Split Review Studio gate helpers
This commit is contained in:
yaojingang
+1
-1
@@ -16,7 +16,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc"
|
||||
"package_sha256": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -16,8 +16,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc",
|
||||
"archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f"
|
||||
"package_sha256": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652",
|
||||
"archive_sha256": "29c3154e87935a6ffc92a42b6e270da17ef0aa2d3c156c518770ece272d4b58b"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -48,7 +48,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f",
|
||||
"archive_sha256": "29c3154e87935a6ffc92a42b6e270da17ef0aa2d3c156c518770ece272d4b58b",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-16T17:29:39Z",
|
||||
"generated_at": "2026-06-16T17:39:17Z",
|
||||
"skill_dir": ".",
|
||||
"privacy_contract": {
|
||||
"storage": "local-first",
|
||||
|
||||
@@ -4,10 +4,10 @@
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"python_file_count": 220,
|
||||
"script_file_count": 145,
|
||||
"python_file_count": 221,
|
||||
"script_file_count": 146,
|
||||
"test_file_count": 75,
|
||||
"internal_module_count": 61,
|
||||
"internal_module_count": 62,
|
||||
"cli_script_count": 86,
|
||||
"command_handler_count": 68,
|
||||
"entrypoint_command_handler_count": 18,
|
||||
@@ -18,7 +18,7 @@
|
||||
"block_line_threshold": 1500,
|
||||
"largest_file_lines": 696,
|
||||
"watchlist_count": 0,
|
||||
"early_watchlist_count": 4,
|
||||
"early_watchlist_count": 3,
|
||||
"hotspot_count": 0,
|
||||
"blocker_count": 0,
|
||||
"decision": "pass"
|
||||
@@ -32,14 +32,6 @@
|
||||
"early_watch": true,
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/review_studio_gates.py",
|
||||
"lines": 646,
|
||||
"kind": "internal-module",
|
||||
"severity": "pass",
|
||||
"early_watch": true,
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "scripts/cross_packager.py",
|
||||
"lines": 638,
|
||||
@@ -119,6 +111,14 @@
|
||||
"severity": "pass",
|
||||
"early_watch": false,
|
||||
"recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_world_class_evidence_ledger.py",
|
||||
"lines": 567,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"early_watch": false,
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
}
|
||||
],
|
||||
"watchlist": [],
|
||||
@@ -131,14 +131,6 @@
|
||||
"early_watch": true,
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/review_studio_gates.py",
|
||||
"lines": 646,
|
||||
"kind": "internal-module",
|
||||
"severity": "pass",
|
||||
"early_watch": true,
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "scripts/cross_packager.py",
|
||||
"lines": 638,
|
||||
|
||||
@@ -5,17 +5,17 @@ Generated at: `2026-06-13`
|
||||
## Summary
|
||||
|
||||
- decision: `pass`
|
||||
- python files: `220`
|
||||
- scripts: `145`
|
||||
- python files: `221`
|
||||
- scripts: `146`
|
||||
- tests: `75`
|
||||
- internal modules: `61`
|
||||
- internal modules: `62`
|
||||
- CLI scripts: `86`
|
||||
- Yao CLI command handlers: `68`
|
||||
- entrypoint command handlers: `18`
|
||||
- command modules: `6`
|
||||
- largest file lines: `696`
|
||||
- early watch threshold lines: `600`
|
||||
- early watchlist: `4`
|
||||
- early watchlist: `3`
|
||||
- watch threshold lines: `720`
|
||||
- watchlist: `0`
|
||||
- hotspots: `0`
|
||||
@@ -36,7 +36,6 @@ No near-threshold files found.
|
||||
| File | Lines | Kind | Recommended next split |
|
||||
| --- | ---: | --- | --- |
|
||||
| `tests/verify_yao_cli.py` | `696` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
|
||||
| `scripts/review_studio_gates.py` | `646` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
|
||||
| `scripts/cross_packager.py` | `638` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
|
||||
| `tests/verify_world_class_evidence_intake.py` | `628` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
|
||||
|
||||
@@ -45,7 +44,6 @@ No near-threshold files found.
|
||||
| File | Lines | Kind | Severity |
|
||||
| --- | ---: | --- | --- |
|
||||
| `tests/verify_yao_cli.py` | `696` | `test` | `pass` |
|
||||
| `scripts/review_studio_gates.py` | `646` | `internal-module` | `pass` |
|
||||
| `scripts/cross_packager.py` | `638` | `cli-script` | `pass` |
|
||||
| `tests/verify_world_class_evidence_intake.py` | `628` | `test` | `pass` |
|
||||
| `scripts/render_benchmark_reproducibility.py` | `595` | `cli-script` | `pass` |
|
||||
@@ -56,6 +54,7 @@ No near-threshold files found.
|
||||
| `tests/verify_review_studio.py` | `580` | `test` | `pass` |
|
||||
| `scripts/render_evidence_consistency.py` | `568` | `cli-script` | `pass` |
|
||||
| `scripts/render_review_studio.py` | `568` | `cli-script` | `pass` |
|
||||
| `tests/verify_world_class_evidence_ledger.py` | `567` | `test` | `pass` |
|
||||
|
||||
## Release Rule
|
||||
|
||||
|
||||
@@ -3,23 +3,36 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"skill_dir": ".",
|
||||
"commit": "d5beede0a62dab0f0780be283a274ed8a5be9dc4",
|
||||
"commit": "5e2163683a483b9b0b0180219994495fc84eb272",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": false,
|
||||
"changed_file_count": 0,
|
||||
"sample": [],
|
||||
"dirty": true,
|
||||
"changed_file_count": 56,
|
||||
"sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" M reports/adoption_drift_report.json",
|
||||
" M reports/architecture_maintainability.json",
|
||||
" M reports/architecture_maintainability.md",
|
||||
" M reports/compiled_targets.json",
|
||||
" M reports/context_budget.json",
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json",
|
||||
" M reports/evidence_consistency.json",
|
||||
" M reports/install_simulation.json",
|
||||
" M reports/install_simulation.md"
|
||||
],
|
||||
"scope": "generation-time status before this report is written"
|
||||
},
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0",
|
||||
"source_contract_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc",
|
||||
"archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f",
|
||||
"evidence_bundle_sha256": "bb4d7860b90e023f5d97f74a87d091f6c4437190dfe7dacb5c740d7675136199",
|
||||
"source_contract_sha256": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652",
|
||||
"archive_sha256": "29c3154e87935a6ffc92a42b6e270da17ef0aa2d3c156c518770ece272d4b58b",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -37,14 +50,15 @@
|
||||
"world_class_source_pass_count": 7,
|
||||
"world_class_source_blocked_count": 6,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 56
|
||||
},
|
||||
"public_claim": {
|
||||
"ready": false,
|
||||
"scope": "public benchmark or world-class readiness claim",
|
||||
"blockers": [
|
||||
"release lock is not clean or commit is unavailable",
|
||||
"provider-backed model holdout evidence is incomplete",
|
||||
"human blind-review adjudication is incomplete",
|
||||
"world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
|
||||
@@ -53,10 +67,10 @@
|
||||
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
|
||||
},
|
||||
"release_lock": {
|
||||
"ready": true,
|
||||
"commit": "d5beede0a62dab0f0780be283a274ed8a5be9dc4",
|
||||
"ready": false,
|
||||
"commit": "5e2163683a483b9b0b0180219994495fc84eb272",
|
||||
"status_scope": "generation-time status before this report is written",
|
||||
"reason": "clean generation-time HEAD"
|
||||
"reason": "working tree was dirty at generation time"
|
||||
},
|
||||
"evidence_bundle": {
|
||||
"algorithm": "sha256(path,label,exists,artifact_sha256)",
|
||||
@@ -64,7 +78,7 @@
|
||||
"existing_count": 25,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0"
|
||||
"sha256": "bb4d7860b90e023f5d97f74a87d091f6c4437190dfe7dacb5c740d7675136199"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -137,8 +151,8 @@
|
||||
"label": "output_execution",
|
||||
"path": "reports/output_execution_runs.json",
|
||||
"exists": true,
|
||||
"bytes": 7966,
|
||||
"sha256": "c0a5988ee9aff029b8c56b0a090aa23fc4efe803bd960f722b5a9a9c15a5c78d"
|
||||
"bytes": 7967,
|
||||
"sha256": "d1036355cee863fa21a20cdd2da5b237b5d262f9ff79b3543f8f6aff579160b2"
|
||||
},
|
||||
{
|
||||
"label": "blind_review",
|
||||
@@ -172,64 +186,64 @@
|
||||
"label": "trust_report",
|
||||
"path": "reports/security_trust_report.json",
|
||||
"exists": true,
|
||||
"bytes": 132641,
|
||||
"sha256": "e0e8b047f580e5c8ff33580c49a99d3221919f52f6c5e3849976ed840a8618d9"
|
||||
"bytes": 133262,
|
||||
"sha256": "17d57bf1beb0dbe9b8859f56c4d7c301f43230d00262d96ae8f0f4a3894ea7a0"
|
||||
},
|
||||
{
|
||||
"label": "python_compatibility",
|
||||
"path": "reports/python_compatibility.json",
|
||||
"exists": true,
|
||||
"bytes": 28940,
|
||||
"sha256": "c3fb22a905196a6d5242bde27f0b33f5233accacb478a80d1fd7a0582243e2bc"
|
||||
"bytes": 29069,
|
||||
"sha256": "716f4554952641019830e895191891dcd9841ce0488570c7a526c7d144adf058"
|
||||
},
|
||||
{
|
||||
"label": "registry_audit",
|
||||
"path": "reports/registry_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 3183,
|
||||
"sha256": "01100afaf317ebcdef836070636905bb3e4d64412c8a8f14d8758db822eba33c"
|
||||
"sha256": "c4ee2793af91f74987c71d0aad7be2a116ed691e7f50dbb11e2df4216309706c"
|
||||
},
|
||||
{
|
||||
"label": "package_verification",
|
||||
"path": "reports/package_verification.json",
|
||||
"exists": true,
|
||||
"bytes": 19338,
|
||||
"sha256": "6dde3b877e00b3e8936d0ffe1e45c77926639f5b21b0a4f30e779e6b4ffd4f57"
|
||||
"sha256": "3c74f6dff362bf61112f7115ad06cb6ec6d94331256a60075757d611b2c1a926"
|
||||
},
|
||||
{
|
||||
"label": "install_simulation",
|
||||
"path": "reports/install_simulation.json",
|
||||
"exists": true,
|
||||
"bytes": 8758,
|
||||
"sha256": "7177ae392187ac0af2ed071c31c758e6e3e4d63230bbbcbdfc1b35719d23b966"
|
||||
"bytes": 8604,
|
||||
"sha256": "7037d27d066b92d5652d8a2b0a1ec0e3d5fa698fd301db2aa4f7675304ab934d"
|
||||
},
|
||||
{
|
||||
"label": "skill_os2_audit",
|
||||
"path": "reports/skill_os2_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 14310,
|
||||
"sha256": "867273823e8244ac65d44e69edb8c3d6c628b0f28f8a3bfdee612b802592654a"
|
||||
"sha256": "50c34274593701e6aa5505524db7c54c3f6a40a085bbeefa9d7d29c1950ba274"
|
||||
},
|
||||
{
|
||||
"label": "world_class_evidence_plan",
|
||||
"path": "reports/world_class_evidence_plan.json",
|
||||
"exists": true,
|
||||
"bytes": 20828,
|
||||
"sha256": "af3c3f101ad992820bf36ddb14b02e7404ef16411567c483f86eed530ca45f62"
|
||||
"sha256": "9b74155fb9bfe44ba838d64b1a31768b83978b154bdd8eaa606f494c816f189f"
|
||||
},
|
||||
{
|
||||
"label": "world_class_evidence_ledger",
|
||||
"path": "reports/world_class_evidence_ledger.json",
|
||||
"exists": true,
|
||||
"bytes": 22285,
|
||||
"sha256": "74deeabfac9f488a35cd816fdf8cd74a52fe73a82958770cbd7b41191a218814"
|
||||
"sha256": "f6e1a69b0359c28c88e9e9e69ff66763c721ac8a112a43a673ce98cd9d3bce41"
|
||||
},
|
||||
{
|
||||
"label": "world_class_evidence_intake",
|
||||
"path": "reports/world_class_evidence_intake.json",
|
||||
"exists": true,
|
||||
"bytes": 19319,
|
||||
"sha256": "69afd0ff3d49ba9e1ea57248e41cfe62a0abfdf06fd0f997ed3008a5656c2566"
|
||||
"sha256": "46f801051ec075725059e4e2682ef2162fd892b5e7255c8d5121d7b24dcc7f2c"
|
||||
},
|
||||
{
|
||||
"label": "world_class_evidence_preflight",
|
||||
@@ -243,21 +257,21 @@
|
||||
"path": "reports/world_class_submission_review.json",
|
||||
"exists": true,
|
||||
"bytes": 13655,
|
||||
"sha256": "17def7ba6982d834e13ce3896dd9093019eec3ee8d2fa5b283ef8d6b17b19be0"
|
||||
"sha256": "9fbd4cd437986fca9a043cbab24aec7d575aaf166a8d9365c79c56f093cab5b8"
|
||||
},
|
||||
{
|
||||
"label": "world_class_operator_runbook",
|
||||
"path": "reports/world_class_operator_runbook.json",
|
||||
"exists": true,
|
||||
"bytes": 24835,
|
||||
"sha256": "00bfa998b24a37cf3f0354d3956f1c722041d5cbada0f4357f27f7c2187d11f1"
|
||||
"sha256": "2d32a2e917b7215afe7a7a93ca8bacffa540a245953aa39e2ee47eea1b169d17"
|
||||
},
|
||||
{
|
||||
"label": "world_class_operator_runbook_markdown",
|
||||
"path": "reports/world_class_operator_runbook.md",
|
||||
"exists": true,
|
||||
"bytes": 15424,
|
||||
"sha256": "337fb764b98ad2707f5a0d7bba88b9c5401256d7be00f8f3dc478e89e3bcb6c2"
|
||||
"sha256": "00d8ebabb91e14a06cacdb212f448668aa1e47b72587448e30681fc53acaad9a"
|
||||
},
|
||||
{
|
||||
"label": "world_class_operator_runbook_html",
|
||||
@@ -271,7 +285,7 @@
|
||||
"path": "reports/world_class_claim_guard.json",
|
||||
"exists": true,
|
||||
"bytes": 18596,
|
||||
"sha256": "c846ffc8565a40c270e711a58e968b005afd75be6df1a442b020deebe850386f"
|
||||
"sha256": "abe7f7d60c0025e140373fadaefbed4063f285c140c74b9c7cfb464e354bb526"
|
||||
}
|
||||
],
|
||||
"missing_artifacts": [],
|
||||
|
||||
@@ -1,19 +1,19 @@
|
||||
# Benchmark Reproducibility
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Commit: `d5beede0a62dab0f0780be283a274ed8a5be9dc4`
|
||||
Working tree dirty at generation: `false`
|
||||
