Extract world-class evidence consistency checks
This commit is contained in:
yaojingang
+1
-1
@@ -16,7 +16,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086"
|
||||
"package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -16,8 +16,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137"
|
||||
"package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -48,7 +48,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"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": "2026-06-15T16:57:40Z",
|
||||
"generated_at": "2026-06-15T17:08:05Z",
|
||||
"skill_dir": ".",
|
||||
"privacy_contract": {
|
||||
"storage": "local-first",
|
||||
|
||||
@@ -4,10 +4,10 @@
|
||||
"generated_at": "2026-06-16",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"python_file_count": 173,
|
||||
"script_file_count": 110,
|
||||
"python_file_count": 174,
|
||||
"script_file_count": 111,
|
||||
"test_file_count": 63,
|
||||
"internal_module_count": 31,
|
||||
"internal_module_count": 32,
|
||||
"cli_script_count": 81,
|
||||
"command_handler_count": 64,
|
||||
"entrypoint_command_handler_count": 18,
|
||||
@@ -16,7 +16,7 @@
|
||||
"watch_line_threshold": 720,
|
||||
"block_line_threshold": 1500,
|
||||
"largest_file_lines": 899,
|
||||
"watchlist_count": 9,
|
||||
"watchlist_count": 8,
|
||||
"hotspot_count": 0,
|
||||
"blocker_count": 0,
|
||||
"decision": "pass"
|
||||
@@ -29,13 +29,6 @@
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_evidence_consistency.py",
|
||||
"lines": 859,
|
||||
"kind": "cli-script",
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_parser.py",
|
||||
"lines": 810,
|
||||
@@ -105,6 +98,13 @@
|
||||
"kind": "internal-module",
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_review_viewer.py",
|
||||
"lines": 685,
|
||||
"kind": "cli-script",
|
||||
"severity": "pass",
|
||||
"recommendation": "Split viewer data assembly from HTML section rendering."
|
||||
}
|
||||
],
|
||||
"watchlist": [
|
||||
@@ -115,13 +115,6 @@
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_evidence_consistency.py",
|
||||
"lines": 859,
|
||||
"kind": "cli-script",
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_parser.py",
|
||||
"lines": 810,
|
||||
|
||||
@@ -5,17 +5,17 @@ Generated at: `2026-06-16`
|
||||
## Summary
|
||||
|
||||
- decision: `pass`
|
||||
- python files: `173`
|
||||
- scripts: `110`
|
||||
- python files: `174`
|
||||
- scripts: `111`
|
||||
- tests: `63`
|
||||
- internal modules: `31`
|
||||
- internal modules: `32`
|
||||
- CLI scripts: `81`
|
||||
- Yao CLI command handlers: `64`
|
||||
- entrypoint command handlers: `18`
|
||||
- command modules: `6`
|
||||
- largest file lines: `899`
|
||||
- watch threshold lines: `720`
|
||||
- watchlist: `9`
|
||||
- watchlist: `8`
|
||||
- hotspots: `0`
|
||||
- blockers: `0`
|
||||
|
||||
@@ -30,7 +30,6 @@ No file-size hotspots found.
|
||||
| File | Lines | Kind | Recommended next split |
|
||||
| --- | ---: | --- | --- |
|
||||
| `tests/verify_yao_cli.py` | `899` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
|
||||
| `scripts/render_evidence_consistency.py` | `859` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
|
||||
| `scripts/yao_cli_parser.py` | `810` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
|
||||
| `scripts/skill_report_layout.py` | `808` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
|
||||
| `scripts/skill_report_model.py` | `801` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
|
||||
@@ -44,7 +43,6 @@ No file-size hotspots found.
|
||||
| File | Lines | Kind | Severity |
|
||||
| --- | ---: | --- | --- |
|
||||
| `tests/verify_yao_cli.py` | `899` | `test` | `pass` |
|
||||
| `scripts/render_evidence_consistency.py` | `859` | `cli-script` | `pass` |
|
||||
| `scripts/yao_cli_parser.py` | `810` | `internal-module` | `pass` |
|
||||
| `scripts/skill_report_layout.py` | `808` | `internal-module` | `pass` |
|
||||
| `scripts/skill_report_model.py` | `801` | `internal-module` | `pass` |
|
||||
@@ -55,6 +53,7 @@ No file-size hotspots found.
|
||||
| `scripts/trust_check.py` | `714` | `internal-module` | `pass` |
|
||||
| `scripts/apply_adaptation.py` | `706` | `cli-script` | `pass` |
|
||||
| `scripts/review_studio_layout.py` | `694` | `internal-module` | `pass` |
|
||||
| `scripts/render_review_viewer.py` | `685` | `cli-script` | `pass` |
|
||||
|
||||
## Release Rule
|
||||
|
||||
|
||||
@@ -3,23 +3,36 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16",
|
||||
"skill_dir": ".",
|
||||
"commit": "09518a4d8637c430311d50a4249913187dbc5057",
|
||||
"commit": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": false,
|
||||
"changed_file_count": 0,
|
||||
"sample": [],
|
||||
"dirty": true,
|
||||
"changed_file_count": 36,
|
||||
"sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" M reports/adoption_drift_report.json",
|
||||
" M reports/architecture_maintainability.json",
|
||||
" M reports/architecture_maintainability.md",
|
||||
" M reports/benchmark_reproducibility.json",
|
||||
" M reports/benchmark_reproducibility.md",
|
||||
" M reports/context_budget.json",
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json",
|
||||
" M reports/evidence_consistency.json",
|
||||
" M reports/install_simulation.json"
|
||||
],
|
||||
"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": 24,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "9bc8af4e6aa04e1f61bc42b432335e0f3500515d3e3d59a6c430ce8c1177fbbe",
|
||||
"source_contract_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"evidence_bundle_sha256": "5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8",
|
||||
"source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 22,
|
||||
@@ -37,14 +50,15 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 36
|
||||
},
|
||||
"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": "09518a4d8637c430311d50a4249913187dbc5057",
|
||||
"ready": false,
|
||||
"commit": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
|
||||
"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": 24,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "9bc8af4e6aa04e1f61bc42b432335e0f3500515d3e3d59a6c430ce8c1177fbbe"
|
||||
"sha256": "5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -137,8 +151,8 @@
|
||||
"label": "output_execution",
|
||||
"path": "reports/output_execution_runs.json",
|
||||
"exists": true,
|
||||
"bytes": 7964,
|
||||
"sha256": "30b43454ef2a4802b13d554100789b1c9c7a1baec9bebcd6fc8cf0ea9830ba41"
|
||||
"bytes": 7967,
|
||||
"sha256": "56430f01ba194dc6dc793eb505f92fec7a8c46e1be4b71976a3d641c9b98c7ec"
|
||||
},
|
||||
{
|
||||
"label": "blind_review",
|
||||
@@ -172,36 +186,36 @@
|
||||
"label": "trust_report",
|
||||
"path": "reports/security_trust_report.json",
|
||||
"exists": true,
|
||||
"bytes": 109099,
|
||||
"sha256": "491354ae881f6682687a62a98c9a4988bbeef931b24565fdf43e6f3a206fd449"
|
||||
"bytes": 109726,
|
||||
"sha256": "a3a6d4e6809ea0b78b8012e37ad68903a54876a06100434efad38ea6bfe9b2bd"
|
||||
},
|
||||
{
|
||||
"label": "python_compatibility",
|
||||
"path": "reports/python_compatibility.json",
|
||||
"exists": true,
|
||||
"bytes": 22887,
|
||||
"sha256": "be0b8550a4404d85a044b3ae612b39d94e8b493723e7aaf02386cace291b8262"
|
||||
"bytes": 23022,
|
||||
"sha256": "e53158aa045e19f51cbf61f4cb8b299c9ac2babeaacd5441ecb911eb99d8089d"
|
||||
},
|
||||
{
|
||||
"label": "registry_audit",
|
||||
"path": "reports/registry_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 3183,
|
||||
"sha256": "870c455a5cd209ff8d9e8793861da074e668083d265230d04e38e8ee0ff1323a"
|
||||
"sha256": "d6b523cc5cbb2d69c35989913e7e68dd4dc2bb04d3bcff88bbcb56fbe8be5084"
|
||||
},
|
||||
{
|
||||
"label": "package_verification",
|
||||
"path": "reports/package_verification.json",
|
||||
"exists": true,
|
||||
"bytes": 19338,
|
||||
"sha256": "c4acb824482d992e0e4339b7eeeb8d23d49da12d3414606222f4916c3ed09df6"
|
||||
"sha256": "ae8ac3872be3299b3d2dc18a29128346a3ecbb579987b1b08156e305237b5119"
|
||||
},
|
||||
{
|
||||
"label": "install_simulation",
|
||||
"path": "reports/install_simulation.json",
|
||||
"exists": true,
|
||||
"bytes": 8604,
|
||||
"sha256": "28ceb014e202269bb96628391d056234794b3570ff25de0ef9bdfd7f755fd85f"
|
||||
"sha256": "3e27a6f7678efe9d94528f811a9d3acf20cf41d6328ad5b5fa0be5714c6396a0"
|
||||
},
|
||||
{
|
||||
"label": "skill_os2_audit",
|
||||
|
||||
@@ -1,19 +1,19 @@
|
||||
# Benchmark Reproducibility
|
||||
|
||||
Generated at: `2026-06-16`
|
||||
Commit: `09518a4d8637c430311d50a4249913187dbc5057`
|
||||
Working tree dirty at generation: `false`
|
||||
Evidence bundle SHA256: `9bc8af4e6aa04e1f61bc42b432335e0f3500515d3e3d59a6c430ce8c1177fbbe`
|
||||
Commit: `391821240ba14f088d0fbe12dd5f1fdca7917a39`
|
||||
Working tree dirty at generation: `true`
|
||||
Evidence bundle SHA256: `5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8`
|
||||
|
||||
## Summary
|
||||
|
||||
- reproducibility ready: `true`
|
||||
- release lock ready: `true`
|
||||
- release lock ready: `false`
|
||||
- methodology complete: `true`
|
||||
- required artifacts: `24`
|
||||
- missing artifacts: `0`
|
||||
- source contract sha256: `f48a71e36bdb`
|
||||
- archive sha256: `00151114ce7f`
|
||||
- source contract sha256: `9fde13846a41`
|
||||
- archive sha256: `83ece575ef74`
|
||||
- output cases: `5`
|
||||
- disclosed failure cases: `3`
|
||||
- reproduction commands: `22`
|
||||
@@ -22,8 +22,8 @@ Evidence bundle SHA256: `9bc8af4e6aa04e1f61bc42b432335e0f3500515d3e3d59a6c430ce8
|
||||
- world-class ready: `false`
|
||||
- world-class source checks: `6` pass / `13` total; `7` blocked
|
||||
- public claim ready: `false`
|
||||
- public claim blockers: `4`
|
||||
- changed files at generation: `0`
|
||||
- public claim blockers: `5`
|
||||
- changed files at generation: `36`
|
||||
|
||||
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: `24` / `24`
|
||||
- sha256: `9bc8af4e6aa04e1f61bc42b432335e0f3500515d3e3d59a6c430ce8c1177fbbe`
|
||||
- sha256: `5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8`
|
||||
|
||||
## Methodology Sections
|
||||
|
||||
@@ -72,16 +73,16 @@ 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 | `30b43454ef2a` |
|
||||
| output_execution | `reports/output_execution_runs.json` | present | `56430f01ba19` |
|
||||
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
|
||||
| review_adjudication | `reports/output_review_adjudication.json` | present | `240485a721af` |
|
||||
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
|
||||
| runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` |
|
||||
| trust_report | `reports/security_trust_report.json` | present | `491354ae881f` |
|
||||
| python_compatibility | `reports/python_compatibility.json` | present | `be0b8550a440` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `870c455a5cd2` |
