Centralize review studio gate contract
This commit is contained in:
yaojingang
+1
-1
@@ -16,7 +16,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642"
|
||||
"package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -16,8 +16,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288"
|
||||
"package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -48,7 +48,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
|
||||
@@ -15,7 +15,7 @@
|
||||
"warn_line_threshold": 900,
|
||||
"watch_line_threshold": 720,
|
||||
"block_line_threshold": 1500,
|
||||
"largest_file_lines": 836,
|
||||
"largest_file_lines": 837,
|
||||
"watchlist_count": 8,
|
||||
"hotspot_count": 0,
|
||||
"blocker_count": 0,
|
||||
@@ -24,7 +24,7 @@
|
||||
"largest_files": [
|
||||
{
|
||||
"path": "tests/verify_review_studio.py",
|
||||
"lines": 836,
|
||||
"lines": 837,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
@@ -110,7 +110,7 @@
|
||||
"watchlist": [
|
||||
{
|
||||
"path": "tests/verify_review_studio.py",
|
||||
"lines": 836,
|
||||
"lines": 837,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
|
||||
@@ -13,7 +13,7 @@ Generated at: `2026-06-16`
|
||||
- Yao CLI command handlers: `68`
|
||||
- entrypoint command handlers: `18`
|
||||
- command modules: `6`
|
||||
- largest file lines: `836`
|
||||
- largest file lines: `837`
|
||||
- watch threshold lines: `720`
|
||||
- watchlist: `8`
|
||||
- hotspots: `0`
|
||||
@@ -29,7 +29,7 @@ No file-size hotspots found.
|
||||
|
||||
| File | Lines | Kind | Recommended next split |
|
||||
| --- | ---: | --- | --- |
|
||||
| `tests/verify_review_studio.py` | `836` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
|
||||
| `tests/verify_review_studio.py` | `837` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
|
||||
| `scripts/skill_report_model.py` | `800` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
|
||||
| `tests/verify_yao_cli.py` | `785` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
|
||||
| `scripts/render_evidence_consistency.py` | `766` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
|
||||
@@ -42,7 +42,7 @@ No file-size hotspots found.
|
||||
|
||||
| File | Lines | Kind | Severity |
|
||||
| --- | ---: | --- | --- |
|
||||
| `tests/verify_review_studio.py` | `836` | `test` | `pass` |
|
||||
| `tests/verify_review_studio.py` | `837` | `test` | `pass` |
|
||||
| `scripts/skill_report_model.py` | `800` | `internal-module` | `pass` |
|
||||
| `tests/verify_yao_cli.py` | `785` | `test` | `pass` |
|
||||
| `scripts/render_evidence_consistency.py` | `766` | `cli-script` | `pass` |
|
||||
|
||||
@@ -3,23 +3,36 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16",
|
||||
"skill_dir": ".",
|
||||
"commit": "499214b052869193d96cdd7e73f537a57eb7bb8d",
|
||||
"commit": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": false,
|
||||
"changed_file_count": 0,
|
||||
"sample": [],
|
||||
"dirty": true,
|
||||
"changed_file_count": 32,
|
||||
"sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.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/output_execution_runs.json",
|
||||
" M reports/output_execution_runs.md"
|
||||
],
|
||||
"scope": "generation-time status before this report is written"
|
||||
},
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8",
|
||||
"source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"evidence_bundle_sha256": "813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a",
|
||||
"source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -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": 32
|
||||
},
|
||||
"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": "499214b052869193d96cdd7e73f537a57eb7bb8d",
|
||||
"ready": false,
|
||||
"commit": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da",
|
||||
"status_scope": "generation-time status before this report is written",
|
||||
"reason": "clean generation-time HEAD"
|
||||
"reason": "working tree was dirty at generation time"
|
||||
},
|
||||
"evidence_bundle": {
|
||||
"algorithm": "sha256(path,label,exists,artifact_sha256)",
|
||||
@@ -64,7 +78,7 @@
|
||||
"existing_count": 25,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8"
|
||||
"sha256": "813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -138,7 +152,7 @@
|
||||
"path": "reports/output_execution_runs.json",
|
||||
"exists": true,
|
||||
"bytes": 7966,
|
||||
"sha256": "fd065f84dd529c38c2a7078d99f185fb23d08e3734fbdf7faab1c897f8129818"
|
||||
"sha256": "93a5679326b29eb9d79c3ada70679f0070be6a8aed6e50d0452c854b48efa475"
|
||||
},
|
||||
{
|
||||
"label": "blind_review",
|
||||
@@ -173,7 +187,7 @@
|
||||
"path": "reports/security_trust_report.json",
|
||||
"exists": true,
|
||||
"bytes": 120363,
|
||||
"sha256": "e6353c1589c371823d9f4944a9be8fa46f154d004668d678c3529c92143a8436"
|
||||
"sha256": "bea31eb462ca6e8021e68181ce3c4d34eaa0122dd34476b697ba59d38391cf36"
|
||||
},
|
||||
{
|
||||
"label": "python_compatibility",
|
||||
@@ -187,14 +201,14 @@
|
||||
"path": "reports/registry_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 3183,
|
||||
"sha256": "879a11cef5138fedb93365e40253d650137c7bae0f810803242640a9c6d273c1"
|
||||
"sha256": "c6d5cf3c3ec415480b7cc72623b1977c5a98e64707a7dbd13ba239dfd44159fe"
|
||||
},
|
||||
{
|
||||
"label": "package_verification",
|
||||
"path": "reports/package_verification.json",
|
||||
"exists": true,
|
||||
"bytes": 19338,
|
||||
"sha256": "45b51edb26bc22e7ab349bf8b050830d219a6971156a9c003538a99e91e47f55"
|
||||
"sha256": "dd90aae6ad68c21bd0db241b033aa00038278fd6396e75fc42f86064911ce51b"
|
||||
},
|
||||
{
|
||||
"label": "install_simulation",
|
||||
|
||||
@@ -1,19 +1,19 @@
|
||||
# Benchmark Reproducibility
|
||||
|
||||
Generated at: `2026-06-16`
|
||||
Commit: `499214b052869193d96cdd7e73f537a57eb7bb8d`
|
||||
Working tree dirty at generation: `false`
|
||||
Evidence bundle SHA256: `7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8`