Evidence bundle SHA256: `5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0`
|
||||
Commit: `5e2163683a483b9b0b0180219994495fc84eb272`
|
||||
Working tree dirty at generation: `true`
|
||||
Evidence bundle SHA256: `bb4d7860b90e023f5d97f74a87d091f6c4437190dfe7dacb5c740d7675136199`
|
||||
|
||||
## Summary
|
||||
|
||||
- reproducibility ready: `true`
|
||||
- release lock ready: `true`
|
||||
- release lock ready: `false`
|
||||
- methodology complete: `true`
|
||||
- required artifacts: `25`
|
||||
- missing artifacts: `0`
|
||||
- source contract sha256: `712f00ca2202`
|
||||
- archive sha256: `69ad979695a4`
|
||||
- source contract sha256: `58b8388686e4`
|
||||
- archive sha256: `29c3154e8793`
|
||||
- output cases: `5`
|
||||
- disclosed failure cases: `3`
|
||||
- reproduction commands: `23`
|
||||
@@ -22,8 +22,8 @@ Evidence bundle SHA256: `5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62
|
||||
- world-class ready: `false`
|
||||
- world-class source checks: `7` pass / `13` total; `6` blocked
|
||||
- public claim ready: `false`
|
||||
- public claim blockers: `4`
|
||||
- changed files at generation: `0`
|
||||
- public claim blockers: `5`
|
||||
- changed files at generation: `56`
|
||||
|
||||
This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
|
||||
|
||||
@@ -35,6 +35,7 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
|
||||
| Blocker |
|
||||
| --- |
|
||||
| release lock is not clean or commit is unavailable |
|
||||
| provider-backed model holdout evidence is incomplete |
|
||||
| human blind-review adjudication is incomplete |
|
||||
| world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) |
|
||||
@@ -42,15 +43,15 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
|
||||
## Release Lock
|
||||
|
||||
- ready: `true`
|
||||
- reason: clean generation-time HEAD
|
||||
- ready: `false`
|
||||
- reason: working tree was dirty at generation time
|
||||
- status scope: generation-time status before this report is written
|
||||
|
||||
## Evidence Bundle
|
||||
|
||||
- algorithm: `sha256(path,label,exists,artifact_sha256)`
|
||||
- artifacts: `25` / `25`
|
||||
- sha256: `5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0`
|
||||
- sha256: `bb4d7860b90e023f5d97f74a87d091f6c4437190dfe7dacb5c740d7675136199`
|
||||
|
||||
## Methodology Sections
|
||||
|
||||
@@ -72,26 +73,26 @@ 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 | `c0a5988ee9af` |
|
||||
| output_execution | `reports/output_execution_runs.json` | present | `d1036355cee8` |
|
||||
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
|
||||
| review_adjudication | `reports/output_review_adjudication.json` | present | `bb8c72a9291e` |
|
||||
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
|
||||
| runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` |
|
||||
| trust_report | `reports/security_trust_report.json` | present | `e0e8b047f580` |
|
||||
| python_compatibility | `reports/python_compatibility.json` | present | `c3fb22a90519` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `01100afaf317` |
|
||||
| package_verification | `reports/package_verification.json` | present | `6dde3b877e00` |
|
||||
| install_simulation | `reports/install_simulation.json` | present | `7177ae392187` |
|
||||
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `867273823e82` |
|
||||
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `af3c3f101ad9` |
|
||||
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `74deeabfac9f` |
|
||||
| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `69afd0ff3d49` |
|
||||
| trust_report | `reports/security_trust_report.json` | present | `17d57bf1beb0` |
|
||||
| python_compatibility | `reports/python_compatibility.json` | present | `716f45549526` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `c4ee2793af91` |
|
||||
| package_verification | `reports/package_verification.json` | present | `3c74f6dff362` |
|
||||
| install_simulation | `reports/install_simulation.json` | present | `7037d27d066b` |
|
||||
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `50c342745937` |
|
||||
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `9b74155fb9bf` |
|
||||
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `f6e1a69b0359` |
|
||||
| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `46f801051ec0` |
|
||||
| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `b7fd72d7e754` |
|
||||
| world_class_submission_review | `reports/world_class_submission_review.json` | present | `17def7ba6982` |
|
||||
| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `00bfa998b24a` |
|
||||
| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `337fb764b98a` |
|
||||
| world_class_submission_review | `reports/world_class_submission_review.json` | present | `9fbd4cd43798` |
|
||||
| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `2d32a2e917b7` |
|
||||
| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `00d8ebabb91e` |
|
||||
| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `ca72c65b437b` |
|
||||
| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `c846ffc8565a` |
|
||||
| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `abe7f7d60c00` |
|
||||
|
||||
## Reproduction Commands
|
||||
|
||||
|
||||
@@ -239,6 +239,7 @@
|
||||
"scripts/review_studio_data.py",
|
||||
"scripts/review_studio_formatting.py",
|
||||
"scripts/review_studio_gate_contract.py",
|
||||
"scripts/review_studio_gate_helpers.py",
|
||||
"scripts/review_studio_gates.py",
|
||||
"scripts/review_studio_layout.py",
|
||||
"scripts/review_studio_output_review.py",
|
||||
@@ -350,7 +351,7 @@
|
||||
],
|
||||
"counts": {
|
||||
"references": 35,
|
||||
"scripts": 145,
|
||||
"scripts": 146,
|
||||
"assets": 6,
|
||||
"reports": 43
|
||||
}
|
||||
@@ -622,7 +623,7 @@
|
||||
"strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.",
|
||||
"counts": {
|
||||
"references": 35,
|
||||
"scripts": 145,
|
||||
"scripts": 146,
|
||||
"assets": 6,
|
||||
"reports": 43
|
||||
},
|
||||
@@ -633,7 +634,7 @@
|
||||
},
|
||||
"scripts": {
|
||||
"strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.",
|
||||
"script_count": 145,
|
||||
"script_count": 146,
|
||||
"help_smoke_failed_count": 0
|
||||
},
|
||||
"permissions": {
|
||||
@@ -877,7 +878,7 @@
|
||||
"strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.",
|
||||
"counts": {
|
||||
"references": 35,
|
||||
"scripts": 145,
|
||||
"scripts": 146,
|
||||
"assets": 6,
|
||||
"reports": 43
|
||||
},
|
||||
@@ -888,7 +889,7 @@
|
||||
},
|
||||
"scripts": {
|
||||
"strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.",
|
||||
"script_count": 145,
|
||||
"script_count": 146,
|
||||
"help_smoke_failed_count": 0
|
||||
},
|
||||
"permissions": {
|
||||
@@ -1184,6 +1185,7 @@
|
||||
"scripts/review_studio_data.py",
|
||||
"scripts/review_studio_formatting.py",
|
||||
"scripts/review_studio_gate_contract.py",
|
||||
"scripts/review_studio_gate_helpers.py",
|
||||
"scripts/review_studio_gates.py",
|
||||
"scripts/review_studio_layout.py",
|
||||
"scripts/review_studio_output_review.py",
|
||||
@@ -1295,7 +1297,7 @@
|
||||
],
|
||||
"counts": {
|
||||
"references": 35,
|
||||
"scripts": 145,
|
||||
"scripts": 146,
|
||||
"assets": 6,
|
||||
"reports": 43
|
||||
}
|
||||
@@ -1567,7 +1569,7 @@
|
||||
"strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.",
|
||||
"counts": {
|
||||
"references": 35,
|
||||
"scripts": 145,
|
||||
"scripts": 146,
|
||||
"assets": 6,
|
||||
"reports": 43
|
||||
},
|
||||
@@ -1578,7 +1580,7 @@
|
||||
},
|
||||
"scripts": {
|
||||
"strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.",
|
||||
"script_count": 145,
|
||||
"script_count": 146,
|
||||
"help_smoke_failed_count": 0
|
||||
},
|
||||
"permissions": {
|
||||
@@ -1822,7 +1824,7 @@
|
||||
"strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.",
|
||||
"counts": {
|
||||
"references": 35,
|
||||
"scripts": 145,
|
||||
"scripts": 146,
|
||||
"assets": 6,
|
||||
"reports": 43
|
||||
},
|
||||
@@ -1833,7 +1835,7 @@
|
||||
},
|
||||
"scripts": {
|
||||
"strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.",
|
||||
"script_count": 145,
|
||||
"script_count": 146,
|
||||
"help_smoke_failed_count": 0
|
||||
},
|
||||
"permissions": {
|
||||
@@ -2129,6 +2131,7 @@
|
||||
"scripts/review_studio_data.py",
|
||||
"scripts/review_studio_formatting.py",
|
||||
"scripts/review_studio_gate_contract.py",
|
||||
"scripts/review_studio_gate_helpers.py",
|
||||
"scripts/review_studio_gates.py",
|
||||
"scripts/review_studio_layout.py",
|
||||
"scripts/review_studio_output_review.py",
|
||||
@@ -2240,7 +2243,7 @@
|
||||
],
|
||||
"counts": {
|
||||
"references": 35,
|
||||
"scripts": 145,
|
||||
"scripts": 146,
|
||||
"assets": 6,
|
||||
"reports": 43
|
||||
}
|
||||
@@ -2512,7 +2515,7 @@
|
||||
"strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.",
|
||||
"counts": {
|
||||
"references": 35,
|
||||
"scripts": 145,
|
||||
"scripts": 146,
|
||||
"assets": 6,
|
||||
"reports": 43
|
||||
},
|
||||
@@ -2522,7 +2525,7 @@
|
||||
},
|
||||
"scripts": {
|
||||
"strategy": "Expose script and permission metadata for downstream clients or installers to enforce.",
|
||||
"script_count": 145,
|
||||
"script_count": 146,
|
||||
"help_smoke_failed_count": 0
|
||||
},
|
||||
"permissions": {
|
||||
@@ -2760,7 +2763,7 @@
|
||||
"strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.",
|
||||
"counts": {
|
||||
"references": 35,
|
||||
"scripts": 145,
|
||||
"scripts": 146,
|
||||
"assets": 6,
|
||||
"reports": 43
|
||||
},
|
||||
@@ -2770,7 +2773,7 @@
|
||||
},
|
||||
"scripts": {
|
||||
"strategy": "Expose script and permission metadata for downstream clients or installers to enforce.",
|
||||
"script_count": 145,
|
||||
"script_count": 146,
|
||||
"help_smoke_failed_count": 0
|
||||
},
|
||||
"permissions": {
|
||||
@@ -3058,6 +3061,7 @@
|
||||
"scripts/review_studio_data.py",
|
||||
"scripts/review_studio_formatting.py",
|
||||
"scripts/review_studio_gate_contract.py",
|
||||
"scripts/review_studio_gate_helpers.py",
|
||||
"scripts/review_studio_gates.py",
|
||||
"scripts/review_studio_layout.py",
|
||||
"scripts/review_studio_output_review.py",
|
||||
@@ -3169,7 +3173,7 @@
|
||||
],
|
||||
"counts": {
|
||||
"references": 35,
|
||||
"scripts": 145,
|
||||
"scripts": 146,
|
||||
"assets": 6,
|
||||
"reports": 43
|
||||
}
|
||||
@@ -3441,7 +3445,7 @@
|
||||
"strategy": "Keep optional directories as relative resources next to SKILL.md.",
|
||||
"counts": {
|
||||
"references": 35,
|
||||
"scripts": 145,
|
||||
"scripts": 146,
|
||||
"assets": 6,
|
||||
"reports": 43
|
||||
},
|
||||
@@ -3452,7 +3456,7 @@
|
||||
},
|
||||
"scripts": {
|
||||
"strategy": "Scripts remain local optional resources and should advertise --help when executable.",
|
||||
"script_count": 145,
|
||||
"script_count": 146,
|
||||
"help_smoke_failed_count": 0
|
||||
},
|
||||
"permissions": {
|
||||
@@ -3689,7 +3693,7 @@
|
||||
"strategy": "Keep optional directories as relative resources next to SKILL.md.",
|
||||
"counts": {
|
||||
"references": 35,
|
||||
"scripts": 145,
|
||||
"scripts": 146,
|
||||
"assets": 6,
|
||||
"reports": 43
|
||||
},
|
||||
@@ -3700,7 +3704,7 @@
|
||||
},
|
||||
"scripts": {
|
||||
"strategy": "Scripts remain local optional resources and should advertise --help when executable.",
|
||||
"script_count": 145,
|
||||
"script_count": 146,
|
||||
"help_smoke_failed_count": 0
|
||||
},
|
||||
"permissions": {
|
||||
@@ -3987,6 +3991,7 @@
|
||||
"scripts/review_studio_data.py",
|
||||
"scripts/review_studio_formatting.py",
|
||||
"scripts/review_studio_gate_contract.py",
|
||||
"scripts/review_studio_gate_helpers.py",
|
||||
"scripts/review_studio_gates.py",
|
||||
"scripts/review_studio_layout.py",
|
||||
"scripts/review_studio_output_review.py",
|
||||
@@ -4098,7 +4103,7 @@
|
||||
],
|
||||
"counts": {
|
||||
"references": 35,
|
||||
"scripts": 145,
|
||||
"scripts": 146,
|
||||
"assets": 6,
|
||||
"reports": 43
|
||||
}
|
||||
@@ -4370,7 +4375,7 @@
|
||||
"strategy": "Install as project or user scoped skill source, preserving relative references and scripts.",
|
||||
"counts": {
|
||||
"references": 35,
|
||||
"scripts": 145,
|
||||
"scripts": 146,
|
||||
"assets": 6,
|
||||
"reports": 43
|
||||
},
|
||||
@@ -4381,7 +4386,7 @@
|
||||
},
|
||||
"scripts": {
|
||||
"strategy": "Scripts require workspace trust and operator/client approval outside this compiler.",
|
||||
"script_count": 145,
|
||||
"script_count": 146,
|
||||
"help_smoke_failed_count": 0
|
||||
},
|
||||
"permissions": {
|
||||
@@ -4622,7 +4627,7 @@
|
||||
"strategy": "Install as project or user scoped skill source, preserving relative references and scripts.",
|
||||
"counts": {
|
||||
"references": 35,
|
||||
"scripts": 145,
|
||||
"scripts": 146,
|
||||
"assets": 6,
|
||||
"reports": 43
|
||||
},
|
||||
@@ -4633,7 +4638,7 @@
|
||||
},
|
||||
