Clarify world-class submission artifact roles
This commit is contained in:
yaojingang
@@ -34,6 +34,8 @@ The generated intake report also includes an `operator_checklist` for each pendi
|
||||
|
||||
The submission kit command creates editable JSON drafts plus a local README for an external operator or human reviewer. Use `--prefill-artifacts` when you want the kit to insert SHA-256 digests for currently available local aggregate artifacts. Prefill is operator convenience only: those drafts still keep `template_only: true` and do not count as evidence until the real run or review exists, the packet is edited truthfully, every artifact ref points to a local aggregate evidence file with a matching `sha256`, and `world-class-intake` validates it.
|
||||
|
||||
The submission kit separates artifact rows into `submission-ref` and `supporting-evidence`. `submission-ref` rows are the concrete paths expected in a real packet's `artifact_refs`; `supporting-evidence` rows help reviewers audit the packet and do not all need to be copied into the submission.
|
||||
|
||||
The submission review command renders a read-only queue that compares valid packets with the source evidence checks and current ledger state. It is for reviewer triage only; it does not accept evidence or make the world-class claim true.
|
||||
|
||||
Accepted intake means "ready for ledger review", not evidence that the final public claim is ready. The ledger remains the source of truth for `ready_to_claim_world_class`.
|
||||
|
||||
+1
-1
@@ -16,7 +16,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60"
|
||||
"package_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -16,8 +16,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096"
|
||||
"package_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -48,7 +48,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
|
||||
@@ -36,6 +36,13 @@
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_world_class_evidence_intake.py",
|
||||
"lines": 867,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_evidence_consistency.py",
|
||||
"lines": 859,
|
||||
@@ -43,13 +50,6 @@
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_world_class_evidence_intake.py",
|
||||
"lines": 842,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_review_studio.py",
|
||||
"lines": 816,
|
||||
@@ -122,6 +122,13 @@
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_world_class_evidence_intake.py",
|
||||
"lines": 867,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_evidence_consistency.py",
|
||||
"lines": 859,
|
||||
@@ -129,13 +136,6 @@
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_world_class_evidence_intake.py",
|
||||
"lines": 842,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_review_studio.py",
|
||||
"lines": 816,
|
||||
|
||||
@@ -31,8 +31,8 @@ No file-size hotspots found.
|
||||
| --- | ---: | --- | --- |
|
||||
| `tests/verify_yao_cli.py` | `899` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
|
||||
| `scripts/yao_cli_parser.py` | `870` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
|
||||
| `tests/verify_world_class_evidence_intake.py` | `867` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
|
||||
| `scripts/render_evidence_consistency.py` | `859` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
|
||||
| `tests/verify_world_class_evidence_intake.py` | `842` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
|
||||
| `tests/verify_review_studio.py` | `816` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
|
||||
| `scripts/skill_report_model.py` | `800` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
|
||||
| `scripts/build_skill_atlas.py` | `730` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
|
||||
@@ -45,8 +45,8 @@ No file-size hotspots found.
|
||||
| --- | ---: | --- | --- |
|
||||
| `tests/verify_yao_cli.py` | `899` | `test` | `pass` |
|
||||
| `scripts/yao_cli_parser.py` | `870` | `internal-module` | `pass` |
|
||||
| `tests/verify_world_class_evidence_intake.py` | `867` | `test` | `pass` |
|
||||
| `scripts/render_evidence_consistency.py` | `859` | `cli-script` | `pass` |
|
||||
| `tests/verify_world_class_evidence_intake.py` | `842` | `test` | `pass` |
|
||||
| `tests/verify_review_studio.py` | `816` | `test` | `pass` |
|
||||
| `scripts/skill_report_model.py` | `800` | `internal-module` | `pass` |
|
||||
| `scripts/build_skill_atlas.py` | `730` | `cli-script` | `pass` |
|
||||
|
||||
@@ -3,23 +3,36 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16",
|
||||
"skill_dir": ".",
|
||||
"commit": "30451d41f615562dfd0380414cc8447d4dad5e38",
|
||||
"commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": false,
|
||||
"changed_file_count": 0,
|
||||
"sample": [],
|
||||
"dirty": true,
|
||||
"changed_file_count": 22,
|
||||
"sample": [
|
||||
" M evidence/world_class/README.md",
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" M reports/architecture_maintainability.json",
|
||||
" M reports/architecture_maintainability.md",
|
||||
" M reports/context_budget.json",
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json",
