Mirror review actions into gates
This commit is contained in:
+1
-1
@@ -16,7 +16,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f"
|
||||
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
|
||||
},
|
||||
"compatibility": {
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-16T21:16:12Z",
|
||||
"skill_dir": ".",
|
||||
"source_patterns": "reports/user_patterns.json",
|
||||
"pattern_count": 5,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Adaptation Proposals
|
||||
|
||||
- Generated at: `2026-06-17`
|
||||
- Generated at: `2026-06-16T21:16:12Z`
|
||||
- Pattern report: `reports/user_patterns.json`
|
||||
- Proposal only: `true`
|
||||
- Writes repository files: `false`
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-16T21:09:51Z",
|
||||
"generated_at": "2026-06-16T21:16:41Z",
|
||||
"skill_dir": ".",
|
||||
"privacy_contract": {
|
||||
"storage": "local-first",
|
||||
|
||||
@@ -18,7 +18,7 @@
|
||||
"block_line_threshold": 1500,
|
||||
"largest_file_lines": 696,
|
||||
"watchlist_count": 0,
|
||||
"early_watchlist_count": 3,
|
||||
"early_watchlist_count": 4,
|
||||
"hotspot_count": 0,
|
||||
"blocker_count": 0,
|
||||
"decision": "pass"
|
||||
@@ -42,12 +42,20 @@
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_evidence_consistency.py",
|
||||
"lines": 625,
|
||||
"lines": 671,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"early_watch": true,
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_evidence_consistency.py",
|
||||
"lines": 647,
|
||||
"kind": "cli-script",
|
||||
"severity": "pass",
|
||||
"early_watch": true,
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_output_review_adjudication.py",
|
||||
"lines": 599,
|
||||
@@ -88,14 +96,6 @@
|
||||
"early_watch": false,
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_evidence_consistency.py",
|
||||
"lines": 580,
|
||||
"kind": "cli-script",
|
||||
"severity": "pass",
|
||||
"early_watch": false,
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_world_class_evidence_ledger.py",
|
||||
"lines": 579,
|
||||
@@ -114,7 +114,7 @@
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_review_studio.py",
|
||||
"lines": 568,
|
||||
"lines": 575,
|
||||
"kind": "cli-script",
|
||||
"severity": "pass",
|
||||
"early_watch": false,
|
||||
@@ -141,11 +141,19 @@
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_evidence_consistency.py",
|
||||
"lines": 625,
|
||||
"lines": 671,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"early_watch": true,
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_evidence_consistency.py",
|
||||
"lines": 647,
|
||||
"kind": "cli-script",
|
||||
"severity": "pass",
|
||||
"early_watch": true,
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
}
|
||||
],
|
||||
"hotspots": [],
|
||||
|
||||
@@ -15,7 +15,7 @@ Generated at: `2026-06-13`
|
||||
- command modules: `6`
|
||||
- largest file lines: `696`
|
||||
- early watch threshold lines: `600`
|
||||
- early watchlist: `3`
|
||||
- early watchlist: `4`
|
||||
- watch threshold lines: `720`
|
||||
- watchlist: `0`
|
||||
- hotspots: `0`
|
||||
@@ -37,7 +37,8 @@ No near-threshold files found.
|
||||
| --- | ---: | --- | --- |
|
||||
| `tests/verify_yao_cli.py` | `696` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
|
||||
| `tests/verify_world_class_evidence_intake.py` | `690` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
|
||||
| `tests/verify_evidence_consistency.py` | `625` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
|
||||
| `tests/verify_evidence_consistency.py` | `671` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
|
||||
| `scripts/render_evidence_consistency.py` | `647` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
|
||||
|
||||
## Largest Files
|
||||
|
||||
@@ -45,16 +46,16 @@ No near-threshold files found.
|
||||
| --- | ---: | --- | --- |
|
||||
| `tests/verify_yao_cli.py` | `696` | `test` | `pass` |
|
||||
| `tests/verify_world_class_evidence_intake.py` | `690` | `test` | `pass` |
|
||||
| `tests/verify_evidence_consistency.py` | `625` | `test` | `pass` |
|
||||
| `tests/verify_evidence_consistency.py` | `671` | `test` | `pass` |
|
||||
| `scripts/render_evidence_consistency.py` | `647` | `cli-script` | `pass` |
|
||||
| `tests/verify_output_review_adjudication.py` | `599` | `test` | `pass` |
|
||||
| `scripts/render_skill_overview.py` | `588` | `cli-script` | `pass` |
|
||||
| `scripts/build_skill_atlas.py` | `586` | `cli-script` | `pass` |
|
||||
| `scripts/optimize_description.py` | `585` | `cli-script` | `pass` |
|
||||
| `scripts/trust_check.py` | `582` | `cli-script` | `pass` |
|
||||
| `scripts/render_evidence_consistency.py` | `580` | `cli-script` | `pass` |
|
||||
| `tests/verify_world_class_evidence_ledger.py` | `579` | `test` | `pass` |
|
||||
| `scripts/world_class_submission_kit_rendering.py` | `576` | `internal-module` | `pass` |
|
||||
| `scripts/render_review_studio.py` | `568` | `cli-script` | `pass` |
|
||||
| `scripts/render_review_studio.py` | `575` | `cli-script` | `pass` |
|
||||
|
||||
## Release Rule
|
||||
|
||||
|
||||
@@ -3,43 +3,49 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"skill_dir": ".",
|
||||
"commit": "4309d9bbcd21ad8e068cfdad034cd9d5a9e3570f",
|
||||
"commit": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": true,
|
||||
"changed_file_count": 13,
|
||||
"changed_file_count": 39,
|
||||
"generated_dirty": true,
|
||||
"generated_changed_file_count": 13,
|
||||
"source_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"generated_changed_file_count": 34,
|
||||
"source_dirty": true,
|
||||
"source_changed_file_count": 5,
|
||||
"sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" 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/evidence_consistency.json",
|
||||
" M reports/review-studio.html",
|
||||
" M reports/review-studio.json",
|
||||
" M reports/review-viewer.json",
|
||||
" M reports/skill-interpretation.json",
|
||||
" M reports/skill-overview.json",
|
||||
" M reports/skillops/weekly/2026-W25.json"
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json"
|
||||
],
|
||||
"source_sample": [
|
||||
" M scripts/render_evidence_consistency.py",
|
||||
" M scripts/render_review_studio.py",
|
||||
" M scripts/review_studio_actions.py",
|
||||
" M tests/verify_evidence_consistency.py",
|
||||
" M tests/verify_review_studio.py"
|
||||
],
|
||||
"source_sample": [],
|
||||
"generated_sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" 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/evidence_consistency.json",
|
||||
" M reports/review-studio.html",
|
||||
" M reports/review-studio.json",
|
||||
" M reports/review-viewer.json",
|
||||
" M reports/skill-interpretation.json",
|
||||
" M reports/skill-overview.json",
|
||||
" M reports/skillops/weekly/2026-W25.json"
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json"
|
||||
],
|
||||
"generated_dirty_prefixes": [
|
||||
"dist/",
|
||||
@@ -53,12 +59,12 @@
|
||||
},
|
||||
"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": "48071ebca4a8bfc9b45e5d4194858870fd0e7f50faff88d4abb79308113126eb",
|
||||
"source_contract_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"evidence_bundle_sha256": "c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce",
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
@@ -77,18 +83,19 @@
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 13,
|
||||
"source_tree_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"changed_file_count": 39,
|
||||
"source_tree_dirty": true,
|
||||
"source_changed_file_count": 5,
|
||||
"generated_tree_dirty": true,
|
||||
"generated_changed_file_count": 13
|
||||
"generated_changed_file_count": 34
|
||||
},
|
||||
"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)",
|
||||
@@ -97,12 +104,12 @@
|
||||
"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": "4309d9bbcd21ad8e068cfdad034cd9d5a9e3570f",
|
||||
"ready": false,
|
||||
"commit": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"status_scope": "generation-time status before this report is written",
|
||||
"source_changed_file_count": 0,
|
||||
"generated_changed_file_count": 13,
|
||||
"reason": "only generated evidence artifacts were dirty at generation time"
|
||||
"source_changed_file_count": 5,
|
||||
"generated_changed_file_count": 34,
|
||||
"reason": "source files were dirty at generation time"
|
||||
},
|
||||
"evidence_bundle": {
|
||||
"algorithm": "sha256(path,label,exists,artifact_sha256)",
|
||||
@@ -110,7 +117,7 @@
|
||||
"existing_count": 25,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "48071ebca4a8bfc9b45e5d4194858870fd0e7f50faff88d4abb79308113126eb"
|
||||
"sha256": "c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -184,7 +191,7 @@
|
||||
"path": "reports/output_execution_runs.json",
|
||||
"exists": true,
|
||||
"bytes": 7966,
|
||||
"sha256": "7795806f55493c49185de218e3a40ef065be44aee0674ffe397c3debf41a278d"
|
||||
"sha256": "9d1dbd75c98b75a63c4c7e3ae4175274a9d54e33fd1ca73561deb4dbc0b315ed"
|
||||
},
|
||||
{
|
||||
"label": "blind_review",
|
||||
@@ -219,7 +226,7 @@
|
||||
"path": "reports/security_trust_report.json",
|
||||
"exists": true,
|
||||
"bytes": 136999,
|
||||
"sha256": "e3bee7ca1d834b40432038b803311412613762086f35baa82a7fcf8545837213"
|
||||
"sha256": "079165fefd9fb3e5c25c1c486738e21bff2a59ca52b03dae9d505d6896341bf1"
|
||||
},
|
||||
{
|
||||
"label": "python_compatibility",
|
||||
@@ -233,7 +240,7 @@
|
||||
"path": "reports/registry_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 3183,
|
||||
"sha256": "b4ecfad8408c2b1a00fe855cdebd71678bb5efbd5493d06fd01a64f6c4eb0800"
|
||||
"sha256": "db05339565be76ece69a89ba4b84dc3af44c711dc68860cbf319b86766d44541"
|
||||
},
|
||||
{