"scripts": {
|
||||
"strategy": "Scripts require workspace trust and operator/client approval outside this compiler.",
|
||||
"script_count": 145,
|
||||
"script_count": 146,
|
||||
"help_smoke_failed_count": 0
|
||||
},
|
||||
"permissions": {
|
||||
|
||||
+10
-10
@@ -6,16 +6,16 @@
|
||||
"context_budget_tier": "production",
|
||||
"context_budget_limit": 1000,
|
||||
"skill_body_tokens": 797,
|
||||
"other_text_tokens": 1083265,
|
||||
"other_text_tokens": 1083735,
|
||||
"estimated_initial_load_tokens": 990,
|
||||
"estimated_total_text_tokens": 1084062,
|
||||
"deferred_resource_tokens": 496411,
|
||||
"estimated_total_text_tokens": 1084532,
|
||||
"deferred_resource_tokens": 496603,
|
||||
"deferred_resource_warn_threshold": 120000,
|
||||
"deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 435517,
|
||||
"file_count": 145
|
||||
"estimated_tokens": 435709,
|
||||
"file_count": 146
|
||||
},
|
||||
{
|
||||
"path": "references",
|
||||
@@ -36,8 +36,8 @@
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 435517,
|
||||
"file_count": 145
|
||||
"estimated_tokens": 435709,
|
||||
"file_count": 146
|
||||
}
|
||||
],
|
||||
"deferred_resource_governance": {
|
||||
@@ -59,14 +59,14 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 435517,
|
||||
"file_count": 145,
|
||||
"estimated_tokens": 435709,
|
||||
"file_count": 146,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
],
|
||||
"summary": "Large deferred resources are indexed and backed by evidence."
|
||||
},
|
||||
"relevant_file_count": 692,
|
||||
"relevant_file_count": 694,
|
||||
"unused_resource_dirs": [],
|
||||
"quality_signal_points": 130,
|
||||
"quality_density": 131.3
|
||||
|
||||
@@ -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 | 496411 | `governed` | scripts:435517 | 131.3 | - | ok |
|
||||
| root | `.` | `production` | 1000 | 990 | 797 | 496603 | `governed` | scripts:435709 | 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 |
|
||||
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-03-31",
|
||||
"targets": [
|
||||
{
|
||||
"label": "root",
|
||||
@@ -8,12 +8,12 @@
|
||||
"budget_limit": 1000,
|
||||
"initial_tokens": 990,
|
||||
"skill_body_tokens": 797,
|
||||
"deferred_resource_tokens": 496411,
|
||||
"deferred_resource_tokens": 496603,
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 435517,
|
||||
"file_count": 145
|
||||
"estimated_tokens": 435709,
|
||||
"file_count": 146
|
||||
}
|
||||
],
|
||||
"deferred_resource_governance": {
|
||||
@@ -35,8 +35,8 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 435517,
|
||||
"file_count": 145,
|
||||
"estimated_tokens": 435709,
|
||||
"file_count": 146,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
],
|
||||
|
||||
@@ -189,12 +189,12 @@
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"status": "pass",
|
||||
"detail": "initial load 990/1000; deferred 496411/120000; top deferred scripts 435517; resource governance governed; quality density 131.3",
|
||||
"detail": "initial load 990/1000; deferred 496603/120000; top deferred scripts 435709; resource governance governed; quality density 131.3",
|
||||
"evidence": "reports/context_budget.json"
|
||||
},
|
||||
"actual": {
|
||||
"status": "pass",
|
||||
"detail": "initial load 990/1000; deferred 496411/120000; top deferred scripts 435517; resource governance governed; quality density 131.3",
|
||||
"detail": "initial load 990/1000; deferred 496603/120000; top deferred scripts 435709; resource governance governed; quality density 131.3",
|
||||
"evidence": "reports/context_budget.json"
|
||||
},
|
||||
"paths": [
|
||||
@@ -222,7 +222,7 @@
|
||||
"actual": {
|
||||
"available": true,
|
||||
"clean": false,
|
||||
"changed_file_count": 11
|
||||
"changed_file_count": 47
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json"
|
||||
@@ -1525,7 +1525,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 145
|
||||
"file_count": 146
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -1540,7 +1540,7 @@
|
||||
"file_count": 235
|
||||
}
|
||||
],
|
||||
"file_count": 448,
|
||||
"file_count": 449,
|
||||
"folder_count": 4,
|
||||
"distribution": [
|
||||
{
|
||||
@@ -1565,7 +1565,7 @@
|
||||
},
|
||||
{
|
||||
"label": "scripts",
|
||||
"value": 145
|
||||
"value": 146
|
||||
},
|
||||
{
|
||||
"label": "evals",
|
||||
@@ -1613,7 +1613,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 145
|
||||
"file_count": 146
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -1628,7 +1628,7 @@
|
||||
"file_count": 235
|
||||
}
|
||||
],
|
||||
"file_count": 448,
|
||||
"file_count": 449,
|
||||
"folder_count": 4,
|
||||
"distribution": [
|
||||
{
|
||||
@@ -1653,7 +1653,7 @@
|
||||
},
|
||||
{
|
||||
"label": "scripts",
|
||||
"value": 145
|
||||
"value": 146
|
||||
},
|
||||
{
|
||||
"label": "evals",
|
||||
@@ -2417,10 +2417,10 @@
|
||||
"score `91`",
|
||||
"`16` gates",
|
||||
"`3` warnings",
|
||||
"`59` declared internal modules",
|
||||
"`86 / 86` CLI help smoke checks passing across `145` scripts",
|
||||
"`683` zip entries",
|
||||
"archive with `683` entries",
|
||||
"`60` declared internal modules",
|
||||
"`86 / 86` CLI help smoke checks passing across `146` scripts",
|
||||
"`684` zip entries",
|
||||
"archive with `684` entries",
|
||||
"`12` installer permission checks enforced",
|
||||
"`0` permission failures",
|
||||
"`25` required artifacts",
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
"installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill",
|
||||
"summary": {
|
||||
"archive_present": true,
|
||||
"archive_entry_count": 683,
|
||||
"archive_entry_count": 684,
|
||||
"archive_extracted": true,
|
||||
"entrypoint_loaded": true,
|
||||
"manifest_loaded": true,
|
||||
|
||||
@@ -34,7 +34,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.94,
|
||||
"duration_ms": 29.88,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -62,7 +62,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 29.02,
|
||||
"duration_ms": 29.59,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -85,7 +85,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.44,
|
||||
"duration_ms": 29.33,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -113,7 +113,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 29.01,
|
||||
"duration_ms": 27.41,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -136,7 +136,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.44,
|
||||
"duration_ms": 28.83,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -164,7 +164,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 28.58,
|
||||
"duration_ms": 28.11,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -187,7 +187,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 27.57,
|
||||
"duration_ms": 28.25,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -214,7 +214,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 30.2,
|
||||
"duration_ms": 27.39,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -237,7 +237,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 31.31,
|
||||
"duration_ms": 38.16,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -266,7 +266,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 29.79,
|
||||
"duration_ms": 28.81,
|
||||
"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 | 28.94 | 33 | 0.0 | pass |
|
||||
| skill-package-contract | with_skill | command | local-output-eval-runner | 29.02 | 73 | 100.0 | pass |
|
||||
| output-eval-expectation | baseline | command | local-output-eval-runner | 28.44 | 36 | 0.0 | pass |
|
||||
| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.01 | 80 | 100.0 | pass |
|
||||
| ir-before-packaging | baseline | command | local-output-eval-runner | 28.44 | 33 | 0.0 | pass |
|
||||
| ir-before-packaging | with_skill | command | local-output-eval-runner | 28.58 | 80 | 100.0 | pass |
|
||||
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 27.57 | 36 | 0.0 | pass |
|
||||
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 30.2 | 65 | 100.0 | pass |
|
||||
| file-backed-governed-package | baseline | command | local-output-eval-runner | 31.31 | 37 | 0.0 | pass |
|
||||
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 29.79 | 98 | 100.0 | pass |
|
||||
| skill-package-contract | baseline | command | local-output-eval-runner | 29.88 | 33 | 0.0 | pass |
|
||||
| skill-package-contract | with_skill | command | local-output-eval-runner | 29.59 | 73 | 100.0 | pass |
|
||||
| output-eval-expectation | baseline | command | local-output-eval-runner | 29.33 | 36 | 0.0 | pass |
|
||||
| output-eval-expectation | with_skill | command | local-output-eval-runner | 27.41 | 80 | 100.0 | pass |
|
||||
| ir-before-packaging | baseline | command | local-output-eval-runner | 28.83 | 33 | 0.0 | pass |
|
||||
| ir-before-packaging | with_skill | command | local-output-eval-runner | 28.11 | 80 | 100.0 | pass |
|
||||
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 28.25 | 36 | 0.0 | pass |
|
||||
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 27.39 | 65 | 100.0 | pass |
|
||||
| file-backed-governed-package | baseline | command | local-output-eval-runner | 38.16 | 37 | 0.0 | pass |
|
||||
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 28.81 | 98 | 100.0 | pass |
|
||||
|
||||
## Next Fixes
|
||||
|
||||
|
||||
@@ -8,8 +8,8 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f",
|
||||
"archive_entry_count": 683,
|
||||
"archive_sha256": "29c3154e87935a6ffc92a42b6e270da17ef0aa2d3c156c518770ece272d4b58b",
|
||||
"archive_entry_count": 684,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
- Package directory: `dist`
|
||||
- Targets: `4 / 4` adapters present
|
||||
- Archive present: `True`
|
||||
- Archive SHA256: `69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f`
|
||||
- Archive SHA256: `29c3154e87935a6ffc92a42b6e270da17ef0aa2d3c156c518770ece272d4b58b`
|
||||
- Failures: `0`
|
||||
- Warnings: `0`
|
||||
|
||||
|
||||
@@ -5,7 +5,7 @@
|
||||
"root": ".",
|
||||
"summary": {
|
||||
"target_python": "3.11",
|
||||
"file_count": 223,
|
||||
"file_count": 224,
|
||||
"issue_count": 0,
|
||||
"syntax_error_count": 0,
|
||||
"fstring_311_violation_count": 0,
|
||||
@@ -580,6 +580,12 @@
|
||||
"issue_count": 0,
|
||||
"issues": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/review_studio_gate_helpers.py",
|
||||
"ok": true,
|
||||
"issue_count": 0,
|
||||
"issues": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/review_studio_gates.py",
|
||||
"ok": true,
|
||||
|
||||
@@ -6,7 +6,7 @@ Generated at: `2026-06-13`
|
||||
|
||||
- decision: `pass`
|
||||
- target python: `3.11`
|
||||
- files scanned: `223`
|
||||
- files scanned: `224`
|
||||
- issues: `0`
|
||||
- syntax errors: `0`
|
||||
- f-string 3.11 violations: `0`
|
||||
|
||||
@@ -21,8 +21,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc",
|
||||
"archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f"
|
||||
"package_sha256": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652",
|
||||
"archive_sha256": "29c3154e87935a6ffc92a42b6e270da17ef0aa2d3c156c518770ece272d4b58b"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -53,7 +53,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f",
|
||||
"archive_sha256": "29c3154e87935a6ffc92a42b6e270da17ef0aa2d3c156c518770ece272d4b58b",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -78,7 +78,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc"
|
||||
"package_sha256": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -6,8 +6,8 @@
|
||||
- Maturity: `governed`
|
||||
- Owner: `Yao Team`
|
||||
- License: `MIT`
|
||||
- Package SHA256: `712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc`
|
||||
- Archive SHA256: `69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f`
|
||||
- Package SHA256: `58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652`
|
||||
- Archive SHA256: `29c3154e87935a6ffc92a42b6e270da17ef0aa2d3c156c518770ece272d4b58b`
|
||||
- Install simulated: `True`
|
||||
|
||||
## Compatibility
|
||||
|
||||
@@ -740,12 +740,12 @@
|
||||
|
||||
<section>
|
||||
<h2>核心指标</h2>
|
||||
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>4 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>145 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>223 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>683 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>146 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>224 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>684 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 496411/120000; top deferred scripts 435517; 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; 145 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; 223 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>220 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 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 7/13 pass; 6 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 496603/120000; top deferred scripts 435709; 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; 146 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; 224 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>221 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 7/13 pass; 6 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
