5 targets in platform-neutral contract
diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json
index 5cd6ae28..ae0085f8 100644
--- a/reports/benchmark_reproducibility.json
+++ b/reports/benchmark_reproducibility.json
@@ -3,19 +3,17 @@
"ok": true,
"generated_at": "2026-06-16",
"skill_dir": ".",
- "commit": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
+ "commit": "4f339c536676c48037194b95ff0a1e157041c453",
"git_status": {
"available": true,
- "dirty": true,
- "changed_file_count": 1,
- "sample": [
- " M reports/context_budget.json"
- ],
+ "dirty": false,
+ "changed_file_count": 0,
+ "sample": [],
"scope": "generation-time status before this report is written"
},
"summary": {
"reproducibility_ready": true,
- "release_lock_ready": false,
+ "release_lock_ready": true,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
@@ -39,15 +37,14 @@
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
- "public_claim_blocker_count": 5,
- "working_tree_dirty": true,
- "changed_file_count": 1
+ "public_claim_blocker_count": 4,
+ "working_tree_dirty": false,
+ "changed_file_count": 0
},
"public_claim": {
"ready": false,
"scope": "public benchmark or world-class readiness claim",
"blockers": [
- "release lock is not clean or commit is unavailable",
"provider-backed model holdout evidence is incomplete",
"human blind-review adjudication is incomplete",
"world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
@@ -56,10 +53,10 @@
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
},
"release_lock": {
- "ready": false,
- "commit": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
+ "ready": true,
+ "commit": "4f339c536676c48037194b95ff0a1e157041c453",
"status_scope": "generation-time status before this report is written",
- "reason": "working tree was dirty at generation time"
+ "reason": "clean generation-time HEAD"
},
"evidence_bundle": {
"algorithm": "sha256(path,label,exists,artifact_sha256)",
diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md
index 8612e1c5..8cc56cc0 100644
--- a/reports/benchmark_reproducibility.md
+++ b/reports/benchmark_reproducibility.md
@@ -1,14 +1,14 @@
# Benchmark Reproducibility
Generated at: `2026-06-16`
-Commit: `7df231b6d229c49a4980eb4e8a97e5dc940bbed6`
-Working tree dirty at generation: `true`
+Commit: `4f339c536676c48037194b95ff0a1e157041c453`
+Working tree dirty at generation: `false`
Evidence bundle SHA256: `e29fb9204676313a6abe14b1a33dfe8c40f88659227570762fff51396ff99a3a`
## Summary
- reproducibility ready: `true`
-- release lock ready: `false`
+- release lock ready: `true`
- methodology complete: `true`
- required artifacts: `25`
- missing artifacts: `0`
@@ -22,8 +22,8 @@ Evidence bundle SHA256: `e29fb9204676313a6abe14b1a33dfe8c40f88659227570762fff513
- world-class ready: `false`
- world-class source checks: `6` pass / `13` total; `7` blocked
- public claim ready: `false`
-- public claim blockers: `5`
-- changed files at generation: `1`
+- public claim blockers: `4`
+- changed files at generation: `0`
This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
@@ -35,7 +35,6 @@ This report proves local benchmark reproducibility only. It keeps external provi
| Blocker |
| --- |
-| release lock is not clean or commit is unavailable |
| provider-backed model holdout evidence is incomplete |
| human blind-review adjudication is incomplete |
| world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) |
@@ -43,8 +42,8 @@ This report proves local benchmark reproducibility only. It keeps external provi
## Release Lock
-- ready: `false`
-- reason: working tree was dirty at generation time
+- ready: `true`
+- reason: clean generation-time HEAD
- status scope: generation-time status before this report is written
## Evidence Bundle
diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json
index 35c18181..8c2378ec 100644
--- a/reports/evidence_consistency.json
+++ b/reports/evidence_consistency.json
@@ -207,8 +207,8 @@
"key": "benchmark-release-lock-self-consistency",
"label": "Benchmark release lock matches git dirty state",
"status": "pass",
- "expected": false,
- "actual": false,
+ "expected": true,
+ "actual": true,
"paths": [
"reports/benchmark_reproducibility.json"
],
@@ -248,8 +248,8 @@
"key": "overview-benchmark-commit",
"label": "overview embeds the benchmark commit",
"status": "pass",
- "expected": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
- "actual": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
+ "expected": "4f339c536676c48037194b95ff0a1e157041c453",
+ "actual": "4f339c536676c48037194b95ff0a1e157041c453",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-overview.json"
@@ -261,7 +261,7 @@
"label": "overview embeds benchmark summary fields",
"status": "pass",
"expected": {
- "release_lock_ready": false,
+ "release_lock_ready": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "1e5b2ced62c29f6d23ad88f576df6f278bfc0582382c11f834f56b64a686ed80",
@@ -271,10 +271,10 @@
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
- "public_claim_blocker_count": 5
+ "public_claim_blocker_count": 4
},
"actual": {
- "release_lock_ready": false,
+ "release_lock_ready": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "1e5b2ced62c29f6d23ad88f576df6f278bfc0582382c11f834f56b64a686ed80",
@@ -284,7 +284,7 @@
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
- "public_claim_blocker_count": 5
+ "public_claim_blocker_count": 4
},
"paths": [
"reports/benchmark_reproducibility.json",
@@ -394,8 +394,8 @@
"key": "interpretation-benchmark-commit",
"label": "interpretation embeds the benchmark commit",
"status": "pass",