|
||||
| package_verification | `reports/package_verification.json` | present | `c4acb824482d` |
|
||||
| install_simulation | `reports/install_simulation.json` | present | `28ceb014e202` |
|
||||
| trust_report | `reports/security_trust_report.json` | present | `a3a6d4e6809e` |
|
||||
| python_compatibility | `reports/python_compatibility.json` | present | `e53158aa045e` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `d6b523cc5cbb` |
|
||||
| package_verification | `reports/package_verification.json` | present | `ae8ac3872be3` |
|
||||
| install_simulation | `reports/install_simulation.json` | present | `3e27a6f7678e` |
|
||||
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `57536bc67370` |
|
||||
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `76a3f8e2b12b` |
|
||||
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `1cb74eaa978b` |
|
||||
|
||||
+10
-10
@@ -6,16 +6,16 @@
|
||||
"context_budget_tier": "production",
|
||||
"context_budget_limit": 1000,
|
||||
"skill_body_tokens": 767,
|
||||
"other_text_tokens": 1376201,
|
||||
"other_text_tokens": 1377236,
|
||||
"estimated_initial_load_tokens": 960,
|
||||
"estimated_total_text_tokens": 1376968,
|
||||
"deferred_resource_tokens": 436849,
|
||||
"estimated_total_text_tokens": 1378003,
|
||||
"deferred_resource_tokens": 436837,
|
||||
"deferred_resource_warn_threshold": 120000,
|
||||
"deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 387638,
|
||||
"file_count": 110
|
||||
"estimated_tokens": 387626,
|
||||
"file_count": 111
|
||||
},
|
||||
{
|
||||
"path": "references",
|
||||
@@ -31,8 +31,8 @@
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 387638,
|
||||
"file_count": 110
|
||||
"estimated_tokens": 387626,
|
||||
"file_count": 111
|
||||
}
|
||||
],
|
||||
"deferred_resource_governance": {
|
||||
@@ -54,14 +54,14 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 387638,
|
||||
"file_count": 110,
|
||||
"estimated_tokens": 387626,
|
||||
"file_count": 111,
|
||||
"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": 563,
|
||||
"relevant_file_count": 565,
|
||||
"unused_resource_dirs": [],
|
||||
"quality_signal_points": 130,
|
||||
"quality_density": 135.4
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
| Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status |
|
||||
| --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- |
|
||||
| root | `.` | `production` | 1000 | 960 | 767 | 436849 | `governed` | scripts:387638 | 135.4 | - | ok |
|
||||
| root | `.` | `production` | 1000 | 960 | 767 | 436837 | `governed` | scripts:387626 | 135.4 | - | ok |
|
||||
| complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok |
|
||||
| governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok |
|
||||
|
||||
|
||||
@@ -8,12 +8,12 @@
|
||||
"budget_limit": 1000,
|
||||
"initial_tokens": 960,
|
||||
"skill_body_tokens": 767,
|
||||
"deferred_resource_tokens": 436849,
|
||||
"deferred_resource_tokens": 436837,
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 387638,
|
||||
"file_count": 110
|
||||
"estimated_tokens": 387626,
|
||||
"file_count": 111
|
||||
}
|
||||
],
|
||||
"deferred_resource_governance": {
|
||||
@@ -35,8 +35,8 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 387638,
|
||||
"file_count": 110,
|
||||
"estimated_tokens": 387626,
|
||||
"file_count": 111,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
],
|
||||
|
||||
@@ -47,8 +47,8 @@
|
||||
"key": "benchmark-release-lock-self-consistency",
|
||||
"label": "Benchmark release lock matches git dirty state",
|
||||
"status": "pass",
|
||||
"expected": true,
|
||||
"actual": true,
|
||||
"expected": false,
|
||||
"actual": false,
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json"
|
||||
],
|
||||
@@ -58,8 +58,8 @@
|
||||
"key": "overview-benchmark-commit",
|
||||
"label": "overview embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "09518a4d8637c430311d50a4249913187dbc5057",
|
||||
"actual": "09518a4d8637c430311d50a4249913187dbc5057",
|
||||
"expected": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
|
||||
"actual": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-overview.json"
|
||||
@@ -71,30 +71,30 @@
|
||||
"label": "overview embeds benchmark summary fields",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 24,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"actual": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 24,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
@@ -204,8 +204,8 @@
|
||||
"key": "interpretation-benchmark-commit",
|
||||
"label": "interpretation embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "09518a4d8637c430311d50a4249913187dbc5057",
|
||||
"actual": "09518a4d8637c430311d50a4249913187dbc5057",
|
||||
"expected": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
|
||||
"actual": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-interpretation.json"
|
||||
@@ -217,30 +217,30 @@
|
||||
"label": "interpretation embeds benchmark summary fields",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 24,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"actual": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 24,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
@@ -1322,7 +1322,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 110
|
||||
"file_count": 111
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -1337,7 +1337,7 @@
|
||||
"file_count": 222
|
||||
}
|
||||
],
|
||||
"file_count": 399,
|
||||
"file_count": 400,
|
||||
"folder_count": 4,
|
||||
"distribution": [
|
||||
{
|
||||
@@ -1362,7 +1362,7 @@
|
||||
},
|
||||
{
|
||||
"label": "scripts",
|
||||
"value": 110
|
||||
"value": 111
|
||||
},
|
||||
{
|
||||
"label": "evals",
|
||||
@@ -1410,7 +1410,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 110
|
||||
"file_count": 111
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -1425,7 +1425,7 @@
|
||||
"file_count": 222
|
||||
}
|
||||
],
|
||||
"file_count": 399,
|
||||
"file_count": 400,
|
||||
"folder_count": 4,
|
||||
"distribution": [
|
||||
{
|
||||
@@ -1450,7 +1450,7 @@
|
||||
},
|
||||
{
|
||||
"label": "scripts",
|
||||
"value": 110
|
||||
"value": 111
|
||||
},
|
||||
{
|
||||
"label": "evals",
|
||||
@@ -2025,13 +2025,13 @@
|
||||
"label": "Skill OS 2.0 review summary mirrors current evidence",
|
||||
"status": "pass",
|
||||
"expected": [
|
||||
"score `91`",
|
||||
"score `89`",
|
||||
"`16` gates",
|
||||
"`3` warnings",
|
||||
"`28` declared internal modules",
|
||||
"`82 / 82` CLI help smoke checks passing across `110` scripts",
|
||||
"`617` zip entries",
|
||||
"archive with `617` entries",
|
||||
"`4` warnings",
|
||||
"`29` declared internal modules",
|
||||
"`82 / 82` CLI help smoke checks passing across `111` scripts",
|
||||
"`618` zip entries",
|
||||
"archive with `618` entries",
|
||||
"`12` installer permission checks enforced",
|
||||
"`0` permission failures",
|
||||
"`24` required artifacts",
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
"installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
|
||||
"summary": {
|
||||
"archive_present": true,
|
||||
"archive_entry_count": 617,
|
||||
"archive_entry_count": 618,
|
||||
"archive_extracted": true,
|
||||
"entrypoint_loaded": true,
|
||||
"manifest_loaded": true,
|
||||
|
||||
@@ -34,7 +34,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.28,
|
||||
"duration_ms": 26.79,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -62,7 +62,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.19,
|
||||
"duration_ms": 27.31,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -85,7 +85,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.08,
|
||||
"duration_ms": 26.66,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -113,7 +113,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.33,
|
||||
"duration_ms": 26.21,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -136,7 +136,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 25.89,
|
||||
"duration_ms": 26.62,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -164,7 +164,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.56,
|
||||
"duration_ms": 26.34,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -187,7 +187,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.12,
|
||||
"duration_ms": 26.51,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -214,7 +214,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.4,
|
||||
"duration_ms": 26.37,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -237,7 +237,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.2,
|
||||
"duration_ms": 26.44,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -266,7 +266,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.1,
|
||||
"duration_ms": 26.21,
|
||||
"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 | 26.28 | 33 | 0.0 | pass |
|
||||
| skill-package-contract | with_skill | command | local-output-eval-runner | 26.19 | 73 | 100.0 | pass |
|
||||
| output-eval-expectation | baseline | command | local-output-eval-runner | 26.08 | 36 | 0.0 | pass |
|
||||
| output-eval-expectation | with_skill | command | local-output-eval-runner | 26.33 | 80 | 100.0 | pass |
|
||||
| ir-before-packaging | baseline | command | local-output-eval-runner | 25.89 | 33 | 0.0 | pass |
|
||||
| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.56 | 80 | 100.0 | pass |
|
||||
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.12 | 36 | 0.0 | pass |
|
||||
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.4 | 65 | 100.0 | pass |
|
||||
| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.2 | 37 | 0.0 | pass |
|
||||
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.1 | 98 | 100.0 | pass |
|
||||
| skill-package-contract | baseline | command | local-output-eval-runner | 26.79 | 33 | 0.0 | pass |
|
||||
| skill-package-contract | with_skill | command | local-output-eval-runner | 27.31 | 73 | 100.0 | pass |
|
||||
| output-eval-expectation | baseline | command | local-output-eval-runner | 26.66 | 36 | 0.0 | pass |
|
||||
| output-eval-expectation | with_skill | command | local-output-eval-runner | 26.21 | 80 | 100.0 | pass |
|
||||
| ir-before-packaging | baseline | command | local-output-eval-runner | 26.62 | 33 | 0.0 | pass |
|
||||
| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.34 | 80 | 100.0 | pass |
|
||||
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.51 | 36 | 0.0 | pass |
|
||||
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.37 | 65 | 100.0 | pass |
|
||||
| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.44 | 37 | 0.0 | pass |
|
||||
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.21 | 98 | 100.0 | pass |
|
||||
|
||||
## Next Fixes
|
||||
|
||||
|
||||
@@ -8,8 +8,8 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"archive_entry_count": 617,