@@ -812,17 +812,17 @@
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 496411/120000; top deferred scripts 435517; resource governance governed; quality density 131.3</p></div>
|
||||
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 496603/120000; top deferred scripts 435709; 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>145</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>712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc</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>146</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>58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652</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>
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>Python 兼容</h2><dl class='kv-grid'><div><dt>目标 Python</dt><dd>3.11</dd></div><div><dt>文件数</dt><dd>223</dd></div><div><dt>问题数</dt><dd>0</dd></div><div><dt>语法错误</dt><dd>0</dd></div><div><dt>F-string 3.11</dt><dd>0</dd></div></dl></div>
|
||||
<div class="panel"><h2>Python 兼容</h2><dl class='kv-grid'><div><dt>目标 Python</dt><dd>3.11</dd></div><div><dt>文件数</dt><dd>224</dd></div><div><dt>问题数</dt><dd>0</dd></div><div><dt>语法错误</dt><dd>0</dd></div><div><dt>F-string 3.11</dt><dd>0</dd></div></dl></div>
|
||||
<div class="panel"><h2>解释器边界</h2><p>CI 和发布审查以 Python 3.11 兼容为底线；本地更高版本允许的新语法不能绕过兼容门禁。</p></div>
|
||||
</section>
|
||||
|
||||
@@ -882,8 +882,8 @@
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>4</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (7/13 pass, 6 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 (7/13 pass, 6 blocked)</span></li></ul></div>
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
@@ -908,7 +908,7 @@
|
||||
|
||||
<section id="release" class="twocol">
|
||||
<div class="panel"><h2>发布路线</h2><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p></div>
|
||||
<div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd>是</dd></div><div><dt>Zip 条目</dt><dd>683</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f</code></dd></div></dl></div>
|
||||
<div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd>是</dd></div><div><dt>Zip 条目</dt><dd>684</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>29c3154e87935a6ffc92a42b6e270da17ef0aa2d3c156c518770ece272d4b58b</code></dd></div></dl></div>
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
|
||||
+200
-164
File diff suppressed because it is too large
Load Diff
+23
-23
@@ -512,7 +512,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 145
|
||||
"file_count": 146
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -527,7 +527,7 @@
|
||||
"file_count": 235
|
||||
}
|
||||
],
|
||||
"file_count": 448,
|
||||
"file_count": 449,
|
||||
"folder_count": 4,
|
||||
"distribution": [
|
||||
{
|
||||
@@ -552,7 +552,7 @@
|
||||
},
|
||||
{
|
||||
"label": "scripts",
|
||||
"value": 145
|
||||
"value": 146
|
||||
},
|
||||
{
|
||||
"label": "evals",
|
||||
@@ -682,7 +682,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 145
|
||||
"file_count": 146
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -996,13 +996,13 @@
|
||||
"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": "5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0",
|
||||
"source_contract_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc",
|
||||
"archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f",
|
||||
"evidence_bundle_sha256": "bb4d7860b90e023f5d97f74a87d091f6c4437190dfe7dacb5c740d7675136199",
|
||||
"source_contract_sha256": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652",
|
||||
"archive_sha256": "29c3154e87935a6ffc92a42b6e270da17ef0aa2d3c156c518770ece272d4b58b",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -1020,11 +1020,11 @@
|
||||
"world_class_source_pass_count": 7,
|
||||
"world_class_source_blocked_count": 6,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 56
|
||||
},
|
||||
"commit": "d5beede0a62dab0f0780be283a274ed8a5be9dc4",
|
||||
"commit": "5e2163683a483b9b0b0180219994495fc84eb272",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
|
||||
@@ -1108,9 +1108,9 @@
|
||||
"failures": []
|
||||
},
|
||||
"trust_security": {
|
||||
"scanned_files": 237,
|
||||
"script_count": 145,
|
||||
"internal_module_count": 59,
|
||||
"scanned_files": 238,
|
||||
"script_count": 146,
|
||||
"internal_module_count": 60,
|
||||
"secret_findings": 0,
|
||||
"dependency_files": [
|
||||
"requirements-ci.txt"
|
||||
@@ -1128,8 +1128,8 @@
|
||||
"help_smoke_failed_count": 0,
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 237,
|
||||
"package_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc"
|
||||
"package_hash_file_count": 238,
|
||||
"package_sha256": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1167,7 +1167,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc",
|
||||
"package_sha256": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652",
|
||||
"archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -1204,7 +1204,7 @@
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
},
|
||||
"generated_at": "2026-06-13"
|
||||
"generated_at": "2026-06-17"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": []
|
||||
@@ -1215,8 +1215,8 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f",
|
||||
"archive_entry_count": 683,
|
||||
"archive_sha256": "29c3154e87935a6ffc92a42b6e270da17ef0aa2d3c156c518770ece272d4b58b",
|
||||
"archive_entry_count": 684,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
@@ -1227,7 +1227,7 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"archive_present": true,
|
||||
"archive_entry_count": 683,
|
||||
"archive_entry_count": 684,
|
||||
"archive_extracted": true,
|
||||
"entrypoint_loaded": true,
|
||||
"manifest_loaded": true,
|
||||
@@ -1299,7 +1299,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc"
|
||||
"to": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -2,9 +2,9 @@
|
||||
"ok": true,
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"scanned_files": 237,
|
||||
"script_count": 145,
|
||||
"internal_module_count": 59,
|
||||
"scanned_files": 238,
|
||||
"script_count": 146,
|
||||
"internal_module_count": 60,
|
||||
"secret_findings": 0,
|
||||
"dependency_files": [
|
||||
"requirements-ci.txt"
|
||||
@@ -22,8 +22,8 @@
|
||||
"help_smoke_failed_count": 0,
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 237,
|
||||
"package_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc"
|
||||
"package_hash_file_count": 238,
|
||||
"package_sha256": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": [],
|
||||
@@ -1306,6 +1306,20 @@
|
||||
"network_urls": [],
|
||||
"network_hosts": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/review_studio_gate_helpers.py",
|
||||
"interface": "internal-module",
|
||||
"interface_declared": true,
|
||||
"interface_reason": "Imported by review_studio_gates.py to keep reusable Review Studio gate helpers out of the main gate sequence.",
|
||||
"has_argparse": false,
|
||||
"has_main_guard": false,
|
||||
"uses_input": false,
|
||||
"uses_network": false,
|
||||
"uses_file_write": false,
|
||||
"uses_subprocess": false,
|
||||
"network_urls": [],
|
||||
"network_hosts": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/review_studio_gates.py",
|
||||
"interface": "internal-module",
|
||||
@@ -2111,7 +2125,7 @@
|
||||
"checked_count": 86,
|
||||
"passed_count": 86,
|
||||
"failed_count": 0,
|
||||
"skipped_count": 59,
|
||||
"skipped_count": 60,
|
||||
"failed_scripts": [],
|
||||
"results": [
|
||||
{
|
||||
@@ -3052,6 +3066,10 @@
|
||||
"path": "scripts/review_studio_gate_contract.py",
|
||||
"reason": "internal module"
|
||||
},
|
||||
{
|
||||
"path": "scripts/review_studio_gate_helpers.py",
|
||||
"reason": "internal module"
|
||||
},
|
||||
{
|
||||
"path": "scripts/review_studio_gates.py",
|
||||
"reason": "internal module"
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
# Security Trust Report
|
||||
|
||||
- OK: `True`
|
||||
- Scanned files: `237`
|
||||
- Scripts: `145`
|
||||
- Internal script modules: `59`
|
||||
- Scanned files: `238`
|
||||
- Scripts: `146`
|
||||
- Internal script modules: `60`
|
||||
- Secret findings: `0`
|
||||
- Network-capable scripts: `3`
|
||||
- Network policy covered scripts: `3`
|
||||
@@ -15,8 +15,8 @@
|
||||
- CLI help smoke failures: `0`
|
||||
- Interactive scripts: `0`
|
||||
- Package hash scope: `source-contract-without-generated-reports`
|
||||
- Package hash files: `237`
|
||||
- Package SHA256: `712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc`
|
||||
- Package hash files: `238`
|
||||
- Package SHA256: `58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652`
|
||||
|
||||
## Failures
|
||||
|
||||
@@ -152,6 +152,7 @@
|
||||
| scripts/review_studio_data.py | internal-module | True | False | False | False | False | False | False | Imported by render_review_studio.py to load Review Studio source reports and metric cards. |
|
||||
| scripts/review_studio_formatting.py | internal-module | True | False | False | False | False | False | False | Imported by render_review_studio.py to format report dictionaries as audit UI panels. |
|
||||
| scripts/review_studio_gate_contract.py | internal-module | True | False | False | False | False | False | False | Imported by review_studio_gates.py for stable gate scoring and contract checks. |
|
||||
| scripts/review_studio_gate_helpers.py | internal-module | True | False | False | False | False | False | False | Imported by review_studio_gates.py to keep reusable Review Studio gate helpers out of the main gate sequence. |
|
||||
| scripts/review_studio_gates.py | internal-module | True | False | False | False | False | False | False | Imported by render_review_studio.py to keep Review Studio gate evaluation separate from HTML rendering. |
|
||||
| scripts/review_studio_layout.py | internal-module | True | False | False | False | False | False | False | Imported by render_review_studio.py to keep Review Studio layout and CSS out of gate logic. |
|
||||
| scripts/review_studio_output_review.py | internal-module | True | False | False | False | False | False | False | Imported by render_review_studio.py to render output review checklist cards. |
|
||||
|
||||
@@ -921,7 +921,7 @@
|
||||
<p><span data-lang="zh-CN">让 reviewer 快速确认关键文件、目录和资产分布。</span><span data-lang="en">Lets reviewers confirm key files, directories, and asset distribution quickly.</span></p>
|
||||
</div>
|
||||
<div class="two-col">
|
||||
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text data-lang="zh-CN" x="20" y="30" class="chart-title">资产分布</text><text data-lang="en" x="20" y="30" class="chart-title">Asset Distribution</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-0.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-1.1" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-1.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="19.0 81.0" stroke-dashoffset="-2.2" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="78.8 21.2" stroke-dashoffset="-21.2" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">448项</text><text data-lang="en" x="130" y="136" text-anchor="middle">448 items</text><text data-lang="zh-CN" x="235" y="78">SKILL.md</text><text data-lang="en" x="235" y="78">SKILL.md</text><text data-lang="zh-CN" x="235" y="100">README.md</text><text data-lang="en" x="235" y="100">README.md</text><text data-lang="zh-CN" x="235" y="122">agents/interface.yaml</text><text data-lang="en" x="235" y="122">agents/interface.yaml</text><text data-lang="zh-CN" x="235" y="144">manifest.json</text><text data-lang="en" x="235" y="144">manifest.json</text><text data-lang="zh-CN" x="235" y="166">references</text><text data-lang="en" x="235" y="166">references</text><text data-lang="zh-CN" x="235" y="188">scripts</text><text data-lang="en" x="235" y="188">scripts</text></svg><figcaption><span data-lang="zh-CN">资产分布图展示当前包体的文件和目录重心。</span><span data-lang="en">The asset distribution chart shows where files and directories are concentrated.</span></figcaption></figure>
|
||||