- "expected": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
- "actual": "7df231b6d229c49a4980eb4e8a97e5dc940bbed6",
+ "expected": "4f339c536676c48037194b95ff0a1e157041c453",
+ "actual": "4f339c536676c48037194b95ff0a1e157041c453",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-interpretation.json"
@@ -407,7 +407,7 @@
"label": "interpretation embeds benchmark summary fields",
"status": "pass",
"expected": {
- "release_lock_ready": false,
+ "release_lock_ready": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "1e5b2ced62c29f6d23ad88f576df6f278bfc0582382c11f834f56b64a686ed80",
@@ -417,10 +417,10 @@
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
- "public_claim_blocker_count": 5
+ "public_claim_blocker_count": 4
},
"actual": {
- "release_lock_ready": false,
+ "release_lock_ready": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "1e5b2ced62c29f6d23ad88f576df6f278bfc0582382c11f834f56b64a686ed80",
@@ -430,7 +430,7 @@
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
- "public_claim_blocker_count": 5
+ "public_claim_blocker_count": 4
},
"paths": [
"reports/benchmark_reproducibility.json",
diff --git a/reports/review-studio.html b/reports/review-studio.html
index cf186086..40739af1 100644
--- a/reports/review-studio.html
+++ b/reports/review-studio.html
@@ -740,12 +740,12 @@
5 targets in platform-neutral contract target contracts compiled from Skill IR 5 cases; 1 file-backed command 10; model 0; recorded 0 review pairs hide baseline vs with-skill labels pending 5; answer key hidden adjudication decisions; pending 5 5 blockers; local reproducible true 2.0 coverage; extensions partial 0, planned 0; evidence pending 4 target conformance pass rate 0 native; 4 installer-enforced 122 scripts scanned; secrets found 196 files scanned for Python 3.11 870 largest lines; 9 watchlist; 68 CLI handlers; 18 in entrypoint 12 scanned skills; route collisions 1 metadata events; 0 missed triggers proposal-review; approval 0; release lock false curator-review; ready 1; top score 88 0 gates covered; human risk decisions 0 valid submissions; 0 invalid 180 public surfaces scanned 0 open blocker annotations 5 targets; MIT license 649 zip entries; package verification 4 adapters; 12 permissions enforced; 0 permission failures declared minor; 0 breaking changes 5 targets in platform-neutral contract target contracts compiled from Skill IR 5 cases; 1 file-backed command 10; model 0; recorded 0 review pairs hide baseline vs with-skill labels pending 5; answer key hidden adjudication decisions; pending 5 4 blockers; local reproducible true 2.0 coverage; extensions partial 0, planned 0; evidence pending 4 target conformance pass rate 0 native; 4 installer-enforced 122 scripts scanned; secrets found 196 files scanned for Python 3.11 870 largest lines; 9 watchlist; 68 CLI handlers; 18 in entrypoint 12 scanned skills; route collisions 1 metadata events; 0 missed triggers proposal-review; approval 0; release lock true curator-review; ready 1; top score 88 0 gates covered; human risk decisions 0 valid submissions; 0 invalid 180 public surfaces scanned 0 open blocker annotations 5 targets; MIT license 649 zip entries; package verification 4 adapters; 12 permissions enforced; 0 permission failures declared minor; 0 breaking changes intent confidence 100/100; Intent is clear enough to package the first routeable version. 13 trigger cases; 0 misroutes; 0 ambiguous 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 initial load 990/1000; deferred 484804/120000; top deferred scripts 424826; resource governance governed; quality density 131.3 5 / 5 targets pass 0 secrets; 122 scripts; 3 network-capable scripts; 0 help smoke failures Python 3.11; 196 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards 193 Python files; 0 hotspots; 9 watchlist files; 0 blockers; largest 870 lines; 68 CLI handlers; 18 in entrypoint 3/3 permissions approved; gaps 0; required file_write, network, subprocess 4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4 12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues 1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false 0 active waivers; 1 warning gates still need reviewer decision 4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures 0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended intent confidence 100/100; Intent is clear enough to package the first routeable version. 13 trigger cases; 0 misroutes; 0 ambiguous 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 initial load 990/1000; deferred 484804/120000; top deferred scripts 424826; resource governance governed; quality density 131.3 5 / 5 targets pass 0 secrets; 122 scripts; 3 network-capable scripts; 0 help smoke failures Python 3.11; 196 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards 193 Python files; 0 hotspots; 9 watchlist files; 0 blockers; largest 870 lines; 68 CLI handlers; 18 in entrypoint 3/3 permissions approved; gaps 0; required file_write, network, subprocess 4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4 12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues 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 0 active waivers; 1 warning gates still need reviewer decision 4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures 0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended核心指标
- 审查闸门
- 意图画布
触发实验
输出实验
上下文
运行矩阵
信任报告
Python 兼容
架构维护
权限批准
权限探针
组合治理
运营回路
人工批准
世界证据
注册审计
发布路线
意图画布
触发实验
输出实验
上下文
运行矩阵
信任报告
Python 兼容
架构维护
权限批准
权限探针
组合治理
运营回路
人工批准
世界证据
注册审计
发布路线
1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false
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