frostbyte_neo/yao-meta-skill
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity

Block answer-key fields in evidence submissions

Browse Source
This commit is contained in:
yaojingang
2026-06-17 00:15:07 +08:00
parent 500f8cc34e
commit 3961b60341
31 changed files with 253 additions and 217 deletions
Download Patch File Download Diff File Expand all files Collapse all files
reports/adaptation_proposals.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-16T16:14:10Z",
"skill_dir": ".",
"source_patterns": "reports/user_patterns.json",
"pattern_count": 5,
reports/adaptation_proposals.md
+1 -1
View File
@@ -1,6 +1,6 @@
# Adaptation Proposals
- Generated at: `2026-06-17`
- Generated at: `2026-06-16T16:14:10Z`
- Pattern report: `reports/user_patterns.json`
- Proposal only: `true`
- Writes repository files: `false`
reports/adoption_drift_report.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-16T16:07:15Z",
"generated_at": "2026-06-16T16:14:10Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
reports/architecture_maintainability.json
+1 -1
View File
@@ -87,7 +87,7 @@
},
{
"path": "tests/verify_world_class_evidence_intake.py",
"lines": 610,
"lines": 628,
"kind": "test",
"severity": "pass",
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
reports/architecture_maintainability.md
+1 -1
View File
@@ -42,7 +42,7 @@ No near-threshold files found.
| `scripts/review_studio_gates.py` | `643` | `internal-module` | `pass` |
| `scripts/cross_packager.py` | `638` | `cli-script` | `pass` |
| `scripts/build_skill_atlas.py` | `637` | `cli-script` | `pass` |
| `tests/verify_world_class_evidence_intake.py` | `610` | `test` | `pass` |
| `tests/verify_world_class_evidence_intake.py` | `628` | `test` | `pass` |
| `scripts/render_benchmark_reproducibility.py` | `595` | `cli-script` | `pass` |
| `scripts/optimize_description.py` | `585` | `cli-script` | `pass` |
reports/benchmark_reproducibility.json
+32 -18
View File
@@ -3,22 +3,35 @@
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "4a5880bea1a07966e0d914c453d22cf6132c5781",
"commit": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a",
"git_status": {
"available": true,
"dirty": false,
"changed_file_count": 0,
"sample": [],
"dirty": true,
"changed_file_count": 30,
"sample": [
" M reports/adaptation_proposals.json",
" M reports/adaptation_proposals.md",
" 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/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"
],
"scope": "generation-time status before this report is written"
},
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "62e7b774ed1b2bd66e28986ad09ffecb9da8ae4d9008641cfe63dcfe354f0c91",
"source_contract_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627",
"evidence_bundle_sha256": "c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c",
"source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -37,14 +50,15 @@
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 30
},
"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)",
@@ -53,10 +67,10 @@
"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": true,
"commit": "4a5880bea1a07966e0d914c453d22cf6132c5781",
"ready": false,
"commit": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a",
"status_scope": "generation-time status before this report is written",
"reason": "clean generation-time HEAD"
"reason": "working tree was dirty at generation time"
},
"evidence_bundle": {
"algorithm": "sha256(path,label,exists,artifact_sha256)",
@@ -64,7 +78,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "62e7b774ed1b2bd66e28986ad09ffecb9da8ae4d9008641cfe63dcfe354f0c91"
"sha256": "c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -138,7 +152,7 @@
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7966,
"sha256": "2ce010cd2fc2062d9a503e14394fae334b340d8c64192cf5536d4d579fd7b32d"
"sha256": "2c9409158a128e6d2ad4c96c499dd412591c7b287d907e8d88987132a0592633"
},
{
"label": "blind_review",
@@ -173,7 +187,7 @@
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 129520,
"sha256": "893952155dde2bb2bc1b0d87fb1bf2c43ff4ed995e39c60bc3681f7f03b2a02d"
"sha256": "0d60cae961055a68ac84d83cc23d6d8456cc4b42b1a103dd963f3343a20987ff"
},
{
"label": "python_compatibility",
@@ -270,8 +284,8 @@
"label": "world_class_claim_guard",
"path": "reports/world_class_claim_guard.json",
"exists": true,
"bytes": 18406,
"sha256": "e331d52d41166a07f068c44bf4c50c5dcdd9f1bce984e4303c832fe5f73d9d66"
"bytes": 18596,
"sha256": "abe7f7d60c0025e140373fadaefbed4063f285c140c74b9c7cfb464e354bb526"
}
],
"missing_artifacts": [],
reports/benchmark_reproducibility.md
+14 -13
View File
@@ -1,18 +1,18 @@
# Benchmark Reproducibility
Generated at: `2026-06-17`
Commit: `4a5880bea1a07966e0d914c453d22cf6132c5781`
Working tree dirty at generation: `false`
Evidence bundle SHA256: `62e7b774ed1b2bd66e28986ad09ffecb9da8ae4d9008641cfe63dcfe354f0c91`
Commit: `500f8cc34ef5ff9a3c8125a72509faabbe95ac9a`
Working tree dirty at generation: `true`
Evidence bundle SHA256: `c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c`
## Summary
- reproducibility ready: `true`
- release lock ready: `true`
- release lock ready: `false`
- methodology complete: `true`
- required artifacts: `25`
- missing artifacts: `0`