|
||||
Commit: `ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da`
|
||||
Working tree dirty at generation: `true`
|
||||
Evidence bundle SHA256: `813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a`
|
||||
|
||||
## Summary
|
||||
|
||||
- reproducibility ready: `true`
|
||||
- release lock ready: `true`
|
||||
- release lock ready: `false`
|
||||
- methodology complete: `true`
|
||||
- required artifacts: `25`
|
||||
- missing artifacts: `0`
|
||||
- source contract sha256: `1e466c4508d6`
|
||||
- archive sha256: `88dc8d392047`
|
||||
- source contract sha256: `363354808bdd`
|
||||
- archive sha256: `a5a62aeb079b`
|
||||
- output cases: `5`
|
||||
- disclosed failure cases: `3`
|
||||
- reproduction commands: `23`
|
||||
@@ -22,8 +22,8 @@ Evidence bundle SHA256: `7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae
|
||||
- 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: `32`
|
||||
|
||||
This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
|
||||
|
||||
@@ -35,6 +35,7 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
|
||||
| Blocker |
|
||||
| --- |
|
||||
| release lock is not clean or commit is unavailable |
|
||||
| provider-backed model holdout evidence is incomplete |
|
||||
| human blind-review adjudication is incomplete |
|
||||
| world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) |
|
||||
@@ -42,15 +43,15 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
|
||||
## Release Lock
|
||||
|
||||
- ready: `true`
|
||||
- reason: clean generation-time HEAD
|
||||
- ready: `false`
|
||||
- reason: working tree was dirty at generation time
|
||||
- status scope: generation-time status before this report is written
|
||||
|
||||
## Evidence Bundle
|
||||
|
||||
- algorithm: `sha256(path,label,exists,artifact_sha256)`
|
||||
- artifacts: `25` / `25`
|
||||
- sha256: `7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8`
|
||||
- sha256: `813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a`
|
||||
|
||||
## Methodology Sections
|
||||
|
||||
@@ -72,15 +73,15 @@ 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 | `fd065f84dd52` |
|
||||
| output_execution | `reports/output_execution_runs.json` | present | `93a5679326b2` |
|
||||
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
|
||||
| review_adjudication | `reports/output_review_adjudication.json` | present | `bb8c72a9291e` |
|
||||
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
|
||||
| runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` |
|
||||
| trust_report | `reports/security_trust_report.json` | present | `e6353c1589c3` |
|
||||
| trust_report | `reports/security_trust_report.json` | present | `bea31eb462ca` |
|
||||
| python_compatibility | `reports/python_compatibility.json` | present | `6843f5283fd7` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `879a11cef513` |
|
||||
| package_verification | `reports/package_verification.json` | present | `45b51edb26bc` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `c6d5cf3c3ec4` |
|
||||
| package_verification | `reports/package_verification.json` | present | `dd90aae6ad68` |
|
||||
| install_simulation | `reports/install_simulation.json` | present | `1c3fdea61d50` |
|
||||
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `c0e499f9f051` |
|
||||
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `130161495dc4` |
|
||||
|
||||
@@ -6,15 +6,15 @@
|
||||
"context_budget_tier": "production",
|
||||
"context_budget_limit": 1000,
|
||||
"skill_body_tokens": 797,
|
||||
"other_text_tokens": 1050165,
|
||||
"other_text_tokens": 1050110,
|
||||
"estimated_initial_load_tokens": 990,
|
||||
"estimated_total_text_tokens": 1050962,
|
||||
"deferred_resource_tokens": 486314,
|
||||
"estimated_total_text_tokens": 1050907,
|
||||
"deferred_resource_tokens": 486227,
|
||||
"deferred_resource_warn_threshold": 120000,
|
||||
"deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 426187,
|
||||
"estimated_tokens": 426100,
|
||||
"file_count": 125
|
||||
},
|
||||
{
|
||||
@@ -36,7 +36,7 @@
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 426187,
|
||||
"estimated_tokens": 426100,
|
||||
"file_count": 125
|
||||
}
|
||||
],
|
||||
@@ -59,7 +59,7 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 426187,
|
||||
"estimated_tokens": 426100,
|
||||
"file_count": 125,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
| Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status |
|
||||
| --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- |
|
||||
| root | `.` | `production` | 1000 | 990 | 797 | 486314 | `governed` | scripts:426187 | 131.3 | - | ok |
|
||||
| root | `.` | `production` | 1000 | 990 | 797 | 486227 | `governed` | scripts:426100 | 131.3 | - | ok |
|
||||
| complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok |
|
||||
| governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok |
|
||||
|
||||
|
||||
@@ -8,11 +8,11 @@
|
||||
"budget_limit": 1000,
|
||||
"initial_tokens": 990,
|
||||
"skill_body_tokens": 797,
|
||||
"deferred_resource_tokens": 486314,
|
||||
"deferred_resource_tokens": 486227,
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 426187,
|
||||
"estimated_tokens": 426100,
|
||||
"file_count": 125
|
||||
}
|
||||
],
|
||||
@@ -35,7 +35,7 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 426187,
|
||||
"estimated_tokens": 426100,
|
||||
"file_count": 125,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
|
||||
@@ -189,12 +189,12 @@
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"status": "pass",
|
||||
"detail": "initial load 990/1000; deferred 486314/120000; top deferred scripts 426187; resource governance governed; quality density 131.3",
|
||||
"detail": "initial load 990/1000; deferred 486227/120000; top deferred scripts 426100; resource governance governed; quality density 131.3",
|
||||
"evidence": "reports/context_budget.json"