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"archive_entry_count": 618,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
- Package directory: `dist`
|
||||
- Targets: `4 / 4` adapters present
|
||||
- Archive present: `True`
|
||||
- Archive SHA256: `00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137`
|
||||
- Archive SHA256: `83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5`
|
||||
- Failures: `0`
|
||||
- Warnings: `0`
|
||||
|
||||
|
||||
@@ -5,7 +5,7 @@
|
||||
"root": ".",
|
||||
"summary": {
|
||||
"target_python": "3.11",
|
||||
"file_count": 176,
|
||||
"file_count": 177,
|
||||
"issue_count": 0,
|
||||
"syntax_error_count": 0,
|
||||
"fstring_311_violation_count": 0,
|
||||
@@ -118,6 +118,12 @@
|
||||
"issue_count": 0,
|
||||
"issues": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/evidence_consistency_world_class.py",
|
||||
"ok": true,
|
||||
"issue_count": 0,
|
||||
"issues": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/export_skill_ir.py",
|
||||
"ok": true,
|
||||
|
||||
@@ -6,7 +6,7 @@ Generated at: `2026-06-16`
|
||||
|
||||
- decision: `pass`
|
||||
- target python: `3.11`
|
||||
- files scanned: `176`
|
||||
- files scanned: `177`
|
||||
- issues: `0`
|
||||
- syntax errors: `0`
|
||||
- f-string 3.11 violations: `0`
|
||||
|
||||
@@ -21,8 +21,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137"
|
||||
"package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -53,7 +53,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"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": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086"
|
||||
"package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -6,8 +6,8 @@
|
||||
- Maturity: `governed`
|
||||
- Owner: `Yao Team`
|
||||
- License: `MIT`
|
||||
- Package SHA256: `f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086`
|
||||
- Archive SHA256: `00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137`
|
||||
- Package SHA256: `9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea`
|
||||
- Archive SHA256: `83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5`
|
||||
- Install simulated: `True`
|
||||
|
||||
## Compatibility
|
||||
|
||||
+13
-13
File diff suppressed because one or more lines are too long
+203
-114
@@ -4,11 +4,11 @@
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"decision": "review",
|
||||
"world_class_score": 91,
|
||||
"world_class_score": 89,
|
||||
"gate_count": 16,
|
||||
"blocker_count": 0,
|
||||
"warning_count": 3,
|
||||
"action_count": 3,
|
||||
"warning_count": 4,
|
||||
"action_count": 4,
|
||||
"annotation_count": 0,
|
||||
"open_annotation_count": 0,
|
||||
"open_annotation_blocker_count": 0,
|
||||
@@ -42,8 +42,8 @@
|
||||
{
|
||||
"key": "context-budget",
|
||||
"label": "上下文",
|
||||
"status": "pass",
|
||||
"detail": "initial load 960/1000; deferred 436849/120000; top deferred scripts 387638; resource governance governed; quality density 135.4",
|
||||
"status": "warn",
|
||||
"detail": "initial load 960/1000; deferred 436837/120000; top deferred scripts 387626; resource governance needs-review; quality density 135.4",
|
||||
"evidence": "reports/context_budget.json",
|
||||
"link": "context_budget.md"
|
||||
},
|
||||
@@ -59,7 +59,7 @@
|
||||
"key": "trust-report",
|
||||
"label": "信任报告",
|
||||
"status": "pass",
|
||||
"detail": "0 secrets; 110 scripts; 3 network-capable scripts; 0 help smoke failures",
|
||||
"detail": "0 secrets; 111 scripts; 3 network-capable scripts; 0 help smoke failures",
|
||||
"evidence": "reports/security_trust_report.json",
|
||||
"link": "security_trust_report.md"
|
||||
},
|
||||
@@ -67,7 +67,7 @@
|
||||
"key": "python-compat",
|
||||
"label": "Python 兼容",
|
||||
"status": "pass",
|
||||
"detail": "Python 3.11; 176 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards",
|
||||
"detail": "Python 3.11; 177 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards",
|
||||
"evidence": "reports/python_compatibility.json",
|
||||
"link": "python_compatibility.md"
|
||||
},
|
||||
@@ -75,7 +75,7 @@
|
||||
"key": "architecture-maintainability",
|
||||
"label": "架构维护",
|
||||
"status": "pass",
|
||||
"detail": "173 Python files; 0 hotspots; 9 watchlist files; 0 blockers; largest 899 lines; 64 CLI handlers; 18 in entrypoint",
|
||||
"detail": "174 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 899 lines; 64 CLI handlers; 18 in entrypoint",
|
||||
"evidence": "reports/architecture_maintainability.json",
|
||||
"link": "architecture_maintainability.md"
|
||||
},
|
||||
@@ -115,7 +115,7 @@
|
||||
"key": "review-waivers",
|
||||
"label": "人工批准",
|
||||
"status": "warn",
|
||||
"detail": "0 active waivers; 1 warning gates still need reviewer decision",
|
||||
"detail": "0 active waivers; 2 warning gates still need reviewer decision",
|
||||
"evidence": "reports/review_waivers.json",
|
||||
"link": "review_waivers.md"
|
||||
},
|
||||
@@ -154,11 +154,19 @@
|
||||
"evidence": "reports/output_quality_scorecard.json",
|
||||
"link": "output_quality_scorecard.md"
|
||||
},
|
||||
{
|
||||
"key": "context-budget",
|
||||
"label": "上下文",
|
||||
"status": "warn",
|
||||
"detail": "initial load 960/1000; deferred 436837/120000; top deferred scripts 387626; resource governance needs-review; quality density 135.4",
|
||||
"evidence": "reports/context_budget.json",
|
||||
"link": "context_budget.md"
|
||||
},
|
||||
{
|
||||
"key": "review-waivers",
|
||||
"label": "人工批准",
|
||||
"status": "warn",
|
||||
"detail": "0 active waivers; 1 warning gates still need reviewer decision",
|
||||
"detail": "0 active waivers; 2 warning gates still need reviewer decision",
|
||||
"evidence": "reports/review_waivers.json",
|
||||
"link": "review_waivers.md"
|
||||
},
|
||||
@@ -235,6 +243,53 @@
|
||||
"verification_command": "python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review",
|
||||
"evidence_steps": []
|
||||
},
|
||||
{
|
||||
"gate_key": "context-budget",
|
||||
"label": "上下文",
|
||||
"status": "warn",
|
||||
"priority": "warning",
|
||||
"summary": "压缩或拆分高成本 deferred resources，保留最小可路由上下文。",
|
||||
"why": "初始加载可以安全，但后续 references、scripts、evals 体量过大时，reviewer 仍需要看到维护和读取成本。",
|
||||
"source_fix": "SKILL.md + references/ + scripts/ + evals/",
|
||||
"source_refs": [
|
||||
{
|
||||
"path": "SKILL.md",
|
||||
"label": "entrypoint",
|
||||
"kind": "source",
|
||||
"line": 9,
|
||||
"exists": true,
|
||||
"link": "../SKILL.md"
|
||||
},
|
||||
{
|
||||
"path": "reports/context_budget.md",
|
||||
"label": "context budget",
|
||||
"kind": "report",
|
||||
"line": 1,
|
||||
"exists": true,
|
||||
"link": "context_budget.md"
|
||||
},
|
||||
{
|
||||
"path": "scripts/resource_boundary_check.py",
|
||||
"label": "resource boundary checker",
|
||||
"kind": "source",
|
||||
"line": 44,
|
||||
"exists": true,
|
||||
"link": "../scripts/resource_boundary_check.py"
|
||||
},
|
||||
{
|
||||
"path": "references/skill-engineering-method.md",
|
||||
"label": "skill engineering method",
|
||||
"kind": "method",
|
||||
"line": 208,
|
||||
"exists": true,
|
||||
"link": "../references/skill-engineering-method.md"
|
||||
}
|
||||
],
|
||||
"evidence": "reports/context_budget.json",
|
||||
"evidence_link": "context_budget.md",
|
||||
"verification_command": "python3 scripts/render_context_reports.py",
|
||||
"evidence_steps": []
|
||||
},
|
||||
{
|
||||
"gate_key": "review-waivers",
|
||||
"label": "人工批准",
|
||||
@@ -1193,7 +1248,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 110
|
||||
"file_count": 111
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -1208,7 +1263,7 @@
|
||||
"file_count": 222
|
||||
}
|
||||
],
|
||||
"file_count": 399,
|
||||
"file_count": 400,
|
||||
"folder_count": 4,
|
||||
"distribution": [
|
||||
{
|
||||
@@ -1233,7 +1288,7 @@
|
||||
},
|
||||
{
|
||||
"label": "scripts",
|
||||
"value": 110
|
||||
"value": 111
|
||||
},
|
||||
{
|
||||
"label": "evals",
|
||||
@@ -1363,7 +1418,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 110
|
||||
"file_count": 111
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -1676,11 +1731,11 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 24,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "9bc8af4e6aa04e1f61bc42b432335e0f3500515d3e3d59a6c430ce8c1177fbbe",
|
||||
"evidence_bundle_sha256": "d4d58b9557d03656a800aad0acee41d5434db006ebbbff2645fbbab80962cc27",
|
||||
"source_contract_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"output_case_count": 5,
|
||||
@@ -1700,11 +1755,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 20
|
||||
},
|
||||
"commit": "09518a4d8637c430311d50a4249913187dbc5057",
|
||||
"commit": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
|
||||
"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.",
|
||||
@@ -1788,9 +1843,9 @@
|
||||
"failures": []
|
||||
},
|
||||
"trust_security": {
|
||||
"scanned_files": 197,
|
||||
"script_count": 110,
|
||||
"internal_module_count": 28,
|
||||
"scanned_files": 198,
|
||||
"script_count": 111,
|
||||
"internal_module_count": 29,
|
||||
"secret_findings": 0,
|
||||
"dependency_files": [
|
||||
"requirements-ci.txt"
|
||||
@@ -1808,8 +1863,8 @@
|
||||
"help_smoke_failed_count": 0,
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 197,
|
||||
"package_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086"
|
||||
"package_hash_file_count": 198,
|
||||
"package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1847,8 +1902,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137"
|
||||
"package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -1879,7 +1934,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -1895,8 +1950,8 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"archive_entry_count": 617,
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"archive_entry_count": 618,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
@@ -1907,7 +1962,7 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"archive_present": true,
|
||||
"archive_entry_count": 617,
|
||||
"archive_entry_count": 618,
|
||||
"archive_extracted": true,
|
||||
"entrypoint_loaded": true,
|
||||
"manifest_loaded": true,
|
||||
@@ -1974,12 +2029,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137"
|
||||
"to": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086"
|
||||
"to": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -4346,7 +4401,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.28,
|
||||
"duration_ms": 26.59,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4374,7 +4429,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.19,
|
||||
"duration_ms": 26.1,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4397,7 +4452,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.08,
|
||||
