Add review action contract fields

This commit is contained in:
yaojingang
2026-06-17 05:25:52 +08:00
parent 10dd886ae7
commit 4c30a659ef
50 changed files with 537 additions and 376 deletions
+1 -1
View File
@@ -16,7 +16,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
"package_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b"
}
]
}
+1 -1
View File
@@ -16,7 +16,7 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"package_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
},
"compatibility": {
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-16T21:24:27Z",
"skill_dir": ".",
"source_patterns": "reports/user_patterns.json",
"pattern_count": 5,
+1 -1
View File
@@ -1,6 +1,6 @@
# Adaptation Proposals
- Generated at: `2026-06-17`
- Generated at: `2026-06-16T21:24:27Z`
- Pattern report: `reports/user_patterns.json`
- Proposal only: `true`
- Writes repository files: `false`
+1 -1
View File
@@ -1,7 +1,7 @@
{
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-16T21:18:14Z",
"generated_at": "2026-06-16T21:24:56Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
+12 -12
View File
@@ -42,7 +42,7 @@
},
{
"path": "tests/verify_evidence_consistency.py",
"lines": 671,
"lines": 686,
"kind": "test",
"severity": "pass",
"early_watch": true,
@@ -50,7 +50,7 @@
},
{
"path": "scripts/render_evidence_consistency.py",
"lines": 647,
"lines": 659,
"kind": "cli-script",
"severity": "pass",
"early_watch": true,
@@ -104,6 +104,14 @@
"early_watch": false,
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/render_review_studio.py",
"lines": 578,
"kind": "cli-script",
"severity": "pass",
"early_watch": false,
"recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
},
{
"path": "scripts/world_class_submission_kit_rendering.py",
"lines": 576,
@@ -111,14 +119,6 @@
"severity": "pass",
"early_watch": false,
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/render_review_studio.py",
"lines": 575,
"kind": "cli-script",
"severity": "pass",
"early_watch": false,
"recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
}
],
"watchlist": [],
@@ -141,7 +141,7 @@
},
{
"path": "tests/verify_evidence_consistency.py",
"lines": 671,
"lines": 686,
"kind": "test",
"severity": "pass",
"early_watch": true,
@@ -149,7 +149,7 @@
},
{
"path": "scripts/render_evidence_consistency.py",
"lines": 647,
"lines": 659,
"kind": "cli-script",
"severity": "pass",
"early_watch": true,
+5 -5
View File
@@ -37,8 +37,8 @@ No near-threshold files found.
| --- | ---: | --- | --- |
| `tests/verify_yao_cli.py` | `696` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
| `tests/verify_world_class_evidence_intake.py` | `690` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
| `tests/verify_evidence_consistency.py` | `671` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
| `scripts/render_evidence_consistency.py` | `647` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
| `tests/verify_evidence_consistency.py` | `686` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
| `scripts/render_evidence_consistency.py` | `659` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
## Largest Files
@@ -46,16 +46,16 @@ No near-threshold files found.
| --- | ---: | --- | --- |
| `tests/verify_yao_cli.py` | `696` | `test` | `pass` |
| `tests/verify_world_class_evidence_intake.py` | `690` | `test` | `pass` |
| `tests/verify_evidence_consistency.py` | `671` | `test` | `pass` |
| `scripts/render_evidence_consistency.py` | `647` | `cli-script` | `pass` |
| `tests/verify_evidence_consistency.py` | `686` | `test` | `pass` |
| `scripts/render_evidence_consistency.py` | `659` | `cli-script` | `pass` |
| `tests/verify_output_review_adjudication.py` | `599` | `test` | `pass` |
| `scripts/render_skill_overview.py` | `588` | `cli-script` | `pass` |
| `scripts/build_skill_atlas.py` | `586` | `cli-script` | `pass` |
| `scripts/optimize_description.py` | `585` | `cli-script` | `pass` |
| `scripts/trust_check.py` | `582` | `cli-script` | `pass` |
| `tests/verify_world_class_evidence_ledger.py` | `579` | `test` | `pass` |
| `scripts/render_review_studio.py` | `578` | `cli-script` | `pass` |
| `scripts/world_class_submission_kit_rendering.py` | `576` | `internal-module` | `pass` |
| `scripts/render_review_studio.py` | `575` | `cli-script` | `pass` |
## Release Rule
+45 -38
View File
@@ -3,43 +3,49 @@
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
"commit": "10dd886ae711ea7edb426ecb7e8747cf38ac55a8",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 15,
"changed_file_count": 52,
"generated_dirty": true,
"generated_changed_file_count": 15,
"source_dirty": false,
"source_changed_file_count": 0,
"generated_changed_file_count": 47,
"source_dirty": true,
"source_changed_file_count": 5,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/adaptation_proposals.json",
" M reports/adaptation_proposals.md",
" M reports/adoption_drift_report.json",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" M reports/benchmark_reproducibility.json",
" M reports/benchmark_reproducibility.md",
" M reports/context_budget.json",
" M reports/evidence_consistency.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md",
" M reports/review-studio.html",
" M reports/review-studio.json",
" M reports/review-viewer.json",
" M reports/skill-interpretation.json"
" M reports/context_budget.md",
" M reports/context_budget_summary.json"
],
"source_sample": [
" M scripts/render_evidence_consistency.py",
" M scripts/render_review_studio.py",
" M scripts/review_studio_actions.py",
" M tests/verify_evidence_consistency.py",
" M tests/verify_review_studio.py"
],
"source_sample": [],
"generated_sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/adaptation_proposals.json",
" M reports/adaptation_proposals.md",
" M reports/adoption_drift_report.json",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" M reports/benchmark_reproducibility.json",
" M reports/benchmark_reproducibility.md",
" M reports/context_budget.json",
" M reports/evidence_consistency.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md",
" M reports/review-studio.html",
" M reports/review-studio.json",
" M reports/review-viewer.json",
" M reports/skill-interpretation.json"
" M reports/context_budget.md",
" M reports/context_budget_summary.json"
],
"generated_dirty_prefixes": [
"dist/",
@@ -53,12 +59,12 @@
},
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15",
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"evidence_bundle_sha256": "ea30ec16d96bab3ffefae8913c3c18940d4ebbe12aa3d7047efc1e1fdf6d2e27",
"source_contract_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -77,18 +83,19 @@
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 15,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"changed_file_count": 52,
"source_tree_dirty": true,
"source_changed_file_count": 5,
"generated_tree_dirty": true,
"generated_changed_file_count": 15
"generated_changed_file_count": 47
},
"public_claim": {
"ready": false,
"scope": "public benchmark or world-class readiness claim",
"blockers": [
"release lock is not clean or commit is unavailable",
"provider-backed model holdout evidence is incomplete",
"human blind-review adjudication is incomplete",
"world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
@@ -97,12 +104,12 @@
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
},
"release_lock": {
"ready": true,
"commit": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
"ready": false,
"commit": "10dd886ae711ea7edb426ecb7e8747cf38ac55a8",
"status_scope": "generation-time status before this report is written",
"source_changed_file_count": 0,
"generated_changed_file_count": 15,
"reason": "only generated evidence artifacts were dirty at generation time"
"source_changed_file_count": 5,
"generated_changed_file_count": 47,
"reason": "source files were dirty at generation time"
},
"evidence_bundle": {
"algorithm": "sha256(path,label,exists,artifact_sha256)",
@@ -110,7 +117,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15"
"sha256": "ea30ec16d96bab3ffefae8913c3c18940d4ebbe12aa3d7047efc1e1fdf6d2e27"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -183,8 +190,8 @@
"label": "output_execution",
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7965,
"sha256": "db2564dbc622814ae57e8459d2a241b0f76fbf78f00af1d484ca5cdaa3265cae"
"bytes": 7966,
"sha256": "8b9ef4d24793119f47c6fcd2b21554b93b5b7415e6387de80b36b835d5a72f2f"
},
{
"label": "blind_review",
@@ -219,7 +226,7 @@
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 136999,
"sha256": "079165fefd9fb3e5c25c1c486738e21bff2a59ca52b03dae9d505d6896341bf1"
"sha256": "35d1ec9d8404ca8f846aa72fdf810abb4c58ef00ca31f2e74de42bc3841471a4"
},
{
"label": "python_compatibility",
@@ -233,7 +240,7 @@
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "db05339565be76ece69a89ba4b84dc3af44c711dc68860cbf319b86766d44541"
"sha256": "3213fd1c9fb85740c2d7c36a04497f3a5cbaffe65f92595196bffdfae5e835e7"
},
{
"label": "package_verification",
+16 -15
View File
@@ -1,20 +1,20 @@
# Benchmark Reproducibility
Generated at: `2026-06-17`