|
||||
},
|
||||
"actual": {
|
||||
"status": "pass",
|
||||
"detail": "initial load 990/1000; deferred 486314/120000; top deferred scripts 426187; resource governance governed; quality density 131.3",
|
||||
"detail": "initial load 990/1000; deferred 486227/120000; top deferred scripts 426100; resource governance governed; quality density 131.3",
|
||||
"evidence": "reports/context_budget.json"
|
||||
},
|
||||
"paths": [
|
||||
@@ -207,8 +207,8 @@
|
||||
"key": "benchmark-release-lock-self-consistency",
|
||||
"label": "Benchmark release lock matches git dirty state",
|
||||
"status": "pass",
|
||||
"expected": true,
|
||||
"actual": true,
|
||||
"expected": false,
|
||||
"actual": false,
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json"
|
||||
],
|
||||
@@ -248,8 +248,8 @@
|
||||
"key": "overview-benchmark-commit",
|
||||
"label": "overview embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "499214b052869193d96cdd7e73f537a57eb7bb8d",
|
||||
"actual": "499214b052869193d96cdd7e73f537a57eb7bb8d",
|
||||
"expected": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da",
|
||||
"actual": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-overview.json"
|
||||
@@ -261,30 +261,30 @@
|
||||
"label": "overview embeds benchmark summary fields",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"actual": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
@@ -394,8 +394,8 @@
|
||||
"key": "interpretation-benchmark-commit",
|
||||
"label": "interpretation embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "499214b052869193d96cdd7e73f537a57eb7bb8d",
|
||||
"actual": "499214b052869193d96cdd7e73f537a57eb7bb8d",
|
||||
"expected": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da",
|
||||
"actual": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-interpretation.json"
|
||||
@@ -407,30 +407,30 @@
|
||||
"label": "interpretation embeds benchmark summary fields",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"actual": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"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",
|
||||
|
||||
@@ -34,7 +34,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 32.31,
|
||||
"duration_ms": 31.35,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -62,7 +62,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 35.69,
|
||||
"duration_ms": 31.06,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -85,7 +85,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 37.25,
|
||||
"duration_ms": 31.69,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -113,7 +113,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 34.3,
|
||||
"duration_ms": 33.39,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -136,7 +136,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 32.89,
|
||||
"duration_ms": 31.94,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -164,7 +164,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 33.18,
|
||||
"duration_ms": 32.09,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -187,7 +187,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 33.42,
|
||||
"duration_ms": 31.3,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -214,7 +214,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 33.85,
|
||||
"duration_ms": 31.15,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -237,7 +237,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 34.38,
|
||||
"duration_ms": 31.77,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -266,7 +266,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 34.62,
|
||||
"duration_ms": 33.75,
|
||||
"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 | 32.31 | 33 | 0.0 | pass |
|
||||
| skill-package-contract | with_skill | command | local-output-eval-runner | 35.69 | 73 | 100.0 | pass |
|
||||
| output-eval-expectation | baseline | command | local-output-eval-runner | 37.25 | 36 | 0.0 | pass |
|
||||
| output-eval-expectation | with_skill | command | local-output-eval-runner | 34.3 | 80 | 100.0 | pass |
|
||||
| ir-before-packaging | baseline | command | local-output-eval-runner | 32.89 | 33 | 0.0 | pass |
|
||||
| ir-before-packaging | with_skill | command | local-output-eval-runner | 33.18 | 80 | 100.0 | pass |
|
||||
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 33.42 | 36 | 0.0 | pass |
|
||||
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 33.85 | 65 | 100.0 | pass |
|
||||
| file-backed-governed-package | baseline | command | local-output-eval-runner | 34.38 | 37 | 0.0 | pass |
|
||||
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 34.62 | 98 | 100.0 | pass |
|
||||
| skill-package-contract | baseline | command | local-output-eval-runner | 31.35 | 33 | 0.0 | pass |
|
||||
| skill-package-contract | with_skill | command | local-output-eval-runner | 31.06 | 73 | 100.0 | pass |
|
||||
| output-eval-expectation | baseline | command | local-output-eval-runner | 31.69 | 36 | 0.0 | pass |
|
||||
| output-eval-expectation | with_skill | command | local-output-eval-runner | 33.39 | 80 | 100.0 | pass |
|
||||
| ir-before-packaging | baseline | command | local-output-eval-runner | 31.94 | 33 | 0.0 | pass |
|
||||
| ir-before-packaging | with_skill | command | local-output-eval-runner | 32.09 | 80 | 100.0 | pass |
|
||||
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 31.3 | 36 | 0.0 | pass |
|
||||
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 31.15 | 65 | 100.0 | pass |
|
||||
| file-backed-governed-package | baseline | command | local-output-eval-runner | 31.77 | 37 | 0.0 | pass |
|
||||
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 33.75 | 98 | 100.0 | pass |
|
||||
|
||||
## Next Fixes
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"archive_entry_count": 652,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
- Package directory: `dist`
|
||||
- Targets: `4 / 4` adapters present
|
||||
- Archive present: `True`