|
||||
" M reports/output_execution_runs.json",
|
||||
" M reports/output_execution_runs.md",
|
||||
" M reports/package_verification.json",
|
||||
" M reports/package_verification.md"
|
||||
],
|
||||
"scope": "generation-time status before this report is written"
|
||||
},
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8a5745cd8b",
|
||||
"source_contract_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"evidence_bundle_sha256": "cb7f095c9e24168f804f6b04a4d30f6be1959f248f693510a57e55eaf842afa0",
|
||||
"source_contract_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -37,14 +50,15 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 22
|
||||
},
|
||||
"public_claim": {
|
||||
"ready": false,
|
||||
"scope": "public benchmark or world-class readiness claim",
|
||||
"blockers": [
|
||||
"release lock is not clean or commit is unavailable",
|
||||
"provider-backed model holdout evidence is incomplete",
|
||||
"human blind-review adjudication is incomplete",
|
||||
"world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
|
||||
@@ -53,10 +67,10 @@
|
||||
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
|
||||
},
|
||||
"release_lock": {
|
||||
"ready": true,
|
||||
"commit": "30451d41f615562dfd0380414cc8447d4dad5e38",
|
||||
"ready": false,
|
||||
"commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
|
||||
"status_scope": "generation-time status before this report is written",
|
||||
"reason": "clean generation-time HEAD"
|
||||
"reason": "working tree was dirty at generation time"
|
||||
},
|
||||
"evidence_bundle": {
|
||||
"algorithm": "sha256(path,label,exists,artifact_sha256)",
|
||||
@@ -64,7 +78,7 @@
|
||||
"existing_count": 25,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8a5745cd8b"
|
||||
"sha256": "cb7f095c9e24168f804f6b04a4d30f6be1959f248f693510a57e55eaf842afa0"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -138,7 +152,7 @@
|
||||
"path": "reports/output_execution_runs.json",
|
||||
"exists": true,
|
||||
"bytes": 7967,
|
||||
"sha256": "dc896e2929e25d8f517ded4024f2bce12030f4be14f885f76255be887117766c"
|
||||
"sha256": "3cacfc88fbb221a0c3e736d2f70683bf45d221b17cfe81ec7be4c8375eab9b14"
|
||||
},
|
||||
{
|
||||
"label": "blind_review",
|
||||
@@ -173,7 +187,7 @@
|
||||
"path": "reports/security_trust_report.json",
|
||||
"exists": true,
|
||||
"bytes": 117850,
|
||||
"sha256": "8a6f0eb0c627b1b8a7ffb45fd431b678827a91590028021e145d6b60d2fc4c2e"
|
||||
"sha256": "6273c1b82d09eda9eaed37cd2335e0a9d71b0de130fce5d0692f37021a92ce4b"
|
||||
},
|
||||
{
|
||||
"label": "python_compatibility",
|
||||
@@ -187,14 +201,14 @@
|
||||
"path": "reports/registry_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 3183,
|
||||
"sha256": "bd4b1f1cd5b21d0bda736ea14db4e6839e3729f66c787ef3be97619e8d069267"
|
||||
"sha256": "de8f4a0257c67a0b605ecaba30fdb89d9a0c7ba5256dd975c1e66b1df884b6fd"
|
||||
},
|
||||
{
|
||||
"label": "package_verification",
|
||||
"path": "reports/package_verification.json",
|
||||
"exists": true,
|
||||
"bytes": 19338,
|
||||
"sha256": "3fe267c06ebba290d312575d3042fc8a1125ebe7c07c1c555eae2948dbf845d0"
|
||||
"sha256": "5ca9869ad3666cbf6fa0b31ba97717117e240be0c927982808ce8bbeccf68eed"
|
||||
},
|
||||
{
|
||||
"label": "install_simulation",
|
||||
|
||||
@@ -1,19 +1,19 @@
|
||||
# Benchmark Reproducibility
|
||||
|
||||
Generated at: `2026-06-16`
|
||||
Commit: `30451d41f615562dfd0380414cc8447d4dad5e38`
|
||||
Working tree dirty at generation: `false`
|
||||
Evidence bundle SHA256: `f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8a5745cd8b`
|
||||
Commit: `e0a19e9b24a28e57e04aa8254013402eb93bf86b`
|
||||
Working tree dirty at generation: `true`
|
||||
Evidence bundle SHA256: `cb7f095c9e24168f804f6b04a4d30f6be1959f248f693510a57e55eaf842afa0`
|
||||
|
||||
## Summary
|
||||
|
||||
- reproducibility ready: `true`
|
||||
- release lock ready: `true`
|
||||
- release lock ready: `false`
|
||||
- methodology complete: `true`
|
||||
- required artifacts: `25`
|
||||
- missing artifacts: `0`
|
||||
- source contract sha256: `1b03b1e4bab9`
|
||||
- archive sha256: `38e8e607c1ed`
|
||||
- source contract sha256: `892708619b13`
|
||||
- archive sha256: `b90b116cb657`
|
||||
- output cases: `5`
|
||||
- disclosed failure cases: `3`
|
||||
- reproduction commands: `23`
|
||||
@@ -22,8 +22,8 @@ Evidence bundle SHA256: `f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8
|
||||
- world-class ready: `false`
|
||||
- world-class source checks: `6` pass / `13` total; `7` blocked
|
||||
- public claim ready: `false`
|
||||
- public claim blockers: `4`
|
||||
- changed files at generation: `0`
|
||||
- public claim blockers: `5`
|
||||
- changed files at generation: `22`
|
||||
|
||||
This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
|
||||
|
||||
@@ -35,6 +35,7 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
|
||||
| Blocker |
|
||||
| --- |
|
||||
| release lock is not clean or commit is unavailable |
|
||||
| provider-backed model holdout evidence is incomplete |
|
||||
| human blind-review adjudication is incomplete |