Commit: `cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547`
Commit: `10dd886ae711ea7edb426ecb7e8747cf38ac55a8`
Working tree dirty at generation: `true`
Source tree dirty at generation: `false`
Source tree dirty at generation: `true`
Generated evidence dirty at generation: `true`
Evidence bundle SHA256: `b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15`
Evidence bundle SHA256: `ea30ec16d96bab3ffefae8913c3c18940d4ebbe12aa3d7047efc1e1fdf6d2e27`
## Summary
- reproducibility ready: `true`
- release lock ready: `true`
- release lock ready: `false`
- methodology complete: `true`
- required artifacts: `25`
- missing artifacts: `0`
- source contract sha256: `a7c24fc193a5`
- source contract sha256: `fda25ac83d07`
- archive sha256: `7db44f059844`
- output cases: `5`
- disclosed failure cases: `3`
@@ -24,10 +24,10 @@ Evidence bundle SHA256: `b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c
- world-class ready: `false`
- world-class source checks: `10` pass / `19` total; `9` blocked
- public claim ready: `false`
- public claim blockers: `4`
- changed files at generation: `15`
- source changed files at generation: `0`
- generated changed files at generation: `15`
- public claim blockers: `5`
- changed files at generation: `52`
- source changed files at generation: `5`
- generated changed files at generation: `47`
This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit and dirty samples are generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
@@ -39,6 +39,7 @@ This report proves local benchmark reproducibility only. It keeps external provi
| Blocker |
| --- |
| release lock is not clean or commit is unavailable |
| provider-backed model holdout evidence is incomplete |
| human blind-review adjudication is incomplete |
| world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) |
@@ -46,15 +47,15 @@ This report proves local benchmark reproducibility only. It keeps external provi
## Release Lock
- ready: `true`
- reason: only generated evidence artifacts were dirty at generation time
- ready: `false`
- reason: source files were dirty at generation time
- status scope: generation-time status before this report is written
## Evidence Bundle
- algorithm: `sha256(path,label,exists,artifact_sha256)`
- artifacts: `25` / `25`
- sha256: `b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15`
- sha256: `ea30ec16d96bab3ffefae8913c3c18940d4ebbe12aa3d7047efc1e1fdf6d2e27`
## Methodology Sections
@@ -76,14 +77,14 @@ This report proves local benchmark reproducibility only. It keeps external provi
| output_cases | `evals/output/cases.jsonl` | present | `a6ae96857116` |
| output_schema | `evals/output/schema.json` | present | `8ee340c95064` |
| output_scorecard | `reports/output_quality_scorecard.json` | present | `0806258a8e08` |
| output_execution | `reports/output_execution_runs.json` | present | `db2564dbc622` |
| output_execution | `reports/output_execution_runs.json` | present | `8b9ef4d24793` |
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
| review_adjudication | `reports/output_review_adjudication.json` | present | `91fd88dd9b0f` |
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
| runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` |
| trust_report | `reports/security_trust_report.json` | present | `079165fefd9f` |
| trust_report | `reports/security_trust_report.json` | present | `35d1ec9d8404` |
| python_compatibility | `reports/python_compatibility.json` | present | `cb95afb7d7cc` |
| registry_audit | `reports/registry_audit.json` | present | `db05339565be` |
| registry_audit | `reports/registry_audit.json` | present | `3213fd1c9fb8` |
| package_verification | `reports/package_verification.json` | present | `7aa6c25e8154` |
| install_simulation | `reports/install_simulation.json` | present | `d2bea19ea46f` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `ad57230481ed` |
+6 -6
View File
@@ -6,15 +6,15 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 797,
"other_text_tokens": 1139267,
"other_text_tokens": 1139919,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1140064,
"deferred_resource_tokens": 515669,
"estimated_total_text_tokens": 1140716,
"deferred_resource_tokens": 515966,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 454366,
"estimated_tokens": 454663,
"file_count": 152
},
{
@@ -36,7 +36,7 @@
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 454366,
"estimated_tokens": 454663,
"file_count": 152
}
],
@@ -59,7 +59,7 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 454366,
"estimated_tokens": 454663,
"file_count": 152,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
+1 -1
View File
@@ -2,7 +2,7 @@
| Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status |
| --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- |
| root | `.` | `production` | 1000 | 990 | 797 | 515669 | `governed` | scripts:454366 | 131.3 | - | ok |
| root | `.` | `production` | 1000 | 990 | 797 | 515966 | `governed` | scripts:454663 | 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 |
+3 -3
View File
@@ -8,11 +8,11 @@
"budget_limit": 1000,
"initial_tokens": 990,
"skill_body_tokens": 797,
"deferred_resource_tokens": 515669,
"deferred_resource_tokens": 515966,
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 454366,
"estimated_tokens": 454663,
"file_count": 152
}
],
@@ -35,7 +35,7 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 454366,
"estimated_tokens": 454663,
"file_count": 152,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
+145 -107
View File
@@ -203,30 +203,48 @@
"output-lab": {
"review_action_id": "review-action-output-lab",
"review_action_status": "warn",
"title_present": true,
"next_step_present": true,
"reason_present": true,
"source_ref_present": true,
"verification_command_present": true,
"top_level_action_id": "review-action-output-lab",
"top_level_action_status": "warn",
"top_level_title_present": true,
"top_level_next_step_present": true,
"top_level_reason_present": true,
"top_level_source_ref_present": true,
"top_level_verification_command_present": true
},
"review-waivers": {
"review_action_id": "review-action-review-waivers",
"review_action_status": "warn",
"title_present": true,
"next_step_present": true,
"reason_present": true,
"source_ref_present": true,
"verification_command_present": true,
"top_level_action_id": "review-action-review-waivers",
"top_level_action_status": "warn",
"top_level_title_present": true,
"top_level_next_step_present": true,
"top_level_reason_present": true,
"top_level_source_ref_present": true,
"top_level_verification_command_present": true
},
"world-class-evidence": {
"review_action_id": "review-action-world-class-evidence",
"review_action_status": "warn",
"title_present": true,
"next_step_present": true,
"reason_present": true,
"source_ref_present": true,
"verification_command_present": true,
"top_level_action_id": "review-action-world-class-evidence",
"top_level_action_status": "warn",
"top_level_title_present": true,
"top_level_next_step_present": true,
"top_level_reason_present": true,
"top_level_source_ref_present": true,
"top_level_verification_command_present": true
}
@@ -248,30 +266,48 @@
"output-lab": {
"review_action_id": "review-action-output-lab",
"review_action_status": "warn",
"title_present": true,
"next_step_present": true,
"reason_present": true,
"source_ref_present": true,
"verification_command_present": true,
"top_level_action_id": "review-action-output-lab",
"top_level_action_status": "warn",
"top_level_title_present": true,
"top_level_next_step_present": true,
"top_level_reason_present": true,
"top_level_source_ref_present": true,
"top_level_verification_command_present": true
},
"review-waivers": {
"review_action_id": "review-action-review-waivers",
"review_action_status": "warn",
"title_present": true,
"next_step_present": true,
"reason_present": true,
"source_ref_present": true,
"verification_command_present": true,
"top_level_action_id": "review-action-review-waivers",
"top_level_action_status": "warn",
"top_level_title_present": true,
"top_level_next_step_present": true,
"top_level_reason_present": true,
"top_level_source_ref_present": true,
"top_level_verification_command_present": true
},
"world-class-evidence": {
"review_action_id": "review-action-world-class-evidence",
"review_action_status": "warn",
"title_present": true,
"next_step_present": true,
"reason_present": true,
"source_ref_present": true,
"verification_command_present": true,
"top_level_action_id": "review-action-world-class-evidence",
"top_level_action_status": "warn",
"top_level_title_present": true,
"top_level_next_step_present": true,
"top_level_reason_present": true,
"top_level_source_ref_present": true,
"top_level_verification_command_present": true
}
@@ -288,12 +324,12 @@
"status": "pass",
"expected": {
"status": "pass",
"detail": "initial load 990/1000; deferred 515669/120000; top deferred scripts 454366; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 515966/120000; top deferred scripts 454663; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json"