|
||||
"label": "package_verification",
|
||||
|
||||
@@ -1,20 +1,20 @@
|
||||
# Benchmark Reproducibility
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Commit: `4309d9bbcd21ad8e068cfdad034cd9d5a9e3570f`
|
||||
Commit: `7050664b482a8ed9ff8d763f08800902fdf1f02d`
|
||||
Working tree dirty at generation: `true`
|
||||
Source tree dirty at generation: `false`
|
||||
Source tree dirty at generation: `true`
|
||||
Generated evidence dirty at generation: `true`
|
||||
Evidence bundle SHA256: `48071ebca4a8bfc9b45e5d4194858870fd0e7f50faff88d4abb79308113126eb`
|
||||
Evidence bundle SHA256: `c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce`
|
||||
|
||||
## Summary
|
||||
|
||||
- reproducibility ready: `true`
|
||||
- release lock ready: `true`
|
||||
- release lock ready: `false`
|
||||
- methodology complete: `true`
|
||||
- required artifacts: `25`
|
||||
- missing artifacts: `0`
|
||||
- source contract sha256: `f57c75f37b2b`
|
||||
- source contract sha256: `a7c24fc193a5`
|
||||
- archive sha256: `7db44f059844`
|
||||
- output cases: `5`
|
||||
- disclosed failure cases: `3`
|
||||
@@ -24,10 +24,10 @@ Evidence bundle SHA256: `48071ebca4a8bfc9b45e5d4194858870fd0e7f50faff88d4abb7930
|
||||
- world-class ready: `false`
|
||||
- world-class source checks: `10` pass / `19` total; `9` blocked
|
||||
- public claim ready: `false`
|
||||
- public claim blockers: `4`
|
||||
- changed files at generation: `13`
|
||||
- source changed files at generation: `0`
|
||||
- generated changed files at generation: `13`
|
||||
- public claim blockers: `5`
|
||||
- changed files at generation: `39`
|
||||
- source changed files at generation: `5`
|
||||
- generated changed files at generation: `34`
|
||||
|
||||
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 and dirty samples are generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
|
||||
|
||||
@@ -39,6 +39,7 @@ 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) |
|
||||
@@ -46,15 +47,15 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
|
||||
## Release Lock
|
||||
|
||||
- ready: `true`
|
||||
- reason: only generated evidence artifacts were dirty at generation time
|
||||
- ready: `false`
|
||||
- reason: source files were 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: `48071ebca4a8bfc9b45e5d4194858870fd0e7f50faff88d4abb79308113126eb`
|
||||
- sha256: `c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce`
|
||||
|
||||
## Methodology Sections
|
||||
|
||||
@@ -76,14 +77,14 @@ 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 | `7795806f5549` |
|
||||
| output_execution | `reports/output_execution_runs.json` | present | `9d1dbd75c98b` |
|
||||
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
|
||||
| review_adjudication | `reports/output_review_adjudication.json` | present | `91fd88dd9b0f` |
|
||||
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
|
||||
| runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` |
|
||||
| trust_report | `reports/security_trust_report.json` | present | `e3bee7ca1d83` |
|
||||
| trust_report | `reports/security_trust_report.json` | present | `079165fefd9f` |
|
||||
| python_compatibility | `reports/python_compatibility.json` | present | `cb95afb7d7cc` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `b4ecfad8408c` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `db05339565be` |
|
||||
| package_verification | `reports/package_verification.json` | present | `7aa6c25e8154` |
|
||||
| install_simulation | `reports/install_simulation.json` | present | `d2bea19ea46f` |
|
||||
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `ad57230481ed` |
|
||||
|
||||
@@ -6,15 +6,15 @@
|
||||
"context_budget_tier": "production",
|
||||
"context_budget_limit": 1000,
|
||||
"skill_body_tokens": 797,
|
||||
"other_text_tokens": 1137373,
|
||||
"other_text_tokens": 1139278,
|
||||
"estimated_initial_load_tokens": 990,
|
||||
"estimated_total_text_tokens": 1138170,
|
||||
"deferred_resource_tokens": 514654,
|
||||
"estimated_total_text_tokens": 1140075,
|
||||
"deferred_resource_tokens": 515669,
|
||||
"deferred_resource_warn_threshold": 120000,
|
||||
"deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 453351,
|
||||
"estimated_tokens": 454366,
|
||||
"file_count": 152
|
||||
},
|
||||
{
|
||||
@@ -36,7 +36,7 @@
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 453351,
|
||||
"estimated_tokens": 454366,
|
||||
"file_count": 152
|
||||
}
|
||||
],
|
||||
@@ -59,7 +59,7 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 453351,
|
||||
"estimated_tokens": 454366,
|
||||
"file_count": 152,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
|
||||
@@ -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 | 514654 | `governed` | scripts:453351 | 131.3 | - | ok |
|
||||
| root | `.` | `production` | 1000 | 990 | 797 | 515669 | `governed` | scripts:454366 | 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 |
|
||||
|
||||
|
||||
@@ -8,11 +8,11 @@
|
||||
"budget_limit": 1000,
|
||||
"initial_tokens": 990,
|
||||
"skill_body_tokens": 797,
|
||||
"deferred_resource_tokens": 514654,
|
||||
"deferred_resource_tokens": 515669,
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 453351,
|
||||
"estimated_tokens": 454366,
|
||||
"file_count": 152
|
||||
}
|
||||
],
|
||||
@@ -35,7 +35,7 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 453351,
|
||||
"estimated_tokens": 454366,
|
||||
"file_count": 152,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
|
||||
+211
-110
@@ -4,14 +4,14 @@
|
||||
"generated_at": "2026-06-17",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"check_count": 37,
|
||||
"pass_count": 37,
|
||||
"check_count": 38,
|
||||
"pass_count": 38,
|
||||
"warn_count": 0,
|
||||
"fail_count": 0,
|
||||
"decision": "consistent"
|
||||
},
|
||||
"status_counts": {
|
||||
"pass": 37,
|
||||
"pass": 38,
|
||||
"warn": 0,
|
||||
"fail": 0
|
||||
},
|
||||
@@ -183,18 +183,117 @@
|
||||
],
|
||||
"detail": "Release refresh and clean-lock instructions must regenerate every first-class report before evidence consistency can be trusted."
|
||||
},
|
||||
{
|
||||
"key": "review-studio-gate-action-mirror",
|
||||
"label": "Review Studio gates mirror review actions",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"non_pass_gate_keys": [
|
||||
"output-lab",
|
||||
"review-waivers",
|
||||
"world-class-evidence"
|
||||
],
|
||||
"action_gate_keys": [
|
||||
"output-lab",
|
||||
"review-waivers",
|
||||
"world-class-evidence"
|
||||
],
|
||||
"pass_gate_action_ids_empty": true,
|
||||
"gate_action_mirrors": {
|
||||
"output-lab": {
|
||||
"review_action_id": "review-action-output-lab",
|
||||
"review_action_status": "warn",
|
||||
"source_ref_present": true,
|
||||
"verification_command_present": true,
|
||||
"top_level_action_id": "review-action-output-lab",
|
||||
"top_level_action_status": "warn",
|
||||
"top_level_source_ref_present": true,
|
||||
"top_level_verification_command_present": true
|
||||
},
|
||||
"review-waivers": {
|
||||
"review_action_id": "review-action-review-waivers",
|
||||
"review_action_status": "warn",
|
||||
"source_ref_present": true,
|
||||
"verification_command_present": true,
|
||||
"top_level_action_id": "review-action-review-waivers",
|
||||
"top_level_action_status": "warn",
|
||||
"top_level_source_ref_present": true,
|
||||
"top_level_verification_command_present": true
|
||||
},
|
||||
"world-class-evidence": {
|
||||
"review_action_id": "review-action-world-class-evidence",
|
||||
"review_action_status": "warn",
|
||||
"source_ref_present": true,
|
||||
"verification_command_present": true,
|
||||
"top_level_action_id": "review-action-world-class-evidence",
|
||||
"top_level_action_status": "warn",
|
||||
"top_level_source_ref_present": true,
|
||||
"top_level_verification_command_present": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"actual": {
|
||||
"non_pass_gate_keys": [
|
||||
"output-lab",
|
||||
"review-waivers",
|
||||
"world-class-evidence"
|
||||
],
|
||||
"action_gate_keys": [
|
||||
"output-lab",
|
||||
"review-waivers",
|
||||
"world-class-evidence"
|
||||
],
|
||||
"pass_gate_action_ids_empty": true,
|
||||
"gate_action_mirrors": {
|
||||
"output-lab": {
|
||||
"review_action_id": "review-action-output-lab",
|
||||
"review_action_status": "warn",
|
||||
"source_ref_present": true,
|
||||
"verification_command_present": true,
|
||||
"top_level_action_id": "review-action-output-lab",
|
||||
"top_level_action_status": "warn",
|
||||
"top_level_source_ref_present": true,
|
||||
"top_level_verification_command_present": true
|
||||
},
|
||||
"review-waivers": {
|
||||
"review_action_id": "review-action-review-waivers",
|
||||
"review_action_status": "warn",
|
||||
"source_ref_present": true,
|
||||
"verification_command_present": true,
|
||||
"top_level_action_id": "review-action-review-waivers",
|
||||
"top_level_action_status": "warn",
|
||||
"top_level_source_ref_present": true,
|
||||
"top_level_verification_command_present": true
|
||||
},
|
||||
"world-class-evidence": {
|
||||
"review_action_id": "review-action-world-class-evidence",
|
||||
"review_action_status": "warn",
|
||||
"source_ref_present": true,
|
||||
"verification_command_present": true,
|
||||
"top_level_action_id": "review-action-world-class-evidence",
|
||||
"top_level_action_status": "warn",
|
||||
"top_level_source_ref_present": true,
|
||||
"top_level_verification_command_present": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"paths": [
|
||||
"reports/review-studio.json"
|
||||
],
|
||||
"detail": "Every non-pass Review Studio gate must have exactly one top-level review action and a gate-local action summary with source refs and a verification command."