"duration_ms": 26.12,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4425,7 +4480,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.33,
|
||||
"duration_ms": 28.36,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4448,7 +4503,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 25.89,
|
||||
"duration_ms": 29.38,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4476,7 +4531,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.56,
|
||||
"duration_ms": 28.48,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4499,7 +4554,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.12,
|
||||
"duration_ms": 26.51,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4526,7 +4581,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.4,
|
||||
"duration_ms": 25.88,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4549,7 +4604,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.2,
|
||||
"duration_ms": 25.99,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4578,7 +4633,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.1,
|
||||
"duration_ms": 26.23,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5299,21 +5354,34 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16",
|
||||
"skill_dir": ".",
|
||||
"commit": "09518a4d8637c430311d50a4249913187dbc5057",
|
||||
"commit": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": false,
|
||||
"changed_file_count": 0,
|
||||
"sample": [],
|
||||
"dirty": true,
|
||||
"changed_file_count": 20,
|
||||
"sample": [
|
||||
" M reports/adoption_drift_report.json",
|
||||
" M reports/architecture_maintainability.json",
|
||||
" M reports/architecture_maintainability.md",
|
||||
" M reports/benchmark_reproducibility.json",
|
||||
" M reports/benchmark_reproducibility.md",
|
||||
" M reports/context_budget.json",
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json",
|
||||
" M reports/output_execution_runs.json",
|
||||
" M reports/output_execution_runs.md",
|
||||
" M reports/python_compatibility.json",
|
||||
" M reports/python_compatibility.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": 24,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "9bc8af4e6aa04e1f61bc42b432335e0f3500515d3e3d59a6c430ce8c1177fbbe",
|
||||
"evidence_bundle_sha256": "d4d58b9557d03656a800aad0acee41d5434db006ebbbff2645fbbab80962cc27",
|
||||
"source_contract_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"output_case_count": 5,
|
||||
@@ -5333,14 +5401,15 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 20
|
||||
},
|
||||
"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)",
|
||||
@@ -5349,10 +5418,10 @@
|
||||
"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": "09518a4d8637c430311d50a4249913187dbc5057",
|
||||
"ready": false,
|
||||
"commit": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
|
||||
"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)",
|
||||
@@ -5360,7 +5429,7 @@
|
||||
"existing_count": 24,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "9bc8af4e6aa04e1f61bc42b432335e0f3500515d3e3d59a6c430ce8c1177fbbe"
|
||||
"sha256": "d4d58b9557d03656a800aad0acee41d5434db006ebbbff2645fbbab80962cc27"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -5433,8 +5502,8 @@
|
||||
"label": "output_execution",
|
||||
"path": "reports/output_execution_runs.json",
|
||||
"exists": true,
|
||||
"bytes": 7964,
|
||||
"sha256": "30b43454ef2a4802b13d554100789b1c9c7a1baec9bebcd6fc8cf0ea9830ba41"
|
||||
"bytes": 7967,
|
||||
"sha256": "2ee3f1028f48673cddeb6242eb30aee3db1eccf26c44499744f3031d6d3520d7"
|
||||
},
|
||||
{
|
||||
"label": "blind_review",
|
||||
@@ -5475,8 +5544,8 @@
|
||||
"label": "python_compatibility",
|
||||
"path": "reports/python_compatibility.json",
|
||||
"exists": true,
|
||||
"bytes": 22887,
|
||||
"sha256": "be0b8550a4404d85a044b3ae612b39d94e8b493723e7aaf02386cace291b8262"
|
||||
"bytes": 23022,
|
||||
"sha256": "e53158aa045e19f51cbf61f4cb8b299c9ac2babeaacd5441ecb911eb99d8089d"
|
||||
},
|
||||
{
|
||||
"label": "registry_audit",
|
||||
@@ -5824,7 +5893,7 @@
|
||||
"label": "Trust Security",
|
||||
"status": "pass",
|
||||
"objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
|
||||
"current": "110 scripts; secrets 0; help failures 0",
|
||||
"current": "111 scripts; secrets 0; help failures 0",
|
||||
"command": "python3 scripts/yao.py trust .",
|
||||
"test": "python3 tests/verify_trust_check.py",
|
||||
"evidence": [
|
||||
@@ -5898,7 +5967,7 @@
|
||||
"label": "Registry Distribution",
|
||||
"status": "pass",
|
||||
"objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
|
||||
"current": "archive entries 617; install failures 0",
|
||||
"current": "archive entries 618; 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": [
|
||||
@@ -11391,9 +11460,9 @@
|
||||
"ok": true,
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"scanned_files": 197,
|
||||
"script_count": 110,
|
||||
"internal_module_count": 28,
|
||||
"scanned_files": 198,
|
||||
"script_count": 111,
|
||||
"internal_module_count": 29,
|
||||
"secret_findings": 0,
|
||||
"dependency_files": [
|
||||
"requirements-ci.txt"
|
||||
@@ -11411,8 +11480,8 @@
|
||||
"help_smoke_failed_count": 0,
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 197,
|
||||
"package_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086"
|
||||
"package_hash_file_count": 198,
|
||||
"package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": [],
|
||||
@@ -11605,6 +11674,20 @@
|
||||
"network_urls": [],
|
||||
"network_hosts": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/evidence_consistency_world_class.py",
|
||||
"interface": "internal-module",
|
||||
"interface_declared": true,
|
||||
"interface_reason": "Imported by render_evidence_consistency.py to isolate world-class evidence workflow consistency checks.",
|
||||
"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/export_skill_ir.py",
|
||||
"interface": "cli",
|
||||
@@ -13010,7 +13093,7 @@
|
||||
"checked_count": 82,
|
||||
"passed_count": 82,
|
||||
"failed_count": 0,
|
||||
"skipped_count": 28,
|
||||
"skipped_count": 29,
|
||||
"failed_scripts": [],
|
||||
"results": [
|
||||
{
|
||||
@@ -13835,6 +13918,10 @@
|
||||
}
|
||||
],
|
||||
"skipped": [
|
||||
{
|
||||
"path": "scripts/evidence_consistency_world_class.py",
|
||||
"reason": "internal module"
|
||||
},
|
||||
{
|
||||
"path": "scripts/html_rendering.py",
|
||||
"reason": "internal module"
|
||||
@@ -14138,7 +14225,7 @@
|
||||
"root": ".",
|
||||
"summary": {
|
||||
"target_python": "3.11",
|
||||
"file_count": 176,
|
||||
"file_count": 177,
|
||||
"issue_count": 0,
|
||||
"syntax_error_count": 0,
|
||||
"fstring_311_violation_count": 0,
|
||||
@@ -14251,6 +14338,12 @@
|
||||
"issue_count": 0,
|
||||
"issues": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/evidence_consistency_world_class.py",
|
||||
"ok": true,
|
||||
"issue_count": 0,
|
||||
"issues": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/export_skill_ir.py",
|
||||
"ok": true,
|
||||
@@ -15224,10 +15317,10 @@
|
||||
"generated_at": "2026-06-16",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"python_file_count": 173,
|
||||
"script_file_count": 110,
|
||||
"python_file_count": 174,
|
||||
"script_file_count": 111,
|
||||
"test_file_count": 63,
|
||||
"internal_module_count": 31,
|
||||
"internal_module_count": 32,
|
||||
"cli_script_count": 81,
|
||||
"command_handler_count": 64,
|
||||
"entrypoint_command_handler_count": 18,
|
||||
@@ -15236,7 +15329,7 @@
|
||||
"watch_line_threshold": 720,
|
||||
"block_line_threshold": 1500,
|
||||
"largest_file_lines": 899,
|
||||
"watchlist_count": 9,
|
||||
"watchlist_count": 8,
|
||||
"hotspot_count": 0,
|
||||
"blocker_count": 0,
|
||||
"decision": "pass"
|
||||
@@ -15249,13 +15342,6 @@
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_evidence_consistency.py",
|
||||
"lines": 859,
|
||||
"kind": "cli-script",
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_parser.py",
|
||||
"lines": 810,
|
||||
@@ -15325,6 +15411,13 @@
|
||||
"kind": "internal-module",
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_review_viewer.py",
|
||||
"lines": 685,
|
||||
"kind": "cli-script",
|
||||
"severity": "pass",
|
||||
"recommendation": "Split viewer data assembly from HTML section rendering."
|
||||
}
|
||||
],
|
||||
"watchlist": [
|
||||
@@ -15335,13 +15428,6 @@
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_evidence_consistency.py",
|
||||
"lines": 859,
|
||||
"kind": "cli-script",
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_parser.py",
|
||||
"lines": 810,
|
||||
@@ -15402,21 +15488,23 @@
|
||||
"context_budget": {
|
||||
"ok": true,
|
||||
"failures": [],
|
||||
"warnings": [],
|
||||
"warnings": [
|
||||
"Deferred resource footprint is high: 436837 estimated tokens across references/scripts/evals. Keep Review Studio warnings visible until the largest resource dirs are split, archived, or justified."
|
||||
],
|
||||
"stats": {
|
||||
"context_budget_tier": "production",
|
||||
"context_budget_limit": 1000,
|
||||
"skill_body_tokens": 767,
|
||||
"other_text_tokens": 1376201,
|
||||
"other_text_tokens": 1376303,
|
||||
"estimated_initial_load_tokens": 960,
|
||||
"estimated_total_text_tokens": 1376968,
|
||||
"deferred_resource_tokens": 436849,
|
||||
"estimated_total_text_tokens": 1377070,
|
||||
"deferred_resource_tokens": 436837,
|
||||
"deferred_resource_warn_threshold": 120000,
|
||||
"deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 387638,
|
||||
"file_count": 110
|
||||
"estimated_tokens": 387626,
|
||||
"file_count": 111
|
||||
},
|
||||
{
|
||||
"path": "references",
|
||||
@@ -15432,37 +15520,38 @@
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 387638,
|
||||
"file_count": 110
|
||||
"estimated_tokens": 387626,
|
||||
"file_count": 111
|
||||
}
|
||||
],
|
||||
"deferred_resource_governance": {
|
||||
"status": "governed",
|
||||
"status": "needs-review",
|
||||
"large_dir_count": 1,
|
||||
"governed_large_dir_count": 1,
|
||||
"governed_large_dir_count": 0,
|
||||
"directories": [
|
||||
{
|
||||
"status": "governed",
|
||||
"status": "needs-review",
|
||||
"evidence": [
|
||||
"reports/security_trust_report.json",
|
||||
"reports/architecture_maintainability.json",
|
||||
"reports/python_compatibility.json"
|
||||
],
|
||||
"reasons": [
|
||||
"trust report covers scripts",
|
||||
"architecture report has no script hotspots or blockers",
|
||||
"Python compatibility report has no issues"
|
||||
],
|
||||
"missing": [],
|
||||
"missing": [
|
||||
"trust report covers scripts"
|
||||
],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 387638,
|
||||
"file_count": 110,
|
||||
"estimated_tokens": 387626,
|
||||
"file_count": 111,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
],
|
||||
"summary": "Large deferred resources are indexed and backed by evidence."