|
||||
| world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) |
|
||||
@@ -42,15 +43,15 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
|
||||
## Release Lock
|
||||
|
||||
- ready: `true`
|
||||
- reason: clean generation-time HEAD
|
||||
- ready: `false`
|
||||
- reason: working tree was dirty at generation time
|
||||
- status scope: generation-time status before this report is written
|
||||
|
||||
## Evidence Bundle
|
||||
|
||||
- algorithm: `sha256(path,label,exists,artifact_sha256)`
|
||||
- artifacts: `25` / `25`
|
||||
- sha256: `f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8a5745cd8b`
|
||||
- sha256: `cb7f095c9e24168f804f6b04a4d30f6be1959f248f693510a57e55eaf842afa0`
|
||||
|
||||
## Methodology Sections
|
||||
|
||||
@@ -72,15 +73,15 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
| output_cases | `evals/output/cases.jsonl` | present | `a6ae96857116` |
|
||||
| output_schema | `evals/output/schema.json` | present | `8ee340c95064` |
|
||||
| output_scorecard | `reports/output_quality_scorecard.json` | present | `0806258a8e08` |
|
||||
| output_execution | `reports/output_execution_runs.json` | present | `dc896e2929e2` |
|
||||
| output_execution | `reports/output_execution_runs.json` | present | `3cacfc88fbb2` |
|
||||
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
|
||||
| review_adjudication | `reports/output_review_adjudication.json` | present | `bb8c72a9291e` |
|
||||
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
|
||||
| runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` |
|
||||
| trust_report | `reports/security_trust_report.json` | present | `8a6f0eb0c627` |
|
||||
| trust_report | `reports/security_trust_report.json` | present | `6273c1b82d09` |
|
||||
| python_compatibility | `reports/python_compatibility.json` | present | `364e9bbc8dd4` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `bd4b1f1cd5b2` |
|
||||
| package_verification | `reports/package_verification.json` | present | `3fe267c06ebb` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `de8f4a0257c6` |
|
||||
| package_verification | `reports/package_verification.json` | present | `5ca9869ad366` |
|
||||
| install_simulation | `reports/install_simulation.json` | present | `0a127a000c33` |
|
||||
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `de180d2b67b0` |
|
||||
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `38e95161404d` |
|
||||
|
||||
@@ -6,15 +6,15 @@
|
||||
"context_budget_tier": "production",
|
||||
"context_budget_limit": 1000,
|
||||
"skill_body_tokens": 797,
|
||||
"other_text_tokens": 1037197,
|
||||
"other_text_tokens": 1039014,
|
||||
"estimated_initial_load_tokens": 990,
|
||||
"estimated_total_text_tokens": 1037994,
|
||||
"deferred_resource_tokens": 478929,
|
||||
"estimated_total_text_tokens": 1039811,
|
||||
"deferred_resource_tokens": 480160,
|
||||
"deferred_resource_warn_threshold": 120000,
|
||||
"deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 419118,
|
||||
"estimated_tokens": 420349,
|
||||
"file_count": 121
|
||||
},
|
||||
{
|
||||
@@ -36,7 +36,7 @@
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 419118,
|
||||
"estimated_tokens": 420349,
|
||||
"file_count": 121
|
||||
}
|
||||
],
|
||||
@@ -59,7 +59,7 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 419118,
|
||||
"estimated_tokens": 420349,
|
||||
"file_count": 121,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
| Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status |
|
||||
| --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- |
|
||||
| root | `.` | `production` | 1000 | 990 | 797 | 478929 | `governed` | scripts:419118 | 131.3 | - | ok |
|
||||
| root | `.` | `production` | 1000 | 990 | 797 | 480160 | `governed` | scripts:420349 | 131.3 | - | ok |
|
||||
| complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok |
|
||||
| governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok |
|
||||
|
||||
|
||||
@@ -8,11 +8,11 @@
|
||||
"budget_limit": 1000,
|
||||
"initial_tokens": 990,
|
||||
"skill_body_tokens": 797,
|
||||
"deferred_resource_tokens": 478929,
|
||||
"deferred_resource_tokens": 480160,
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 419118,
|
||||
"estimated_tokens": 420349,
|
||||
"file_count": 121
|
||||
}
|
||||
],
|
||||
@@ -35,7 +35,7 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 419118,
|
||||
"estimated_tokens": 420349,
|
||||
"file_count": 121,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
|
||||
@@ -189,12 +189,12 @@
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"status": "pass",
|
||||
"detail": "initial load 990/1000; deferred 478929/120000; top deferred scripts 419118; resource governance governed; quality density 131.3",
|
||||
"detail": "initial load 990/1000; deferred 480160/120000; top deferred scripts 420349; resource governance governed; quality density 131.3",
|
||||
"evidence": "reports/context_budget.json"
|
||||
},
|
||||
"actual": {
|
||||
"status": "pass",
|
||||
"detail": "initial load 990/1000; deferred 478929/120000; top deferred scripts 419118; resource governance governed; quality density 131.3",