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text data-lang="zh-CN" x="20" y="30" class="chart-title">资产分布</text><text data-lang="en" x="20" y="30" class="chart-title">Asset Distribution</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-0.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-1.1" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-1.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="18.9 81.1" stroke-dashoffset="-2.2" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="78.9 21.1" stroke-dashoffset="-21.1" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">449项</text><text data-lang="en" x="130" y="136" text-anchor="middle">449 items</text><text data-lang="zh-CN" x="235" y="78">SKILL.md</text><text data-lang="en" x="235" y="78">SKILL.md</text><text data-lang="zh-CN" x="235" y="100">README.md</text><text data-lang="en" x="235" y="100">README.md</text><text data-lang="zh-CN" x="235" y="122">agents/interface.yaml</text><text data-lang="en" x="235" y="122">agents/interface.yaml</text><text data-lang="zh-CN" x="235" y="144">manifest.json</text><text data-lang="en" x="235" y="144">manifest.json</text><text data-lang="zh-CN" x="235" y="166">references</text><text data-lang="en" x="235" y="166">references</text><text data-lang="zh-CN" x="235" y="188">scripts</text><text data-lang="en" x="235" y="188">scripts</text></svg><figcaption><span data-lang="zh-CN">资产分布图展示当前包体的文件和目录重心。</span><span data-lang="en">The asset distribution chart shows where files and directories are concentrated.</span></figcaption></figure>
|
||||
<table>
|
||||
<thead><tr><th><span data-lang="zh-CN">路径</span><span data-lang="en">Path</span></th><th><span data-lang="zh-CN">作用</span><span data-lang="en">Role</span></th><th><span data-lang="zh-CN">类型</span><span data-lang="en">Type</span></th></tr></thead>
|
||||
<tbody><tr><td>SKILL.md</td><td><span data-lang="zh-CN">Skill 入口文件</span><span data-lang="en">Skill entrypoint</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>README.md</td><td><span data-lang="zh-CN">人类可读使用说明</span><span data-lang="en">Human-readable usage guide</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>agents/interface.yaml</td><td><span data-lang="zh-CN">跨平台接口元数据</span><span data-lang="en">Neutral interface metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>manifest.json</td><td><span data-lang="zh-CN">生命周期与打包元数据</span><span data-lang="en">Lifecycle and portability metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>references</td><td><span data-lang="zh-CN">扩展指导与复用资料</span><span data-lang="en">Extended guidance and reusable notes</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>scripts</td><td><span data-lang="zh-CN">确定性脚本或本地工具</span><span data-lang="en">Deterministic helpers or local tooling</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>evals</td><td><span data-lang="zh-CN">触发与质量检查</span><span data-lang="en">Trigger and quality checks</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>reports</td><td><span data-lang="zh-CN">生成的证据与总结报告</span><span data-lang="en">Generated evidence and overview artifacts</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr></tbody>
|
||||
|
||||
@@ -512,7 +512,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 145
|
||||
"file_count": 146
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -527,7 +527,7 @@
|
||||
"file_count": 235
|
||||
}
|
||||
],
|
||||
"file_count": 448,
|
||||
"file_count": 449,
|
||||
"folder_count": 4,
|
||||
"distribution": [
|
||||
{
|
||||
@@ -552,7 +552,7 @@
|
||||
},
|
||||
{
|
||||
"label": "scripts",
|
||||
"value": 145
|
||||
"value": 146
|
||||
},
|
||||
{
|
||||
"label": "evals",
|
||||
@@ -686,7 +686,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 145
|
||||
"file_count": 146
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -1000,13 +1000,13 @@
|
||||
"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": "5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0",
|
||||
"source_contract_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc",
|
||||
"archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f",
|
||||
"evidence_bundle_sha256": "bb4d7860b90e023f5d97f74a87d091f6c4437190dfe7dacb5c740d7675136199",
|
||||
"source_contract_sha256": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652",
|
||||
"archive_sha256": "29c3154e87935a6ffc92a42b6e270da17ef0aa2d3c156c518770ece272d4b58b",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -1024,11 +1024,11 @@
|
||||
"world_class_source_pass_count": 7,
|
||||
"world_class_source_blocked_count": 6,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 56
|
||||
},
|
||||
"commit": "d5beede0a62dab0f0780be283a274ed8a5be9dc4",
|
||||
"commit": "5e2163683a483b9b0b0180219994495fc84eb272",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
|
||||
@@ -1112,9 +1112,9 @@
|
||||
"failures": []
|
||||
},
|
||||
"trust_security": {
|
||||
"scanned_files": 237,
|
||||
"script_count": 145,
|
||||
"internal_module_count": 59,
|
||||
"scanned_files": 238,
|
||||
"script_count": 146,
|
||||
"internal_module_count": 60,
|
||||
"secret_findings": 0,
|
||||
"dependency_files": [
|
||||
"requirements-ci.txt"
|
||||
@@ -1132,8 +1132,8 @@
|
||||
"help_smoke_failed_count": 0,
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 237,
|
||||
"package_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc"
|
||||
"package_hash_file_count": 238,
|
||||
"package_sha256": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1171,7 +1171,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc",
|
||||
"package_sha256": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652",
|
||||
"archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -1208,7 +1208,7 @@
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
},
|
||||
"generated_at": "2026-06-13"
|
||||
"generated_at": "2026-06-17"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": []
|
||||
@@ -1219,8 +1219,8 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f",
|
||||
"archive_entry_count": 683,
|
||||
"archive_sha256": "29c3154e87935a6ffc92a42b6e270da17ef0aa2d3c156c518770ece272d4b58b",
|
||||
"archive_entry_count": 684,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
@@ -1231,7 +1231,7 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"archive_present": true,
|
||||
"archive_entry_count": 683,
|
||||
"archive_entry_count": 684,
|
||||
"archive_extracted": true,
|
||||
"entrypoint_loaded": true,
|
||||
"manifest_loaded": true,
|
||||
@@ -1303,7 +1303,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc"
|
||||
"to": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -133,13 +133,13 @@ Next move: add real client or installer permission enforcement integration.
|
||||
| Output Eval | `5` cases, with-skill pass rate `100`, baseline pass rate `0`, with file-backed, near-neighbor, boundary coverage, `10` local command-runner execution runs, `0` recorded fixture runs, `0` provider model-executed runs in root release evidence, `10` estimated token counts, provider runner v0 available, `5` blind A/B review pairs, a generated `reports/output_review_decisions.json` template, `0 / 5` reviewer decisions pending, `0` answer keys revealed, and `5` pending answers hidden |
|
||||
| Runtime Conformance | `5 / 5` targets passing |
|
||||
| Target Compiler | `5 / 5` compiled target contracts generated for OpenAI, Claude, generic, Agent Skills compatible, and VS Code / Copilot outputs, including target permission contracts and target-native behavior contracts |
|
||||
| Trust | `0` secret findings, `1` pinned dependency file, `59` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `86 / 86` CLI help smoke checks passing across `145` scripts, source-contract hash scope explicit |
|
||||
| Trust | `0` secret findings, `1` pinned dependency file, `60` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `86 / 86` CLI help smoke checks passing across `146` scripts, source-contract hash scope explicit |
|
||||
| Permission Governance | `3 / 3` required high-permission capabilities approved, `0` missing, `0` invalid, `0` expired |
|
||||
| Runtime Permission Probes | `4 / 4` target adapters probed, `0` native-enforcement adapters, `4` explicit metadata fallbacks, `4` residual risks retained for reviewer visibility |
|
||||
| Skill Atlas | `12` scanned skills, `1` actionable root skill, `1` telemetry report, `0` actionable route collisions, `0` actionable owner gaps, `0` actionable stale skills, `0` actionable drift signals, `24` scoped non-actionable issue signals retained for visibility |
|
||||
| Registry Audit | package metadata generated with version, owner, license, source checksum, archive checksum, Skill IR provenance, and compatibility matrix |
|
||||
| Package Verification | `4 / 4` target adapters present, archive verified, `683` zip entries, `0` failures, `0` warnings |
|
||||
| Install Simulation | archive with `683` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings |
|
||||
| Package Verification | `4 / 4` target adapters present, archive verified, `684` zip entries, `0` failures, `0` warnings |
|
||||
| Install Simulation | archive with `684` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings |
|
||||
| Local Install Sync Preflight | `make sync-local-install` and `make sync-active-install` rebuild the package first, then sync only after install simulation passes with `12` enforced installer permission checks and `0` permission failures |
|
||||
| Upgrade Check | current package declares `minor` over the 1.0.0 baseline, recommended bump is `minor`, and release notes include added targets plus checksum changes |
|
||||
| Adoption Drift | `1` metadata-only review event, `1` adoption sample, adoption `100`, risk band `low`; optional `yao.py` CLI capture, external client `telemetry-emit`, `5` `telemetry-hooks` recipes, Browser/Chrome native messaging host, and validated external JSONL import are available but off by default for reproducible release evidence; raw `reports/telemetry_events.jsonl` is gitignored and blocked from zip packages |
|
||||
|
||||
@@ -921,7 +921,7 @@
|
||||
<p><span data-lang="zh-CN">让 reviewer 快速确认关键文件、目录和资产分布。</span><span data-lang="en">Lets reviewers confirm key files, directories, and asset distribution quickly.</span></p>
|
||||
</div>
|
||||
<div class="two-col">
|
||||
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text data-lang="zh-CN" x="20" y="30" class="chart-title">资产分布</text><text data-lang="en" x="20" y="30" class="chart-title">Asset Distribution</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-0.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-1.1" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-1.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="19.0 81.0" stroke-dashoffset="-2.2" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="78.8 21.2" stroke-dashoffset="-21.2" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">448项</text><text data-lang="en" x="130" y="136" text-anchor="middle">448 items</text><text data-lang="zh-CN" x="235" y="78">SKILL.md</text><text data-lang="en" x="235" y="78">SKILL.md</text><text data-lang="zh-CN" x="235" y="100">README.md</text><text data-lang="en" x="235" y="100">README.md</text><text data-lang="zh-CN" x="235" y="122">agents/interface.yaml</text><text data-lang="en" x="235" y="122">agents/interface.yaml</text><text data-lang="zh-CN" x="235" y="144">manifest.json</text><text data-lang="en" x="235" y="144">manifest.json</text><text data-lang="zh-CN" x="235" y="166">references</text><text data-lang="en" x="235" y="166">references</text><text data-lang="zh-CN" x="235" y="188">scripts</text><text data-lang="en" x="235" y="188">scripts</text></svg><figcaption><span data-lang="zh-CN">资产分布图展示当前包体的文件和目录重心。</span><span data-lang="en">The asset distribution chart shows where files and directories are concentrated.</span></figcaption></figure>
|
||||
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text data-lang="zh-CN" x="20" y="30" class="chart-title">资产分布</text><text data-lang="en" x="20" y="30" class="chart-title">Asset Distribution</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-0.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-1.1" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-1.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="18.9 81.1" stroke-dashoffset="-2.2" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="78.9 21.1" stroke-dashoffset="-21.1" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">449项</text><text data-lang="en" x="130" y="136" text-anchor="middle">449 items</text><text data-lang="zh-CN" x="235" y="78">SKILL.md</text><text data-lang="en" x="235" y="78">SKILL.md</text><text data-lang="zh-CN" x="235" y="100">README.md</text><text data-lang="en" x="235" y="100">README.md</text><text data-lang="zh-CN" x="235" y="122">agents/interface.yaml</text><text data-lang="en" x="235" y="122">agents/interface.yaml</text><text data-lang="zh-CN" x="235" y="144">manifest.json</text><text data-lang="en" x="235" y="144">manifest.json</text><text data-lang="zh-CN" x="235" y="166">references</text><text data-lang="en" x="235" y="166">references</text><text data-lang="zh-CN" x="235" y="188">scripts</text><text data-lang="en" x="235" y="188">scripts</text></svg><figcaption><span data-lang="zh-CN">资产分布图展示当前包体的文件和目录重心。</span><span data-lang="en">The asset distribution chart shows where files and directories are concentrated.</span></figcaption></figure>