- source contract sha256: `fcfe5f3c7222`
- source contract sha256: `d50f6ac9714b`
- archive sha256: `5802e5f52255`
- output cases: `5`
- disclosed failure cases: `3`
@@ -22,8 +22,8 @@ Evidence bundle SHA256: `62e7b774ed1b2bd66e28986ad09ffecb9da8ae4d9008641cfe63dcf
- world-class ready: `false`
- world-class source checks: `6` pass / `13` total; `7` blocked
- public claim ready: `false`
- public claim blockers: `4`
- changed files at generation: `0`
- public claim blockers: `5`
- changed files at generation: `30`
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.
@@ -35,6 +35,7 @@ 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) |
@@ -42,15 +43,15 @@ This report proves local benchmark reproducibility only. It keeps external provi
## Release Lock
- ready: `true`
- reason: clean generation-time HEAD
- ready: `false`
- reason: working tree was dirty at generation time
- status scope: generation-time status before this report is written
## Evidence Bundle
- algorithm: `sha256(path,label,exists,artifact_sha256)`
- artifacts: `25` / `25`
- sha256: `62e7b774ed1b2bd66e28986ad09ffecb9da8ae4d9008641cfe63dcfe354f0c91`
- sha256: `c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c`
## Methodology Sections
@@ -72,12 +73,12 @@ 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 | `2ce010cd2fc2` |
| output_execution | `reports/output_execution_runs.json` | present | `2c9409158a12` |
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
| 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 | `893952155dde` |
| trust_report | `reports/security_trust_report.json` | present | `0d60cae96105` |
| python_compatibility | `reports/python_compatibility.json` | present | `8b48340618cc` |
| registry_audit | `reports/registry_audit.json` | present | `e75a341d15e4` |
| package_verification | `reports/package_verification.json` | present | `a27941fdb865` |
@@ -91,7 +92,7 @@ This report proves local benchmark reproducibility only. It keeps external provi
| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `f90d59c3e586` |
| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `be79ee0f70a3` |
| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `9a7be02a6990` |
| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `e331d52d4116` |
| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `abe7f7d60c00` |
## Reproduction Commands
reports/context_budget.json
+6 -6
View File
@@ -6,15 +6,15 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 797,
"other_text_tokens": 1076491,
"other_text_tokens": 1076748,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1077288,
"deferred_resource_tokens": 495322,
"estimated_total_text_tokens": 1077545,
"deferred_resource_tokens": 495216,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 435224,
"estimated_tokens": 435118,
"file_count": 140
},
{
@@ -36,7 +36,7 @@
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 435224,
"estimated_tokens": 435118,
"file_count": 140
}
],
@@ -59,7 +59,7 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 435224,
"estimated_tokens": 435118,
"file_count": 140,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
reports/context_budget.md
+1 -1
View File
@@ -2,7 +2,7 @@
| Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status |
| --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- |
| root | `.` | `production` | 1000 | 990 | 797 | 495322 | `governed` | scripts:435224 | 131.3 | - | ok |
| root | `.` | `production` | 1000 | 990 | 797 | 495216 | `governed` | scripts:435118 | 131.3 | - | ok |
| complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok |
| governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok |
reports/context_budget_summary.json
+3 -3
View File
@@ -8,11 +8,11 @@
"budget_limit": 1000,
"initial_tokens": 990,
"skill_body_tokens": 797,
"deferred_resource_tokens": 495322,
"deferred_resource_tokens": 495216,
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 435224,
"estimated_tokens": 435118,
"file_count": 140
}
],
@@ -35,7 +35,7 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 435224,
"estimated_tokens": 435118,
"file_count": 140,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
reports/evidence_consistency.json
+20 -20
View File
@@ -189,12 +189,12 @@
"status": "pass",
"expected": {
"status": "pass",
"detail": "initial load 990/1000; deferred 495322/120000; top deferred scripts 435224; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 495216/120000; top deferred scripts 435118; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json"
},
"actual": {
"status": "pass",
"detail": "initial load 990/1000; deferred 495322/120000; top deferred scripts 435224; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 495216/120000; top deferred scripts 435118; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json"
},
"paths": [
@@ -207,8 +207,8 @@
"key": "benchmark-release-lock-self-consistency",
"label": "Benchmark release lock matches git dirty state",
"status": "pass",
"expected": true,
"actual": true,
"expected": false,
"actual": false,
"paths": [
"reports/benchmark_reproducibility.json"
],
@@ -248,8 +248,8 @@
"key": "overview-benchmark-commit",
"label": "overview embeds the benchmark commit",
"status": "pass",