|
||||
},
|
||||
{
|
||||
"key": "review-studio-context-budget-mirror",
|
||||
"label": "Review Studio mirrors context budget governance",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"status": "pass",
|
||||
"detail": "initial load 990/1000; deferred 514654/120000; top deferred scripts 453351; resource governance governed; quality density 131.3",
|
||||
"detail": "initial load 990/1000; deferred 515669/120000; top deferred scripts 454366; resource governance governed; quality density 131.3",
|
||||
"evidence": "reports/context_budget.json"
|
||||
},
|
||||
"actual": {
|
||||
"status": "pass",
|
||||
"detail": "initial load 990/1000; deferred 514654/120000; top deferred scripts 453351; resource governance governed; quality density 131.3",
|
||||
"detail": "initial load 990/1000; deferred 515669/120000; top deferred scripts 454366; resource governance governed; quality density 131.3",
|
||||
"evidence": "reports/context_budget.json"
|
||||
},
|
||||
"paths": [
|
||||
@@ -207,8 +306,8 @@
|
||||
"key": "benchmark-release-lock-self-consistency",
|
||||
"label": "Benchmark release lock matches source dirty state",
|
||||
"status": "pass",
|
||||
"expected": true,
|
||||
"actual": true,
|
||||
"expected": false,
|
||||
"actual": false,
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json"
|
||||
],
|
||||
@@ -222,7 +321,7 @@
|
||||
"actual": {
|
||||
"available": true,
|
||||
"clean": false,
|
||||
"changed_file_count": 12
|
||||
"changed_file_count": 56
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json"
|
||||
@@ -263,8 +362,8 @@
|
||||
"key": "overview-benchmark-commit",
|
||||
"label": "overview embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "4309d9bbcd21ad8e068cfdad034cd9d5a9e3570f",
|
||||
"actual": "4309d9bbcd21ad8e068cfdad034cd9d5a9e3570f",
|
||||
"expected": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"actual": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-overview.json"
|
||||
@@ -276,30 +375,30 @@
|
||||
"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": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"world_class_source_pass_count": 9,
|
||||
"world_class_source_blocked_count": 10,
|
||||
"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": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"world_class_source_pass_count": 9,
|
||||
"world_class_source_blocked_count": 10,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
@@ -313,13 +412,13 @@
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"skill_activation": 1
|
||||
"review_event": 1
|
||||
},
|
||||
"source_types": {
|
||||
"manual": 1
|
||||
@@ -327,13 +426,13 @@
|
||||
},
|
||||
"actual": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"skill_activation": 1
|
||||
"review_event": 1
|
||||
},
|
||||
"source_types": {
|
||||
"manual": 1
|
||||
@@ -356,8 +455,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 10,
|
||||
"source_blocked_count": 9,
|
||||
"source_pass_count": 9,
|
||||
"source_blocked_count": 10,
|
||||
"ready_to_claim_world_class": false,
|
||||
"decision": "evidence-pending"
|
||||
},
|
||||
@@ -368,8 +467,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 10,
|
||||
"source_blocked_count": 9,
|
||||
"source_pass_count": 9,
|
||||
"source_blocked_count": 10,
|
||||
"ready_to_claim_world_class": false,
|
||||
"decision": "evidence-pending"
|
||||
},
|
||||
@@ -389,7 +488,7 @@
|
||||
"pending_count": 4,
|
||||
"accepted_count": 0,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 10
|
||||
"source_pass_count": 9
|
||||
},
|
||||
"actual": {
|
||||
"ready": false,
|
||||
@@ -397,7 +496,7 @@
|
||||
"pending_count": 4,
|
||||
"accepted_count": 0,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 10
|
||||
"source_pass_count": 9
|
||||
},
|
||||
"paths": [
|
||||
"reports/world_class_evidence_ledger.json",
|
||||
@@ -409,8 +508,8 @@
|
||||
"key": "interpretation-benchmark-commit",
|
||||
"label": "interpretation embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "4309d9bbcd21ad8e068cfdad034cd9d5a9e3570f",
|
||||
"actual": "4309d9bbcd21ad8e068cfdad034cd9d5a9e3570f",
|
||||
"expected": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"actual": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-interpretation.json"
|
||||
@@ -422,30 +521,30 @@
|
||||
"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": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"world_class_source_pass_count": 9,
|
||||
"world_class_source_blocked_count": 10,
|
||||
"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": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"world_class_source_pass_count": 9,
|
||||
"world_class_source_blocked_count": 10,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
@@ -459,13 +558,13 @@
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"skill_activation": 1
|
||||
"review_event": 1
|
||||
},
|
||||
"source_types": {
|
||||
"manual": 1
|
||||
@@ -473,13 +572,13 @@
|
||||
},
|
||||
"actual": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"skill_activation": 1
|
||||
"review_event": 1
|
||||
},
|
||||
"source_types": {
|
||||
"manual": 1
|
||||
@@ -502,8 +601,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 10,
|
||||
"source_blocked_count": 9,
|
||||
"source_pass_count": 9,
|
||||
"source_blocked_count": 10,
|
||||
"ready_to_claim_world_class": false,
|
||||
"decision": "evidence-pending"
|
||||
},
|
||||
@@ -514,8 +613,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 10,
|
||||
"source_blocked_count": 9,
|
||||
"source_pass_count": 9,
|
||||
"source_blocked_count": 10,
|
||||
"ready_to_claim_world_class": false,
|
||||
"decision": "evidence-pending"
|
||||
},
|
||||
@@ -535,7 +634,7 @@
|
||||
"pending_count": 4,
|
||||
"accepted_count": 0,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 10
|
||||
"source_pass_count": 9
|
||||
},
|
||||
"actual": {
|
||||
"ready": false,
|
||||
@@ -543,7 +642,7 @@
|
||||
"pending_count": 4,
|
||||
"accepted_count": 0,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 10
|
||||
"source_pass_count": 9
|
||||
},
|
||||
"paths": [
|
||||
"reports/world_class_evidence_ledger.json",
|
||||
@@ -1342,7 +1441,7 @@
|
||||
"external_pending_count": 3,
|
||||
"human_pending_count": 1,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 10,
|
||||
"source_pass_count": 9,
|
||||
"conclusion_zh": "世界级证据尚未完成:4 项待补,0 项已接受。",
|
||||
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
|
||||
"entries": [
|
||||
@@ -1402,7 +1501,8 @@
|
||||
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
|
||||
"summary_en": "Real external-client metadata-only events have not been imported yet.",
|
||||
"blocked_checks": [
|
||||
"External events"
|
||||
"External events",
|
||||
"Adoption sample"
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -1416,7 +1516,7 @@
|
||||
"external_pending_count": 3,
|
||||
"human_pending_count": 1,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 10,
|
||||
"source_pass_count": 9,
|
||||
"conclusion_zh": "世界级证据尚未完成:4 项待补,0 项已接受。",
|
||||
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
|
||||
"entries": [
|
||||
@@ -1476,7 +1576,8 @@
|
||||
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
|
||||
"summary_en": "Real external-client metadata-only events have not been imported yet.",
|
||||
"blocked_checks": [
|
||||
"External events"
|
||||
"External events",
|
||||
"Adoption sample"
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -1826,15 +1927,15 @@
|
||||
"expected": {
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"world_class_source_pass_count": 9,
|
||||
"world_class_source_blocked_count": 10,
|
||||
"public_claim_ready": false
|
||||
},
|
||||
"actual": {
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"world_class_source_pass_count": 9,
|
||||
"world_class_source_blocked_count": 10,
|
||||
"public_claim_ready": false
|
||||
},
|
||||
"paths": [
|
||||
@@ -1850,8 +1951,8 @@
|
||||
"expected": {
|
||||
"pending_count": 4,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 10,
|
||||
"source_blocked_count": 9,
|
||||
"source_pass_count": 9,
|
||||
"source_blocked_count": 10,
|
||||
"ready_to_claim_world_class": false,
|
||||
"preflight_counts_as_evidence": false,
|
||||
"credential_value_exposed": false
|
||||
@@ -1859,8 +1960,8 @@
|
||||
"actual": {
|
||||
"pending_count": 4,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 10,
|
||||
"source_blocked_count": 9,
|
||||
"source_pass_count": 9,
|
||||
"source_blocked_count": 10,
|
||||
"ready_to_claim_world_class": false,
|
||||
"preflight_counts_as_evidence": false,
|
||||
"credential_value_exposed": false
|
||||
@@ -2037,7 +2138,7 @@
|
||||
"summary": {
|
||||
"phase_queue_count": 2,
|
||||
"phase_queue_blocked_count": 2,
|
||||
"phase_queue_row_count": 13,
|
||||
"phase_queue_row_count": 14,
|
||||
"phase_queue_next_phase": "unblock-access",
|
||||
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
|
||||
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
@@ -2070,8 +2171,8 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 9,
|
||||
"row_count": 9,
|
||||
"blocked_count": 10,
|
||||
"row_count": 10,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator",
|
||||
"human reviewer",
|
||||
@@ -2213,15 +2314,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -2231,7 +2332,7 @@
|
||||
"operator_runbook_summary": {
|
||||
"phase_queue_count": 2,
|
||||
"phase_queue_blocked_count": 2,
|
||||
"phase_queue_row_count": 13,
|
||||
"phase_queue_row_count": 14,
|
||||
"phase_queue_next_phase": "unblock-access",
|
||||
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
|
||||
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
@@ -2264,8 +2365,8 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 9,
|
||||
"row_count": 9,
|
||||
"blocked_count": 10,
|
||||
"row_count": 10,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator",
|
||||
"human reviewer",
|
||||
@@ -2407,15 +2508,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -2545,15 +2646,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -2564,7 +2665,7 @@
|
||||
"summary": {
|
||||
"phase_queue_count": 2,
|
||||
"phase_queue_blocked_count": 2,
|
||||
"phase_queue_row_count": 13,
|
||||
"phase_queue_row_count": 14,
|
||||
"phase_queue_next_phase": "unblock-access",
|
||||
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
|
||||
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
@@ -2597,8 +2698,8 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 9,
|
||||
"row_count": 9,
|
||||
"blocked_count": 10,
|
||||
"row_count": 10,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator",
|
||||
"human reviewer",
|
||||
@@ -2619,7 +2720,7 @@
|
||||
"operator_runbook_summary": {
|
||||
"phase_queue_count": 2,
|
||||
"phase_queue_blocked_count": 2,
|
||||
"phase_queue_row_count": 13,
|
||||
"phase_queue_row_count": 14,
|
||||
"phase_queue_next_phase": "unblock-access",
|
||||
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
|
||||
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
@@ -2652,8 +2753,8 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 9,