|
||||
<table>
|
||||
<thead><tr><th><span data-lang="zh-CN">路径</span><span data-lang="en">Path</span></th><th><span data-lang="zh-CN">作用</span><span data-lang="en">Role</span></th><th><span data-lang="zh-CN">类型</span><span data-lang="en">Type</span></th></tr></thead>
|
||||
<tbody><tr><td>SKILL.md</td><td><span data-lang="zh-CN">Skill 入口文件</span><span data-lang="en">Skill entrypoint</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>README.md</td><td><span data-lang="zh-CN">人类可读使用说明</span><span data-lang="en">Human-readable usage guide</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>agents/interface.yaml</td><td><span data-lang="zh-CN">跨平台接口元数据</span><span data-lang="en">Neutral interface metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>manifest.json</td><td><span data-lang="zh-CN">生命周期与打包元数据</span><span data-lang="en">Lifecycle and portability metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>references</td><td><span data-lang="zh-CN">扩展指导与复用资料</span><span data-lang="en">Extended guidance and reusable notes</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>scripts</td><td><span data-lang="zh-CN">确定性脚本或本地工具</span><span data-lang="en">Deterministic helpers or local tooling</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>evals</td><td><span data-lang="zh-CN">触发与质量检查</span><span data-lang="en">Trigger and quality checks</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>reports</td><td><span data-lang="zh-CN">生成的证据与总结报告</span><span data-lang="en">Generated evidence and overview artifacts</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr></tbody>
|
||||
|
||||
+23
-23
@@ -511,7 +511,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 145
|
||||
"file_count": 146
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -526,7 +526,7 @@
|
||||
"file_count": 235
|
||||
}
|
||||
],
|
||||
"file_count": 448,
|
||||
"file_count": 449,
|
||||
"folder_count": 4,
|
||||
"distribution": [
|
||||
{
|
||||
@@ -551,7 +551,7 @@
|
||||
},
|
||||
{
|
||||
"label": "scripts",
|
||||
"value": 145
|
||||
"value": 146
|
||||
},
|
||||
{
|
||||
"label": "evals",
|
||||
@@ -681,7 +681,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 145
|
||||
"file_count": 146
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -995,13 +995,13 @@
|
||||
"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": "5d4d3f13e4b19870cbd85e50ad56ae3d426c425df6dd63dfd458c62f5c7967e0",
|
||||
"source_contract_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc",
|
||||
"archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f",
|
||||
"evidence_bundle_sha256": "bb4d7860b90e023f5d97f74a87d091f6c4437190dfe7dacb5c740d7675136199",
|
||||
"source_contract_sha256": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652",
|
||||
"archive_sha256": "29c3154e87935a6ffc92a42b6e270da17ef0aa2d3c156c518770ece272d4b58b",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -1019,11 +1019,11 @@
|
||||
"world_class_source_pass_count": 7,
|
||||
"world_class_source_blocked_count": 6,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 56
|
||||
},
|
||||
"commit": "d5beede0a62dab0f0780be283a274ed8a5be9dc4",
|
||||
"commit": "5e2163683a483b9b0b0180219994495fc84eb272",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
|
||||
@@ -1107,9 +1107,9 @@
|
||||
"failures": []
|
||||
},
|
||||
"trust_security": {
|
||||
"scanned_files": 237,
|
||||
"script_count": 145,
|
||||
"internal_module_count": 59,
|
||||
"scanned_files": 238,
|
||||
"script_count": 146,
|
||||
"internal_module_count": 60,
|
||||
"secret_findings": 0,
|
||||
"dependency_files": [
|
||||
"requirements-ci.txt"
|
||||
@@ -1127,8 +1127,8 @@
|
||||
"help_smoke_failed_count": 0,
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 237,
|
||||
"package_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc"
|
||||
"package_hash_file_count": 238,
|
||||
"package_sha256": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1166,7 +1166,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc",
|
||||
"package_sha256": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652",
|
||||
"archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -1203,7 +1203,7 @@
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
},
|
||||
"generated_at": "2026-06-13"
|
||||
"generated_at": "2026-06-17"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": []
|
||||
@@ -1214,8 +1214,8 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f",
|
||||
"archive_entry_count": 683,
|
||||
"archive_sha256": "29c3154e87935a6ffc92a42b6e270da17ef0aa2d3c156c518770ece272d4b58b",
|
||||
"archive_entry_count": 684,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
@@ -1226,7 +1226,7 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"archive_present": true,
|
||||
"archive_entry_count": 683,
|
||||
"archive_entry_count": 684,
|
||||
"archive_extracted": true,
|
||||
"entrypoint_loaded": true,
|
||||
"manifest_loaded": true,
|
||||
@@ -1298,7 +1298,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc"
|
||||
"to": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -154,6 +154,7 @@
|
||||
"scripts/review_studio_data.py",
|
||||
"scripts/review_studio_formatting.py",
|
||||
"scripts/review_studio_gate_contract.py",
|
||||
"scripts/review_studio_gate_helpers.py",
|
||||
"scripts/review_studio_gates.py",
|
||||
"scripts/review_studio_layout.py",
|
||||
"scripts/review_studio_output_review.py",
|
||||
|
||||
@@ -197,7 +197,7 @@
|
||||
"key": "trust-security",
|
||||
"label": "Trust Security",
|
||||
"status": "pass",
|
||||
"current": "secrets 0; scripts 145; help failures 0",
|
||||
"current": "secrets 0; scripts 146; help failures 0",
|
||||
"target": "Secrets, scripts, dependencies, permissions, and package hash are reviewable",
|
||||
"evidence": [
|
||||
{
|
||||
@@ -285,7 +285,7 @@
|
||||
"key": "registry-distribution",
|
||||
"label": "Registry Distribution",
|
||||
"status": "pass",
|
||||
"current": "zip entries 683; install failures 0; permission failures 0",
|
||||
"current": "zip entries 684; install failures 0; permission failures 0",
|
||||
"target": "Package metadata, archive checksum, package verification, and install simulation pass",
|
||||
"evidence": [
|
||||
{
|
||||
|
||||
@@ -23,11 +23,11 @@ Generated at: `2026-06-13`
|
||||
| Human Adjudication | human-required | 0/5 decisions; pending 5 | Real reviewer decisions recorded before claiming output review completion | Record real A/B choices in the decision template, then regenerate adjudication. |
|
||||
| Benchmark Reproducibility | pass | artifacts 25; missing 0; failures 3 | Public methodology, reproducible commands, required artifacts, and failure disclosure are machine-checkable | Keep the manifest current with every benchmark, package, and release evidence change. |
|
||||
| Runtime Conformance | pass | 5/5 targets pass | Target package structure, metadata, relative paths, and degradation notes pass | Keep target conformance fixtures updated as platform contracts change. |
|
||||
| Trust Security | pass | secrets 0; scripts 145; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. |
|
||||
| Trust Security | pass | secrets 0; scripts 146; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. |
|
||||
| Permission Metadata | pass | 4/4 target probes pass; metadata fallback 4; installer enforcement 4 | Packaged adapters expose explicit permission metadata, residual risks, and installer enforcement evidence when available | Preserve residual-risk notes until real native enforcement exists. |
|
||||
| Native Permission Enforcement | external-required | native-enforced targets 0; installer-enforced targets 4 | At least one target/client enforces approved permissions at runtime | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. |
|
||||
| Skill Atlas | pass | 12 skills; actionable collisions 0 | Workspace catalog, route overlap, stale/owner gaps, drift, and no-route opportunities | Feed real drift data into Atlas once client telemetry is installed. |
|
||||
| Registry Distribution | pass | zip entries 683; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. |
|
||||
| Registry Distribution | pass | zip entries 684; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. |
|
||||
| Review Studio | pass | decision review; warnings 3; score 91 | One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations | Resolve human/external warning gates before claiming full release readiness. |
|
||||
| Telemetry Drift | pass | events 1; risk low; recipes 5 | Local-first metadata-only event contract, aggregate drift report, hook recipes, and import path | Keep raw JSONL out of distributed packages and use aggregate reports for Atlas. |
|
||||
| Native Client Telemetry | external-required | external source events 0; adoption samples 1 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. |
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"item_count": 21,
|
||||
@@ -130,7 +130,7 @@
|
||||
"label": "Trust Security",
|
||||
"status": "pass",
|
||||
"objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
|
||||
"current": "145 scripts; secrets 0; help failures 0",
|
||||
"current": "146 scripts; secrets 0; help failures 0",
|
||||
"command": "python3 scripts/yao.py trust .",
|
||||
"test": "python3 tests/verify_trust_check.py",
|
||||
"evidence": [
|
||||
@@ -204,7 +204,7 @@
|
||||
"label": "Registry Distribution",
|
||||
"status": "pass",
|
||||
"objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
|
||||
"current": "archive entries 683; install failures 0",
|
||||
"current": "archive entries 684; install failures 0",
|
||||
"command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .",
|
||||
"test": "python3 tests/verify_registry_audit.py",
|
||||
"evidence": [
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Skill OS 2.0 Blueprint Coverage
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
@@ -26,9 +26,9 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
|
||||
| Skill IR | `pass` | schema 2.0.0; targets 5 | `python3 scripts/yao.py skill-ir .` | `python3 tests/verify_skill_ir.py` |
|
||||
| Output Eval Lab | `pass` | 5 cases; delta 100.0; execution 10 | `python3 scripts/yao.py output-exec . && python3 scripts/yao.py output-review .` | `python3 tests/verify_output_eval_lab.py` |
|
||||
| Runtime Conformance | `pass` | 5/5 targets pass | `python3 scripts/yao.py conformance .` | `python3 tests/verify_conformance_suite.py` |
|
||||
| Trust Security | `pass` | 145 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
|
||||
| Trust Security | `pass` | 146 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
|
||||
| Skill Atlas | `pass` | 12 scanned skills; actionable collisions 0 | `python3 scripts/yao.py skill-atlas --workspace-root .` | `python3 tests/verify_skill_atlas.py` |
|
||||
| Registry Distribution | `pass` | archive entries 683; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` |
|
||||
| Registry Distribution | `pass` | archive entries 684; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` |
|
||||
| Review Studio | `pass` | 16 gates; decision review; warnings 3 | `python3 scripts/yao.py review-studio .` | `python3 tests/verify_review_studio.py` |
|
||||
| Telemetry Drift | `pass` | events 1; recipes 5; risk low | `python3 scripts/yao.py telemetry-hooks . && python3 scripts/yao.py adoption-drift .` | `python3 tests/verify_telemetry_hooks.py` |
|
||||
|
||||
|
||||
@@ -70,12 +70,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "69ad979695a4b08bfcb0dd44f7b8f6b6553465f416b950bb2f7d90e6c669427f"
|
||||
"to": "29c3154e87935a6ffc92a42b6e270da17ef0aa2d3c156c518770ece272d4b58b"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "712f00ca2202e81f1a88fc46adea462b248dcec996e09125f7c0fc97af5476fc"
|
||||
"to": "58b8388686e47011bcd943ed528b172b2f5991430fcc41eb3f86146f47498652"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"evidence_item_count": 4,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# World-Class Evidence Preflight
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
|
||||
@@ -0,0 +1,140 @@
|
||||
"""Helper functions for Review Studio gate evaluation."""
|
||||
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
try:
|
||||
from trust_check import permission_governance_status as compute_permission_governance_status
|
||||
from trust_check import script_inventory as trust_script_inventory
|
||||
except ImportError: # pragma: no cover
|
||||
compute_permission_governance_status = None
|
||||
trust_script_inventory = None
|
||||
|
||||
from review_studio_gate_contract import min_output_cases
|
||||
|
||||
|
||||
SCRIPT_INTERFACE = "internal-module"
|
||||
SCRIPT_INTERFACE_REASON = "Imported by review_studio_gates.py to keep reusable Review Studio gate helpers out of the main gate sequence."