},
"actual": {
"status": "pass",
"detail": "initial load 990/1000; deferred 515669/120000; top deferred scripts 454366; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 515966/120000; top deferred scripts 454663; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json"
},
"paths": [
@@ -306,8 +342,8 @@
"key": "benchmark-release-lock-self-consistency",
"label": "Benchmark release lock matches source dirty state",
"status": "pass",
"expected": true,
"actual": true,
"expected": false,
"actual": false,
"paths": [
"reports/benchmark_reproducibility.json"
],
@@ -321,7 +357,7 @@
"actual": {
"available": true,
"clean": false,
"changed_file_count": 12
"changed_file_count": 58
},
"paths": [
"reports/benchmark_reproducibility.json"
@@ -362,8 +398,8 @@
"key": "overview-benchmark-commit",
"label": "overview embeds the benchmark commit",
"status": "pass",
"expected": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
"actual": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
"expected": "10dd886ae711ea7edb426ecb7e8747cf38ac55a8",
"actual": "10dd886ae711ea7edb426ecb7e8747cf38ac55a8",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-overview.json"
@@ -375,30 +411,30 @@
"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": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"source_contract_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"public_claim_ready": false,
"public_claim_blocker_count": 4
"public_claim_blocker_count": 5
},
"actual": {
"release_lock_ready": true,
"release_lock_ready": false,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"source_contract_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"public_claim_ready": false,
"public_claim_blocker_count": 4
"public_claim_blocker_count": 5
},
"paths": [
"reports/benchmark_reproducibility.json",
@@ -412,13 +448,13 @@
"status": "pass",
"expected": {
"event_count": 1,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_rate": 100.0,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_rate": 0,
"risk_band": "low",
"event_types": {
"skill_activation": 1
"review_event": 1
},
"source_types": {
"manual": 1
@@ -426,13 +462,13 @@
},
"actual": {
"event_count": 1,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_rate": 100.0,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_rate": 0,
"risk_band": "low",
"event_types": {
"skill_activation": 1
"review_event": 1
},
"source_types": {
"manual": 1
@@ -455,8 +491,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 19,
"source_pass_count": 10,
"source_blocked_count": 9,
"source_pass_count": 9,
"source_blocked_count": 10,
"ready_to_claim_world_class": false,
"decision": "evidence-pending"
},
@@ -467,8 +503,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 19,
"source_pass_count": 10,
"source_blocked_count": 9,
"source_pass_count": 9,
"source_blocked_count": 10,
"ready_to_claim_world_class": false,
"decision": "evidence-pending"
},
@@ -488,7 +524,7 @@
"pending_count": 4,
"accepted_count": 0,
"source_check_count": 19,
"source_pass_count": 10
"source_pass_count": 9
},
"actual": {
"ready": false,
@@ -496,7 +532,7 @@
"pending_count": 4,
"accepted_count": 0,
"source_check_count": 19,
"source_pass_count": 10
"source_pass_count": 9
},
"paths": [
"reports/world_class_evidence_ledger.json",
@@ -508,8 +544,8 @@
"key": "interpretation-benchmark-commit",
"label": "interpretation embeds the benchmark commit",
"status": "pass",
"expected": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
"actual": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
"expected": "10dd886ae711ea7edb426ecb7e8747cf38ac55a8",
"actual": "10dd886ae711ea7edb426ecb7e8747cf38ac55a8",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-interpretation.json"
@@ -521,30 +557,30 @@
"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": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"source_contract_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"public_claim_ready": false,
"public_claim_blocker_count": 4
"public_claim_blocker_count": 5
},
"actual": {
"release_lock_ready": true,
"release_lock_ready": false,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"source_contract_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"public_claim_ready": false,
"public_claim_blocker_count": 4
"public_claim_blocker_count": 5
},
"paths": [
"reports/benchmark_reproducibility.json",
@@ -558,13 +594,13 @@
"status": "pass",
"expected": {
"event_count": 1,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_rate": 100.0,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_rate": 0,
"risk_band": "low",
"event_types": {
"skill_activation": 1
"review_event": 1
},
"source_types": {
"manual": 1
@@ -572,13 +608,13 @@
},
"actual": {
"event_count": 1,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_rate": 100.0,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_rate": 0,
"risk_band": "low",
"event_types": {
"skill_activation": 1
"review_event": 1
},
"source_types": {
"manual": 1
@@ -601,8 +637,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 19,
"source_pass_count": 10,
"source_blocked_count": 9,
"source_pass_count": 9,
"source_blocked_count": 10,
"ready_to_claim_world_class": false,
"decision": "evidence-pending"
},
@@ -613,8 +649,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 19,
"source_pass_count": 10,
"source_blocked_count": 9,
"source_pass_count": 9,
"source_blocked_count": 10,
"ready_to_claim_world_class": false,
"decision": "evidence-pending"
},
@@ -634,7 +670,7 @@
"pending_count": 4,
"accepted_count": 0,
"source_check_count": 19,
"source_pass_count": 10
"source_pass_count": 9
},
"actual": {
"ready": false,
@@ -642,7 +678,7 @@
"pending_count": 4,
"accepted_count": 0,
"source_check_count": 19,
"source_pass_count": 10
"source_pass_count": 9
},
"paths": [
"reports/world_class_evidence_ledger.json",
@@ -1441,7 +1477,7 @@
"external_pending_count": 3,
"human_pending_count": 1,
"source_check_count": 19,
"source_pass_count": 10,
"source_pass_count": 9,
"conclusion_zh": "世界级证据尚未完成:4 项待补,0 项已接受。",
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
"entries": [
@@ -1501,7 +1537,8 @@
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
"summary_en": "Real external-client metadata-only events have not been imported yet.",
"blocked_checks": [
"External events"
"External events",
"Adoption sample"
]
}
]
@@ -1515,7 +1552,7 @@
"external_pending_count": 3,
"human_pending_count": 1,
"source_check_count": 19,
"source_pass_count": 10,
"source_pass_count": 9,
"conclusion_zh": "世界级证据尚未完成:4 项待补,0 项已接受。",
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
"entries": [
@@ -1575,7 +1612,8 @@
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
"summary_en": "Real external-client metadata-only events have not been imported yet.",
"blocked_checks": [
"External events"
"External events",
"Adoption sample"
]
}
]
@@ -1925,15 +1963,15 @@
"expected": {
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"public_claim_ready": false
},
"actual": {
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"public_claim_ready": false
},
"paths": [
@@ -1949,8 +1987,8 @@
"expected": {
"pending_count": 4,
"source_check_count": 19,
"source_pass_count": 10,
"source_blocked_count": 9,
"source_pass_count": 9,
"source_blocked_count": 10,
"ready_to_claim_world_class": false,
"preflight_counts_as_evidence": false,
"credential_value_exposed": false
@@ -1958,8 +1996,8 @@
"actual": {
"pending_count": 4,
"source_check_count": 19,
"source_pass_count": 10,
"source_blocked_count": 9,
"source_pass_count": 9,
"source_blocked_count": 10,
"ready_to_claim_world_class": false,
"preflight_counts_as_evidence": false,
"credential_value_exposed": false
@@ -2136,7 +2174,7 @@
"summary": {
"phase_queue_count": 2,
"phase_queue_blocked_count": 2,
"phase_queue_row_count": 13,
"phase_queue_row_count": 14,
"phase_queue_next_phase": "unblock-access",
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
@@ -2169,8 +2207,8 @@
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 9,
"row_count": 9,
"blocked_count": 10,
"row_count": 10,
"owners": [
"Browser/Chrome/IDE/provider client integrator",
"human reviewer",
@@ -2312,15 +2350,15 @@
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"blocked_count": 2,
"row_count": 2,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-external_source_events",
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
@@ -2330,7 +2368,7 @@
"operator_runbook_summary": {
"phase_queue_count": 2,
"phase_queue_blocked_count": 2,
"phase_queue_row_count": 13,
"phase_queue_row_count": 14,
"phase_queue_next_phase": "unblock-access",
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
@@ -2363,8 +2401,8 @@
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 9,
"row_count": 9,
"blocked_count": 10,
"row_count": 10,
"owners": [
"Browser/Chrome/IDE/provider client integrator",
"human reviewer",
@@ -2506,15 +2544,15 @@
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"blocked_count": 2,
"row_count": 2,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-external_source_events",