|
||||
"row_count": 9,
|
||||
"blocked_count": 10,
|
||||
"row_count": 10,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator",
|
||||
"human reviewer",
|
||||
@@ -2795,15 +2896,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -2933,15 +3034,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -3071,15 +3172,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -3179,8 +3280,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 10,
|
||||
"source_blocked_count": 9,
|
||||
"source_pass_count": 9,
|
||||
"source_blocked_count": 10,
|
||||
"plan_keys": [
|
||||
"human-adjudication",
|
||||
"native-client-telemetry",
|
||||
@@ -3328,8 +3429,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 10,
|
||||
"source_blocked_count": 9,
|
||||
"source_pass_count": 9,
|
||||
"source_blocked_count": 10,
|
||||
"plan_keys": [
|
||||
"human-adjudication",
|
||||
"native-client-telemetry",
|
||||
|
||||
@@ -5,8 +5,8 @@ Generated at: `2026-06-17`
|
||||
## Summary
|
||||
|
||||
- decision: `consistent`
|
||||
- checks: `37`
|
||||
- pass: `37`
|
||||
- checks: `38`
|
||||
- pass: `38`
|
||||
- warn: `0`
|
||||
- fail: `0`
|
||||
|
||||
@@ -18,6 +18,7 @@ This gate compares generated evidence reports against each other. It does not cr
|
||||
| --- | --- | --- | --- |
|
||||
| Required report artifacts are readable | `pass` | The consistency gate can only be trusted when every source JSON report parses and every source Markdown report is readable. | `reports/benchmark_reproducibility.json`, `reports/skill-overview.json`, `reports/skill-interpretation.json`, `reports/adoption_drift_report.json`, `reports/world_class_evidence_ledger.json`, `reports/world_class_evidence_plan.json`, `reports/world_class_evidence_intake.json`, `reports/world_class_evidence_preflight.json`, `reports/world_class_submission_review.json`, `reports/world_class_operator_runbook.json`, `reports/skill_os2_coverage.json`, `reports/review-studio.json`, `reports/package_verification.json`, `reports/install_simulation.json`, `reports/security_trust_report.json`, `reports/context_budget.json`, `reports/world_class_claim_guard.json`, `reports/skill-os-2-review.md` |
|
||||
| Release evidence flow covers first-class reports | `pass` | Release refresh and clean-lock instructions must regenerate every first-class report before evidence consistency can be trusted. | `AGENTS.md`, `reports/output_execution_runs.json`, `reports/install_simulation.json`, `reports/security_trust_report.json`, `reports/registry_audit.json`, `reports/package_verification.json`, `reports/upgrade_check.json`, `reports/adoption_drift_report.json`, `reports/architecture_maintainability.json`, `reports/python_compatibility.json`, `reports/runtime_permission_probes.json`, `reports/review_waivers.json`, `reports/review_annotations.json`, `reports/skill_atlas.json`, `reports/skill_os2_audit.json`, `reports/skill_os2_coverage.json`, `reports/context_budget.json`, `reports/context_budget_summary.json`, `reports/benchmark_reproducibility.json`, `reports/skill-overview.json`, `reports/skill-interpretation.json`, `reports/review-viewer.json`, `reports/world_class_evidence_preflight.json`, `reports/skillops/daily`, `reports/skillops/weekly`, `reports/review-studio.json`, `reports/evidence_consistency.json` |
|
||||
| Review Studio gates mirror review actions | `pass` | Every non-pass Review Studio gate must have exactly one top-level review action and a gate-local action summary with source refs and a verification command. | `reports/review-studio.json` |
|
||||
| Review Studio mirrors context budget governance | `pass` | Review Studio must not keep stale context warnings after context reports prove large deferred resources are governed. | `reports/context_budget.json`, `reports/review-studio.json` |
|
||||
| Benchmark release lock matches source dirty state | `pass` | The benchmark release lock must be blocked by source changes, while generated evidence artifacts are tracked as generation context. | `reports/benchmark_reproducibility.json` |
|
||||
| Clean worktree keeps a clean benchmark release lock | `pass` | Dirty or non-git worktrees cannot prove final release-lock freshness, so this check is advisory until the final clean-lock pass. | `reports/benchmark_reproducibility.json` |
|
||||
|
||||
@@ -34,7 +34,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 31.59,
|
||||
"duration_ms": 32.49,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -62,7 +62,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.83,
|
||||
"duration_ms": 28.38,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -85,7 +85,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.22,
|
||||
"duration_ms": 28.39,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -113,7 +113,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.41,
|
||||
"duration_ms": 28.18,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -136,7 +136,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.5,
|
||||
"duration_ms": 28.12,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -164,7 +164,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.37,
|
||||
"duration_ms": 28.24,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -187,7 +187,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 29.23,
|
||||
"duration_ms": 29.02,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -214,7 +214,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.25,
|
||||
"duration_ms": 30.75,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -237,7 +237,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 27.97,
|
||||
"duration_ms": 35.6,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -266,7 +266,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.02,
|
||||
"duration_ms": 31.44,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
|
||||
@@ -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 | 31.59 | 33 | 0.0 | pass |
|
||||
| skill-package-contract | with_skill | command | local-output-eval-runner | 28.83 | 73 | 100.0 | pass |
|
||||
| output-eval-expectation | baseline | command | local-output-eval-runner | 28.22 | 36 | 0.0 | pass |
|
||||
| output-eval-expectation | with_skill | command | local-output-eval-runner | 28.41 | 80 | 100.0 | pass |
|
||||
| ir-before-packaging | baseline | command | local-output-eval-runner | 28.5 | 33 | 0.0 | pass |
|
||||
| ir-before-packaging | with_skill | command | local-output-eval-runner | 28.37 | 80 | 100.0 | pass |
|
||||
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 29.23 | 36 | 0.0 | pass |
|
||||
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 28.25 | 65 | 100.0 | pass |
|
||||
| file-backed-governed-package | baseline | command | local-output-eval-runner | 27.97 | 37 | 0.0 | pass |
|
||||
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 28.02 | 98 | 100.0 | pass |
|
||||
| skill-package-contract | baseline | command | local-output-eval-runner | 32.49 | 33 | 0.0 | pass |
|
||||
| skill-package-contract | with_skill | command | local-output-eval-runner | 28.38 | 73 | 100.0 | pass |
|
||||
| output-eval-expectation | baseline | command | local-output-eval-runner | 28.39 | 36 | 0.0 | pass |
|
||||
| output-eval-expectation | with_skill | command | local-output-eval-runner | 28.18 | 80 | 100.0 | pass |
|
||||
| ir-before-packaging | baseline | command | local-output-eval-runner | 28.12 | 33 | 0.0 | pass |
|
||||
| ir-before-packaging | with_skill | command | local-output-eval-runner | 28.24 | 80 | 100.0 | pass |
|
||||
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 29.02 | 36 | 0.0 | pass |
|
||||
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 30.75 | 65 | 100.0 | pass |
|
||||
| file-backed-governed-package | baseline | command | local-output-eval-runner | 35.6 | 37 | 0.0 | pass |
|
||||
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 31.44 | 98 | 100.0 | pass |
|
||||
|
||||
## Next Fixes
|
||||
|
||||
|
||||
@@ -21,7 +21,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -78,7 +78,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f"
|
||||
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
- Maturity: `governed`
|
||||
- Owner: `Yao Team`
|
||||
- License: `MIT`
|
||||
- Package SHA256: `f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f`
|
||||
- Package SHA256: `a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba`
|
||||
- Archive SHA256: `7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2`
|
||||
- Install simulated: `True`
|
||||
|
||||
|
||||
@@ -772,12 +772,12 @@
|
||||
|
||||
<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>152 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>231 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>696 largest lines; 0 watchlist; 3 early; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock true</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>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>689 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>152 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>231 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>696 largest lines; 0 watchlist; 4 early; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock true</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>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>689 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 514654/120000; top deferred scripts 453351; 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; 152 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; 231 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>228 Python files; 0 hotspots; 0 watchlist files; 3 early watch 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 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</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 10/19 pass; 9 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 515669/120000; top deferred scripts 454366; 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; 152 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; 231 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>228 Python files; 0 hotspots; 0 watchlist files; 4 early watch 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 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 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 10/19 pass; 9 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>
|
||||
@@ -844,12 +844,12 @@
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 514654/120000; top deferred scripts 453351; resource governance governed; quality density 131.3</p></div>
|
||||
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 515669/120000; top deferred scripts 454366; 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>152</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>f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f</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>152</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>a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba</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>