|
||||
|
||||
|
||||
def load_json(path: Path) -> dict[str, Any]:
|
||||
if not path.exists():
|
||||
return {}
|
||||
try:
|
||||
payload = json.loads(path.read_text(encoding="utf-8"))
|
||||
except json.JSONDecodeError:
|
||||
return {}
|
||||
return payload if isinstance(payload, dict) else {}
|
||||
|
||||
|
||||
def link_from(output_html: Path, target: Path) -> str:
|
||||
return os.path.relpath(target.resolve(), output_html.parent.resolve())
|
||||
|
||||
|
||||
def report_link(output_html: Path, skill_dir: Path, rel_path: str) -> str:
|
||||
return link_from(output_html, skill_dir / rel_path)
|
||||
|
||||
|
||||
def gate(key: str, label: str, status: str, detail: str, evidence: str, link: str = "") -> dict[str, str]:
|
||||
return {
|
||||
"key": key,
|
||||
"label": label,
|
||||
"status": status,
|
||||
"detail": detail,
|
||||
"evidence": evidence,
|
||||
"link": link,
|
||||
}
|
||||
|
||||
|
||||
def target_maturity(skill_dir: Path, overview: dict[str, Any]) -> str:
|
||||
manifest = load_json(skill_dir / "manifest.json")
|
||||
if manifest.get("maturity_tier"):
|
||||
return str(manifest["maturity_tier"])
|
||||
metadata = overview.get("metadata", {}) if isinstance(overview, dict) else {}
|
||||
if metadata.get("maturity_tier"):
|
||||
return str(metadata["maturity_tier"])
|
||||
return "scaffold"
|
||||
|
||||
|
||||
def fallback_permission_governance(skill_dir: Path) -> dict[str, Any]:
|
||||
if compute_permission_governance_status is None or trust_script_inventory is None:
|
||||
return {}
|
||||
try:
|
||||
scripts = trust_script_inventory(skill_dir)
|
||||
return compute_permission_governance_status(skill_dir, scripts)
|
||||
except Exception:
|
||||
return {}
|
||||
|
||||
|
||||
def build_output_lab_gate(
|
||||
skill_dir: Path,
|
||||
output_html: Path,
|
||||
maturity: str,
|
||||
output: dict[str, Any],
|
||||
output_execution: dict[str, Any],
|
||||
output_blind: dict[str, Any],
|
||||
output_review: dict[str, Any],
|
||||
) -> dict[str, str]:
|
||||
output_summary = output.get("summary", {})
|
||||
output_execution_summary = output_execution.get("summary", {})
|
||||
output_blind_summary = output_blind.get("summary", {})
|
||||
output_review_summary = output_review.get("summary", {})
|
||||
required_cases = min_output_cases(maturity)
|
||||
case_count = int(output_summary.get("case_count", 0) or 0)
|
||||
file_backed = int(output_summary.get("file_backed_case_count", 0) or 0)
|
||||
near_neighbor = int(output_summary.get("near_neighbor_case_count", 0) or 0)
|
||||
boundary = int(output_summary.get("boundary_case_count", 0) or 0)
|
||||
blind_pair_count = int(output_blind_summary.get("pair_count", 0) or 0)
|
||||
execution_variant_count = int(output_execution_summary.get("variant_run_count", 0) or 0)
|
||||
execution_command_count = int(output_execution_summary.get("command_executed_count", 0) or 0)
|
||||
execution_model_count = int(output_execution_summary.get("model_executed_count", 0) or 0)
|
||||
execution_recorded_count = int(output_execution_summary.get("recorded_fixture_count", 0) or 0)
|
||||
review_pair_count = int(output_review_summary.get("pair_count", 0) or 0)
|
||||
review_judgment_count = int(output_review_summary.get("judgment_count", 0) or 0)
|
||||
review_pending_count = int(output_review_summary.get("pending_count", 0) or 0)
|
||||
review_invalid_count = int(output_review_summary.get("invalid_decision_count", 0) or 0)
|
||||
production_like = maturity in {"production", "library", "governed"}
|
||||
blind_missing = production_like and (not output_blind or blind_pair_count < case_count)
|
||||
review_missing = production_like and case_count > 0 and not output_review
|
||||
review_pending = production_like and bool(output_review) and review_pending_count > 0
|
||||
execution_failed = bool(output_execution) and (
|
||||
not output_execution.get("ok", True) or int(output_execution_summary.get("failure_count", 0) or 0) > 0
|
||||
)
|
||||
review_invalid = bool(output_review) and (not output_review.get("ok", True) or review_invalid_count > 0)
|
||||
output_blocked = (
|
||||
not output.get("ok", False)
|
||||
or not output_summary.get("gate_pass", False)
|
||||
or case_count < required_cases
|
||||
or execution_failed
|
||||
or review_invalid
|
||||
)
|
||||
output_warn = file_backed == 0 or near_neighbor == 0 or boundary == 0 or blind_missing or review_missing or review_pending
|
||||
if not output:
|
||||
output_status = "warn"
|
||||
output_detail = "output eval scorecard is missing; generate it before production review"
|
||||
else:
|
||||
output_status = "block" if output_blocked else ("warn" if output_warn else "pass")
|
||||
output_detail = (
|
||||
f"{case_count}/{required_cases} cases; with-skill {output_summary.get('with_skill_pass_rate', 0)}; "
|
||||
f"baseline {output_summary.get('baseline_pass_rate', 0)}; file-backed {file_backed}; near-neighbor {near_neighbor}; "
|
||||
f"blind A/B {blind_pair_count}"
|
||||
+ (
|
||||
f"; exec {execution_variant_count}; command {execution_command_count}; "
|
||||
f"model {execution_model_count}; recorded {execution_recorded_count}"
|
||||
if output_execution
|
||||
else ""
|
||||
)
|
||||
+ (f"; reviewed {review_judgment_count}/{review_pair_count}" if output_review else "")
|
||||
+ (f"; review pending {review_pending_count}" if review_pending else "")
|
||||
+ ("; review adjudication missing" if review_missing else "")
|
||||
)
|
||||
return gate(
|
||||
"output-lab",
|
||||
"输出实验",
|
||||
output_status,
|
||||
output_detail,
|
||||
"reports/output_quality_scorecard.json",
|
||||
report_link(output_html, skill_dir, "reports/output_quality_scorecard.md"),
|
||||
)
|
||||
+30
-133
@@ -1,18 +1,9 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Gate evaluation contract for Review Studio 2.0."""
|
||||
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
try:
|
||||
from trust_check import permission_governance_status as compute_permission_governance_status
|
||||
from trust_check import script_inventory as trust_script_inventory
|
||||
except ImportError: # pragma: no cover
|
||||
compute_permission_governance_status = None
|
||||
trust_script_inventory = None
|
||||
|
||||
from review_studio_gate_contract import (
|
||||
GATE_WEIGHTS,
|
||||
REVIEW_STUDIO_GATE_KEYS,
|
||||
@@ -22,6 +13,13 @@ from review_studio_gate_contract import (
|
||||
status_label,
|
||||
weighted_score,
|
||||
)
|
||||
from review_studio_gate_helpers import (
|
||||
build_output_lab_gate,
|
||||
fallback_permission_governance,
|
||||
gate,
|
||||
report_link,
|
||||
target_maturity,
|
||||
)
|
||||
|
||||
|
||||
SCRIPT_INTERFACE = "internal-module"
|
||||
@@ -30,54 +28,6 @@ SCRIPT_INTERFACE_REASON = "Imported by render_review_studio.py to keep Review St
|
||||
|
||||
ROOT = Path(__file__).resolve().parent.parent
|
||||
|
||||
def _load_json(path: Path) -> dict[str, Any]:
|
||||
if not path.exists():
|
||||
return {}
|
||||
try:
|
||||
payload = json.loads(path.read_text(encoding="utf-8"))
|
||||
except json.JSONDecodeError:
|
||||
return {}
|
||||
return payload if isinstance(payload, dict) else {}
|
||||
|
||||
|
||||
def _link_from(output_html: Path, target: Path) -> str:
|
||||
return os.path.relpath(target.resolve(), output_html.parent.resolve())
|
||||
|
||||
|
||||
def _report_link(output_html: Path, skill_dir: Path, rel_path: str) -> str:
|
||||
return _link_from(output_html, skill_dir / rel_path)
|
||||
|
||||
|
||||
def gate(key: str, label: str, status: str, detail: str, evidence: str, link: str = "") -> dict[str, str]:
|
||||
return {
|
||||
"key": key,
|
||||
"label": label,
|
||||
"status": status,
|
||||
"detail": detail,
|
||||
"evidence": evidence,
|
||||
"link": link,
|
||||
}
|
||||
|
||||
|
||||
def target_maturity(skill_dir: Path, overview: dict[str, Any]) -> str:
|
||||
manifest = _load_json(skill_dir / "manifest.json")
|
||||
if manifest.get("maturity_tier"):
|
||||
return str(manifest["maturity_tier"])
|
||||
metadata = overview.get("metadata", {}) if isinstance(overview, dict) else {}
|
||||
if metadata.get("maturity_tier"):
|
||||
return str(metadata["maturity_tier"])
|
||||
return "scaffold"
|
||||
|
||||
|
||||
def fallback_permission_governance(skill_dir: Path) -> dict[str, Any]:
|
||||
if compute_permission_governance_status is None or trust_script_inventory is None:
|
||||
return {}
|
||||
try:
|
||||
scripts = trust_script_inventory(skill_dir)
|
||||
return compute_permission_governance_status(skill_dir, scripts)
|
||||
except Exception:
|
||||
return {}
|
||||
|
||||
|
||||
def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, Any]]) -> list[dict[str, str]]:
|
||||
overview = data["overview"]
|
||||
@@ -94,7 +44,7 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An
|
||||
intent_status,
|
||||
f"intent confidence {intent_score}/100; {intent.get('recommended_action', 'review current intent frame')}",
|
||||
"reports/intent-confidence.json",
|
||||
_report_link(output_html, skill_dir, "reports/intent-confidence.md"),
|
||||
report_link(output_html, skill_dir, "reports/intent-confidence.md"),
|
||||
)
|
||||
)
|
||||
|
||||
@@ -115,72 +65,19 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An
|
||||
route_status,
|
||||
route_detail,
|
||||
"reports/route_scorecard.json",
|
||||
_report_link(output_html, skill_dir, "reports/route_scorecard.md"),
|
||||
report_link(output_html, skill_dir, "reports/route_scorecard.md"),
|
||||
)
|
||||
)
|
||||
|
||||
output = data["output_quality"]
|
||||
output_execution = data["output_execution"]
|
||||
output_blind = data["output_blind_review"]
|
||||
output_review = data["output_review_adjudication"]
|
||||
output_summary = output.get("summary", {})
|
||||
output_execution_summary = output_execution.get("summary", {})
|
||||
output_blind_summary = output_blind.get("summary", {})
|
||||
output_review_summary = output_review.get("summary", {})
|
||||
required_cases = min_output_cases(maturity)
|
||||
case_count = int(output_summary.get("case_count", 0) or 0)
|
||||
file_backed = int(output_summary.get("file_backed_case_count", 0) or 0)
|
||||
near_neighbor = int(output_summary.get("near_neighbor_case_count", 0) or 0)
|
||||
boundary = int(output_summary.get("boundary_case_count", 0) or 0)
|
||||
blind_pair_count = int(output_blind_summary.get("pair_count", 0) or 0)
|
||||
execution_variant_count = int(output_execution_summary.get("variant_run_count", 0) or 0)
|
||||
execution_command_count = int(output_execution_summary.get("command_executed_count", 0) or 0)
|
||||
execution_model_count = int(output_execution_summary.get("model_executed_count", 0) or 0)
|
||||
execution_recorded_count = int(output_execution_summary.get("recorded_fixture_count", 0) or 0)
|
||||
review_pair_count = int(output_review_summary.get("pair_count", 0) or 0)
|
||||
review_judgment_count = int(output_review_summary.get("judgment_count", 0) or 0)
|
||||
review_pending_count = int(output_review_summary.get("pending_count", 0) or 0)
|
||||
review_invalid_count = int(output_review_summary.get("invalid_decision_count", 0) or 0)
|
||||
blind_missing = maturity in {"production", "library", "governed"} and (not output_blind or blind_pair_count < case_count)
|
||||
review_missing = maturity in {"production", "library", "governed"} and case_count > 0 and not output_review
|
||||
review_pending = maturity in {"production", "library", "governed"} and bool(output_review) and review_pending_count > 0
|
||||
execution_failed = bool(output_execution) and (not output_execution.get("ok", True) or int(output_execution_summary.get("failure_count", 0) or 0) > 0)
|
||||
review_invalid = bool(output_review) and (not output_review.get("ok", True) or review_invalid_count > 0)
|
||||
output_blocked = (
|
||||
not output.get("ok", False)
|
||||
or not output_summary.get("gate_pass", False)
|
||||
or case_count < required_cases
|
||||
or execution_failed
|
||||
or review_invalid
|
||||
)
|
||||