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
@@ -2644,15 +2682,15 @@
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"blocked_count": 2,
"row_count": 2,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-external_source_events",
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
@@ -2663,7 +2701,7 @@
"summary": {
"phase_queue_count": 2,
"phase_queue_blocked_count": 2,
"phase_queue_row_count": 13,
"phase_queue_row_count": 14,
"phase_queue_next_phase": "unblock-access",
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
@@ -2696,8 +2734,8 @@
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 9,
"row_count": 9,
"blocked_count": 10,
"row_count": 10,
"owners": [
"Browser/Chrome/IDE/provider client integrator",
"human reviewer",
@@ -2718,7 +2756,7 @@
"operator_runbook_summary": {
"phase_queue_count": 2,
"phase_queue_blocked_count": 2,
"phase_queue_row_count": 13,
"phase_queue_row_count": 14,
"phase_queue_next_phase": "unblock-access",
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
@@ -2751,8 +2789,8 @@
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 9,
"row_count": 9,
"blocked_count": 10,
"row_count": 10,
"owners": [
"Browser/Chrome/IDE/provider client integrator",
"human reviewer",
@@ -2894,15 +2932,15 @@
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"blocked_count": 2,
"row_count": 2,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-external_source_events",
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
@@ -3032,15 +3070,15 @@
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"blocked_count": 2,
"row_count": 2,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-external_source_events",
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
@@ -3170,15 +3208,15 @@
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"blocked_count": 2,
"row_count": 2,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-external_source_events",
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
@@ -3278,8 +3316,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 19,
"source_pass_count": 10,
"source_blocked_count": 9,
"source_pass_count": 9,
"source_blocked_count": 10,
"plan_keys": [
"human-adjudication",
"native-client-telemetry",
@@ -3427,8 +3465,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 19,
"source_pass_count": 10,
"source_blocked_count": 9,
"source_pass_count": 9,
"source_blocked_count": 10,
"plan_keys": [
"human-adjudication",
"native-client-telemetry",
+10 -10
View File
@@ -34,7 +34,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.77,
"duration_ms": 31.88,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -62,7 +62,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 31.71,
"duration_ms": 29.84,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -85,7 +85,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 29.59,
"duration_ms": 29.68,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -113,7 +113,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 29.77,
"duration_ms": 29.2,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -136,7 +136,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.5,
"duration_ms": 28.39,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -164,7 +164,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.06,
"duration_ms": 28.25,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -187,7 +187,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 35.9,
"duration_ms": 28.69,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -214,7 +214,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 29.67,
"duration_ms": 28.13,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -237,7 +237,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.52,
"duration_ms": 28.09,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -266,7 +266,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.91,
"duration_ms": 28.16,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
+10 -10
View File
@@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext
| Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status |
| --- | --- | --- | --- | ---: | ---: | ---: | --- |
| skill-package-contract | baseline | command | local-output-eval-runner | 33.77 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 31.71 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 29.59 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.77 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 32.5 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 30.06 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 35.9 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 29.67 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 30.52 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 30.91 | 98 | 100.0 | pass |
| skill-package-contract | baseline | command | local-output-eval-runner | 31.88 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 29.84 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 29.68 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.2 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 28.39 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 28.25 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 28.69 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 28.13 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 28.09 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 28.16 | 98 | 100.0 | pass |
## Next Fixes
+2 -2
View File
@@ -21,7 +21,7 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"package_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
},
"compatibility": {
@@ -78,7 +78,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
"package_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b"
}
]
},
+1 -1
View File
@@ -6,7 +6,7 @@
- Maturity: `governed`
- Owner: `Yao Team`
- License: `MIT`
- Package SHA256: `a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba`
- Package SHA256: `fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b`
- Archive SHA256: `7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2`
- Install simulated: `True`
+8 -8
View File
@@ -772,12 +772,12 @@
<section>
<h2>核心指标</h2>
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>4 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>152 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>231 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>696 largest lines; 0 watchlist; 4 early; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock true</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>182 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>689 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>5 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>152 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>231 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>696 largest lines; 0 watchlist; 4 early; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock true</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>182 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>689 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
</section>
<section>
<h2>审查闸门</h2>
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 990/1000; deferred 515669/120000; top deferred scripts 454366; resource governance governed; quality density 131.3</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 152 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 231 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>228 Python files; 0 hotspots; 0 watchlist files; 4 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 10/19 pass; 9 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 990/1000; deferred 515966/120000; top deferred scripts 454663; resource governance governed; quality density 131.3</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 152 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 231 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>228 Python files; 0 hotspots; 0 watchlist files; 4 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 10/19 pass; 9 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
</section>
<section>
@@ -844,12 +844,12 @@
</section>
<section class="twocol">
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 515669/120000; top deferred scripts 454366; resource governance governed; quality density 131.3</p></div>
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 515966/120000; top deferred scripts 454663; resource governance governed; quality density 131.3</p></div>
<div class="panel"><h2>编译证据</h2><p>Review reports/compiled_targets.md before packaging to inspect target adapter modes, generated files, preserved semantics, warnings, and unsupported features.</p></div>
</section>
<section id="trust" class="twocol">
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>152</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba</code></dd></div></dl></div>
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>152</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b</code></dd></div></dl></div>