|
||||
|
||||
@@ -874,14 +874,14 @@
|
||||
</section>
|
||||
|
||||
<section id="telemetry" class="twocol">
|
||||
<div class="panel"><h2>运营回路</h2><p>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</p></div>
|
||||
<div class="panel"><h2>运营回路</h2><p>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 false</p></div>
|
||||
<div class="panel"><h2>漂移信号</h2><dl class='kv-grid'><div><dt>事件数</dt><dd>1</dd></div><div><dt>采用率</dt><dd>100</dd></div><div><dt>漏触发</dt><dd>0</dd></div><div><dt>Bad Output Count</dt><dd>0</dd></div><div><dt>风险带</dt><dd>low</dd></div></dl></div>
|
||||
</section>
|
||||
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>日常运维</h2><dl class='kv-grid'><div><dt>决策</dt><dd>proposal-review</dd></div><div><dt>提案数</dt><dd>5</dd></div><div><dt>Approval Count</dt><dd>0</dd></div><div><dt>Pending Review Count</dt><dd>0</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>世界级</dt><dd>否</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>2</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>2</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
|
||||
</section>
|
||||
|
||||
|
||||
@@ -914,8 +914,8 @@
|
||||
</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 (10/19 pass, 9 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 (10/19 pass, 9 blocked)</span></li></ul></div>
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
|
||||
+204
-110
@@ -22,7 +22,11 @@
|
||||
"status": "pass",
|
||||
"detail": "intent confidence 100/100; Intent is clear enough to package the first routeable version.",
|
||||
"evidence": "reports/intent-confidence.json",
|
||||
"link": "intent-confidence.md"
|
||||
"link": "intent-confidence.md",
|
||||
"review_action_id": "",
|
||||
"review_action_status": "",
|
||||
"review_action_source_ref_count": 0,
|
||||
"review_action_verification_command": ""
|
||||
},
|
||||
{
|
||||
"key": "trigger-lab",
|
||||
@@ -30,7 +34,11 @@
|
||||
"status": "pass",
|
||||
"detail": "13 trigger cases; 0 misroutes; 0 ambiguous",
|
||||
"evidence": "reports/route_scorecard.json",
|
||||
"link": "route_scorecard.md"
|
||||
"link": "route_scorecard.md",
|
||||
"review_action_id": "",
|
||||
"review_action_status": "",
|
||||
"review_action_source_ref_count": 0,
|
||||
"review_action_verification_command": ""
|
||||
},
|
||||
{
|
||||
"key": "output-lab",
|
||||
@@ -38,15 +46,23 @@
|
||||
"status": "warn",
|
||||
"detail": "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",
|
||||
"evidence": "reports/output_quality_scorecard.json",
|
||||
"link": "output_quality_scorecard.md"
|
||||
"link": "output_quality_scorecard.md",
|
||||
"review_action_id": "review-action-output-lab",
|
||||
"review_action_status": "warn",
|
||||
"review_action_source_ref_count": 6,
|
||||
"review_action_verification_command": "python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review"
|
||||
},
|
||||
{
|
||||
"key": "context-budget",
|
||||
"label": "上下文",
|
||||
"status": "pass",
|
||||
"detail": "initial load 990/1000; deferred 514654/120000; top deferred scripts 453351; resource governance governed; quality density 131.3",
|
||||
"detail": "initial load 990/1000; deferred 515669/120000; top deferred scripts 454366; resource governance governed; quality density 131.3",
|
||||
"evidence": "reports/context_budget.json",
|
||||
"link": "context_budget.md"
|
||||
"link": "context_budget.md",
|
||||
"review_action_id": "",
|
||||
"review_action_status": "",
|
||||
"review_action_source_ref_count": 0,
|
||||
"review_action_verification_command": ""
|
||||
},
|
||||
{
|
||||
"key": "runtime-matrix",
|
||||
@@ -54,7 +70,11 @@
|
||||
"status": "pass",
|
||||
"detail": "5 / 5 targets pass",
|
||||
"evidence": "reports/conformance_matrix.json",
|
||||
"link": "conformance_matrix.md"
|
||||
"link": "conformance_matrix.md",
|
||||
"review_action_id": "",
|
||||
"review_action_status": "",
|
||||
"review_action_source_ref_count": 0,
|
||||
"review_action_verification_command": ""
|
||||
},
|
||||
{
|
||||
"key": "trust-report",
|
||||
@@ -62,7 +82,11 @@
|
||||
"status": "pass",
|
||||
"detail": "0 secrets; 152 scripts; 3 network-capable scripts; 0 help smoke failures",
|
||||
"evidence": "reports/security_trust_report.json",
|
||||
"link": "security_trust_report.md"
|
||||
"link": "security_trust_report.md",
|
||||
"review_action_id": "",
|
||||
"review_action_status": "",
|
||||
"review_action_source_ref_count": 0,
|
||||
"review_action_verification_command": ""
|
||||
},
|
||||
{
|
||||
"key": "python-compat",
|
||||
@@ -70,15 +94,23 @@
|
||||
"status": "pass",
|
||||
"detail": "Python 3.11; 231 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards",
|
||||
"evidence": "reports/python_compatibility.json",
|
||||
"link": "python_compatibility.md"
|
||||
"link": "python_compatibility.md",
|
||||
"review_action_id": "",
|
||||
"review_action_status": "",
|
||||
"review_action_source_ref_count": 0,
|
||||
"review_action_verification_command": ""
|
||||
},
|
||||
{
|
||||
"key": "architecture-maintainability",
|
||||
"label": "架构维护",
|
||||
"status": "pass",
|
||||
"detail": "228 Python files; 0 hotspots; 0 watchlist files; 3 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint",
|
||||
"detail": "228 Python files; 0 hotspots; 0 watchlist files; 4 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint",
|
||||
"evidence": "reports/architecture_maintainability.json",
|
||||
"link": "architecture_maintainability.md"
|
||||
"link": "architecture_maintainability.md",
|
||||
"review_action_id": "",
|
||||
"review_action_status": "",
|
||||
"review_action_source_ref_count": 0,
|
||||
"review_action_verification_command": ""
|
||||
},
|
||||
{
|
||||
"key": "permission-gates",
|
||||
@@ -86,7 +118,11 @@
|
||||
"status": "pass",
|
||||
"detail": "3/3 permissions approved; gaps 0; required file_write, network, subprocess",
|
||||
"evidence": "reports/security_trust_report.json + security/permission_policy.json",
|
||||
"link": "../security/permission_policy.md"
|
||||
"link": "../security/permission_policy.md",
|
||||
"review_action_id": "",
|
||||
"review_action_status": "",
|
||||
"review_action_source_ref_count": 0,
|
||||
"review_action_verification_command": ""
|
||||
},
|
||||
{
|
||||
"key": "permission-runtime",
|
||||
@@ -94,7 +130,11 @@
|
||||
"status": "pass",
|
||||
"detail": "4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4",
|
||||
"evidence": "reports/runtime_permission_probes.json",
|
||||
"link": "runtime_permission_probes.md"
|
||||
"link": "runtime_permission_probes.md",
|
||||
"review_action_id": "",
|
||||
"review_action_status": "",
|
||||
"review_action_source_ref_count": 0,
|
||||
"review_action_verification_command": ""
|
||||
},
|
||||
{
|
||||
"key": "skill-atlas",
|
||||
@@ -102,15 +142,23 @@
|
||||
"status": "pass",
|
||||
"detail": "12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues",
|
||||
"evidence": "reports/skill_atlas.json",
|
||||
"link": "skill_atlas.html"
|
||||
"link": "skill_atlas.html",
|
||||
"review_action_id": "",
|
||||
"review_action_status": "",
|
||||
"review_action_source_ref_count": 0,
|
||||
"review_action_verification_command": ""
|
||||
},
|
||||
{
|
||||
"key": "operations-loop",
|
||||
"label": "运营回路",
|
||||
"status": "pass",
|
||||
"detail": "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",
|
||||
"detail": "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 false",
|
||||
"evidence": "reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly",
|
||||
"link": "adoption_drift_report.md"
|
||||
"link": "adoption_drift_report.md",
|
||||
"review_action_id": "",
|
||||
"review_action_status": "",
|
||||
"review_action_source_ref_count": 0,
|
||||
"review_action_verification_command": ""
|
||||
},
|
||||
{
|
||||
"key": "review-waivers",
|
||||
@@ -118,7 +166,11 @@
|
||||
"status": "warn",
|
||||
"detail": "0 active waivers; 1 warning gates still need reviewer decision",
|
||||
"evidence": "reports/review_waivers.json",
|
||||
"link": "review_waivers.md"
|
||||
"link": "review_waivers.md",
|
||||
"review_action_id": "review-action-review-waivers",
|
||||
"review_action_status": "warn",
|
||||
"review_action_source_ref_count": 2,
|
||||
"review_action_verification_command": "python3 scripts/render_review_waivers.py ."
|
||||
},
|
||||
{
|
||||
"key": "world-class-evidence",
|
||||
@@ -126,7 +178,11 @@
|
||||
"status": "warn",
|
||||
"detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 10/19 pass; 9 blocked; overclaim guard true",
|
||||
"evidence": "reports/world_class_evidence_ledger.json",
|
||||
"link": "world_class_evidence_ledger.md"
|
||||
"link": "world_class_evidence_ledger.md",
|
||||
"review_action_id": "review-action-world-class-evidence",
|
||||
"review_action_status": "warn",
|
||||
"review_action_source_ref_count": 16,
|
||||
"review_action_verification_command": "python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py review-studio ."
|
||||
},
|
||||
{
|
||||
"key": "registry-audit",
|
||||
@@ -134,7 +190,11 @@
|
||||
"status": "pass",
|
||||
"detail": "yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures",
|
||||
"evidence": "reports/registry_audit.json + reports/install_simulation.json",
|
||||
"link": "registry_audit.md"
|
||||
"link": "registry_audit.md",
|
||||
"review_action_id": "",
|
||||
"review_action_status": "",
|
||||
"review_action_source_ref_count": 0,
|
||||
"review_action_verification_command": ""
|
||||
},
|
||||
{
|
||||
"key": "release-notes",
|
||||
@@ -142,7 +202,11 @@
|
||||
"status": "pass",
|
||||
"detail": "0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended",
|
||||
"evidence": "reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md",
|
||||
"link": "promotion_decisions.md"
|
||||
"link": "promotion_decisions.md",
|
||||
"review_action_id": "",
|
||||
"review_action_status": "",
|
||||
"review_action_source_ref_count": 0,
|
||||
"review_action_verification_command": ""
|
||||
}
|
||||
],
|
||||
"gate_contract": {
|
||||
@@ -198,7 +262,11 @@
|
||||
"status": "warn",
|
||||
"detail": "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",
|
||||
"evidence": "reports/output_quality_scorecard.json",
|
||||
"link": "output_quality_scorecard.md"
|
||||
"link": "output_quality_scorecard.md",
|
||||
"review_action_id": "review-action-output-lab",
|
||||
"review_action_status": "warn",
|
||||
"review_action_source_ref_count": 6,
|
||||
"review_action_verification_command": "python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review"
|
||||
},
|
||||
{
|
||||
"key": "review-waivers",
|
||||
@@ -206,7 +274,11 @@
|
||||
"status": "warn",
|
||||
"detail": "0 active waivers; 1 warning gates still need reviewer decision",
|
||||
"evidence": "reports/review_waivers.json",
|
||||
"link": "review_waivers.md"
|
||||
"link": "review_waivers.md",
|
||||
"review_action_id": "review-action-review-waivers",
|
||||
"review_action_status": "warn",
|
||||
"review_action_source_ref_count": 2,
|
||||
"review_action_verification_command": "python3 scripts/render_review_waivers.py ."