|
||||
- Archive SHA256: `88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288`
|
||||
- Archive SHA256: `a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482`
|
||||
- Failures: `0`
|
||||
- Warnings: `0`
|
||||
|
||||
|
||||
@@ -21,8 +21,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288"
|
||||
"package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -53,7 +53,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"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": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642"
|
||||
"package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -6,8 +6,8 @@
|
||||
- Maturity: `governed`
|
||||
- Owner: `Yao Team`
|
||||
- License: `MIT`
|
||||
- Package SHA256: `1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642`
|
||||
- Archive SHA256: `88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288`
|
||||
- Package SHA256: `363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453`
|
||||
- Archive SHA256: `a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482`
|
||||
- Install simulated: `True`
|
||||
|
||||
## Compatibility
|
||||
|
||||
+11
-11
@@ -740,12 +740,12 @@
|
||||
|
||||
<section>
|
||||
<h2>核心指标</h2>
|
||||
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>4 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>125 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>199 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>836 largest lines; 8 watchlist; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock true</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>180 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>652 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
|
||||
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>5 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>125 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>199 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>837 largest lines; 8 watchlist; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock false</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>180 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>652 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<h2>审查闸门</h2>
|
||||
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 990/1000; deferred 486314/120000; top deferred scripts 426187; resource governance governed; quality density 131.3</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 125 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 199 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>196 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 836 lines; 68 CLI handlers; 18 in entrypoint</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
|
||||
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 990/1000; deferred 486227/120000; top deferred scripts 426100; resource governance governed; quality density 131.3</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 125 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 199 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>196 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 837 lines; 68 CLI handlers; 18 in entrypoint</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
|
||||
</section>
|
||||
|
||||
<div class="twocol">
|
||||
@@ -807,12 +807,12 @@
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 486314/120000; top deferred scripts 426187; resource governance governed; quality density 131.3</p></div>
|
||||
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 486227/120000; top deferred scripts 426100; resource governance governed; quality density 131.3</p></div>
|
||||
<div class="panel"><h2>编译证据</h2><p>Review reports/compiled_targets.md before packaging to inspect target adapter modes, generated files, preserved semantics, warnings, and unsupported features.</p></div>
|
||||
</section>
|
||||
|
||||
<section id="trust" class="twocol">
|
||||
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>125</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642</code></dd></div></dl></div>
|
||||
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>125</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453</code></dd></div></dl></div>
|
||||
<div class="panel"><h2>安全边界</h2><p>高风险 secret、远程 inline execution、缺失依赖策略或无法解释的脚本接口应阻断 governed release。</p></div>
|
||||
</section>
|
||||
|
||||
@@ -837,14 +837,14 @@
|
||||
</section>
|
||||
|
||||
<section id="telemetry" class="twocol">
|
||||
<div class="panel"><h2>运营回路</h2><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true</p></div>
|
||||
<div class="panel"><h2>运营回路</h2><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false</p></div>
|
||||
<div class="panel"><h2>漂移信号</h2><dl class='kv-grid'><div><dt>事件数</dt><dd>1</dd></div><div><dt>采用率</dt><dd>0</dd></div><div><dt>漏触发</dt><dd>0</dd></div><div><dt>Bad Output Count</dt><dd>0</dd></div><div><dt>风险带</dt><dd>low</dd></div></dl></div>
|
||||
</section>
|
||||
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>日常运维</h2><dl class='kv-grid'><div><dt>决策</dt><dd>proposal-review</dd></div><div><dt>提案数</dt><dd>5</dd></div><div><dt>Approval Count</dt><dd>0</dd></div><div><dt>Pending Review Count</dt><dd>0</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>世界级</dt><dd>否</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>1</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>日常运维</h2><dl class='kv-grid'><div><dt>决策</dt><dd>proposal-review</dd></div><div><dt>提案数</dt><dd>5</dd></div><div><dt>Approval Count</dt><dd>0</dd></div><div><dt>Pending Review Count</dt><dd>0</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>世界级</dt><dd>否</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>1</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
|
||||
</section>
|
||||
|
||||
|
||||
@@ -877,8 +877,8 @@
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>4</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