<div class="panel"><h2>安全边界</h2><p>高风险 secret、远程 inline execution、缺失依赖策略或无法解释的脚本接口应阻断 governed release。</p></div>
</section>
@@ -874,14 +874,14 @@
</section>
<section id="telemetry" class="twocol">
<div class="panel"><h2>运营回路</h2><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true</p></div>
<div class="panel"><h2>运营回路</h2><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false</p></div>
<div class="panel"><h2>漂移信号</h2><dl class='kv-grid'><div><dt>事件数</dt><dd>1</dd></div><div><dt>采用率</dt><dd>100</dd></div><div><dt>漏触发</dt><dd>0</dd></div><div><dt>Bad Output Count</dt><dd>0</dd></div><div><dt>风险带</dt><dd>low</dd></div></dl></div>
</section>
<section class="twocol">
<div class="panel"><h2>日常运维</h2><dl class='kv-grid'><div><dt>决策</dt><dd>proposal-review</dd></div><div><dt>提案数</dt><dd>5</dd></div><div><dt>Approval Count</dt><dd>0</dd></div><div><dt>Pending Review Count</dt><dd>0</dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>世界级</dt><dd></dd></div><div><dt>Writes Source Files</dt><dd></dd></div><div><dt>Auto Patch Enabled</dt><dd></dd></div></dl></div>
<div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>2</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>Writes Source Files</dt><dd></dd></div><div><dt>Auto Patch Enabled</dt><dd></dd></div></dl></div>
<div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>2</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>Writes Source Files</dt><dd></dd></div><div><dt>Auto Patch Enabled</dt><dd></dd></div></dl></div>
</section>
@@ -914,8 +914,8 @@
</section>
<section class="twocol">
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd></dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>可公开声明</dt><dd></dd></div><div><dt>声明阻断</dt><dd>4</dd></div><div><dt>Provider 证据</dt><dd></dd></div><div><dt>人审完成</dt><dd></dd></div><div><dt>世界级就绪</dt><dd></dd></div></dl></div>
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (10/19 pass, 9 blocked)</span></li></ul></div>
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd></dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>可公开声明</dt><dd></dd></div><div><dt>声明阻断</dt><dd>5</dd></div><div><dt>Provider 证据</dt><dd></dd></div><div><dt>人审完成</dt><dd></dd></div><div><dt>世界级就绪</dt><dd></dd></div></dl></div>
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>release lock is not clean or commit is unavailable</span></li><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (10/19 pass, 9 blocked)</span></li></ul></div>
</section>
<section class="twocol">
+163 -90
View File
@@ -25,6 +25,9 @@
"link": "intent-confidence.md",
"review_action_id": "",
"review_action_status": "",
"review_action_title": "",
"review_action_next_step": "",
"review_action_reason": "",
"review_action_source_ref_count": 0,
"review_action_verification_command": ""
},
@@ -37,6 +40,9 @@
"link": "route_scorecard.md",
"review_action_id": "",
"review_action_status": "",
"review_action_title": "",
"review_action_next_step": "",
"review_action_reason": "",
"review_action_source_ref_count": 0,
"review_action_verification_command": ""
},
@@ -49,6 +55,9 @@
"link": "output_quality_scorecard.md",
"review_action_id": "review-action-output-lab",
"review_action_status": "warn",
"review_action_title": "输出实验",
"review_action_next_step": "补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。同步补足盲审声明。",
"review_action_reason": "没有输出质量和人工盲评证据时,Skill 只能证明会触发,不能证明输出真的更好且经得起审查。",
"review_action_source_ref_count": 6,
"review_action_verification_command": "python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review"
},
@@ -56,11 +65,14 @@
"key": "context-budget",
"label": "上下文",
"status": "pass",
"detail": "initial load 990/1000; deferred 515669/120000; top deferred scripts 454366; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 515966/120000; top deferred scripts 454663; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json",
"link": "context_budget.md",
"review_action_id": "",
"review_action_status": "",
"review_action_title": "",
"review_action_next_step": "",
"review_action_reason": "",
"review_action_source_ref_count": 0,
"review_action_verification_command": ""
},
@@ -73,6 +85,9 @@
"link": "conformance_matrix.md",
"review_action_id": "",
"review_action_status": "",
"review_action_title": "",
"review_action_next_step": "",
"review_action_reason": "",
"review_action_source_ref_count": 0,
"review_action_verification_command": ""
},
@@ -85,6 +100,9 @@
"link": "security_trust_report.md",
"review_action_id": "",
"review_action_status": "",
"review_action_title": "",
"review_action_next_step": "",
"review_action_reason": "",
"review_action_source_ref_count": 0,
"review_action_verification_command": ""
},
@@ -97,6 +115,9 @@
"link": "python_compatibility.md",
"review_action_id": "",
"review_action_status": "",
"review_action_title": "",
"review_action_next_step": "",
"review_action_reason": "",
"review_action_source_ref_count": 0,
"review_action_verification_command": ""
},
@@ -109,6 +130,9 @@
"link": "architecture_maintainability.md",
"review_action_id": "",
"review_action_status": "",
"review_action_title": "",
"review_action_next_step": "",
"review_action_reason": "",
"review_action_source_ref_count": 0,
"review_action_verification_command": ""
},
@@ -121,6 +145,9 @@
"link": "../security/permission_policy.md",
"review_action_id": "",
"review_action_status": "",
"review_action_title": "",
"review_action_next_step": "",
"review_action_reason": "",
"review_action_source_ref_count": 0,
"review_action_verification_command": ""
},
@@ -133,6 +160,9 @@
"link": "runtime_permission_probes.md",
"review_action_id": "",
"review_action_status": "",
"review_action_title": "",
"review_action_next_step": "",
"review_action_reason": "",
"review_action_source_ref_count": 0,
"review_action_verification_command": ""
},
@@ -145,6 +175,9 @@
"link": "skill_atlas.html",
"review_action_id": "",
"review_action_status": "",
"review_action_title": "",
"review_action_next_step": "",
"review_action_reason": "",
"review_action_source_ref_count": 0,
"review_action_verification_command": ""
},
@@ -152,11 +185,14 @@
"key": "operations-loop",
"label": "运营回路",
"status": "pass",
"detail": "1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true",
"detail": "1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false",
"evidence": "reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly",
"link": "adoption_drift_report.md",
"review_action_id": "",
"review_action_status": "",
"review_action_title": "",
"review_action_next_step": "",
"review_action_reason": "",
"review_action_source_ref_count": 0,
"review_action_verification_command": ""
},
@@ -169,6 +205,9 @@
"link": "review_waivers.md",
"review_action_id": "review-action-review-waivers",
"review_action_status": "warn",
"review_action_title": "人工批准",
"review_action_next_step": "对保留的 warning 写入 reviewer、理由、范围和到期时间,或修掉 warning。",
"review_action_reason": "warning 可以被接受,但必须可审计、会过期,并且不能掩盖 blocker。",
"review_action_source_ref_count": 2,
"review_action_verification_command": "python3 scripts/render_review_waivers.py ."
},
@@ -181,6 +220,9 @@
"link": "world_class_evidence_ledger.md",
"review_action_id": "review-action-world-class-evidence",
"review_action_status": "warn",
"review_action_title": "世界证据",
"review_action_next_step": "补齐 provider、真人盲评、原生权限执行和真实客户端遥测证据,或明确本次发布不声明 world-class 完成。",
"review_action_reason": "世界级结论必须来自已接受的外部/人工证据;计划、metadata fallback、待评审和本地命令都不能替代完成证据。",
"review_action_source_ref_count": 16,
"review_action_verification_command": "python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py review-studio ."
},
@@ -193,6 +235,9 @@
"link": "registry_audit.md",
"review_action_id": "",
"review_action_status": "",
"review_action_title": "",
"review_action_next_step": "",
"review_action_reason": "",
"review_action_source_ref_count": 0,
"review_action_verification_command": ""
},
@@ -205,6 +250,9 @@
"link": "promotion_decisions.md",
"review_action_id": "",
"review_action_status": "",
"review_action_title": "",
"review_action_next_step": "",
"review_action_reason": "",
"review_action_source_ref_count": 0,
"review_action_verification_command": ""
}
@@ -265,6 +313,9 @@
"link": "output_quality_scorecard.md",
"review_action_id": "review-action-output-lab",
"review_action_status": "warn",
"review_action_title": "输出实验",
"review_action_next_step": "补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。同步补足盲审声明。",
"review_action_reason": "没有输出质量和人工盲评证据时,Skill 只能证明会触发,不能证明输出真的更好且经得起审查。",
"review_action_source_ref_count": 6,
"review_action_verification_command": "python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review"
},
@@ -277,6 +328,9 @@
"link": "review_waivers.md",
"review_action_id": "review-action-review-waivers",
"review_action_status": "warn",
"review_action_title": "人工批准",
"review_action_next_step": "对保留的 warning 写入 reviewer、理由、范围和到期时间,或修掉 warning。",
"review_action_reason": "warning 可以被接受,但必须可审计、会过期,并且不能掩盖 blocker。",
"review_action_source_ref_count": 2,
"review_action_verification_command": "python3 scripts/render_review_waivers.py ."