|
||||
},
|
||||
{
|
||||
"key": "world-class-evidence",
|
||||
@@ -214,11 +286,16 @@
|
||||
"status": "warn",
|
||||
"detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 10/19 pass; 9 blocked; overclaim guard true",
|
||||
"evidence": "reports/world_class_evidence_ledger.json",
|
||||
"link": "world_class_evidence_ledger.md"
|
||||
"link": "world_class_evidence_ledger.md",
|
||||
"review_action_id": "review-action-world-class-evidence",
|
||||
"review_action_status": "warn",
|
||||
"review_action_source_ref_count": 16,
|
||||
"review_action_verification_command": "python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py review-studio ."
|
||||
}
|
||||
],
|
||||
"review_actions": [
|
||||
{
|
||||
"action_id": "review-action-output-lab",
|
||||
"gate_key": "output-lab",
|
||||
"label": "输出实验",
|
||||
"status": "warn",
|
||||
@@ -294,6 +371,7 @@
|
||||
"evidence_steps": []
|
||||
},
|
||||
{
|
||||
"action_id": "review-action-review-waivers",
|
||||
"gate_key": "review-waivers",
|
||||
"label": "人工批准",
|
||||
"status": "warn",
|
||||
@@ -329,6 +407,7 @@
|
||||
"evidence_steps": []
|
||||
},
|
||||
{
|
||||
"action_id": "review-action-world-class-evidence",
|
||||
"gate_key": "world-class-evidence",
|
||||
"label": "世界证据",
|
||||
"status": "warn",
|
||||
@@ -2363,12 +2442,12 @@
|
||||
"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": "48071ebca4a8bfc9b45e5d4194858870fd0e7f50faff88d4abb79308113126eb",
|
||||
"source_contract_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"evidence_bundle_sha256": "c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce",
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
@@ -2387,15 +2466,15 @@
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 13,
|
||||
"source_tree_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"changed_file_count": 39,
|
||||
"source_tree_dirty": true,
|
||||
"source_changed_file_count": 5,
|
||||
"generated_tree_dirty": true,
|
||||
"generated_changed_file_count": 13
|
||||
"generated_changed_file_count": 34
|
||||
},
|
||||
"commit": "4309d9bbcd21ad8e068cfdad034cd9d5a9e3570f",
|
||||
"commit": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
|
||||
@@ -2500,7 +2579,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 244,
|
||||
"package_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f"
|
||||
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -2538,7 +2617,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -2670,7 +2749,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f"
|
||||
"to": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -5184,7 +5263,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 31.59,
|
||||
"duration_ms": 32.49,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5212,7 +5291,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.83,
|
||||
"duration_ms": 28.38,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5235,7 +5314,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.22,
|
||||
"duration_ms": 28.39,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5263,7 +5342,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.41,
|
||||
"duration_ms": 28.18,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5286,7 +5365,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.5,
|
||||
"duration_ms": 28.12,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5314,7 +5393,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.37,
|
||||
"duration_ms": 28.24,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5337,7 +5416,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 29.23,
|
||||
"duration_ms": 29.02,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5364,7 +5443,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.25,
|
||||
"duration_ms": 30.75,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5387,7 +5466,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 27.97,
|
||||
"duration_ms": 35.6,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5416,7 +5495,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.02,
|
||||
"duration_ms": 31.44,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -6197,43 +6276,49 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"skill_dir": ".",
|
||||
"commit": "4309d9bbcd21ad8e068cfdad034cd9d5a9e3570f",
|
||||
"commit": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": true,
|
||||
"changed_file_count": 13,
|
||||
"changed_file_count": 39,
|
||||
"generated_dirty": true,
|
||||
"generated_changed_file_count": 13,
|
||||
"source_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"generated_changed_file_count": 34,
|
||||
"source_dirty": true,
|
||||
"source_changed_file_count": 5,
|
||||
"sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" 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/evidence_consistency.json",
|
||||
" M reports/review-studio.html",
|
||||
" M reports/review-studio.json",
|
||||
" M reports/review-viewer.json",
|
||||
" M reports/skill-interpretation.json",
|
||||
" M reports/skill-overview.json",
|
||||
" M reports/skillops/weekly/2026-W25.json"
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json"
|
||||
],
|
||||
"source_sample": [
|
||||
" M scripts/render_evidence_consistency.py",
|
||||
" M scripts/render_review_studio.py",
|
||||
" M scripts/review_studio_actions.py",
|
||||
" M tests/verify_evidence_consistency.py",
|
||||
" M tests/verify_review_studio.py"
|
||||
],
|
||||
"source_sample": [],
|
||||
"generated_sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" 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/evidence_consistency.json",
|
||||
" M reports/review-studio.html",
|
||||
" M reports/review-studio.json",
|
||||
" M reports/review-viewer.json",
|
||||
" M reports/skill-interpretation.json",
|
||||
" M reports/skill-overview.json",
|
||||
" M reports/skillops/weekly/2026-W25.json"
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json"
|
||||
],
|
||||
"generated_dirty_prefixes": [
|
||||
"dist/",
|
||||
@@ -6247,12 +6332,12 @@
|
||||
},
|
||||
"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": "48071ebca4a8bfc9b45e5d4194858870fd0e7f50faff88d4abb79308113126eb",
|
||||
"source_contract_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"evidence_bundle_sha256": "c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce",
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
@@ -6271,18 +6356,19 @@
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 13,
|
||||
"source_tree_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"changed_file_count": 39,
|
||||
"source_tree_dirty": true,
|
||||
"source_changed_file_count": 5,
|
||||
"generated_tree_dirty": true,
|
||||
"generated_changed_file_count": 13
|
||||
"generated_changed_file_count": 34
|
||||
},
|
||||
"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)",
|
||||
@@ -6291,12 +6377,12 @@
|
||||
"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": "4309d9bbcd21ad8e068cfdad034cd9d5a9e3570f",
|
||||
"ready": false,
|
||||
"commit": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"status_scope": "generation-time status before this report is written",
|
||||
"source_changed_file_count": 0,
|
||||
"generated_changed_file_count": 13,
|
||||
"reason": "only generated evidence artifacts were dirty at generation time"
|
||||
"source_changed_file_count": 5,
|
||||
"generated_changed_file_count": 34,
|
||||
"reason": "source files were dirty at generation time"
|
||||
},
|
||||
"evidence_bundle": {
|
||||
"algorithm": "sha256(path,label,exists,artifact_sha256)",
|
||||
@@ -6304,7 +6390,7 @@
|
||||
"existing_count": 25,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "48071ebca4a8bfc9b45e5d4194858870fd0e7f50faff88d4abb79308113126eb"
|
||||
"sha256": "c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -6378,7 +6464,7 @@
|
||||
"path": "reports/output_execution_runs.json",
|
||||
"exists": true,
|
||||
"bytes": 7966,
|
||||
"sha256": "7795806f55493c49185de218e3a40ef065be44aee0674ffe397c3debf41a278d"
|
||||
"sha256": "9d1dbd75c98b75a63c4c7e3ae4175274a9d54e33fd1ca73561deb4dbc0b315ed"
|
||||
},
|
||||
{
|
||||
"label": "blind_review",
|
||||
@@ -6413,7 +6499,7 @@
|
||||
"path": "reports/security_trust_report.json",
|
||||
"exists": true,
|
||||
"bytes": 136999,
|
||||
"sha256": "e3bee7ca1d834b40432038b803311412613762086f35baa82a7fcf8545837213"
|
||||
"sha256": "079165fefd9fb3e5c25c1c486738e21bff2a59ca52b03dae9d505d6896341bf1"
|
||||
},
|
||||
{
|
||||
"label": "python_compatibility",
|
||||
@@ -6427,7 +6513,7 @@
|
||||
"path": "reports/registry_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 3183,
|
||||
"sha256": "b4ecfad8408c2b1a00fe855cdebd71678bb5efbd5493d06fd01a64f6c4eb0800"
|
||||
"sha256": "db05339565be76ece69a89ba4b84dc3af44c711dc68860cbf319b86766d44541"
|
||||
},
|
||||
{
|
||||
"label": "package_verification",
|
||||
@@ -7263,7 +7349,7 @@
|
||||
"label": "Evidence Consistency",
|
||||
"status": "pass",
|
||||
"objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
|
||||
"current": "37 consistency checks",
|
||||
"current": "38 consistency checks",
|
||||
"command": "make ci-test",
|
||||
"test": "tests/verify_evidence_consistency.py",
|
||||
"evidence": [
|
||||
@@ -12868,7 +12954,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 244,
|
||||
"package_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f"
|
||||
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": [],
|
||||
@@ -17810,7 +17896,7 @@
|
||||
"block_line_threshold": 1500,
|
||||
"largest_file_lines": 696,
|
||||
"watchlist_count": 0,
|
||||
"early_watchlist_count": 3,
|
||||
"early_watchlist_count": 4,
|
||||
"hotspot_count": 0,
|
||||
"blocker_count": 0,
|
||||
"decision": "pass"
|
||||
@@ -17834,12 +17920,20 @@
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_evidence_consistency.py",
|
||||
"lines": 625,
|
||||
"lines": 671,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"early_watch": true,
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_evidence_consistency.py",
|
||||
"lines": 647,
|
||||
"kind": "cli-script",
|
||||
"severity": "pass",
|
||||
"early_watch": true,
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_output_review_adjudication.py",
|
||||
"lines": 599,
|
||||
@@ -17880,14 +17974,6 @@
|
||||
"early_watch": false,
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_evidence_consistency.py",
|
||||
"lines": 580,
|
||||
"kind": "cli-script",
|
||||
"severity": "pass",
|
||||
"early_watch": false,
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_world_class_evidence_ledger.py",
|
||||
"lines": 579,
|
||||
@@ -17906,7 +17992,7 @@
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_review_studio.py",
|
||||
"lines": 568,
|
||||
"lines": 575,
|
||||
"kind": "cli-script",
|
||||
"severity": "pass",
|
||||
"early_watch": false,
|
||||
@@ -17933,11 +18019,19 @@
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_evidence_consistency.py",
|
||||
"lines": 625,
|
||||
"lines": 671,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"early_watch": true,
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_evidence_consistency.py",
|
||||
"lines": 647,
|
||||
"kind": "cli-script",
|
||||
"severity": "pass",
|
||||
"early_watch": true,
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
}
|
||||
],
|
||||
"hotspots": [],
|
||||
@@ -17955,15 +18049,15 @@
|
||||
"context_budget_tier": "production",
|
||||
"context_budget_limit": 1000,
|
||||
"skill_body_tokens": 797,
|
||||
"other_text_tokens": 1137373,
|
||||
"other_text_tokens": 1139278,
|
||||
"estimated_initial_load_tokens": 990,
|
||||
"estimated_total_text_tokens": 1138170,
|
||||
"deferred_resource_tokens": 514654,
|
||||
"estimated_total_text_tokens": 1140075,
|
||||
"deferred_resource_tokens": 515669,
|
||||
"deferred_resource_warn_threshold": 120000,
|
||||
"deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 453351,
|
||||
"estimated_tokens": 454366,
|
||||
"file_count": 152
|
||||
},
|
||||
{
|
||||
@@ -17985,7 +18079,7 @@
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 453351,
|
||||
"estimated_tokens": 454366,
|
||||
"file_count": 152
|
||||
}
|
||||
],
|
||||
@@ -18008,7 +18102,7 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 453351,
|
||||
"estimated_tokens": 454366,