|
||||
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>5</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>release lock is not clean or commit is unavailable</span></li><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
@@ -898,12 +898,12 @@
|
||||
|
||||
<section id="registry" class="twocol">
|
||||
<div class="panel"><h2>注册审计</h2><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p></div>
|
||||
<div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible, vscode</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288</code></dd></div></dl></div>
|
||||
<div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible, vscode</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482</code></dd></div></dl></div>
|
||||
</section>
|
||||
|
||||
<section id="release" class="twocol">
|
||||
<div class="panel"><h2>发布路线</h2><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p></div>
|
||||
<div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd>是</dd></div><div><dt>Zip 条目</dt><dd>652</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288</code></dd></div></dl></div>
|
||||
<div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd>是</dd></div><div><dt>Zip 条目</dt><dd>652</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482</code></dd></div></dl></div>
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
|
||||
+84
-70
@@ -43,7 +43,7 @@
|
||||
"key": "context-budget",
|
||||
"label": "上下文",
|
||||
"status": "pass",
|
||||
"detail": "initial load 990/1000; deferred 486314/120000; top deferred scripts 426187; resource governance governed; quality density 131.3",
|
||||
"detail": "initial load 990/1000; deferred 486227/120000; top deferred scripts 426100; resource governance governed; quality density 131.3",
|
||||
"evidence": "reports/context_budget.json",
|
||||
"link": "context_budget.md"
|
||||
},
|
||||
@@ -75,7 +75,7 @@
|
||||
"key": "architecture-maintainability",
|
||||
"label": "架构维护",
|
||||
"status": "pass",
|
||||
"detail": "196 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 836 lines; 68 CLI handlers; 18 in entrypoint",
|
||||
"detail": "196 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 837 lines; 68 CLI handlers; 18 in entrypoint",
|
||||
"evidence": "reports/architecture_maintainability.json",
|
||||
"link": "architecture_maintainability.md"
|
||||
},
|
||||
@@ -107,7 +107,7 @@
|
||||
"key": "operations-loop",
|
||||
"label": "运营回路",
|
||||
"status": "pass",
|
||||
"detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true",
|
||||
"detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false",
|
||||
"evidence": "reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly",
|
||||
"link": "adoption_drift_report.md"
|
||||
},
|
||||
@@ -1922,13 +1922,13 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8",
|
||||
"source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"evidence_bundle_sha256": "813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a",
|
||||
"source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -1946,11 +1946,11 @@
|
||||
"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": 32
|
||||
},
|
||||
"commit": "499214b052869193d96cdd7e73f537a57eb7bb8d",
|
||||
"commit": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da",
|
||||
"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.",
|
||||
@@ -2055,7 +2055,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 216,
|
||||
"package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642"
|
||||
"package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -2093,8 +2093,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288"
|
||||
"package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -2125,7 +2125,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -2141,7 +2141,7 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"archive_entry_count": 652,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
@@ -2220,12 +2220,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288"
|
||||
"to": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642"
|
||||
"to": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -4642,7 +4642,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 32.31,
|
||||
"duration_ms": 31.35,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4670,7 +4670,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 35.69,
|
||||
"duration_ms": 31.06,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4693,7 +4693,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 37.25,
|
||||
"duration_ms": 31.69,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4721,7 +4721,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 34.3,
|
||||
"duration_ms": 33.39,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4744,7 +4744,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 32.89,
|
||||
"duration_ms": 31.94,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4772,7 +4772,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 33.18,
|
||||
"duration_ms": 32.09,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4795,7 +4795,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 33.42,
|
||||
"duration_ms": 31.3,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4822,7 +4822,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 33.85,
|
||||
"duration_ms": 31.15,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4845,7 +4845,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 34.38,
|
||||
"duration_ms": 31.77,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4874,7 +4874,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 34.62,
|
||||
"duration_ms": 33.75,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5600,23 +5600,36 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16",
|
||||
"skill_dir": ".",
|
||||
"commit": "499214b052869193d96cdd7e73f537a57eb7bb8d",
|
||||