"expected": "4a5880bea1a07966e0d914c453d22cf6132c5781",
"actual": "4a5880bea1a07966e0d914c453d22cf6132c5781",
"expected": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a",
"actual": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-overview.json"
@@ -261,30 +261,30 @@
"label": "overview embeds benchmark summary fields",
"status": "pass",
"expected": {
"release_lock_ready": true,
"release_lock_ready": false,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627",
"source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4
"public_claim_blocker_count": 5
},
"actual": {
"release_lock_ready": true,
"release_lock_ready": false,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627",
"source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4
"public_claim_blocker_count": 5
},
"paths": [
"reports/benchmark_reproducibility.json",
@@ -394,8 +394,8 @@
"key": "interpretation-benchmark-commit",
"label": "interpretation embeds the benchmark commit",
"status": "pass",
"expected": "4a5880bea1a07966e0d914c453d22cf6132c5781",
"actual": "4a5880bea1a07966e0d914c453d22cf6132c5781",
"expected": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a",
"actual": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-interpretation.json"
@@ -407,30 +407,30 @@
"label": "interpretation embeds benchmark summary fields",
"status": "pass",
"expected": {
"release_lock_ready": true,
"release_lock_ready": false,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627",
"source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4
"public_claim_blocker_count": 5
},
"actual": {
"release_lock_ready": true,
"release_lock_ready": false,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627",
"source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4
"public_claim_blocker_count": 5
},
"paths": [
"reports/benchmark_reproducibility.json",
reports/output_execution_runs.json
+10 -10
View File
@@ -34,7 +34,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.21,
"duration_ms": 25.96,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -62,7 +62,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.58,
"duration_ms": 26.2,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -85,7 +85,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.38,
"duration_ms": 26.36,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -113,7 +113,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.17,
"duration_ms": 26.09,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -136,7 +136,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.22,
"duration_ms": 26.43,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -164,7 +164,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.2,
"duration_ms": 26.16,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -187,7 +187,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.05,
"duration_ms": 27.55,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -214,7 +214,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.83,
"duration_ms": 28.86,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -237,7 +237,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.02,
"duration_ms": 28.87,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -266,7 +266,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.32,
"duration_ms": 30.17,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
reports/output_execution_runs.md
+10 -10
View File
@@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext
| Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status |
| --- | --- | --- | --- | ---: | ---: | ---: | --- |
| skill-package-contract | baseline | command | local-output-eval-runner | 27.21 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 26.58 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 26.38 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 26.17 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 26.22 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.2 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.05 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 25.83 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.02 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.32 | 98 | 100.0 | pass |
| skill-package-contract | baseline | command | local-output-eval-runner | 25.96 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 26.2 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 26.36 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 26.09 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 26.43 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.16 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 27.55 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 28.86 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 28.87 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 30.17 | 98 | 100.0 | pass |
## Next Fixes
reports/review-studio.html
+7 -7
View File
@@ -740,12 +740,12 @@
<section>
<h2>核心指标</h2>