|
||||
"file_count": 152,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
@@ -19933,7 +20027,7 @@
|
||||
"adoption_drift": {
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-16T21:09:51Z",
|
||||
"generated_at": "2026-06-16T21:16:41Z",
|
||||
"skill_dir": ".",
|
||||
"privacy_contract": {
|
||||
"storage": "local-first",
|
||||
@@ -20531,7 +20625,7 @@
|
||||
"weekly_curator": {
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-16T21:16:12Z",
|
||||
"skill_dir": ".",
|
||||
"decision": "curator-review",
|
||||
"week_id": "2026-W25",
|
||||
@@ -20545,7 +20639,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -20565,7 +20659,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -20818,7 +20912,7 @@
|
||||
"no_route_opportunity_count": 0
|
||||
},
|
||||
"release_state": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4
|
||||
@@ -20996,7 +21090,7 @@
|
||||
"adaptation_proposals": {
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-16T21:16:12Z",
|
||||
"skill_dir": ".",
|
||||
"source_patterns": "reports/user_patterns.json",
|
||||
"pattern_count": 5,
|
||||
@@ -27398,7 +27492,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -27455,7 +27549,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f"
|
||||
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -28491,7 +28585,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f"
|
||||
"to": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
+12
-12
@@ -1005,12 +1005,12 @@
|
||||
"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": "48071ebca4a8bfc9b45e5d4194858870fd0e7f50faff88d4abb79308113126eb",
|
||||
"source_contract_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"evidence_bundle_sha256": "c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce",
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
@@ -1029,15 +1029,15 @@
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 13,
|
||||
"source_tree_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"changed_file_count": 39,
|
||||
"source_tree_dirty": true,
|
||||
"source_changed_file_count": 5,
|
||||
"generated_tree_dirty": true,
|
||||
"generated_changed_file_count": 13
|
||||
"generated_changed_file_count": 34
|
||||
},
|
||||
"commit": "4309d9bbcd21ad8e068cfdad034cd9d5a9e3570f",
|
||||
"commit": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
|
||||
@@ -1142,7 +1142,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 244,
|
||||
"package_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f"
|
||||
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1180,7 +1180,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -1312,7 +1312,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f"
|
||||
"to": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -23,7 +23,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 244,
|
||||
"package_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f"
|
||||
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": [],
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
- Interactive scripts: `0`
|
||||
- Package hash scope: `source-contract-without-generated-reports`
|
||||
- Package hash files: `244`
|
||||
- Package SHA256: `f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f`
|
||||
- Package SHA256: `a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba`
|
||||
|
||||
## Failures
|
||||
|
||||
|
||||
@@ -1009,12 +1009,12 @@
|
||||
"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": "48071ebca4a8bfc9b45e5d4194858870fd0e7f50faff88d4abb79308113126eb",
|
||||
"source_contract_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"evidence_bundle_sha256": "c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce",
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
@@ -1033,15 +1033,15 @@
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 13,
|
||||
"source_tree_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"changed_file_count": 39,
|
||||
"source_tree_dirty": true,
|
||||
"source_changed_file_count": 5,
|
||||
"generated_tree_dirty": true,
|
||||
"generated_changed_file_count": 13
|
||||
"generated_changed_file_count": 34
|
||||
},
|
||||
"commit": "4309d9bbcd21ad8e068cfdad034cd9d5a9e3570f",
|
||||
"commit": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
|
||||
@@ -1146,7 +1146,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 244,
|
||||
"package_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f"
|
||||
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1184,7 +1184,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -1316,7 +1316,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f"
|
||||
"to": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
+12
-12
@@ -1004,12 +1004,12 @@
|
||||
"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": "48071ebca4a8bfc9b45e5d4194858870fd0e7f50faff88d4abb79308113126eb",
|
||||
"source_contract_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"evidence_bundle_sha256": "c31e8bd9e49e60f14344e25ae71dabf911612d9c1ae6aee292ce566c66b88fce",
|
||||
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
@@ -1028,15 +1028,15 @@
|
||||
"world_class_source_pass_count": 10,
|
||||
"world_class_source_blocked_count": 9,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 13,
|
||||
"source_tree_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"changed_file_count": 39,
|
||||
"source_tree_dirty": true,
|
||||
"source_changed_file_count": 5,
|
||||
"generated_tree_dirty": true,
|
||||
"generated_changed_file_count": 13
|
||||
"generated_changed_file_count": 34
|
||||
},
|
||||
"commit": "4309d9bbcd21ad8e068cfdad034cd9d5a9e3570f",
|
||||
"commit": "7050664b482a8ed9ff8d763f08800902fdf1f02d",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
|
||||
@@ -1141,7 +1141,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 244,
|
||||
"package_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f"
|
||||
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1179,7 +1179,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f",
|
||||
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -1311,7 +1311,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f"
|
||||
"to": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -613,7 +613,7 @@
|
||||
"label": "Evidence Consistency",
|
||||
"status": "pass",
|
||||
"objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
|
||||
"current": "37 consistency checks",
|
||||
"current": "38 consistency checks",
|
||||
"command": "make ci-test",
|
||||
"test": "tests/verify_evidence_consistency.py",
|
||||
"evidence": [
|
||||
|
||||
@@ -48,7 +48,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
|
||||
| Registry Package Format | `pass` | registry ok True | `make ci-test` | `tests/verify_registry_audit.py` |
|
||||
| Review Studio 2.0 | `pass` | 16 review gates | `make ci-test` | `tests/verify_review_studio.py` |
|
||||
| Migration V2 Docs | `pass` | migration guide present | `make ci-test` | `docs review` |
|
||||
| Evidence Consistency | `pass` | 37 consistency checks | `make ci-test` | `tests/verify_evidence_consistency.py` |
|
||||
| Evidence Consistency | `pass` | 38 consistency checks | `make ci-test` | `tests/verify_evidence_consistency.py` |
|
||||
|
||||
## Reference Extension Tracks
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16T21:09:22Z",
|
||||
"generated_at": "2026-06-16T21:16:12Z",
|
||||
"skill_dir": ".",
|
||||
"decision": "proposal-review",
|
||||
"source_supplied": false,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Daily SkillOps Report
|
||||
|
||||
Generated at: `2026-06-16T21:09:22Z`
|
||||
Generated at: `2026-06-16T21:16:12Z`
|
||||
|
||||
## Summary
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-16T21:16:12Z",
|
||||
"skill_dir": ".",
|
||||
"decision": "curator-review",
|
||||
"week_id": "2026-W25",
|
||||
@@ -15,7 +15,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -35,7 +35,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -288,7 +288,7 @@
|
||||
"no_route_opportunity_count": 0
|
||||
},
|
||||
"release_state": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Weekly SkillOps Curator Report
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Generated at: `2026-06-16T21:16:12Z`
|
||||
Week: `2026-W25`
|
||||
|
||||
## Summary
|
||||
@@ -13,7 +13,7 @@ Week: `2026-W25`
|
||||
- top_score: `88`
|
||||
- skill_count: `12`
|
||||
- actionable_portfolio_issue_count: `0`
|
||||
- release_lock_ready: `True`
|
||||
- release_lock_ready: `False`
|
||||
- evidence_consistency_ok: `True`
|
||||
- public_world_class_ready: `False`
|
||||
- world_class_pending_count: `4`
|
||||
|
||||
@@ -75,7 +75,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "f57c75f37b2b029c9b7a42d18d8daa4b5c9bb51defbc8e22774583243473007f"
|
||||
"to": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -55,6 +55,71 @@ def git_worktree_status(skill_dir: Path) -> dict[str, Any]:
|
||||
return {"available": True, "clean": not changes, "changed_file_count": len(changes)}
|
||||
|
||||
|
||||
def build_review_studio_gate_action_mirror_check(review_studio: dict[str, Any]) -> dict[str, Any]:
|
||||
gates = review_studio.get("gates", []) if isinstance(review_studio.get("gates", []), list) else []
|
||||
actions = (
|
||||
review_studio.get("review_actions", [])
|
||||
if isinstance(review_studio.get("review_actions", []), list)
|
||||
else []
|
||||
)
|
||||
non_pass_gates = [gate for gate in gates if isinstance(gate, dict) and gate.get("status") != "pass"]
|
||||
pass_gates = [gate for gate in gates if isinstance(gate, dict) and gate.get("status") == "pass"]
|
||||
actions_by_gate = {
|
||||
str(action.get("gate_key", "")): action
|
||||
for action in actions
|
||||
if isinstance(action, dict) and str(action.get("gate_key", ""))
|
||||
}
|
||||
expected = {
|
||||
"non_pass_gate_keys": sorted(str(gate.get("key", "")) for gate in non_pass_gates),
|
||||
"action_gate_keys": sorted(str(gate.get("key", "")) for gate in non_pass_gates),
|
||||
"pass_gate_action_ids_empty": True,
|
||||
"gate_action_mirrors": {
|
||||
str(gate.get("key", "")): {
|
||||
"review_action_id": f"review-action-{gate.get('key', '')}",
|
||||
"review_action_status": gate.get("status", ""),
|
||||
"source_ref_present": True,
|
||||
"verification_command_present": True,
|
||||
}
|
||||
for gate in non_pass_gates
|
||||
},
|
||||
}
|
||||
actual = {
|
||||
"non_pass_gate_keys": sorted(str(gate.get("key", "")) for gate in non_pass_gates),
|
||||
"action_gate_keys": sorted(actions_by_gate),
|
||||
"pass_gate_action_ids_empty": all(not gate.get("review_action_id") for gate in pass_gates),
|
||||
"gate_action_mirrors": {},
|
||||
}
|
||||
for gate in non_pass_gates:
|
||||
key = str(gate.get("key", ""))
|
||||
action = actions_by_gate.get(key, {})
|
||||
actual["gate_action_mirrors"][key] = {
|
||||
"review_action_id": gate.get("review_action_id", ""),
|
||||
"review_action_status": gate.get("review_action_status", ""),
|
||||
"source_ref_present": bool(gate.get("review_action_source_ref_count")),
|
||||
"verification_command_present": bool(gate.get("review_action_verification_command")),
|
||||
"top_level_action_id": action.get("action_id", ""),
|
||||
"top_level_action_status": action.get("status", ""),
|
||||
"top_level_source_ref_present": bool(action.get("source_refs")),
|
||||
"top_level_verification_command_present": bool(action.get("verification_command")),
|
||||
}
|
||||
expected["gate_action_mirrors"][key]["top_level_action_id"] = f"review-action-{key}"
|
||||
expected["gate_action_mirrors"][key]["top_level_action_status"] = gate.get("status", "")
|
||||
expected["gate_action_mirrors"][key]["top_level_source_ref_present"] = True
|
||||
expected["gate_action_mirrors"][key]["top_level_verification_command_present"] = True
|
||||
return {
|
||||
"key": "review-studio-gate-action-mirror",
|
||||
"label": "Review Studio gates mirror review actions",
|
||||
"status": "pass" if expected == actual else "fail",
|
||||
"expected": expected,
|
||||
"actual": actual,
|
||||
"paths": [REQUIRED_REPORTS["review_studio"]],
|
||||
"detail": (
|
||||
"Every non-pass Review Studio gate must have exactly one top-level review action and a gate-local "
|
||||
"action summary with source refs and a verification command."