"commit": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": false,
|
||||
"changed_file_count": 0,
|
||||
"sample": [],
|
||||
"dirty": true,
|
||||
"changed_file_count": 32,
|
||||
"sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.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/output_execution_runs.json",
|
||||
" M reports/output_execution_runs.md"
|
||||
],
|
||||
"scope": "generation-time status before this report is written"
|
||||
},
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8",
|
||||
"source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"evidence_bundle_sha256": "813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a",
|
||||
"source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -5634,14 +5647,15 @@
|
||||
"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": 32
|
||||
},
|
||||
"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)",
|
||||
@@ -5650,10 +5664,10 @@
|
||||
"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": "499214b052869193d96cdd7e73f537a57eb7bb8d",
|
||||
"ready": false,
|
||||
"commit": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da",
|
||||
"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)",
|
||||
@@ -5661,7 +5675,7 @@
|
||||
"existing_count": 25,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8"
|
||||
"sha256": "813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -5735,7 +5749,7 @@
|
||||
"path": "reports/output_execution_runs.json",
|
||||
"exists": true,
|
||||
"bytes": 7966,
|
||||
"sha256": "fd065f84dd529c38c2a7078d99f185fb23d08e3734fbdf7faab1c897f8129818"
|
||||
"sha256": "93a5679326b29eb9d79c3ada70679f0070be6a8aed6e50d0452c854b48efa475"
|
||||
},
|
||||
{
|
||||
"label": "blind_review",
|
||||
@@ -5770,7 +5784,7 @@
|
||||
"path": "reports/security_trust_report.json",
|
||||
"exists": true,
|
||||
"bytes": 120363,
|
||||
"sha256": "e6353c1589c371823d9f4944a9be8fa46f154d004668d678c3529c92143a8436"
|
||||
"sha256": "bea31eb462ca6e8021e68181ce3c4d34eaa0122dd34476b697ba59d38391cf36"
|
||||
},
|
||||
{
|
||||
"label": "python_compatibility",
|
||||
@@ -5784,14 +5798,14 @@
|
||||
"path": "reports/registry_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 3183,
|
||||
"sha256": "879a11cef5138fedb93365e40253d650137c7bae0f810803242640a9c6d273c1"
|
||||
"sha256": "c6d5cf3c3ec415480b7cc72623b1977c5a98e64707a7dbd13ba239dfd44159fe"
|
||||
},
|
||||
{
|
||||
"label": "package_verification",
|
||||
"path": "reports/package_verification.json",
|
||||
"exists": true,
|
||||
"bytes": 19338,
|
||||
"sha256": "45b51edb26bc22e7ab349bf8b050830d219a6971156a9c003538a99e91e47f55"
|
||||
"sha256": "dd90aae6ad68c21bd0db241b033aa00038278fd6396e75fc42f86064911ce51b"
|
||||
},
|
||||
{
|
||||
"label": "install_simulation",
|
||||
@@ -12045,7 +12059,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 216,
|
||||
"package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642"
|
||||
"package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": [],
|
||||
@@ -16304,7 +16318,7 @@
|
||||
"warn_line_threshold": 900,
|
||||
"watch_line_threshold": 720,
|
||||
"block_line_threshold": 1500,
|
||||
"largest_file_lines": 836,
|
||||
"largest_file_lines": 837,
|
||||
"watchlist_count": 8,
|
||||
"hotspot_count": 0,
|
||||
"blocker_count": 0,
|
||||
@@ -16313,7 +16327,7 @@
|
||||
"largest_files": [
|
||||
{
|
||||
"path": "tests/verify_review_studio.py",
|
||||
"lines": 836,
|
||||
"lines": 837,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
@@ -16399,7 +16413,7 @@
|
||||
"watchlist": [
|
||||
{
|
||||
"path": "tests/verify_review_studio.py",
|
||||
"lines": 836,
|
||||
"lines": 837,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
@@ -16469,15 +16483,15 @@
|
||||
"context_budget_tier": "production",
|
||||
"context_budget_limit": 1000,
|
||||
"skill_body_tokens": 797,
|
||||
"other_text_tokens": 1050165,
|
||||
"other_text_tokens": 1050110,
|
||||
"estimated_initial_load_tokens": 990,
|
||||
"estimated_total_text_tokens": 1050962,
|
||||
"deferred_resource_tokens": 486314,
|
||||
"estimated_total_text_tokens": 1050907,
|
||||
"deferred_resource_tokens": 486227,
|
||||
"deferred_resource_warn_threshold": 120000,
|
||||
"deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 426187,
|
||||
"estimated_tokens": 426100,
|
||||
"file_count": 125
|
||||
},
|
||||
{
|
||||
@@ -16499,7 +16513,7 @@
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 426187,
|
||||
"estimated_tokens": 426100,
|
||||
"file_count": 125
|
||||
}
|
||||
],
|
||||
@@ -16522,7 +16536,7 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 426187,
|
||||
"estimated_tokens": 426100,
|
||||
"file_count": 125,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
@@ -18516,7 +18530,7 @@
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
@@ -18533,7 +18547,7 @@
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
@@ -18982,7 +18996,7 @@
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true
|
||||
},
|
||||
"actions": [
|
||||
@@ -19031,7 +19045,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -19051,7 +19065,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -19303,7 +19317,7 @@
|
||||
"no_route_opportunity_count": 0
|
||||
},
|
||||
"release_state": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4
|
||||
@@ -23413,8 +23427,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288"
|
||||
"package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -23445,7 +23459,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -23470,7 +23484,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642"
|
||||
"package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -23493,7 +23507,7 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"archive_entry_count": 652,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
@@ -24501,12 +24515,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288"
|
||||