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>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>140 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>218 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>696 largest lines; 0 watchlist; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock false</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>180 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>658 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>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>140 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>218 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>696 largest lines; 0 watchlist; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock false</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>182 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>658 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
</section>
<section>
<h2>审查闸门</h2>
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 990/1000; deferred 495322/120000; top deferred scripts 435224; resource governance governed; quality density 131.3</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 140 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 218 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>215 Python files; 0 hotspots; 0 watchlist files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 990/1000; deferred 495216/120000; top deferred scripts 435118; resource governance governed; quality density 131.3</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 140 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 218 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>215 Python files; 0 hotspots; 0 watchlist files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
</section>
<section>
@@ -812,12 +812,12 @@
</section>
<section class="twocol">
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 495322/120000; top deferred scripts 435224; resource governance governed; quality density 131.3</p></div>
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 495216/120000; top deferred scripts 435118; resource governance governed; quality density 131.3</p></div>
<div class="panel"><h2>编译证据</h2><p>Review reports/compiled_targets.md before packaging to inspect target adapter modes, generated files, preserved semantics, warnings, and unsupported features.</p></div>
</section>
<section id="trust" class="twocol">
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>140</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627</code></dd></div></dl></div>
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>140</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69</code></dd></div></dl></div>
<div class="panel"><h2>安全边界</h2><p>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。</p></div>
</section>
@@ -882,8 +882,8 @@
</section>
<section class="twocol">
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>4</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>5</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>release lock is not clean or commit is unavailable</span></li><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
</section>
<section class="twocol">
@@ -897,7 +897,7 @@
</section>
<section class="twocol">
<div class="panel"><h2>声明守卫</h2><dl class='kv-grid'><div><dt>台账可声明</dt><dd>否</dd></div><div><dt>台账待补</dt><dd>4</dd></div><div><dt>声明面</dt><dd>180</dd></div><div><dt>违规数</dt><dd>0</dd></div><div><dt>Overclaim Guard Active</dt><dd>是</dd></div></dl></div>
<div class="panel"><h2>声明守卫</h2><dl class='kv-grid'><div><dt>台账可声明</dt><dd>否</dd></div><div><dt>台账待补</dt><dd>4</dd></div><div><dt>声明面</dt><dd>182</dd></div><div><dt>违规数</dt><dd>0</dd></div><div><dt>Overclaim Guard Active</dt><dd>是</dd></div></dl></div>
<div class="panel"><h2>声明边界</h2><p>claim guard 扫描 README、docs 和 reports 中的完成态表述；ledger 未 ready 时，任何英文完成断言、true 状态声明或中文完成态都会阻断发布审查。</p></div>
</section>
reports/review-studio.json
+75 -53
View File
@@ -44,7 +44,7 @@
"key": "context-budget",
"label": "上下文",
"status": "pass",
"detail": "initial load 990/1000; deferred 495322/120000; top deferred scripts 435224; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 495216/120000; top deferred scripts 435118; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json",
"link": "context_budget.md"
},
@@ -1968,12 +1968,12 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "62e7b774ed1b2bd66e28986ad09ffecb9da8ae4d9008641cfe63dcfe354f0c91",
"source_contract_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627",
"evidence_bundle_sha256": "c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c",
"source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -1992,11 +1992,11 @@
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 30
},
"commit": "4a5880bea1a07966e0d914c453d22cf6132c5781",
"commit": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a",
"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.",
@@ -2101,7 +2101,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 231,
"package_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627"
"package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69"
},
"skill_atlas": {
"skill_count": 12,
@@ -4701,7 +4701,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.21,
"duration_ms": 25.96,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4729,7 +4729,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.58,
"duration_ms": 26.2,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4752,7 +4752,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.38,
