "sha256": "88c94a496b941ef0538a7bab550c85d2fc07487edf35e4cd39bde14b1475108c" }, { "label": "package_verification", @@ -5951,15 +5937,15 @@ "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, - "bytes": 8758, - "sha256": "c91884a915384363d4ea0339de5c9a3e37ede4356ad1069edf0ae6f880366cc7" + "bytes": 8604, + "sha256": "044b2cf73dd4559a2a0b2f6cbb5560677d409d4716d135261fac6399012d1abb" }, { "label": "skill_os2_audit", "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14310, - "sha256": "4f193d15332d6ae7c6df397b0c777219fc9627b61c176ca70f66e43b4e94d08e" + "sha256": "e63bc60e69cdc0e613983edea2a66f6c80d0e4da92efd6f90203c390b813350d" }, { "label": "world_class_evidence_plan", @@ -17296,15 +17282,15 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1094713, + "other_text_tokens": 1094791, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1095510, - "deferred_resource_tokens": 498644, + "estimated_total_text_tokens": 1095588, + "deferred_resource_tokens": 498646, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 437614, + "estimated_tokens": 437616, "file_count": 147 }, { @@ -17326,7 +17312,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 437614, + "estimated_tokens": 437616, "file_count": 147 } ], @@ -17349,7 +17335,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 437614, + "estimated_tokens": 437616, "file_count": 147, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } diff --git a/reports/review-viewer.json b/reports/review-viewer.json index a0b2368b..99644f99 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -1000,12 +1000,12 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec", - "source_contract_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7", + "evidence_bundle_sha256": "89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9", + "source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995", "archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1024,11 +1024,11 @@ "world_class_source_pass_count": 9, "world_class_source_blocked_count": 8, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 32 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, - "commit": "d709f043a2c286646a5c72d7345faaed932200de", + "commit": "360f05503df3d7543d74417bcaf3f6a749a23477", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -1133,7 +1133,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 239, - "package_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7" + "package_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995" }, "skill_atlas": { "skill_count": 12, @@ -1208,7 +1208,7 @@ "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-17" }, "failures": [], "warnings": [] diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index bcc3e95c..5819b4e5 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -1004,12 +1004,12 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec", - "source_contract_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7", + "evidence_bundle_sha256": "89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9", + "source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995", "archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1028,11 +1028,11 @@ "world_class_source_pass_count": 9, "world_class_source_blocked_count": 8, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 32 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, - "commit": "d709f043a2c286646a5c72d7345faaed932200de", + "commit": "360f05503df3d7543d74417bcaf3f6a749a23477", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -1137,7 +1137,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 239, - "package_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7" + "package_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995" }, "skill_atlas": { "skill_count": 12, @@ -1212,7 +1212,7 @@ "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-17" }, "failures": [], "warnings": [] diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 176696a0..c2f8e9c0 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -999,12 +999,12 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": false, + "release_lock_ready": true, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "16f2d277d5d15e9c1c1605610f163e7060e52bf80f6d5bca4f8ccc94595ab1ec", - "source_contract_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7", + "evidence_bundle_sha256": "89447ea6d6ec41f79db4ce33978d0d0d426138b0ace0746153dc2a7daba4baa9", + "source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995", "archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1023,11 +1023,11 @@ "world_class_source_pass_count": 9, "world_class_source_blocked_count": 8, "public_claim_ready": false, - "public_claim_blocker_count": 5, - "working_tree_dirty": true, - "changed_file_count": 32 + "public_claim_blocker_count": 4, + "working_tree_dirty": false, + "changed_file_count": 0 }, - "commit": "d709f043a2c286646a5c72d7345faaed932200de", + "commit": "360f05503df3d7543d74417bcaf3f6a749a23477", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -1132,7 +1132,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 239, - "package_sha256": "83ea6e60852fae9271eb72658d8b3c0268e6adb21d80b2fd0fd9438805481ca7" + "package_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995" }, "skill_atlas": { "skill_count": 12, @@ -1207,7 +1207,7 @@ "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-17" }, "failures": [], "warnings": []