"to": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642"
|
||||
"to": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
+15
-15
@@ -997,13 +997,13 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8",
|
||||
"source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"evidence_bundle_sha256": "813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a",
|
||||
"source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -1021,11 +1021,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 32
|
||||
},
|
||||
"commit": "499214b052869193d96cdd7e73f537a57eb7bb8d",
|
||||
"commit": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
|
||||
@@ -1130,7 +1130,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 216,
|
||||
"package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642"
|
||||
"package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1168,8 +1168,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288"
|
||||
"package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -1200,7 +1200,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -1216,7 +1216,7 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"archive_entry_count": 652,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
@@ -1295,12 +1295,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288"
|
||||
"to": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642"
|
||||
"to": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -23,7 +23,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 216,
|
||||
"package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642"
|
||||
"package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": [],
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
- Interactive scripts: `0`
|
||||
- Package hash scope: `source-contract-without-generated-reports`
|
||||
- Package hash files: `216`
|
||||
- Package SHA256: `1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642`
|
||||
- Package SHA256: `363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453`
|
||||
|
||||
## Failures
|
||||
|
||||
|
||||
@@ -1001,13 +1001,13 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8",
|
||||
"source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"evidence_bundle_sha256": "813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a",
|
||||
"source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -1025,11 +1025,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 32
|
||||
},
|
||||
"commit": "499214b052869193d96cdd7e73f537a57eb7bb8d",
|
||||
"commit": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
|
||||
@@ -1134,7 +1134,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 216,
|
||||
"package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642"
|
||||
"package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1172,8 +1172,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288"
|
||||
"package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -1204,7 +1204,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -1220,7 +1220,7 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"archive_entry_count": 652,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
@@ -1299,12 +1299,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288"
|
||||
"to": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642"
|
||||
"to": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
+15
-15
@@ -996,13 +996,13 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "7540215c8aa2db458cd10433f2cac56bc2931c58df057232309fdae3a5f8e0e8",
|
||||
"source_contract_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"evidence_bundle_sha256": "813517ab4bc2b504a720544f29c80e1bf7b09bbd1938ffdbb840b33aa5abb76a",
|
||||
"source_contract_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -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": 32
|
||||
},
|
||||
"commit": "499214b052869193d96cdd7e73f537a57eb7bb8d",
|
||||
"commit": "ca94d734ee43bd514d4bf83f5c9a7cb7bdc161da",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
|
||||
@@ -1129,7 +1129,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 216,
|
||||
"package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642"
|
||||
"package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1167,8 +1167,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642",
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288"
|
||||
"package_sha256": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -1199,7 +1199,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -1215,7 +1215,7 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288",
|
||||
"archive_sha256": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482",
|
||||
"archive_entry_count": 652,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
@@ -1294,12 +1294,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288"
|
||||
"to": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642"
|
||||
"to": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -14,7 +14,7 @@
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
@@ -31,7 +31,7 @@
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
@@ -480,7 +480,7 @@
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true
|
||||
},
|
||||
"actions": [
|
||||
|
||||
@@ -14,7 +14,7 @@ Generated at: `2026-06-16`
|
||||
- local blueprint ready: `true`
|
||||
- public world-class ready: `false`
|
||||
- world-class pending: `4`
|
||||
- release lock ready: `true`
|
||||
- release lock ready: `false`
|
||||
- evidence consistency ok: `true`
|
||||
|
||||
This report is an operations cockpit for explicit-source SkillOps. It does not scan private logs, write source files, apply patches, or count as world-class external or human evidence.
|
||||
|
||||
@@ -15,7 +15,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -35,7 +35,7 @@
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -287,7 +287,7 @@
|
||||
"no_route_opportunity_count": 0
|
||||
},
|
||||