|
||||
"summary": "One or more large deferred resource directories still need explicit governance evidence."
|
||||
},
|
||||
"relevant_file_count": 563,
|
||||
"relevant_file_count": 565,
|
||||
"unused_resource_dirs": [],
|
||||
"quality_signal_points": 130,
|
||||
"quality_density": 135.4
|
||||
@@ -17330,7 +17419,7 @@
|
||||
"adoption_drift": {
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-15T16:57:40Z",
|
||||
"generated_at": "2026-06-15T17:03:40Z",
|
||||
"skill_dir": ".",
|
||||
"privacy_contract": {
|
||||
"storage": "local-first",
|
||||
@@ -20445,8 +20534,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137"
|
||||
"package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -20477,7 +20566,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -20502,7 +20591,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086"
|
||||
"package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -20525,8 +20614,8 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"archive_entry_count": 617,
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"archive_entry_count": 618,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
@@ -21191,7 +21280,7 @@
|
||||
"installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
|
||||
"summary": {
|
||||
"archive_present": true,
|
||||
"archive_entry_count": 617,
|
||||
"archive_entry_count": 618,
|
||||
"archive_extracted": true,
|
||||
"entrypoint_loaded": true,
|
||||
"manifest_loaded": true,
|
||||
@@ -21533,12 +21622,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137"
|
||||
"to": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086"
|
||||
"to": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
+25
-25
@@ -513,7 +513,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 110
|
||||
"file_count": 111
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -528,7 +528,7 @@
|
||||
"file_count": 222
|
||||
}
|
||||
],
|
||||
"file_count": 399,
|
||||
"file_count": 400,
|
||||
"folder_count": 4,
|
||||
"distribution": [
|
||||
{
|
||||
@@ -553,7 +553,7 @@
|
||||
},
|
||||
{
|
||||
"label": "scripts",
|
||||
"value": 110
|
||||
"value": 111
|
||||
},
|
||||
{
|
||||
"label": "evals",
|
||||
@@ -683,7 +683,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 110
|
||||
"file_count": 111
|
||||
},
|
||||
{
|
||||
"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": 24,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "9bc8af4e6aa04e1f61bc42b432335e0f3500515d3e3d59a6c430ce8c1177fbbe",
|
||||
"source_contract_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"evidence_bundle_sha256": "5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8",
|
||||
"source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 22,
|
||||
@@ -1020,11 +1020,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 36
|
||||
},
|
||||
"commit": "09518a4d8637c430311d50a4249913187dbc5057",
|
||||
"commit": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
|
||||
"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": 197,
|
||||
"script_count": 110,
|
||||
"internal_module_count": 28,
|
||||
"scanned_files": 198,
|
||||
"script_count": 111,
|
||||
"internal_module_count": 29,
|
||||
"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": 197,
|
||||
"package_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086"
|
||||
"package_hash_file_count": 198,
|
||||
"package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1167,8 +1167,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137"
|
||||
"package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -1199,7 +1199,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -1215,8 +1215,8 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"archive_entry_count": 617,
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"archive_entry_count": 618,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
@@ -1227,7 +1227,7 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"archive_present": true,
|
||||
"archive_entry_count": 617,
|
||||
"archive_entry_count": 618,
|
||||
"archive_extracted": true,
|
||||
"entrypoint_loaded": true,
|
||||
"manifest_loaded": true,
|
||||
@@ -1294,12 +1294,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137"
|
||||
"to": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086"
|
||||
"to": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -2,9 +2,9 @@
|
||||
"ok": true,
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"scanned_files": 197,
|
||||
"script_count": 110,
|
||||
"internal_module_count": 28,
|
||||
"scanned_files": 198,
|
||||
"script_count": 111,
|
||||
"internal_module_count": 29,
|
||||
"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": 197,
|
||||
"package_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086"
|
||||
"package_hash_file_count": 198,
|
||||
"package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": [],
|
||||
@@ -216,6 +216,20 @@
|
||||
"network_urls": [],
|
||||
"network_hosts": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/evidence_consistency_world_class.py",
|
||||
"interface": "internal-module",
|
||||
"interface_declared": true,
|
||||
"interface_reason": "Imported by render_evidence_consistency.py to isolate world-class evidence workflow consistency checks.",
|
||||
"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/export_skill_ir.py",
|
||||
"interface": "cli",
|
||||
@@ -1621,7 +1635,7 @@
|
||||
"checked_count": 82,
|
||||
"passed_count": 82,
|
||||
"failed_count": 0,
|
||||
"skipped_count": 28,
|
||||
"skipped_count": 29,
|
||||
"failed_scripts": [],
|
||||
"results": [
|
||||
{
|
||||
@@ -2446,6 +2460,10 @@
|
||||
}
|
||||
],
|
||||
"skipped": [
|
||||
{
|
||||
"path": "scripts/evidence_consistency_world_class.py",
|
||||
"reason": "internal module"
|
||||
},
|
||||
{
|
||||
"path": "scripts/html_rendering.py",
|
||||
"reason": "internal module"
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
# Security Trust Report
|
||||
|
||||
- OK: `True`
|
||||
- Scanned files: `197`
|
||||
- Scripts: `110`
|
||||
- Internal script modules: `28`
|
||||
- Scanned files: `198`
|
||||
- Scripts: `111`
|
||||
- Internal script modules: `29`
|
||||
- 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: `197`
|
||||
- Package SHA256: `f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086`
|
||||
- Package hash files: `198`
|
||||
- Package SHA256: `9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea`
|
||||
|
||||
## Failures
|
||||
|
||||
@@ -75,6 +75,7 @@
|
||||
| scripts/cross_packager.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
|
||||
| scripts/diff_eval.py | cli | False | True | True | False | False | False | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
|
||||
| scripts/emit_telemetry_event.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
|
||||
| scripts/evidence_consistency_world_class.py | internal-module | True | False | False | False | False | False | False | Imported by render_evidence_consistency.py to isolate world-class evidence workflow consistency checks. |
|
||||
| scripts/export_skill_ir.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
|
||||
| scripts/github_benchmark_scan.py | cli | False | True | True | False | True | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
|
||||
| scripts/governance_check.py | cli | False | True | True | False | False | False | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
|
||||
|
||||
@@ -930,7 +930,7 @@
|
||||
<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="0.7 99.3" 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="0.7 99.3" stroke-dashoffset="-0.7" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-1.4" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-2.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="23.0 77.0" stroke-dashoffset="-2.7" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="74.3 25.7" stroke-dashoffset="-25.7" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">399项</text><text data-lang="en" x="130" y="136" text-anchor="middle">399 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="0.7 99.3" 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="0.7 99.3" stroke-dashoffset="-0.7" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-1.3" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-2.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="22.8 77.2" stroke-dashoffset="-2.7" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="74.5 25.5" stroke-dashoffset="-25.5" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">400项</text><text data-lang="en" x="130" y="136" text-anchor="middle">400 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>
|
||||
|
||||
@@ -513,7 +513,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 110
|
||||
"file_count": 111
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -528,7 +528,7 @@
|
||||
"file_count": 222
|
||||
}
|
||||
],
|
||||
"file_count": 399,
|
||||
"file_count": 400,
|
||||
"folder_count": 4,
|
||||
"distribution": [
|
||||
{
|
||||
@@ -553,7 +553,7 @@
|
||||
},
|
||||
{
|
||||
"label": "scripts",
|
||||
"value": 110
|
||||
"value": 111
|
||||
},
|
||||
{
|
||||
"label": "evals",
|
||||
@@ -687,7 +687,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 110
|
||||
"file_count": 111
|
||||
},
|
||||
{
|
||||
"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": 24,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "9bc8af4e6aa04e1f61bc42b432335e0f3500515d3e3d59a6c430ce8c1177fbbe",
|
||||
"source_contract_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"evidence_bundle_sha256": "5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8",
|
||||
"source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 22,
|
||||
@@ -1024,11 +1024,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 36
|
||||
},
|
||||
"commit": "09518a4d8637c430311d50a4249913187dbc5057",
|
||||
"commit": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
|
||||
"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": 197,
|
||||
"script_count": 110,
|
||||
"internal_module_count": 28,
|
||||
"scanned_files": 198,
|
||||
"script_count": 111,
|
||||
"internal_module_count": 29,
|
||||
"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": 197,
|
||||
"package_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086"
|
||||
"package_hash_file_count": 198,
|
||||
"package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1171,8 +1171,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137"
|
||||
"package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -1203,7 +1203,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -1219,8 +1219,8 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"archive_entry_count": 617,
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"archive_entry_count": 618,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
@@ -1231,7 +1231,7 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"archive_present": true,
|
||||
"archive_entry_count": 617,
|
||||
"archive_entry_count": 618,
|
||||
"archive_extracted": true,
|
||||
"entrypoint_loaded": true,
|
||||
"manifest_loaded": true,
|
||||
@@ -1298,12 +1298,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137"
|
||||
"to": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086"
|
||||
"to": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -37,7 +37,7 @@ Yao Meta Skill is no longer only a Meta Skill factory. The current working tree
|
||||
- Local Install Sync Preflight v0 so source-to-local and source-to-active install syncs rebuild the package first, run install simulation, enforce installer permission coverage, and refuse to copy files before any destructive sync when the package is not install-ready.
|
||||
- Atlas Scope Policy v0 so examples, evolution snapshots, embedded generated skills, and validator fixtures remain visible in the full portfolio report without polluting release-actionable gates.
|
||||
- Review Annotations v0 for reviewer comments tied to Review Studio gates, source/report paths, and optional line numbers; open blocker annotations now block the Review Studio decision.
|
||||
- Review Studio now avoids over-claiming release readiness when blind A/B adjudication and world-class evidence are still pending: the root Meta Skill is in `review` with score `91`, no blockers, three warnings, and explicit actions for Output Lab reviewer adjudication, waiver handling, and world-class evidence completion.