"duration_ms": 26.36,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4780,7 +4780,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.17,
"duration_ms": 26.09,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4803,7 +4803,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.22,
"duration_ms": 26.43,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4831,7 +4831,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.2,
"duration_ms": 26.16,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4854,7 +4854,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.05,
"duration_ms": 27.55,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4881,7 +4881,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.83,
"duration_ms": 28.86,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4904,7 +4904,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.02,
"duration_ms": 28.87,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4933,7 +4933,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.32,
"duration_ms": 30.17,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5659,22 +5659,35 @@
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "4a5880bea1a07966e0d914c453d22cf6132c5781",
"commit": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a",
"git_status": {
"available": true,
"dirty": false,
"changed_file_count": 0,
"sample": [],
"dirty": true,
"changed_file_count": 30,
"sample": [
" M reports/adaptation_proposals.json",
" M reports/adaptation_proposals.md",
" 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/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"
],
"scope": "generation-time status before this report is written"
},
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "62e7b774ed1b2bd66e28986ad09ffecb9da8ae4d9008641cfe63dcfe354f0c91",
"source_contract_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627",
"evidence_bundle_sha256": "c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c",
"source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -5693,14 +5706,15 @@
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 30
},
"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)",
@@ -5709,10 +5723,10 @@
"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": true,
"commit": "4a5880bea1a07966e0d914c453d22cf6132c5781",
"ready": false,
"commit": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a",
"status_scope": "generation-time status before this report is written",
"reason": "clean generation-time HEAD"
"reason": "working tree was dirty at generation time"
},
"evidence_bundle": {
"algorithm": "sha256(path,label,exists,artifact_sha256)",
@@ -5720,7 +5734,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "62e7b774ed1b2bd66e28986ad09ffecb9da8ae4d9008641cfe63dcfe354f0c91"
"sha256": "c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -5794,7 +5808,7 @@
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7966,
"sha256": "2ce010cd2fc2062d9a503e14394fae334b340d8c64192cf5536d4d579fd7b32d"
"sha256": "2c9409158a128e6d2ad4c96c499dd412591c7b287d907e8d88987132a0592633"
},
{
"label": "blind_review",
@@ -5829,7 +5843,7 @@
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 129520,
"sha256": "893952155dde2bb2bc1b0d87fb1bf2c43ff4ed995e39c60bc3681f7f03b2a02d"
"sha256": "0d60cae961055a68ac84d83cc23d6d8456cc4b42b1a103dd963f3343a20987ff"
},
{
"label": "python_compatibility",
@@ -5926,8 +5940,8 @@
"label": "world_class_claim_guard",
"path": "reports/world_class_claim_guard.json",
"exists": true,
"bytes": 18406,
"sha256": "e331d52d41166a07f068c44bf4c50c5dcdd9f1bce984e4303c832fe5f73d9d66"
"bytes": 18596,
"sha256": "abe7f7d60c0025e140373fadaefbed4063f285c140c74b9c7cfb464e354bb526"
}
],
"missing_artifacts": [],
@@ -6815,11 +6829,11 @@
"exists": true
},
{
"path": "reports/skillops/daily/2026-06-16.json",
"path": "reports/skillops/daily/2026-06-17.json",
"exists": true
},
{
"path": "reports/skillops/daily/2026-06-16.md",
"path": "reports/skillops/daily/2026-06-17.md",
"exists": true
}
],
@@ -12104,7 +12118,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 231,
"package_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627"
"package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69"
},
"failures": [],
"warnings": [],
@@ -16819,7 +16833,7 @@
},
{
"path": "tests/verify_world_class_evidence_intake.py",
"lines": 610,
"lines": 628,
"kind": "test",
"severity": "pass",
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
@@ -16855,15 +16869,15 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 797,
"other_text_tokens": 1076491,
"other_text_tokens": 1076748,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1077288,
"deferred_resource_tokens": 495322,
"estimated_total_text_tokens": 1077545,
"deferred_resource_tokens": 495216,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 435224,
"estimated_tokens": 435118,
"file_count": 140
},
{
@@ -16885,7 +16899,7 @@
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 435224,
"estimated_tokens": 435118,
"file_count": 140
}
],
@@ -16908,7 +16922,7 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 435224,
"estimated_tokens": 435118,
"file_count": 140,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