"release_state": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4
|
||||
|
||||
@@ -13,7 +13,7 @@ Week: `2026-W25`
|
||||
- top_score: `88`
|
||||
- skill_count: `12`
|
||||
- actionable_portfolio_issue_count: `0`
|
||||
- release_lock_ready: `True`
|
||||
- release_lock_ready: `False`
|
||||
- evidence_consistency_ok: `True`
|
||||
- public_world_class_ready: `False`
|
||||
- world_class_pending_count: `4`
|
||||
|
||||
@@ -70,12 +70,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "88dc8d39204730f91d5738858e9000ac9b657ba09ab02d6d4804dac1b2546288"
|
||||
"to": "a5a62aeb079b925fe3e52446a607508209ab40a9fa9b2be2335dee35b182c482"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "1e466c4508d6ebb845923331fe534197df4fddf9e3b778c789ce8d349a555642"
|
||||
"to": "363354808bdd7c9517352e7a709ea13cd2a3878e526fb1f7121f71de5e746453"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -6,26 +6,10 @@ from datetime import date, timedelta
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from review_studio_gates import REVIEW_STUDIO_GATE_KEYS
|
||||
|
||||
|
||||
ROOT = Path(__file__).resolve().parent.parent
|
||||
REVIEW_STUDIO_GATE_KEYS = {
|
||||
"intent-canvas",
|
||||
"trigger-lab",
|
||||
"output-lab",
|
||||
"context-budget",
|
||||
"runtime-matrix",
|
||||
"trust-report",
|
||||
"python-compat",
|
||||
"architecture-maintainability",
|
||||
"permission-gates",
|
||||
"permission-runtime",
|
||||
"skill-atlas",
|
||||
"operations-loop",
|
||||
"review-waivers",
|
||||
"world-class-evidence",
|
||||
"registry-audit",
|
||||
"release-notes",
|
||||
}
|
||||
NON_WAIVABLE_GATE_KEYS = {"review-waivers", "world-class-evidence"}
|
||||
WAIVERABLE_GATE_KEYS = REVIEW_STUDIO_GATE_KEYS - NON_WAIVABLE_GATE_KEYS
|
||||
KNOWN_GATE_KEYS = WAIVERABLE_GATE_KEYS
|
||||
|
||||
@@ -20,6 +20,26 @@ SCRIPT_INTERFACE_REASON = "Imported by render_review_studio.py to keep Review St
|
||||
|
||||
ROOT = Path(__file__).resolve().parent.parent
|
||||
|
||||
GATE_WEIGHTS = {
|
||||
"trigger-lab": 15,
|
||||
"output-lab": 20,
|
||||
"context-budget": 10,
|
||||
"runtime-matrix": 10,
|
||||
"trust-report": 10,
|
||||
"python-compat": 10,
|
||||
"architecture-maintainability": 10,
|
||||
"permission-gates": 10,
|
||||
"permission-runtime": 10,
|
||||
"skill-atlas": 10,
|
||||
"operations-loop": 10,
|
||||
"review-waivers": 10,
|
||||
"world-class-evidence": 10,
|
||||
"registry-audit": 10,
|
||||
"release-notes": 10,
|
||||
"intent-canvas": 10,
|
||||
}
|
||||
REVIEW_STUDIO_GATE_KEYS = frozenset(GATE_WEIGHTS)
|
||||
|
||||
|
||||
def _load_json(path: Path) -> dict[str, Any]:
|
||||
if not path.exists():
|
||||
@@ -653,28 +673,10 @@ def build_gates(skill_dir: Path, output_html: Path, data: dict[str, dict[str, An
|
||||
|
||||
|
||||
def weighted_score(gates: list[dict[str, str]]) -> int:
|
||||
weights = {
|
||||
"trigger-lab": 15,
|
||||
"output-lab": 20,
|
||||
"context-budget": 10,
|
||||
"runtime-matrix": 10,
|
||||
"trust-report": 10,
|
||||
"python-compat": 10,
|
||||
"architecture-maintainability": 10,
|
||||
"permission-gates": 10,
|
||||
"permission-runtime": 10,
|
||||
"skill-atlas": 10,
|
||||
"operations-loop": 10,
|
||||
"review-waivers": 10,
|
||||
"world-class-evidence": 10,
|
||||
"registry-audit": 10,
|
||||
"release-notes": 10,
|
||||
"intent-canvas": 10,
|
||||
}
|
||||
earned = 0.0
|
||||
total = 0.0
|
||||
for item in gates:
|
||||
weight = weights.get(item["key"], 5)
|
||||
weight = GATE_WEIGHTS.get(item["key"], 5)
|
||||
total += weight
|
||||
if item["status"] == "pass":
|
||||
earned += weight
|
||||
|
||||
@@ -308,7 +308,8 @@ def main() -> None:
|
||||
"world-class-evidence",
|
||||
}, payload
|
||||
gate_keys = {item["key"] for item in payload["gates"]}
|
||||
assert {"intent-canvas", "trigger-lab", "output-lab", "context-budget", "runtime-matrix", "trust-report", "python-compat", "architecture-maintainability", "permission-gates", "permission-runtime", "skill-atlas", "operations-loop", "review-waivers", "world-class-evidence", "registry-audit", "release-notes"} <= gate_keys, payload
|
||||
assert gate_keys == review_gates.REVIEW_STUDIO_GATE_KEYS, payload
|
||||
assert set(review_gates.GATE_WEIGHTS) == review_gates.REVIEW_STUDIO_GATE_KEYS, review_gates.GATE_WEIGHTS
|
||||
output_gate = next(item for item in payload["gates"] if item["key"] == "output-lab")
|
||||
assert output_gate["status"] == "warn", output_gate
|
||||
assert "5/5 cases" in output_gate["detail"], output_gate
|
||||
|
||||
@@ -11,6 +11,7 @@ SCRIPT = ROOT / "scripts" / "render_review_waivers.py"
|
||||
sys.path.insert(0, str(ROOT / "scripts"))
|
||||
|
||||
import render_review_waivers as review_waivers # noqa: E402
|
||||
import review_studio_gates as review_gates # noqa: E402
|
||||
|
||||
|
||||
def run(*args: str, check: bool = True) -> subprocess.CompletedProcess:
|
||||
@@ -24,7 +25,7 @@ def run(*args: str, check: bool = True) -> subprocess.CompletedProcess:
|
||||
|
||||
|
||||
def main() -> None:
|
||||
assert review_waivers.REVIEW_STUDIO_GATE_KEYS == {
|
||||
expected_gate_keys = {
|
||||
"intent-canvas",
|
||||
"trigger-lab",
|
||||
"output-lab",
|
||||
@@ -41,7 +42,10 @@ def main() -> None:
|
||||
"world-class-evidence",
|
||||
"registry-audit",
|
||||
"release-notes",
|
||||
}, review_waivers.REVIEW_STUDIO_GATE_KEYS
|
||||
}
|
||||
assert review_gates.REVIEW_STUDIO_GATE_KEYS == expected_gate_keys, review_gates.REVIEW_STUDIO_GATE_KEYS
|
||||
assert set(review_gates.GATE_WEIGHTS) == expected_gate_keys, review_gates.GATE_WEIGHTS
|
||||
assert review_waivers.REVIEW_STUDIO_GATE_KEYS == review_gates.REVIEW_STUDIO_GATE_KEYS
|
||||
assert review_waivers.NON_WAIVABLE_GATE_KEYS == {"review-waivers", "world-class-evidence"}
|
||||
assert "python-compat" in review_waivers.WAIVERABLE_GATE_KEYS
|
||||
assert "architecture-maintainability" in review_waivers.WAIVERABLE_GATE_KEYS
|
||||
|
||||
Reference in New Issue
Block a user