|
||||
- Review Studio now avoids over-claiming release readiness when blind A/B adjudication, context-budget pressure, waiver handling, and world-class evidence are still pending: the root Meta Skill is in `review` with score `89`, no blockers, four warnings, and explicit actions for Output Lab reviewer adjudication, context-budget follow-up, waiver handling, and world-class evidence completion.
|
||||
- Review Studio Output Lab actions now link directly to `reports/output_review_decisions.json`, so pending blind A/B reviewer decisions have a concrete template instead of only a general adjudication warning.
|
||||
- Output Review Adjudication now preserves blind-review integrity by hiding expected winners for pending or invalid reviewer decisions; answer keys are revealed only after a valid A/B decision exists for that case.
|
||||
- Provider Output Eval Runner v0 so `python3 scripts/yao.py output-exec --provider-runner openai` can collect real provider-backed model evidence through a reviewed OpenAI Responses API compatible runner instead of ad hoc shell glue.
|
||||
@@ -91,7 +91,7 @@ Next move: run provider-backed holdout cases with real credentials and one real
|
||||
|
||||
### 3. Review Studio is unified and now has reviewer actions plus annotations
|
||||
|
||||
The Review Studio page aggregates intent, trigger, output, context, runtime, trust, permission approvals, runtime permission probes, atlas, operations-loop, reviewer waiver, reviewer annotations, registry, world-class evidence, and release gates. It exposes current warnings directly and emits `review_actions` for each non-pass gate with a source-fix location, structured `source_refs`, reason, evidence path, and verification command. It now also loads `reports/review_annotations.json`, renders reviewer comments tied to gates and source/report paths, and blocks the page decision when any open blocker annotation exists. The current root report is intentionally not a clean pass: decision `review`, score `91`, `16` gates, `0` blockers, `3` warnings, `3` actions, and `0` open annotation blockers. The warnings are useful evidence: the automated Output Eval Lab is strong, but the blind A/B adjudication still has `5` pending reviewer decisions and the world-class ledger still has `4` pending external or human evidence entries, so the package should not claim fully reviewed or world-class status.
|
||||
The Review Studio page aggregates intent, trigger, output, context, runtime, trust, permission approvals, runtime permission probes, atlas, operations-loop, reviewer waiver, reviewer annotations, registry, world-class evidence, and release gates. It exposes current warnings directly and emits `review_actions` for each non-pass gate with a source-fix location, structured `source_refs`, reason, evidence path, and verification command. It now also loads `reports/review_annotations.json`, renders reviewer comments tied to gates and source/report paths, and blocks the page decision when any open blocker annotation exists. The current root report is intentionally not a clean pass: decision `review`, score `89`, `16` gates, `0` blockers, `4` warnings, `4` actions, and `0` open annotation blockers. The warnings are useful evidence: the automated Output Eval Lab is strong, but the blind A/B adjudication still has `5` pending reviewer decisions, the context budget is close to its limit, and the world-class ledger still has `4` pending external or human evidence entries, so the package should not claim fully reviewed or world-class status.
|
||||
|
||||
Next move: add richer source-line anchors inside generated reports, record real reviewer annotations during the next human review pass, and close the provider, native-permission, real-client telemetry, and human review evidence entries in the world-class ledger.
|
||||
|
||||
@@ -114,19 +114,19 @@ 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, `28` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `82 / 82` CLI help smoke checks passing across `110` scripts, source-contract hash scope explicit |
|
||||
| Trust | `0` secret findings, `1` pinned dependency file, `29` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `82 / 82` CLI help smoke checks passing across `111` 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, `617` zip entries, `0` failures, `0` warnings |
|
||||
| Install Simulation | archive with `617` 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, `618` zip entries, `0` failures, `0` warnings |
|
||||
| Install Simulation | archive with `618` 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, `0` adoption samples, adoption `0`, 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 |
|
||||
| Review Waivers | ledger generated; current release has `1` warning gate that still needs reviewer decision or a time-bounded waiver; blockers remain non-waivable in v0, and world-class evidence gaps must be closed with accepted evidence rather than waived as completed |
|
||||
| Review Annotations | ledger generated; current release has `0` reviewer annotations and `0` open annotation blockers |
|
||||
| Review Studio | decision `review`, world-class score `91`, `16` gates, `0` blockers, `3` warnings, `3` review actions, `0` open annotation blockers |
|
||||
| Review Studio | decision `review`, world-class score `89`, `16` gates, `0` blockers, `4` warnings, `4` review actions, `0` open annotation blockers |
|
||||
| Skill OS 2.0 Audit | `15` audited areas, with local foundation evidence separated from human-required and external-required gaps |
|
||||
| World-Class Evidence Plan | `4` remaining evidence tasks: `1` human-required and `3` external-required, all with runbooks, success checks, and privacy contracts |
|
||||
| World-Class Evidence Ledger | `4` evidence entries remain pending: `1` human-required and `3` external-required; anti-overclaim guards block planned work, metadata fallbacks, pending review, and local command runners from counting as completion |
|
||||
|
||||
@@ -930,7 +930,7 @@
|
||||
<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="0.7 99.3" 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="0.7 99.3" stroke-dashoffset="-0.7" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-1.4" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-2.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="23.0 77.0" stroke-dashoffset="-2.7" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="74.3 25.7" stroke-dashoffset="-25.7" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">399项</text><text data-lang="en" x="130" y="136" text-anchor="middle">399 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="0.7 99.3" 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="0.7 99.3" stroke-dashoffset="-0.7" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-1.3" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-2.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="22.8 77.2" stroke-dashoffset="-2.7" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="74.5 25.5" stroke-dashoffset="-25.5" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">400项</text><text data-lang="en" x="130" y="136" text-anchor="middle">400 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>
|
||||
|
||||
+25
-25
@@ -512,7 +512,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 110
|
||||
"file_count": 111
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -527,7 +527,7 @@
|
||||
"file_count": 222
|
||||
}
|
||||
],
|
||||
"file_count": 399,
|
||||
"file_count": 400,
|
||||
"folder_count": 4,
|
||||
"distribution": [
|
||||
{
|
||||
@@ -552,7 +552,7 @@
|
||||
},
|
||||
{
|
||||
"label": "scripts",
|
||||
"value": 110
|
||||
"value": 111
|
||||
},
|
||||
{
|
||||
"label": "evals",
|
||||
@@ -682,7 +682,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 110
|
||||
"file_count": 111
|
||||
},
|
||||
{
|
||||
"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": 24,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "9bc8af4e6aa04e1f61bc42b432335e0f3500515d3e3d59a6c430ce8c1177fbbe",
|
||||
"source_contract_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"evidence_bundle_sha256": "5ad19434d41f67e6a8dbcbccbd22ffefed11008d75ebb00a78f0d24f3f8910a8",
|
||||
"source_contract_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 22,
|
||||
@@ -1019,11 +1019,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 36
|
||||
},
|
||||
"commit": "09518a4d8637c430311d50a4249913187dbc5057",
|
||||
"commit": "391821240ba14f088d0fbe12dd5f1fdca7917a39",
|
||||
"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": 197,
|
||||
"script_count": 110,
|
||||
"internal_module_count": 28,
|
||||
"scanned_files": 198,
|
||||
"script_count": 111,
|
||||
"internal_module_count": 29,
|
||||
"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": 197,
|
||||
"package_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086"
|
||||
"package_hash_file_count": 198,
|
||||
"package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1166,8 +1166,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086",
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137"
|
||||
"package_sha256": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -1198,7 +1198,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -1214,8 +1214,8 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137",
|
||||
"archive_entry_count": 617,
|
||||
"archive_sha256": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5",
|
||||
"archive_entry_count": 618,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
@@ -1226,7 +1226,7 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"archive_present": true,
|
||||
"archive_entry_count": 617,
|
||||
"archive_entry_count": 618,
|
||||
"archive_extracted": true,
|
||||
"entrypoint_loaded": true,
|
||||
"manifest_loaded": true,
|
||||
@@ -1293,12 +1293,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137"
|
||||
"to": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086"
|
||||
"to": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -130,7 +130,7 @@
|
||||
"label": "Trust Security",
|
||||
"status": "pass",
|
||||
"objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
|
||||
"current": "110 scripts; secrets 0; help failures 0",
|
||||
"current": "111 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 617; install failures 0",
|
||||
"current": "archive entries 618; 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": [
|
||||
@@ -245,7 +245,7 @@
|
||||
"label": "Review Studio",
|
||||
"status": "pass",
|
||||
"objective": "One HTML page supports first-pass production review across trigger, output, runtime, trust, release, and evidence actions.",
|
||||
"current": "16 gates; decision review; warnings 3",
|
||||
"current": "16 gates; decision review; warnings 4",
|
||||
"command": "python3 scripts/yao.py review-studio .",
|
||||
"test": "python3 tests/verify_review_studio.py",
|
||||
"evidence": [
|
||||
|
||||
@@ -26,10 +26,10 @@ 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` | 110 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
|
||||
| Trust Security | `pass` | 111 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 617; 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` |
|
||||
| Registry Distribution | `pass` | archive entries 618; 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 4 | `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` |
|
||||
|
||||
## Recommended PR Coverage
|
||||
|
||||
@@ -70,12 +70,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "00151114ce7fee627882964137dd5259583f5521c75c6570789345e874454137"
|
||||
"to": "83ece575ef740a97b6a398f77ed4bc9f1869cde756257c64fdd90d8785c6f3a5"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "f48a71e36bdbcaa353bd4e6bfc499bda41f047aeffe3d8eae2f99509ec693086"
|
||||
"to": "9fde13846a41c2d1442b6e80350313246dedebe02590ce1f2f07f2da1109c9ea"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -0,0 +1,197 @@
|
||||
from typing import Any
|
||||
|
||||
|
||||
SCRIPT_INTERFACE = "internal-module"
|
||||
SCRIPT_INTERFACE_REASON = "Imported by render_evidence_consistency.py to isolate world-class evidence workflow consistency checks."