output_warn = file_backed == 0 or near_neighbor == 0 or boundary == 0 or blind_missing or review_missing or review_pending
|
||||
if not output:
|
||||
output_status = "warn"
|
||||
output_detail = "output eval scorecard is missing; generate it before production review"
|
||||
else:
|
||||
output_status = "block" if output_blocked else ("warn" if output_warn else "pass")
|
||||
output_detail = (
|
||||
f"{case_count}/{required_cases} cases; with-skill {output_summary.get('with_skill_pass_rate', 0)}; "
|
||||
f"baseline {output_summary.get('baseline_pass_rate', 0)}; file-backed {file_backed}; near-neighbor {near_neighbor}; "
|
||||
f"blind A/B {blind_pair_count}"
|
||||
+ (
|
||||
f"; exec {execution_variant_count}; command {execution_command_count}; "
|
||||
f"model {execution_model_count}; recorded {execution_recorded_count}"
|
||||
if output_execution
|
||||
else ""
|
||||
)
|
||||
+ (f"; reviewed {review_judgment_count}/{review_pair_count}" if output_review else "")
|
||||
+ (f"; review pending {review_pending_count}" if review_pending else "")
|
||||
+ ("; review adjudication missing" if review_missing else "")
|
||||
)
|
||||
gates.append(
|
||||
gate(
|
||||
"output-lab",
|
||||
"输出实验",
|
||||
output_status,
|
||||
output_detail,
|
||||
"reports/output_quality_scorecard.json",
|
||||
_report_link(output_html, skill_dir, "reports/output_quality_scorecard.md"),
|
||||
build_output_lab_gate(
|
||||
skill_dir,
|
||||
output_html,
|
||||
maturity,
|
||||
data["output_quality"],
|
||||
data["output_execution"],
|
||||
data["output_blind_review"],
|
||||
data["output_review_adjudication"],
|
||||
)
|
||||
)
|
||||
|
||||
@@ -214,7 +111,7 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An
|
||||
context_status,
|
||||
context_detail,
|
||||
"reports/context_budget.json",
|
||||
_report_link(output_html, skill_dir, "reports/context_budget.md"),
|
||||
report_link(output_html, skill_dir, "reports/context_budget.md"),
|
||||
)
|
||||
)
|
||||
|
||||
@@ -234,7 +131,7 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An
|
||||
conformance_status,
|
||||
conformance_detail,
|
||||
"reports/conformance_matrix.json",
|
||||
_report_link(output_html, skill_dir, "reports/conformance_matrix.md"),
|
||||
report_link(output_html, skill_dir, "reports/conformance_matrix.md"),
|
||||
)
|
||||
)
|
||||
|
||||
@@ -258,7 +155,7 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An
|
||||
trust_status,
|
||||
trust_detail,
|
||||
"reports/security_trust_report.json",
|
||||
_report_link(output_html, skill_dir, "reports/security_trust_report.md"),
|
||||
report_link(output_html, skill_dir, "reports/security_trust_report.md"),
|
||||
)
|
||||
)
|
||||
|
||||
@@ -290,7 +187,7 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An
|
||||
python_compat_status,
|
||||
python_compat_detail,
|
||||
"reports/python_compatibility.json",
|
||||
_report_link(output_html, skill_dir, "reports/python_compatibility.md"),
|
||||
report_link(output_html, skill_dir, "reports/python_compatibility.md"),
|
||||
)
|
||||
)
|
||||
|
||||
@@ -330,7 +227,7 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An
|
||||
architecture_status,
|
||||
architecture_detail,
|
||||
"reports/architecture_maintainability.json",
|
||||
_report_link(output_html, skill_dir, "reports/architecture_maintainability.md"),
|
||||
report_link(output_html, skill_dir, "reports/architecture_maintainability.md"),
|
||||
)
|
||||
)
|
||||
|
||||
@@ -364,7 +261,7 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An
|
||||
permission_status,
|
||||
permission_detail,
|
||||
"reports/security_trust_report.json + security/permission_policy.json",
|
||||
_report_link(output_html, skill_dir, "security/permission_policy.md"),
|
||||
report_link(output_html, skill_dir, "security/permission_policy.md"),
|
||||
)
|
||||
)
|
||||
|
||||
@@ -392,7 +289,7 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An
|
||||
runtime_permission_status,
|
||||
runtime_permission_detail,
|
||||
"reports/runtime_permission_probes.json",
|
||||
_report_link(output_html, skill_dir, "reports/runtime_permission_probes.md"),
|
||||
report_link(output_html, skill_dir, "reports/runtime_permission_probes.md"),
|
||||
)
|
||||
)
|
||||
|
||||
@@ -426,7 +323,7 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An
|
||||
atlas_status,
|
||||
atlas_detail,
|
||||
"reports/skill_atlas.json",
|
||||
_report_link(output_html, skill_dir, "reports/skill_atlas.html"),
|
||||
report_link(output_html, skill_dir, "reports/skill_atlas.html"),
|
||||
)
|
||||
)
|
||||
|
||||
@@ -489,7 +386,7 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An
|
||||
adoption_status,
|
||||
adoption_detail,
|
||||
"reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly",
|
||||
_report_link(output_html, skill_dir, "reports/adoption_drift_report.md"),
|
||||
report_link(output_html, skill_dir, "reports/adoption_drift_report.md"),
|
||||
)
|
||||
)
|
||||
|
||||
@@ -524,7 +421,7 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An
|
||||
waiver_status,
|
||||
waiver_detail,
|
||||
"reports/review_waivers.json",
|
||||
_report_link(output_html, skill_dir, "reports/review_waivers.md"),
|
||||
report_link(output_html, skill_dir, "reports/review_waivers.md"),
|
||||
)
|
||||
)
|
||||
|
||||
@@ -567,7 +464,7 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An
|
||||
world_class_status,
|
||||
world_class_detail,
|
||||
"reports/world_class_evidence_ledger.json",
|
||||
_report_link(output_html, skill_dir, "reports/world_class_evidence_ledger.md"),
|
||||
report_link(output_html, skill_dir, "reports/world_class_evidence_ledger.md"),
|
||||
)
|
||||
)
|
||||
|
||||
@@ -607,7 +504,7 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An
|
||||
registry_status,
|
||||
registry_detail,
|
||||
"reports/registry_audit.json + reports/install_simulation.json",
|
||||
_report_link(output_html, skill_dir, "reports/registry_audit.md"),
|
||||
report_link(output_html, skill_dir, "reports/registry_audit.md"),
|
||||
)
|
||||
)
|
||||
|
||||
@@ -639,7 +536,7 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An
|
||||
release_status,
|
||||
release_detail,
|
||||
"reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md",
|
||||
_report_link(output_html, skill_dir, "reports/promotion_decisions.md") if promotion else str(migration_path),
|
||||
report_link(output_html, skill_dir, "reports/promotion_decisions.md") if promotion else str(migration_path),
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
@@ -202,6 +202,7 @@
|
||||
"scripts/review_studio_data.py",
|
||||
"scripts/review_studio_formatting.py",
|
||||
"scripts/review_studio_gate_contract.py",
|
||||
"scripts/review_studio_gate_helpers.py",
|
||||
"scripts/review_studio_gates.py",
|
||||
"scripts/review_studio_layout.py",
|
||||
"scripts/review_studio_output_review.py",
|
||||
|
||||
@@ -110,6 +110,7 @@
|
||||
"scripts/review_studio_data.py",
|
||||
"scripts/review_studio_formatting.py",
|
||||
"scripts/review_studio_gate_contract.py",
|
||||
"scripts/review_studio_gate_helpers.py",
|
||||
"scripts/review_studio_gates.py",
|
||||
"scripts/review_studio_layout.py",
|
||||
"scripts/review_studio_output_review.py",
|
||||
|
||||
@@ -40,7 +40,7 @@ def main() -> None:
|
||||
assert payload["summary"]["decision"] == "pass", payload["summary"]
|
||||
assert payload["summary"]["early_watch_line_threshold"] == 600, payload["summary"]
|
||||
assert payload["summary"]["watch_line_threshold"] == 720, payload["summary"]
|
||||
assert payload["summary"]["early_watchlist_count"] >= 4, payload["summary"]
|
||||
assert payload["summary"]["early_watchlist_count"] >= 3, payload["summary"]
|
||||
assert payload["summary"]["watchlist_count"] == 0, payload["summary"]
|
||||
assert payload["summary"]["hotspot_count"] == 0, payload["summary"]
|
||||
assert payload["summary"]["blocker_count"] == 0, payload["summary"]
|
||||
@@ -59,6 +59,7 @@ def main() -> None:
|
||||
assert "scripts/build_skill_atlas.py" not in early_watch_paths, payload["early_watchlist"]
|
||||
assert "scripts/skill_report_model.py" not in early_watch_paths, payload["early_watchlist"]
|
||||
assert "scripts/render_review_studio.py" not in early_watch_paths, payload["early_watchlist"]
|
||||
assert "scripts/review_studio_gates.py" not in early_watch_paths, payload["early_watchlist"]
|
||||
renderer_lines = len((ROOT / "scripts" / "render_review_studio.py").read_text(encoding="utf-8").splitlines())
|
||||
action_module = (ROOT / "scripts" / "review_studio_actions.py").read_text(encoding="utf-8")
|
||||
action_lines = len(action_module.splitlines())
|
||||
@@ -76,7 +77,7 @@ def main() -> None:
|
||||
assert "No file-size hotspots found." in markdown, markdown
|
||||
assert "No near-threshold files found." in markdown, markdown
|
||||
assert "## Early Watchlist" in markdown, markdown
|
||||
assert "- early watchlist: `4`" in markdown, markdown
|
||||
assert "- early watchlist: `3`" in markdown, markdown
|
||||
early_watch_markdown = markdown.split("## Early Watchlist", 1)[1].split("## Largest Files", 1)[0]
|
||||
assert "scripts/render_review_viewer.py" not in markdown, markdown
|
||||
assert "scripts/render_skill_os2_coverage.py" not in markdown, markdown
|
||||
@@ -84,6 +85,7 @@ def main() -> None:
|
||||
assert "scripts/build_skill_atlas.py" not in early_watch_markdown, early_watch_markdown
|
||||
assert "scripts/skill_report_model.py" not in early_watch_markdown, early_watch_markdown
|
||||
assert "scripts/render_review_studio.py" not in early_watch_markdown, early_watch_markdown
|
||||
assert "scripts/review_studio_gates.py" not in early_watch_markdown, early_watch_markdown
|
||||
assert "Do not split a file only for line count" in markdown, markdown
|
||||
|
||||
blocker_proc = subprocess.run(
|
||||
|
||||
@@ -236,7 +236,7 @@ def main() -> None:
|
||||
assert full_payload["data"]["python_compatibility"]["summary"]["issue_count"] == 0, full_payload["data"]["python_compatibility"]
|
||||
assert full_payload["data"]["architecture_maintainability"]["summary"]["hotspot_count"] == 0, full_payload["data"]["architecture_maintainability"]
|
||||
assert full_payload["data"]["architecture_maintainability"]["summary"]["watchlist_count"] == 0, full_payload["data"]["architecture_maintainability"]
|
||||
assert full_payload["data"]["architecture_maintainability"]["summary"]["early_watchlist_count"] >= 4, full_payload["data"]["architecture_maintainability"]
|
||||
assert full_payload["data"]["architecture_maintainability"]["summary"]["early_watchlist_count"] >= 3, full_payload["data"]["architecture_maintainability"]
|
||||
assert full_payload["data"]["architecture_maintainability"]["summary"]["blocker_count"] == 0, full_payload["data"]["architecture_maintainability"]
|
||||
action_keys = {item["gate_key"] for item in full_payload["review_actions"]}
|
||||
assert action_keys == {"output-lab", "review-waivers", "world-class-evidence"}, full_payload["review_actions"]
|
||||
|
||||
@@ -103,6 +103,7 @@ def main() -> None:
|
||||
"scripts/reference_synthesis_markdown.py",
|
||||
"scripts/review_studio_formatting.py",
|
||||
"scripts/review_studio_gate_contract.py",
|
||||
"scripts/review_studio_gate_helpers.py",
|
||||
"scripts/review_studio_gates.py",
|
||||
"scripts/review_studio_layout.py",
|
||||
"scripts/review_studio_panels.py",
|
||||
@@ -144,6 +145,7 @@ def main() -> None:
|
||||
assert "reference_synthesis_markdown.py" not in warning_text, payload["warnings"]
|
||||
assert "review_studio_formatting.py" not in warning_text, payload["warnings"]
|
||||
assert "review_studio_gate_contract.py" not in warning_text, payload["warnings"]
|
||||
assert "review_studio_gate_helpers.py" not in warning_text, payload["warnings"]
|
||||
assert "review_studio_gates.py" not in warning_text, payload["warnings"]
|
||||
assert "review_studio_layout.py" not in warning_text, payload["warnings"]
|
||||
assert "review_studio_panels.py" not in warning_text, payload["warnings"]
|
||||
|
||||
Reference in New Issue
Block a user