},
@@ -289,6 +343,9 @@
"link": "world_class_evidence_ledger.md",
"review_action_id": "review-action-world-class-evidence",
"review_action_status": "warn",
"review_action_title": "世界证据",
"review_action_next_step": "补齐 provider、真人盲评、原生权限执行和真实客户端遥测证据,或明确本次发布不声明 world-class 完成。",
"review_action_reason": "世界级结论必须来自已接受的外部/人工证据;计划、metadata fallback、待评审和本地命令都不能替代完成证据。",
"review_action_source_ref_count": 16,
"review_action_verification_command": "python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py review-studio ."
}
@@ -297,10 +354,13 @@
{
"action_id": "review-action-output-lab",
"gate_key": "output-lab",
"title": "输出实验",
"label": "输出实验",
"status": "warn",
"priority": "warning",
"next_step": "补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。同步补足盲审声明。",
"summary": "补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。同步补足盲审声明。",
"reason": "没有输出质量和人工盲评证据时,Skill 只能证明会触发,不能证明输出真的更好且经得起审查。",
"why": "没有输出质量和人工盲评证据时,Skill 只能证明会触发,不能证明输出真的更好且经得起审查。",
"source_fix": "evals/output/cases.jsonl + reports/output_quality_scorecard.md + reports/output_review_kit.html + reports/output_review_adjudication.md + reports/output_review_decisions.json",
"source_refs": [
@@ -373,10 +433,13 @@
{
"action_id": "review-action-review-waivers",
"gate_key": "review-waivers",
"title": "人工批准",
"label": "人工批准",
"status": "warn",
"priority": "warning",
"next_step": "对保留的 warning 写入 reviewer、理由、范围和到期时间,或修掉 warning。",
"summary": "对保留的 warning 写入 reviewer、理由、范围和到期时间,或修掉 warning。",
"reason": "warning 可以被接受,但必须可审计、会过期,并且不能掩盖 blocker。",
"why": "warning 可以被接受,但必须可审计、会过期,并且不能掩盖 blocker。",
"source_fix": "reports/review_waivers.md",
"source_refs": [
@@ -409,10 +472,13 @@
{
"action_id": "review-action-world-class-evidence",
"gate_key": "world-class-evidence",
"title": "世界证据",
"label": "世界证据",
"status": "warn",
"priority": "warning",
"next_step": "补齐 provider、真人盲评、原生权限执行和真实客户端遥测证据,或明确本次发布不声明 world-class 完成。",
"summary": "补齐 provider、真人盲评、原生权限执行和真实客户端遥测证据,或明确本次发布不声明 world-class 完成。",
"reason": "世界级结论必须来自已接受的外部/人工证据;计划、metadata fallback、待评审和本地命令都不能替代完成证据。",
"why": "世界级结论必须来自已接受的外部/人工证据;计划、metadata fallback、待评审和本地命令都不能替代完成证据。",
"source_fix": "reports/world_class_operator_runbook.html + reports/world_class_evidence_ledger.md + reports/world_class_evidence_intake.md + reports/world_class_submission_review.md",
"source_refs": [
@@ -2442,12 +2508,12 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15",
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"evidence_bundle_sha256": "ea30ec16d96bab3ffefae8913c3c18940d4ebbe12aa3d7047efc1e1fdf6d2e27",
"source_contract_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -2466,15 +2532,15 @@
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 15,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"changed_file_count": 52,
"source_tree_dirty": true,
"source_changed_file_count": 5,
"generated_tree_dirty": true,
"generated_changed_file_count": 15
"generated_changed_file_count": 47
},
"commit": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
"commit": "10dd886ae711ea7edb426ecb7e8747cf38ac55a8",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
@@ -2579,7 +2645,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 244,
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
"package_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b"
},
"skill_atlas": {
"skill_count": 12,
@@ -2617,7 +2683,7 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"package_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
},
"compatibility": {
@@ -2749,7 +2815,7 @@
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
"to": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b"
}
]
},
@@ -5263,7 +5329,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.77,
"duration_ms": 31.88,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5291,7 +5357,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 31.71,
"duration_ms": 29.84,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5314,7 +5380,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 29.59,
"duration_ms": 29.68,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5342,7 +5408,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 29.77,
"duration_ms": 29.2,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5365,7 +5431,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.5,
"duration_ms": 28.39,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5393,7 +5459,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.06,
"duration_ms": 28.25,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5416,7 +5482,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 35.9,
"duration_ms": 28.69,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5443,7 +5509,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 29.67,
"duration_ms": 28.13,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5466,7 +5532,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.52,
"duration_ms": 28.09,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5495,7 +5561,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.91,
"duration_ms": 28.16,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -6276,43 +6342,49 @@
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
"commit": "10dd886ae711ea7edb426ecb7e8747cf38ac55a8",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 15,
"changed_file_count": 52,
"generated_dirty": true,
"generated_changed_file_count": 15,
"source_dirty": false,
"source_changed_file_count": 0,
"generated_changed_file_count": 47,
"source_dirty": true,
"source_changed_file_count": 5,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/adaptation_proposals.json",
" M reports/adaptation_proposals.md",
" M reports/adoption_drift_report.json",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" M reports/benchmark_reproducibility.json",
" M reports/benchmark_reproducibility.md",
" M reports/context_budget.json",
" M reports/evidence_consistency.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md",
" M reports/review-studio.html",
" M reports/review-studio.json",
" M reports/review-viewer.json",
" M reports/skill-interpretation.json"
" M reports/context_budget.md",
" M reports/context_budget_summary.json"
],
"source_sample": [
" M scripts/render_evidence_consistency.py",
" M scripts/render_review_studio.py",
" M scripts/review_studio_actions.py",
" M tests/verify_evidence_consistency.py",
" M tests/verify_review_studio.py"
],
"source_sample": [],
"generated_sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/adaptation_proposals.json",
" M reports/adaptation_proposals.md",
" M reports/adoption_drift_report.json",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" M reports/benchmark_reproducibility.json",
" M reports/benchmark_reproducibility.md",
" M reports/context_budget.json",
" M reports/evidence_consistency.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md",
" M reports/review-studio.html",
" M reports/review-studio.json",
" M reports/review-viewer.json",
" M reports/skill-interpretation.json"
" M reports/context_budget.md",
" M reports/context_budget_summary.json"
],
"generated_dirty_prefixes": [
"dist/",
@@ -6326,12 +6398,12 @@
},
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15",
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"evidence_bundle_sha256": "ea30ec16d96bab3ffefae8913c3c18940d4ebbe12aa3d7047efc1e1fdf6d2e27",
"source_contract_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -6350,18 +6422,19 @@
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 15,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"changed_file_count": 52,
"source_tree_dirty": true,
"source_changed_file_count": 5,
"generated_tree_dirty": true,
"generated_changed_file_count": 15
"generated_changed_file_count": 47
},
"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)",
@@ -6370,12 +6443,12 @@
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
},
"release_lock": {
"ready": true,
"commit": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
"ready": false,
"commit": "10dd886ae711ea7edb426ecb7e8747cf38ac55a8",
"status_scope": "generation-time status before this report is written",
"source_changed_file_count": 0,
"generated_changed_file_count": 15,
"reason": "only generated evidence artifacts were dirty at generation time"
"source_changed_file_count": 5,
"generated_changed_file_count": 47,
"reason": "source files were dirty at generation time"
},
"evidence_bundle": {
"algorithm": "sha256(path,label,exists,artifact_sha256)",
@@ -6383,7 +6456,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15"
"sha256": "ea30ec16d96bab3ffefae8913c3c18940d4ebbe12aa3d7047efc1e1fdf6d2e27"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -6456,8 +6529,8 @@
"label": "output_execution",
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7965,
"sha256": "db2564dbc622814ae57e8459d2a241b0f76fbf78f00af1d484ca5cdaa3265cae"
"bytes": 7966,
"sha256": "8b9ef4d24793119f47c6fcd2b21554b93b5b7415e6387de80b36b835d5a72f2f"
},
{
"label": "blind_review",
@@ -6492,7 +6565,7 @@
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 136999,