|
||||
|
||||
|
||||
def keyed_items(payload: dict[str, Any], collection_key: str) -> dict[str, dict[str, Any]]:
|
||||
collection = payload.get(collection_key)
|
||||
if not isinstance(collection, list):
|
||||
return {}
|
||||
keyed: dict[str, dict[str, Any]] = {}
|
||||
for item in collection:
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
key = item.get("key") or item.get("evidence_key")
|
||||
if isinstance(key, str):
|
||||
keyed[key] = item
|
||||
return keyed
|
||||
|
||||
|
||||
def command_key_set(item: dict[str, Any]) -> set[str]:
|
||||
commands = item.get("commands")
|
||||
if isinstance(commands, dict):
|
||||
return {key for key, value in commands.items() if isinstance(key, str) and value}
|
||||
if isinstance(commands, list):
|
||||
keys: set[str] = set()
|
||||
for command in commands:
|
||||
if isinstance(command, dict) and isinstance(command.get("key"), str) and command.get("command"):
|
||||
keys.add(command["key"])
|
||||
return keys
|
||||
return set()
|
||||
|
||||
|
||||
def world_class_review_action_steps(review_studio: dict[str, Any]) -> dict[str, dict[str, Any]]:
|
||||
actions = review_studio.get("review_actions")
|
||||
if not isinstance(actions, list):
|
||||
return {}
|
||||
for action in actions:
|
||||
if not isinstance(action, dict) or action.get("gate_key") != "world-class-evidence":
|
||||
continue
|
||||
steps = action.get("evidence_steps")
|
||||
if not isinstance(steps, list):
|
||||
return {}
|
||||
keyed: dict[str, dict[str, Any]] = {}
|
||||
for step in steps:
|
||||
if isinstance(step, dict) and isinstance(step.get("key"), str):
|
||||
keyed[step["key"]] = step
|
||||
return keyed
|
||||
return {}
|
||||
|
||||
|
||||
def command_groups_present(command_keys: set[str]) -> dict[str, bool]:
|
||||
return {
|
||||
"prepare_submission": "prepare_submission" in command_keys,
|
||||
"validate_intake": "validate_intake" in command_keys,
|
||||
"submission_review": bool({"submission_review", "review_queue"} & command_keys),
|
||||
"refresh_ledger": "refresh_ledger" in command_keys,
|
||||
"guard_claim": "guard_claim" in command_keys,
|
||||
}
|
||||
|
||||
|
||||
def has_next_action(item: dict[str, Any]) -> bool:
|
||||
for key in ["next_action", "audit_next_action"]:
|
||||
value = item.get(key)
|
||||
if isinstance(value, str) and value.strip():
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def command_expectations(keys: list[str]) -> dict[str, dict[str, dict[str, bool]]]:
|
||||
expected_group = {
|
||||
"prepare_submission": True,
|
||||
"validate_intake": True,
|
||||
"submission_review": True,
|
||||
"refresh_ledger": True,
|
||||
"guard_claim": True,
|
||||
}
|
||||
return {
|
||||
key: {
|
||||
"intake": dict(expected_group),
|
||||
"operator_runbook": dict(expected_group),
|
||||
"review_studio": dict(expected_group),
|
||||
}
|
||||
for key in keys
|
||||
}
|
||||
|
||||
|
||||
def build_world_class_workflow_check(
|
||||
*,
|
||||
ledger: dict[str, Any],
|
||||
world_class_plan: dict[str, Any],
|
||||
world_class_intake: dict[str, Any],
|
||||
world_class_submission_review: dict[str, Any],
|
||||
world_class_operator_runbook: dict[str, Any],
|
||||
review_studio: dict[str, Any],
|
||||
report_paths: dict[str, str],
|
||||
) -> dict[str, Any]:
|
||||
ledger_summary = ledger.get("summary") if isinstance(ledger.get("summary"), dict) else {}
|
||||
plan_summary = world_class_plan.get("summary") if isinstance(world_class_plan.get("summary"), dict) else {}
|
||||
intake_summary = world_class_intake.get("summary") if isinstance(world_class_intake.get("summary"), dict) else {}
|
||||
submission_review_summary = (
|
||||
world_class_submission_review.get("summary")
|
||||
if isinstance(world_class_submission_review.get("summary"), dict)
|
||||
else {}
|
||||
)
|
||||
operator_runbook_summary = (
|
||||
world_class_operator_runbook.get("summary")
|
||||
if isinstance(world_class_operator_runbook.get("summary"), dict)
|
||||
else {}
|
||||
)
|
||||
|
||||
ledger_items = keyed_items(ledger, "entries")
|
||||
plan_tasks = keyed_items(world_class_plan, "tasks")
|
||||
intake_checklist = keyed_items(world_class_intake, "operator_checklist")
|
||||
submission_review_items = keyed_items(world_class_submission_review, "items")
|
||||
operator_runbook_items = keyed_items(world_class_operator_runbook, "items")
|
||||
review_action_steps = world_class_review_action_steps(review_studio)
|
||||
pending_keys = sorted(key for key, item in ledger_items.items() if item.get("status") != "accepted")
|
||||
|
||||
actual_command_groups = {
|
||||
key: {
|
||||
"intake": command_groups_present(command_key_set(intake_checklist.get(key, {}))),
|
||||
"operator_runbook": command_groups_present(command_key_set(operator_runbook_items.get(key, {}))),
|
||||
"review_studio": command_groups_present(command_key_set(review_action_steps.get(key, {}))),
|
||||
}
|
||||
for key in pending_keys
|
||||
}
|
||||
expected = {
|
||||
"keys": pending_keys,
|
||||
"pending_count": ledger_summary.get("pending_count"),
|
||||
"human_pending_count": ledger_summary.get("human_pending_count"),
|
||||
"external_pending_count": ledger_summary.get("external_pending_count"),
|
||||
"source_check_count": ledger_summary.get("source_check_count"),
|
||||
"source_pass_count": ledger_summary.get("source_pass_count"),
|
||||
"source_blocked_count": ledger_summary.get("source_blocked_count"),
|
||||
"plan_keys": pending_keys,
|
||||
"intake_keys": pending_keys,
|
||||
"submission_review_keys": pending_keys,
|
||||
"operator_runbook_keys": pending_keys,
|
||||
"review_studio_keys": pending_keys,
|
||||
"intake_ready_to_claim_world_class": False,
|
||||
"submission_review_ready_to_claim_world_class": False,
|
||||
"submission_review_counts_as_completion": False,
|
||||
"operator_runbook_ready_to_claim_world_class": False,
|
||||
"operator_runbook_counts_as_completion": False,
|
||||
"next_actions_present": {key: True for key in pending_keys},
|
||||
"commands": command_expectations(pending_keys),
|
||||
}
|
||||
actual = {
|
||||
"keys": pending_keys,
|
||||
"pending_count": plan_summary.get("task_count"),
|
||||
"human_pending_count": plan_summary.get("human_task_count"),
|
||||
"external_pending_count": plan_summary.get("external_task_count"),
|
||||
"source_check_count": submission_review_summary.get("source_check_count"),
|
||||
"source_pass_count": submission_review_summary.get("source_pass_count"),
|
||||
"source_blocked_count": submission_review_summary.get("source_blocked_count"),
|
||||
"plan_keys": sorted(plan_tasks),
|
||||
"intake_keys": sorted(intake_checklist),
|
||||
"submission_review_keys": sorted(submission_review_items),
|
||||
"operator_runbook_keys": sorted(operator_runbook_items),
|
||||
"review_studio_keys": sorted(review_action_steps),
|
||||
"intake_ready_to_claim_world_class": intake_summary.get("ready_to_claim_world_class"),
|
||||
"submission_review_ready_to_claim_world_class": submission_review_summary.get("ready_to_claim_world_class"),
|
||||
"submission_review_counts_as_completion": submission_review_summary.get(
|
||||
"review_counts_submission_as_completion"
|
||||
),
|
||||
"operator_runbook_ready_to_claim_world_class": operator_runbook_summary.get("ready_to_claim_world_class"),
|
||||
"operator_runbook_counts_as_completion": operator_runbook_summary.get("runbook_counts_as_completion"),
|
||||
"next_actions_present": {
|
||||
key: all(
|
||||
has_next_action(collection.get(key, {}))
|
||||
for collection in [plan_tasks, intake_checklist, submission_review_items, review_action_steps]
|
||||
)
|
||||
for key in pending_keys
|
||||
},
|
||||
"commands": actual_command_groups,
|
||||
}
|
||||
return {
|
||||
"key": "world-class-evidence-workflow-coverage",
|
||||
"label": "World-class evidence workflows cover every pending ledger entry",
|
||||
"status": "pass" if expected == actual else "fail",
|
||||
"expected": expected,
|
||||
"actual": actual,
|
||||
"paths": [
|
||||
report_paths["world_class_ledger"],
|
||||
report_paths["world_class_plan"],
|
||||
report_paths["world_class_intake"],
|
||||
report_paths["world_class_submission_review"],
|
||||
report_paths["world_class_operator_runbook"],
|
||||
report_paths["review_studio"],
|
||||
],
|
||||
"detail": (
|
||||
"Every pending world-class evidence key must have matching plan, intake, submission review, "
|
||||
"operator runbook, and Review Studio actions without counting planned work as completion."