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
def build_report(skill_dir: Path, generated_at: str) -> dict[str, Any]:
|
||||
reports: dict[str, dict[str, Any]] = {}
|
||||
text_reports: dict[str, str] = {}
|
||||
@@ -100,6 +165,8 @@ def build_report(skill_dir: Path, generated_at: str) -> dict[str, Any]:
|
||||
context_budget = reports["context_budget"]
|
||||
claim_guard = reports["world_class_claim_guard"]
|
||||
|
||||
checks.append(build_review_studio_gate_action_mirror_check(review_studio))
|
||||
|
||||
benchmark_summary = nested(benchmark, ["summary"], {})
|
||||
adoption_summary = nested(adoption, ["summary"], {})
|
||||
ledger_summary = nested(ledger, ["summary"], {})
|
||||
|
||||
@@ -514,6 +514,13 @@ def render_review_studio(skill_dir: Path, output_html: Path | None = None, outpu
|
||||
contract = gate_contract(gates)
|
||||
blockers, warnings = add_blockers_from_gate(gates)
|
||||
review_actions = build_review_actions(gates, skill_dir, output_html, data)
|
||||
action_by_gate = {str(item.get("gate_key", "")): item for item in review_actions}
|
||||
for gate in gates:
|
||||
action = action_by_gate.get(str(gate.get("key", "")))
|
||||
gate["review_action_id"] = str(action.get("action_id", "")) if action else ""
|
||||
gate["review_action_status"] = str(action.get("status", "")) if action else ""
|
||||
gate["review_action_source_ref_count"] = len(action.get("source_refs", [])) if action else 0
|
||||
gate["review_action_verification_command"] = str(action.get("verification_command", "")) if action else ""
|
||||
score = weighted_score(gates)
|
||||
annotation_summary = data["review_annotations"].get("summary", {})
|
||||
open_annotation_blockers = int(annotation_summary.get("open_blocker_count", 0) or 0)
|
||||
|
||||
@@ -297,6 +297,7 @@ def build_review_actions(
|
||||
refs = source_refs(skill_dir, output_html, guidance.get("source_paths", []))
|
||||
actions.append(
|
||||
{
|
||||
"action_id": f"review-action-{gate_item['key']}",
|
||||
"gate_key": gate_item["key"],
|
||||
"label": gate_item["label"],
|
||||
"status": gate_item["status"],
|
||||
|
||||
@@ -165,6 +165,20 @@ def main() -> None:
|
||||
assert checks["skill-ir-evidence-path-contract"]["actual"]["review_studio_evidence_path"] == (
|
||||
"skill-ir/examples/yao-meta-skill.json"
|
||||
), checks["skill-ir-evidence-path-contract"]
|
||||
assert checks["review-studio-gate-action-mirror"]["status"] == "pass", checks[
|
||||
"review-studio-gate-action-mirror"
|
||||
]
|
||||
gate_action_mirror = checks["review-studio-gate-action-mirror"]["actual"]
|
||||
assert gate_action_mirror["non_pass_gate_keys"] == [
|
||||
"output-lab",
|
||||
"review-waivers",
|
||||
"world-class-evidence",
|
||||
], gate_action_mirror
|
||||
assert gate_action_mirror["action_gate_keys"] == gate_action_mirror["non_pass_gate_keys"], gate_action_mirror
|
||||
assert gate_action_mirror["pass_gate_action_ids_empty"] is True, gate_action_mirror
|
||||
assert gate_action_mirror["gate_action_mirrors"]["world-class-evidence"]["source_ref_present"] is True, (
|
||||
gate_action_mirror
|
||||
)
|
||||
assert checks["overview-benchmark-summary"]["status"] == "pass", checks["overview-benchmark-summary"]
|
||||
assert checks["interpretation-adoption-summary"]["status"] == "pass", checks["interpretation-adoption-summary"]
|
||||
assert checks["coverage-world-class-boundary"]["status"] == "pass", checks["coverage-world-class-boundary"]
|
||||
@@ -397,6 +411,38 @@ def main() -> None:
|
||||
phase_queue_drift_checks["world-class-phase-queue-consistency"]
|
||||
)
|
||||
|
||||
gate_action_drift_root = TMP / "gate-action-drift-skill"
|
||||
copy_reports(gate_action_drift_root)
|
||||
gate_action_path = gate_action_drift_root / "reports" / "review-studio.json"
|
||||
gate_action_payload = json.loads(gate_action_path.read_text(encoding="utf-8"))
|
||||
for gate in gate_action_payload["gates"]:
|
||||
if gate["key"] == "world-class-evidence":
|
||||
gate["review_action_id"] = ""
|
||||
gate["review_action_source_ref_count"] = 0
|
||||
for action in gate_action_payload["review_actions"]:
|
||||
if action["gate_key"] == "world-class-evidence":
|
||||
action["source_refs"] = []
|
||||
gate_action_path.write_text(json.dumps(gate_action_payload, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
|
||||
gate_action_drift_proc = run(
|
||||
[
|
||||
sys.executable,
|
||||
str(SCRIPT),
|
||||
str(gate_action_drift_root),
|
||||
"--output-json",
|
||||
str(TMP / "gate_action_drift.json"),
|
||||
"--output-md",
|
||||
str(TMP / "gate_action_drift.md"),
|
||||
"--generated-at",
|
||||
"2026-06-15",
|
||||
]
|
||||
)
|
||||
assert gate_action_drift_proc.returncode == 2, gate_action_drift_proc.stdout
|
||||
gate_action_drift_payload = json.loads(gate_action_drift_proc.stdout)
|
||||
gate_action_drift_checks = {item["key"]: item for item in gate_action_drift_payload["checks"]}
|
||||
assert gate_action_drift_checks["review-studio-gate-action-mirror"]["status"] == "fail", (
|
||||
gate_action_drift_checks["review-studio-gate-action-mirror"]
|
||||
)
|
||||
|
||||
release_flow_drift_root = TMP / "release-flow-drift-skill"
|
||||
copy_reports(release_flow_drift_root)
|
||||
agents_path = release_flow_drift_root / "AGENTS.md"
|
||||
|
||||
@@ -35,8 +35,20 @@ def main() -> None:
|
||||
"review-waivers",
|
||||
"world-class-evidence",
|
||||
}, payload
|
||||
action_by_gate = {item["gate_key"]: item for item in payload["review_actions"]}
|
||||
gate_keys = {item["key"] for item in payload["gates"]}
|
||||
assert gate_keys == review_gates.REVIEW_STUDIO_GATE_KEYS, payload
|
||||
for gate in payload["gates"]:
|
||||
if gate["status"] == "pass":
|
||||
assert gate["review_action_id"] == "", gate
|
||||
assert gate["review_action_source_ref_count"] == 0, gate
|
||||
assert gate["review_action_verification_command"] == "", gate
|
||||
continue
|
||||
action = action_by_gate[gate["key"]]
|
||||
assert gate["review_action_id"] == action["action_id"] == f"review-action-{gate['key']}", gate
|
||||
assert gate["review_action_status"] == action["status"] == gate["status"], gate
|
||||
assert gate["review_action_source_ref_count"] == len(action["source_refs"]) > 0, gate
|
||||
assert gate["review_action_verification_command"] == action["verification_command"], gate
|
||||
assert set(review_gates.GATE_WEIGHTS) == review_gates.REVIEW_STUDIO_GATE_KEYS, review_gates.GATE_WEIGHTS
|
||||
gate_contract = payload["gate_contract"]
|
||||
assert gate_contract["ok"] is True, gate_contract
|
||||
|
||||
Reference in New Issue
Block a user