@@ -18811,7 +18825,7 @@
"adoption_drift": {
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-16T16:07:15Z",
"generated_at": "2026-06-16T16:14:10Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
@@ -19409,7 +19423,7 @@
"weekly_curator": {
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-16T16:14:10Z",
"skill_dir": ".",
"decision": "curator-review",
"week_id": "2026-W25",
@@ -19874,7 +19888,7 @@
"adaptation_proposals": {
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-16T16:14:10Z",
"skill_dir": ".",
"source_patterns": "reports/user_patterns.json",
"pattern_count": 5,
@@ -23043,9 +23057,9 @@
"summary": {
"ledger_ready_to_claim_world_class": false,
"ledger_pending_count": 4,
"claim_surface_count": 180,
"json_claim_surface_count": 88,
"metadata_claim_surface_count": 89,
"claim_surface_count": 182,
"json_claim_surface_count": 89,
"metadata_claim_surface_count": 90,
"package_claim_surface_count": 17,
"violation_count": 0,
"overclaim_guard_active": true,
@@ -23655,6 +23669,14 @@
"path": "reports/skillops/daily/2026-06-16.md",
"violation_count": 0
},
{
"path": "reports/skillops/daily/2026-06-17.json",
"violation_count": 0
},
{
"path": "reports/skillops/daily/2026-06-17.md",
"violation_count": 0
},
{
"path": "reports/skillops/weekly/2026-W25.json",
"violation_count": 0
reports/review-viewer.json
+8 -8
View File
@@ -997,12 +997,12 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "62e7b774ed1b2bd66e28986ad09ffecb9da8ae4d9008641cfe63dcfe354f0c91",
"source_contract_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627",
"evidence_bundle_sha256": "c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c",
"source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -1021,11 +1021,11 @@
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 30
},
"commit": "4a5880bea1a07966e0d914c453d22cf6132c5781",
"commit": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a",
"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.",
@@ -1130,7 +1130,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 231,
"package_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627"
"package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69"
},
"skill_atlas": {
"skill_count": 12,
reports/security_trust_report.json
+1 -1
View File
@@ -23,7 +23,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 231,
"package_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627"
"package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69"
},
"failures": [],
"warnings": [],
reports/security_trust_report.md
+1 -1
View File
@@ -16,7 +16,7 @@
- Interactive scripts: `0`
- Package hash scope: `source-contract-without-generated-reports`
- Package hash files: `231`
- Package SHA256: `fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627`
- Package SHA256: `d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69`
## Failures
reports/skill-interpretation.json
+8 -8
View File
@@ -1001,12 +1001,12 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "62e7b774ed1b2bd66e28986ad09ffecb9da8ae4d9008641cfe63dcfe354f0c91",
"source_contract_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627",
"evidence_bundle_sha256": "c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c",
"source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -1025,11 +1025,11 @@
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 30
},
"commit": "4a5880bea1a07966e0d914c453d22cf6132c5781",
"commit": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a",
"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.",
@@ -1134,7 +1134,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 231,
"package_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627"
"package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69"
},
"skill_atlas": {
"skill_count": 12,
reports/skill-os-2-review.md
+2 -1
View File
@@ -23,6 +23,7 @@ Yao Meta Skill is no longer only a Meta Skill factory. The current working tree
- World-Class Intake Contract Hardening v0 so real evidence submissions must use the ledger's canonical `<evidence-key>.json` filename and are recursively rejected when they include raw prompt, output, transcript, message, credential, secret, token, or API-key fields.
- World-Class Human Evidence Guard v0 so human-adjudication decision artifacts recursively reject raw content, credential, secret, token, and answer-key fields before blind A/B review evidence can be accepted.
- Output Review Privacy Guard v0 so the blind-review importer and world-class human evidence validator share one recursive blocked-field contract for raw content, credential, secret, token, and answer-key leakage.
- World-Class Submission Privacy Guard v0 so real evidence submission packets reuse the same blocked-field contract and reject nested answer-key leakage before ledger review.
- World-Class Provider Evidence Guard v0 so provider holdout submissions must reconcile `summary` counts with `runs` rows and include at least one passing model run whose provider, model, timing, non-estimated usage, and output hash match the submitted provenance.
- World-Class Native Permission Evidence Guard v0 so native-permission submissions must reconcile runtime probe summary counts with target rows, require at least one native-enforced target row, and keep installer permission checks failure-free.