|
||||
),
|
||||
}
|
||||
@@ -6,6 +6,8 @@ from datetime import date
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from evidence_consistency_world_class import build_world_class_workflow_check
|
||||
|
||||
|
||||
ROOT = Path(__file__).resolve().parent.parent
|
||||
SCRIPT_INTERFACE = "cli"
|
||||
@@ -149,69 +151,6 @@ def as_int(value: Any) -> int | None:
|
||||
return None
|
||||
|
||||
|
||||
def keyed_items(payload: dict[str, Any], collection_key: str) -> dict[str, dict[str, Any]]:
|
||||
collection = payload.get(collection_key)
|
||||
if not isinstance(collection, list):
|
||||
return {}
|
||||
keyed: dict[str, dict[str, Any]] = {}
|
||||
for item in collection:
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
key = item.get("key") or item.get("evidence_key")
|
||||
if isinstance(key, str):
|
||||
keyed[key] = item
|
||||
return keyed
|
||||
|
||||
|
||||
def command_key_set(item: dict[str, Any]) -> set[str]:
|
||||
commands = item.get("commands")
|
||||
if isinstance(commands, dict):
|
||||
return {key for key, value in commands.items() if isinstance(key, str) and value}
|
||||
if isinstance(commands, list):
|
||||
keys: set[str] = set()
|
||||
for command in commands:
|
||||
if isinstance(command, dict) and isinstance(command.get("key"), str) and command.get("command"):
|
||||
keys.add(command["key"])
|
||||
return keys
|
||||
return set()
|
||||
|
||||
|
||||
def world_class_review_action_steps(review_studio: dict[str, Any]) -> dict[str, dict[str, Any]]:
|
||||
actions = review_studio.get("review_actions")
|
||||
if not isinstance(actions, list):
|
||||
return {}
|
||||
for action in actions:
|
||||
if not isinstance(action, dict) or action.get("gate_key") != "world-class-evidence":
|
||||
continue
|
||||
steps = action.get("evidence_steps")
|
||||
if not isinstance(steps, list):
|
||||
return {}
|
||||
keyed: dict[str, dict[str, Any]] = {}
|
||||
for step in steps:
|
||||
if isinstance(step, dict) and isinstance(step.get("key"), str):
|
||||
keyed[step["key"]] = step
|
||||
return keyed
|
||||
return {}
|
||||
|
||||
|
||||
def command_groups_present(command_keys: set[str]) -> dict[str, bool]:
|
||||
return {
|
||||
"prepare_submission": "prepare_submission" in command_keys,
|
||||
"validate_intake": "validate_intake" in command_keys,
|
||||
"submission_review": bool({"submission_review", "review_queue"} & command_keys),
|
||||
"refresh_ledger": "refresh_ledger" in command_keys,
|
||||
"guard_claim": "guard_claim" in command_keys,
|
||||
}
|
||||
|
||||
|
||||
def has_next_action(item: dict[str, Any]) -> bool:
|
||||
for key in ["next_action", "audit_next_action"]:
|
||||
value = item.get(key)
|
||||
if isinstance(value, str) and value.strip():
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def add_check(
|
||||
checks: list[dict[str, Any]],
|
||||
*,
|
||||
@@ -332,10 +271,6 @@ def build_report(skill_dir: Path, generated_at: str) -> dict[str, Any]:
|
||||
benchmark_summary = nested(benchmark, ["summary"], {})
|
||||
adoption_summary = nested(adoption, ["summary"], {})
|
||||
ledger_summary = nested(ledger, ["summary"], {})
|
||||
plan_summary = nested(world_class_plan, ["summary"], {})
|
||||
intake_summary = nested(world_class_intake, ["summary"], {})
|
||||
submission_review_summary = nested(world_class_submission_review, ["summary"], {})
|
||||
operator_runbook_summary = nested(world_class_operator_runbook, ["summary"], {})
|
||||
coverage_summary = nested(coverage, ["summary"], {})
|
||||
studio_summary = nested(review_studio, ["summary"], {})
|
||||
package_summary = nested(package_verification, ["summary"], {})
|
||||
@@ -585,130 +520,16 @@ def build_report(skill_dir: Path, generated_at: str) -> dict[str, Any]:
|
||||
],
|
||||
detail="The overclaim guard must scan package manifests, adapter metadata, security policy, and ledger surfaces before public readiness can be trusted.",
|
||||
)
|
||||
ledger_items = keyed_items(ledger, "entries")
|
||||
plan_tasks = keyed_items(world_class_plan, "tasks")
|
||||
intake_checklist = keyed_items(world_class_intake, "operator_checklist")
|
||||
submission_review_items = keyed_items(world_class_submission_review, "items")
|
||||
operator_runbook_items = keyed_items(world_class_operator_runbook, "items")
|
||||
review_action_steps = world_class_review_action_steps(review_studio)
|
||||
pending_world_class_keys = sorted(
|
||||
key for key, item in ledger_items.items() if item.get("status") != "accepted"
|
||||
)
|
||||
expected_command_groups = {
|
||||
key: {
|
||||
"intake": {
|
||||
"prepare_submission": True,
|
||||
"validate_intake": True,
|
||||
"submission_review": True,
|
||||
"refresh_ledger": True,
|
||||
"guard_claim": True,
|
||||
},
|
||||
"operator_runbook": {
|
||||
"prepare_submission": True,
|
||||
"validate_intake": True,
|
||||
"submission_review": True,
|
||||
"refresh_ledger": True,
|
||||
"guard_claim": True,
|
||||
},
|
||||
"review_studio": {
|
||||
"prepare_submission": True,
|
||||
"validate_intake": True,
|
||||
"submission_review": True,
|
||||
"refresh_ledger": True,
|
||||
"guard_claim": True,
|
||||
},
|
||||
}
|
||||
for key in pending_world_class_keys
|
||||
}
|
||||
actual_command_groups = {
|
||||
key: {
|
||||
"intake": command_groups_present(command_key_set(intake_checklist.get(key, {}))),
|
||||
"operator_runbook": command_groups_present(command_key_set(operator_runbook_items.get(key, {}))),
|
||||
"review_studio": command_groups_present(command_key_set(review_action_steps.get(key, {}))),
|
||||
}
|
||||
for key in pending_world_class_keys
|
||||
}
|
||||
expected_world_class_workflow = {
|
||||
"keys": pending_world_class_keys,
|
||||
"pending_count": ledger_summary.get("pending_count") if isinstance(ledger_summary, dict) else None,
|
||||
"human_pending_count": ledger_summary.get("human_pending_count") if isinstance(ledger_summary, dict) else None,
|
||||
"external_pending_count": ledger_summary.get("external_pending_count") if isinstance(ledger_summary, dict) else None,
|
||||
"source_check_count": ledger_summary.get("source_check_count") if isinstance(ledger_summary, dict) else None,
|
||||
"source_pass_count": ledger_summary.get("source_pass_count") if isinstance(ledger_summary, dict) else None,
|
||||
"source_blocked_count": ledger_summary.get("source_blocked_count") if isinstance(ledger_summary, dict) else None,
|
||||
"plan_keys": pending_world_class_keys,
|
||||
"intake_keys": pending_world_class_keys,
|
||||
"submission_review_keys": pending_world_class_keys,
|
||||
"operator_runbook_keys": pending_world_class_keys,
|
||||
"review_studio_keys": pending_world_class_keys,
|
||||
"intake_ready_to_claim_world_class": False,
|
||||
"submission_review_ready_to_claim_world_class": False,
|
||||
"submission_review_counts_as_completion": False,
|
||||
"operator_runbook_ready_to_claim_world_class": False,
|
||||
"operator_runbook_counts_as_completion": False,
|
||||
"next_actions_present": {key: True for key in pending_world_class_keys},
|
||||
"commands": expected_command_groups,
|
||||
}
|
||||
actual_world_class_workflow = {
|
||||
"keys": pending_world_class_keys,
|
||||
"pending_count": plan_summary.get("task_count") if isinstance(plan_summary, dict) else None,
|
||||
"human_pending_count": plan_summary.get("human_task_count") if isinstance(plan_summary, dict) else None,
|
||||
"external_pending_count": plan_summary.get("external_task_count") if isinstance(plan_summary, dict) else None,
|
||||
"source_check_count": submission_review_summary.get("source_check_count")
|
||||
if isinstance(submission_review_summary, dict)
|
||||
else None,
|
||||
"source_pass_count": submission_review_summary.get("source_pass_count")
|
||||
if isinstance(submission_review_summary, dict)
|
||||
else None,
|
||||
"source_blocked_count": submission_review_summary.get("source_blocked_count")
|
||||
if isinstance(submission_review_summary, dict)
|
||||
else None,
|
||||
"plan_keys": sorted(plan_tasks),
|
||||
"intake_keys": sorted(intake_checklist),
|
||||
"submission_review_keys": sorted(submission_review_items),
|
||||
"operator_runbook_keys": sorted(operator_runbook_items),
|
||||
"review_studio_keys": sorted(review_action_steps),
|
||||
"intake_ready_to_claim_world_class": intake_summary.get("ready_to_claim_world_class")
|
||||
if isinstance(intake_summary, dict)
|
||||
else None,
|
||||
"submission_review_ready_to_claim_world_class": submission_review_summary.get("ready_to_claim_world_class")
|
||||
if isinstance(submission_review_summary, dict)
|
||||
else None,
|
||||
"submission_review_counts_as_completion": submission_review_summary.get(
|
||||
"review_counts_submission_as_completion"
|
||||
checks.append(
|
||||
build_world_class_workflow_check(
|
||||
ledger=ledger,
|
||||
world_class_plan=world_class_plan,
|
||||
world_class_intake=world_class_intake,
|
||||
world_class_submission_review=world_class_submission_review,
|
||||
world_class_operator_runbook=world_class_operator_runbook,
|
||||
review_studio=review_studio,
|
||||
report_paths=REQUIRED_REPORTS,
|
||||
)
|
||||
if isinstance(submission_review_summary, dict)
|
||||
else None,
|
||||
"operator_runbook_ready_to_claim_world_class": operator_runbook_summary.get("ready_to_claim_world_class")
|
||||
if isinstance(operator_runbook_summary, dict)
|
||||
else None,
|
||||
"operator_runbook_counts_as_completion": operator_runbook_summary.get("runbook_counts_as_completion")
|
||||
if isinstance(operator_runbook_summary, dict)
|
||||
else None,
|
||||
"next_actions_present": {
|
||||
key: all(
|
||||
has_next_action(collection.get(key, {}))
|
||||
for collection in [plan_tasks, intake_checklist, submission_review_items, review_action_steps]
|
||||
)
|
||||
for key in pending_world_class_keys
|
||||
},
|
||||
"commands": actual_command_groups,
|
||||
}
|
||||
compare_values(
|
||||
checks,
|
||||
key="world-class-evidence-workflow-coverage",
|
||||
label="World-class evidence workflows cover every pending ledger entry",
|
||||
expected=expected_world_class_workflow,
|
||||
actual=actual_world_class_workflow,
|
||||
paths=[
|
||||
REQUIRED_REPORTS["world_class_ledger"],
|
||||
REQUIRED_REPORTS["world_class_plan"],
|
||||
REQUIRED_REPORTS["world_class_intake"],
|
||||
REQUIRED_REPORTS["world_class_submission_review"],
|
||||
REQUIRED_REPORTS["world_class_operator_runbook"],
|
||||
REQUIRED_REPORTS["review_studio"],
|
||||
],
|
||||
detail="Every pending world-class evidence key must have matching plan, intake, submission review, operator runbook, and Review Studio actions without counting planned work as completion.",
|
||||
)
|
||||
skill_os2_review = text_reports.get("skill_os2_review", "")
|
||||
ci_target_count = ci_default_target_count(skill_dir / "scripts" / "ci_test.py")
|
||||
|
||||
@@ -91,6 +91,7 @@ def main() -> None:
|
||||
"scripts/review_studio_formatting.py",
|
||||
"scripts/review_studio_gates.py",
|
||||
"scripts/review_studio_layout.py",
|
||||
"scripts/evidence_consistency_world_class.py",
|
||||
"scripts/skill_report_charts.py",
|
||||
"scripts/skill_report_i18n.py",
|
||||
"scripts/skill_report_layout.py",
|
||||
@@ -113,6 +114,7 @@ def main() -> None:
|
||||
assert "review_studio_formatting.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 "evidence_consistency_world_class.py" not in warning_text, payload["warnings"]
|
||||
assert "skill_report_charts.py" not in warning_text, payload["warnings"]
|
||||
assert "skill_report_i18n.py" not in warning_text, payload["warnings"]
|
||||
assert "skill_report_layout.py" not in warning_text, payload["warnings"]
|
||||
|
||||
Reference in New Issue
Block a user