"sha256": "079165fefd9fb3e5c25c1c486738e21bff2a59ca52b03dae9d505d6896341bf1"
"sha256": "35d1ec9d8404ca8f846aa72fdf810abb4c58ef00ca31f2e74de42bc3841471a4"
},
{
"label": "python_compatibility",
@@ -6506,7 +6579,7 @@
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "db05339565be76ece69a89ba4b84dc3af44c711dc68860cbf319b86766d44541"
"sha256": "3213fd1c9fb85740c2d7c36a04497f3a5cbaffe65f92595196bffdfae5e835e7"
},
{
"label": "package_verification",
@@ -12947,7 +13020,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 244,
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
"package_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b"
},
"failures": [],
"warnings": [],
@@ -17913,7 +17986,7 @@
},
{
"path": "tests/verify_evidence_consistency.py",
"lines": 671,
"lines": 686,
"kind": "test",
"severity": "pass",
"early_watch": true,
@@ -17921,7 +17994,7 @@
},
{
"path": "scripts/render_evidence_consistency.py",
"lines": 647,
"lines": 659,
"kind": "cli-script",
"severity": "pass",
"early_watch": true,
@@ -17975,6 +18048,14 @@
"early_watch": false,
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/render_review_studio.py",
"lines": 578,
"kind": "cli-script",
"severity": "pass",
"early_watch": false,
"recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
},
{
"path": "scripts/world_class_submission_kit_rendering.py",
"lines": 576,
@@ -17982,14 +18063,6 @@
"severity": "pass",
"early_watch": false,
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/render_review_studio.py",
"lines": 575,
"kind": "cli-script",
"severity": "pass",
"early_watch": false,
"recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
}
],
"watchlist": [],
@@ -18012,7 +18085,7 @@
},
{
"path": "tests/verify_evidence_consistency.py",
"lines": 671,
"lines": 686,
"kind": "test",
"severity": "pass",
"early_watch": true,
@@ -18020,7 +18093,7 @@
},
{
"path": "scripts/render_evidence_consistency.py",
"lines": 647,
"lines": 659,
"kind": "cli-script",
"severity": "pass",
"early_watch": true,
@@ -18042,15 +18115,15 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 797,
"other_text_tokens": 1139268,
"other_text_tokens": 1139919,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1140065,
"deferred_resource_tokens": 515669,
"estimated_total_text_tokens": 1140716,
"deferred_resource_tokens": 515966,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 454366,
"estimated_tokens": 454663,
"file_count": 152
},
{
@@ -18072,7 +18145,7 @@
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 454366,
"estimated_tokens": 454663,
"file_count": 152
}
],
@@ -18095,7 +18168,7 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 454366,
"estimated_tokens": 454663,
"file_count": 152,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
@@ -20020,7 +20093,7 @@
"adoption_drift": {
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-16T21:16:41Z",
"generated_at": "2026-06-16T21:24:56Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
@@ -20618,7 +20691,7 @@
"weekly_curator": {
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-16T21:24:27Z",
"skill_dir": ".",
"decision": "curator-review",
"week_id": "2026-W25",
@@ -20632,7 +20705,7 @@
"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,
@@ -20652,7 +20725,7 @@
"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,
@@ -20905,7 +20978,7 @@
"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
@@ -21083,7 +21156,7 @@
"adaptation_proposals": {
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-16T21:24:27Z",
"skill_dir": ".",
"source_patterns": "reports/user_patterns.json",
"pattern_count": 5,
@@ -27485,7 +27558,7 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"package_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
},
"compatibility": {
@@ -27542,7 +27615,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
"package_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b"
}
]
},
@@ -28578,7 +28651,7 @@
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
"to": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b"
}
]
},
+12 -12
View File
@@ -1005,12 +1005,12 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15",
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"evidence_bundle_sha256": "ea30ec16d96bab3ffefae8913c3c18940d4ebbe12aa3d7047efc1e1fdf6d2e27",
"source_contract_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -1029,15 +1029,15 @@
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 15,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"changed_file_count": 52,
"source_tree_dirty": true,
"source_changed_file_count": 5,
"generated_tree_dirty": true,
"generated_changed_file_count": 15
"generated_changed_file_count": 47
},
"commit": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
"commit": "10dd886ae711ea7edb426ecb7e8747cf38ac55a8",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
@@ -1142,7 +1142,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 244,
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
"package_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b"
},
"skill_atlas": {
"skill_count": 12,
@@ -1180,7 +1180,7 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"package_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
},
"compatibility": {
@@ -1312,7 +1312,7 @@
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
"to": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b"
}
]
},
+1 -1
View File
@@ -23,7 +23,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 244,
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
"package_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b"
},
"failures": [],
"warnings": [],
+1 -1
View File
@@ -16,7 +16,7 @@
- Interactive scripts: `0`
- Package hash scope: `source-contract-without-generated-reports`
- Package hash files: `244`
- Package SHA256: `a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba`
- Package SHA256: `fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b`
## Failures
+12 -12
View File
@@ -1009,12 +1009,12 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15",
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"evidence_bundle_sha256": "ea30ec16d96bab3ffefae8913c3c18940d4ebbe12aa3d7047efc1e1fdf6d2e27",
"source_contract_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -1033,15 +1033,15 @@
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 15,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"changed_file_count": 52,
"source_tree_dirty": true,
"source_changed_file_count": 5,
"generated_tree_dirty": true,
"generated_changed_file_count": 15
"generated_changed_file_count": 47
},
"commit": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
"commit": "10dd886ae711ea7edb426ecb7e8747cf38ac55a8",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
@@ -1146,7 +1146,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 244,
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
"package_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b"
},
"skill_atlas": {
"skill_count": 12,
@@ -1184,7 +1184,7 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"package_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
},
"compatibility": {
@@ -1316,7 +1316,7 @@
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
"to": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b"
}
]
},
+12 -12
View File
@@ -1004,12 +1004,12 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "b29129730b143a8ee3e8f3976ea953ed7173e0c7de9c4e8a2fc2f4c47635fe15",
"source_contract_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"evidence_bundle_sha256": "ea30ec16d96bab3ffefae8913c3c18940d4ebbe12aa3d7047efc1e1fdf6d2e27",
"source_contract_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
"failure_disclosure_count": 3,
@@ -1028,15 +1028,15 @@
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"public_claim_ready": false,
"public_claim_blocker_count": 4,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 15,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"changed_file_count": 52,
"source_tree_dirty": true,
"source_changed_file_count": 5,
"generated_tree_dirty": true,
"generated_changed_file_count": 15
"generated_changed_file_count": 47
},
"commit": "cd71fd61e4d1c8db758ac0d2e9d1873a5a4ef547",
"commit": "10dd886ae711ea7edb426ecb7e8747cf38ac55a8",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
@@ -1141,7 +1141,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 244,
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
"package_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b"
},
"skill_atlas": {
"skill_count": 12,
@@ -1179,7 +1179,7 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba",
"package_sha256": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
},
"compatibility": {
@@ -1311,7 +1311,7 @@
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
"to": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b"
}
]
},
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"item_count": 21,
+1 -1
View File
@@ -1,6 +1,6 @@
# Skill OS 2.0 Blueprint Coverage
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-16T21:16:12Z",
"generated_at": "2026-06-16T21:24:27Z",
"skill_dir": ".",