- World-Class Native Telemetry Evidence Guard v0 so native-client-telemetry submissions must reconcile adoption summary counts with external metadata event rows and keep hook recipes metadata-only without claiming native auto-capture.
@@ -71,7 +72,7 @@ This is still not the final world-class state. Target-native behavior contracts
| Skill OS 2.0 Audit | `scripts/render_skill_os2_audit.py`, `reports/skill_os2_audit.md`, `tests/verify_skill_os2_audit.py` | v0 landed |
| World-Class Evidence Plan | `scripts/render_world_class_evidence_plan.py`, `reports/world_class_evidence_plan.md`, `tests/verify_world_class_evidence_plan.py` | v0 landed |
| World-Class Evidence Ledger | `scripts/render_world_class_evidence_ledger.py`, `reports/world_class_evidence_ledger.md`, `tests/verify_world_class_evidence_ledger.py` | v0 landed |
| World-Class Evidence Intake | `scripts/world_class_evidence_contract.py`, `scripts/world_class_human_evidence.py`, `scripts/output_review_privacy.py`, `scripts/world_class_provider_evidence.py`, `scripts/world_class_native_permission_evidence.py`, `scripts/world_class_native_telemetry_evidence.py`, `scripts/render_world_class_evidence_intake.py`, `evidence/world_class/intake.schema.json`, `tests/verify_world_class_evidence_intake.py` with canonical filename, source-artifact validation, recursive human decision privacy and answer-key validation, provider run-row validation, native permission target-row validation, native telemetry event-row validation, and nested raw-field rejection | v0 landed |
| World-Class Evidence Intake | `scripts/world_class_evidence_contract.py`, `scripts/world_class_human_evidence.py`, `scripts/output_review_privacy.py`, `scripts/world_class_provider_evidence.py`, `scripts/world_class_native_permission_evidence.py`, `scripts/world_class_native_telemetry_evidence.py`, `scripts/render_world_class_evidence_intake.py`, `evidence/world_class/intake.schema.json`, `tests/verify_world_class_evidence_intake.py` with canonical filename, source-artifact validation, recursive human decision privacy and answer-key validation, provider run-row validation, native permission target-row validation, native telemetry event-row validation, nested raw-field rejection, and real-submission answer-key leakage rejection | v0 landed |
| World-Class Submission Kit | `scripts/prepare_world_class_submission_kit.py`, `scripts/world_class_submission_matrix.py`, `scripts/world_class_submission_kit_rendering.py`, `tests/verify_world_class_submission_kit.py` with draft, artifact, source-check, next-action matrix evidence, and separated Markdown/HTML rendering | v0 landed |
| Runtime Conformance | `scripts/run_conformance_suite.py`, `reports/conformance_matrix.md` | v0 landed |
| Trust & Security | `scripts/trust_check.py`, `reports/security_trust_report.md`, `security/*.md` | v0 landed |
reports/skill-overview.json
+8 -8
View File
@@ -996,12 +996,12 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "62e7b774ed1b2bd66e28986ad09ffecb9da8ae4d9008641cfe63dcfe354f0c91",
"source_contract_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627",
"evidence_bundle_sha256": "c76666b64b01fbc6f421863b68fd621585935574fe0ce3959a472c26604e1c2c",
"source_contract_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -1020,11 +1020,11 @@
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"working_tree_dirty": false,
"changed_file_count": 0
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 30
},
"commit": "4a5880bea1a07966e0d914c453d22cf6132c5781",
"commit": "500f8cc34ef5ff9a3c8125a72509faabbe95ac9a",
"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.",
@@ -1129,7 +1129,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 231,
"package_sha256": "fcfe5f3c722285daf14b6f83118ad71bdca21694d86d870d234d9f5df2f4e627"
"package_sha256": "d50f6ac9714b62b985f9f9edb181f87bb57246be1e4249cb92e7e4a87ae5aa69"
},
"skill_atlas": {
"skill_count": 12,
reports/skill_os2_coverage.json
+2 -2
View File
@@ -749,11 +749,11 @@
"exists": true
},
{
"path": "reports/skillops/daily/2026-06-16.json",
"path": "reports/skillops/daily/2026-06-17.json",
"exists": true
},
{
"path": "reports/skillops/daily/2026-06-16.md",
"path": "reports/skillops/daily/2026-06-17.md",
"exists": true
}
],
reports/skill_os2_coverage.md
+1 -1
View File
@@ -235,7 +235,7 @@ These extension tracks come from the user-supplied 2.0 reference plan. They are
- objective: Daily operations layer summarizes explicit-source conversation patterns, proposal-only adaptation work, approval state, release locks, and world-class evidence gaps.
- status: `covered`
- existing evidence: `scripts/render_daily_skillops_report.py`, `tests/verify_daily_skillops.py`, `reports/skillops/daily/2026-06-16.json`, `reports/skillops/daily/2026-06-16.md`
- existing evidence: `scripts/render_daily_skillops_report.py`, `tests/verify_daily_skillops.py`, `reports/skillops/daily/2026-06-17.json`, `reports/skillops/daily/2026-06-17.md`
- next action: Keep Daily SkillOps report aligned with proposal, approval, coverage, and world-class ledger contracts as the operations layer evolves.
### Weekly Curator Report
reports/skillops/daily/2026-06-16.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-16T16:07:16Z",
"generated_at": "2026-06-16T16:14:10Z",
"skill_dir": ".",
"decision": "proposal-review",
"source_supplied": false,
reports/skillops/daily/2026-06-16.md
+1 -1
View File
@@ -1,6 +1,6 @@
# Daily SkillOps Report
Generated at: `2026-06-16T16:07:16Z`
Generated at: `2026-06-16T16:14:10Z`
## Summary
reports/skillops/weekly/2026-W25.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-16T16:14:10Z",
"skill_dir": ".",
"decision": "curator-review",
"week_id": "2026-W25",
reports/skillops/weekly/2026-W25.md
+1 -1
View File
@@ -1,6 +1,6 @@
# Weekly SkillOps Curator Report
Generated at: `2026-06-17`
Generated at: `2026-06-16T16:14:10Z`
Week: `2026-W25`
## Summary
reports/world_class_claim_guard.json
+11 -3
View File
@@ -6,9 +6,9 @@
"summary": {
"ledger_ready_to_claim_world_class": false,
"ledger_pending_count": 4,
"claim_surface_count": 180,
"json_claim_surface_count": 88,
"metadata_claim_surface_count": 89,
"claim_surface_count": 182,
"json_claim_surface_count": 89,
"metadata_claim_surface_count": 90,
"package_claim_surface_count": 17,
"violation_count": 0,
"overclaim_guard_active": true,
@@ -618,6 +618,14 @@
"path": "reports/skillops/daily/2026-06-16.md",
"violation_count": 0
},
{
"path": "reports/skillops/daily/2026-06-17.json",
"violation_count": 0
},
{
"path": "reports/skillops/daily/2026-06-17.md",
"violation_count": 0
},
{
"path": "reports/skillops/weekly/2026-W25.json",
"violation_count": 0
reports/world_class_claim_guard.md
+3 -3
View File
@@ -7,9 +7,9 @@ Generated at: `2026-06-17`
- decision: `claim-guard-pass-evidence-pending`
- ledger ready to claim world-class: `false`
- ledger pending evidence: `4`
- claim surfaces scanned: `180`
- JSON claim surfaces scanned: `88`
- metadata claim surfaces scanned: `89`
- claim surfaces scanned: `182`
- JSON claim surfaces scanned: `89`
- metadata claim surfaces scanned: `90`
- package/runtime claim surfaces scanned: `17`
- violations: `0`
- overclaim guard active: `true`
scripts/world_class_evidence_contract.py
+3 -31
View File
@@ -6,6 +6,7 @@ from datetime import datetime, timezone
from pathlib import Path
from typing import Any
from output_review_privacy import BLOCKED_DECISION_FIELDS
from world_class_human_evidence import validate_human_adjudication_report
from world_class_native_permission_evidence import validate_native_permission_report
from world_class_native_telemetry_evidence import validate_native_telemetry_report
@@ -102,36 +103,7 @@ PLACEHOLDER_FRAGMENTS = (
"client or installer component",
"/local/path/not/committed",
)
FORBIDDEN_REAL_SUBMISSION_FIELDS = {
"api_key",
"assistant_message",
"assistant_messages",
"baseline_output",
"credential",
"credentials",
"input",
"inputs",
"message",
"messages",
"model_output",
"output",
"outputs",
"prompt",
"prompts",
"raw_content",
"raw_output",
"raw_prompt",
"raw_provider_prompt",
"raw_user_content",
"secret",
"secrets",
"token",
"transcript",
"transcripts",
"user_message",
"user_messages",
"with_skill_output",
}
FORBIDDEN_REAL_SUBMISSION_FIELDS = BLOCKED_DECISION_FIELDS
def load_json(path: Path) -> dict[str, Any]:
@@ -236,7 +208,7 @@ def validate_real_submission_privacy_fields(
add_error(
errors,
not blocked_paths,
"real submission must not include raw content, credential, secret, token, prompt, output, transcript, or message fields: "
"real submission must not include raw content, credential, secret, token, prompt, output, transcript, message, or answer-key fields: "
+ ", ".join(blocked_paths[:8]),
)
tests/verify_world_class_evidence_intake.py
+18
View File
@@ -381,6 +381,24 @@ def assert_external_contract_artifact_validation() -> None:
assert provider_leak_result["status"] == "fail", provider_leak_result
assert any("raw content, credential, secret" in error for error in provider_leak_result["errors"]), provider_leak_result["errors"]
assert any("$.raw_prompt" in error and "$.provenance.messages" in error for error in provider_leak_result["errors"]), provider_leak_result["errors"]
provider_answer_key_leak = provider_artifact_submission(skill_root)
provider_answer_key_leak["provenance"]["Expected_Winner_Variant"] = "A"
provider_answer_key_leak["review_notes"] = [{"answer_key": "blind answer key must not be embedded"}]
provider_answer_key_leak_result = validate_payload(
provider_answer_key_leak,
provider_entry,
path=skill_root / "evidence" / "world_class" / "submissions" / "provider-holdout.json",
root=skill_root,
template_expected=False,
)
assert provider_answer_key_leak_result["status"] == "fail", provider_answer_key_leak_result
assert any("answer-key fields" in error for error in provider_answer_key_leak_result["errors"]), (
provider_answer_key_leak_result["errors"]
)
assert any(
"$.provenance.Expected_Winner_Variant" in error and "$.review_notes[0].answer_key" in error
for error in provider_answer_key_leak_result["errors"]
), provider_answer_key_leak_result["errors"]
write_provider_artifact(skill_root, complete=False)
provider_invalid = validate_payload(
provider_artifact_submission(skill_root),