"decision": "proposal-review",
"source_supplied": false,
+1 -1
View File
@@ -1,6 +1,6 @@
# Daily SkillOps Report
Generated at: `2026-06-16T21:16:12Z`
Generated at: `2026-06-16T21:24:27Z`
## Summary
+4 -4
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-16T21:24:27Z",
"skill_dir": ".",
"decision": "curator-review",
"week_id": "2026-W25",
@@ -15,7 +15,7 @@
"top_score": 88,
"skill_count": 12,
"actionable_portfolio_issue_count": 0,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
@@ -35,7 +35,7 @@
"top_score": 88,
"skill_count": 12,
"actionable_portfolio_issue_count": 0,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
@@ -288,7 +288,7 @@
"no_route_opportunity_count": 0
},
"release_state": {
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4
+2 -2
View File
@@ -1,6 +1,6 @@
# Weekly SkillOps Curator Report
Generated at: `2026-06-17`
Generated at: `2026-06-16T21:24:27Z`
Week: `2026-W25`
## Summary
@@ -13,7 +13,7 @@ Week: `2026-W25`
- top_score: `88`
- skill_count: `12`
- actionable_portfolio_issue_count: `0`
- release_lock_ready: `True`
- release_lock_ready: `False`
- evidence_consistency_ok: `True`
- public_world_class_ready: `False`
- world_class_pending_count: `4`
+1 -1
View File
@@ -75,7 +75,7 @@
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "a7c24fc193a5b24d2016ac6e6d49120e525f3ef8c266bf66a5894db2c3f99bba"
"to": "fda25ac83d07a671d3789d6b10409bee61479200101c7e3c925df9a1998e412b"
}
]
},
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"ledger_ready_to_claim_world_class": false,
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Claim Guard
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"schema_present": true,
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Intake
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"decision": "evidence-pending",
"ready_to_claim_world_class": false,
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Ledger
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"audit_decision": "continue-iteration",
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Plan
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"evidence_item_count": 4,
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Preflight
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"evidence_item_count": 4,
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Operator Runbook
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"decision": "awaiting-submissions",
"ready_to_claim_world_class": false,
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Submission Review
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary
+12
View File
@@ -77,6 +77,9 @@ def build_review_studio_gate_action_mirror_check(review_studio: dict[str, Any])
str(gate.get("key", "")): {
"review_action_id": f"review-action-{gate.get('key', '')}",
"review_action_status": gate.get("status", ""),
"title_present": True,
"next_step_present": True,
"reason_present": True,
"source_ref_present": True,
"verification_command_present": True,
}
@@ -95,15 +98,24 @@ def build_review_studio_gate_action_mirror_check(review_studio: dict[str, Any])
actual["gate_action_mirrors"][key] = {
"review_action_id": gate.get("review_action_id", ""),
"review_action_status": gate.get("review_action_status", ""),
"title_present": bool(gate.get("review_action_title")),
"next_step_present": bool(gate.get("review_action_next_step")),
"reason_present": bool(gate.get("review_action_reason")),
"source_ref_present": bool(gate.get("review_action_source_ref_count")),
"verification_command_present": bool(gate.get("review_action_verification_command")),
"top_level_action_id": action.get("action_id", ""),
"top_level_action_status": action.get("status", ""),
"top_level_title_present": bool(action.get("title")),
"top_level_next_step_present": bool(action.get("next_step")),
"top_level_reason_present": bool(action.get("reason")),
"top_level_source_ref_present": bool(action.get("source_refs")),
"top_level_verification_command_present": bool(action.get("verification_command")),
}
expected["gate_action_mirrors"][key]["top_level_action_id"] = f"review-action-{key}"
expected["gate_action_mirrors"][key]["top_level_action_status"] = gate.get("status", "")
expected["gate_action_mirrors"][key]["top_level_title_present"] = True
expected["gate_action_mirrors"][key]["top_level_next_step_present"] = True
expected["gate_action_mirrors"][key]["top_level_reason_present"] = True
expected["gate_action_mirrors"][key]["top_level_source_ref_present"] = True
expected["gate_action_mirrors"][key]["top_level_verification_command_present"] = True
return {
+3
View File
@@ -519,6 +519,9 @@ def render_review_studio(skill_dir: Path, output_html: Path | None = None, outpu
action = action_by_gate.get(str(gate.get("key", "")))
gate["review_action_id"] = str(action.get("action_id", "")) if action else ""
gate["review_action_status"] = str(action.get("status", "")) if action else ""
gate["review_action_title"] = str(action.get("title", "")) if action else ""
gate["review_action_next_step"] = str(action.get("next_step", "")) if action else ""
gate["review_action_reason"] = str(action.get("reason", "")) if action else ""
gate["review_action_source_ref_count"] = len(action.get("source_refs", [])) if action else 0
gate["review_action_verification_command"] = str(action.get("verification_command", "")) if action else ""
score = weighted_score(gates)
+3
View File
@@ -299,10 +299,13 @@ def build_review_actions(
{
"action_id": f"review-action-{gate_item['key']}",
"gate_key": gate_item["key"],
"title": gate_item["label"],
"label": gate_item["label"],
"status": gate_item["status"],
"priority": "blocker" if gate_item["status"] == "block" else "warning",
"next_step": guidance["summary"],
"summary": guidance["summary"],
"reason": guidance["why"],
"why": guidance["why"],
"source_fix": guidance["source_fix"],
"source_refs": refs,
+15
View File
@@ -179,6 +179,15 @@ def main() -> None:
assert gate_action_mirror["gate_action_mirrors"]["world-class-evidence"]["source_ref_present"] is True, (
gate_action_mirror
)
assert gate_action_mirror["gate_action_mirrors"]["world-class-evidence"]["title_present"] is True, (
gate_action_mirror
)
assert gate_action_mirror["gate_action_mirrors"]["world-class-evidence"]["next_step_present"] is True, (
gate_action_mirror
)
assert gate_action_mirror["gate_action_mirrors"]["world-class-evidence"]["reason_present"] is True, (
gate_action_mirror
)
assert checks["overview-benchmark-summary"]["status"] == "pass", checks["overview-benchmark-summary"]
assert checks["interpretation-adoption-summary"]["status"] == "pass", checks["interpretation-adoption-summary"]
assert checks["coverage-world-class-boundary"]["status"] == "pass", checks["coverage-world-class-boundary"]
@@ -418,9 +427,15 @@ def main() -> None:
for gate in gate_action_payload["gates"]:
if gate["key"] == "world-class-evidence":
gate["review_action_id"] = ""
gate["review_action_title"] = ""
gate["review_action_next_step"] = ""
gate["review_action_reason"] = ""
gate["review_action_source_ref_count"] = 0
for action in gate_action_payload["review_actions"]:
if action["gate_key"] == "world-class-evidence":
action["title"] = ""
action["next_step"] = ""
action["reason"] = ""
action["source_refs"] = []
gate_action_path.write_text(json.dumps(gate_action_payload, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
gate_action_drift_proc = run(
+9
View File
@@ -41,12 +41,18 @@ def main() -> None:
for gate in payload["gates"]:
if gate["status"] == "pass":
assert gate["review_action_id"] == "", gate
assert gate["review_action_title"] == "", gate
assert gate["review_action_next_step"] == "", gate
assert gate["review_action_reason"] == "", gate
assert gate["review_action_source_ref_count"] == 0, gate
assert gate["review_action_verification_command"] == "", gate
continue
action = action_by_gate[gate["key"]]
assert gate["review_action_id"] == action["action_id"] == f"review-action-{gate['key']}", gate
assert gate["review_action_status"] == action["status"] == gate["status"], gate
assert gate["review_action_title"] == action["title"] == action["label"], gate
assert gate["review_action_next_step"] == action["next_step"] == action["summary"], gate
assert gate["review_action_reason"] == action["reason"] == action["why"], gate
assert gate["review_action_source_ref_count"] == len(action["source_refs"]) > 0, gate
assert gate["review_action_verification_command"] == action["verification_command"], gate
assert set(review_gates.GATE_WEIGHTS) == review_gates.REVIEW_STUDIO_GATE_KEYS, review_gates.GATE_WEIGHTS
@@ -308,6 +314,9 @@ def main() -> None:
output_html,
)
assert len(synthetic_actions) == 1, synthetic_actions
assert synthetic_actions[0]["title"] == "输出实验", synthetic_actions
assert synthetic_actions[0]["next_step"] == synthetic_actions[0]["summary"], synthetic_actions
assert synthetic_actions[0]["reason"] == synthetic_actions[0]["why"], synthetic_actions
assert synthetic_actions[0]["source_refs"], synthetic_actions
assert {item["path"] for item in synthetic_actions[0]["source_refs"]} >= {
"evals/output/cases.jsonl",