|
||||
"detail": "initial load 990/1000; deferred 480160/120000; top deferred scripts 420349; resource governance governed; quality density 131.3",
|
||||
"evidence": "reports/context_budget.json"
|
||||
},
|
||||
"paths": [
|
||||
@@ -207,8 +207,8 @@
|
||||
"key": "benchmark-release-lock-self-consistency",
|
||||
"label": "Benchmark release lock matches git dirty state",
|
||||
"status": "pass",
|
||||
"expected": true,
|
||||
"actual": true,
|
||||
"expected": false,
|
||||
"actual": false,
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json"
|
||||
],
|
||||
@@ -248,8 +248,8 @@
|
||||
"key": "overview-benchmark-commit",
|
||||
"label": "overview embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "30451d41f615562dfd0380414cc8447d4dad5e38",
|
||||
"actual": "30451d41f615562dfd0380414cc8447d4dad5e38",
|
||||
"expected": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
|
||||
"actual": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-overview.json"
|
||||
@@ -261,30 +261,30 @@
|
||||
"label": "overview embeds benchmark summary fields",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"source_contract_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"actual": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"source_contract_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
@@ -394,8 +394,8 @@
|
||||
"key": "interpretation-benchmark-commit",
|
||||
"label": "interpretation embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "30451d41f615562dfd0380414cc8447d4dad5e38",
|
||||
"actual": "30451d41f615562dfd0380414cc8447d4dad5e38",
|
||||
"expected": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
|
||||
"actual": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-interpretation.json"
|
||||
@@ -407,30 +407,30 @@
|
||||
"label": "interpretation embeds benchmark summary fields",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"source_contract_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"actual": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"source_contract_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 13,
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4
|
||||
"public_claim_blocker_count": 5
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
|
||||
@@ -34,7 +34,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.75,
|
||||
"duration_ms": 27.55,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -62,7 +62,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 25.99,
|
||||
"duration_ms": 28.21,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -85,7 +85,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.29,
|
||||
"duration_ms": 28.18,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -113,7 +113,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 29.72,
|
||||
"duration_ms": 29.22,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -136,7 +136,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 29.38,
|
||||
"duration_ms": 29.62,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -164,7 +164,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 37.41,
|
||||
"duration_ms": 28.61,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -187,7 +187,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.96,
|
||||
"duration_ms": 27.07,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -214,7 +214,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.52,
|
||||
"duration_ms": 26.04,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -237,7 +237,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 27.23,
|
||||
"duration_ms": 26.26,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -266,7 +266,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.38,
|
||||
"duration_ms": 26.28,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
|
||||
@@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext
|
||||
|
||||
| Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status |
|
||||
| --- | --- | --- | --- | ---: | ---: | ---: | --- |
|
||||
| skill-package-contract | baseline | command | local-output-eval-runner | 26.75 | 33 | 0.0 | pass |
|
||||
| skill-package-contract | with_skill | command | local-output-eval-runner | 25.99 | 73 | 100.0 | pass |
|
||||
| output-eval-expectation | baseline | command | local-output-eval-runner | 26.29 | 36 | 0.0 | pass |
|
||||
| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.72 | 80 | 100.0 | pass |
|
||||
| ir-before-packaging | baseline | command | local-output-eval-runner | 29.38 | 33 | 0.0 | pass |
|
||||
| ir-before-packaging | with_skill | command | local-output-eval-runner | 37.41 | 80 | 100.0 | pass |
|
||||
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.96 | 36 | 0.0 | pass |
|
||||
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.52 | 65 | 100.0 | pass |
|
||||
| file-backed-governed-package | baseline | command | local-output-eval-runner | 27.23 | 37 | 0.0 | pass |
|
||||
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.38 | 98 | 100.0 | pass |
|
||||
| skill-package-contract | baseline | command | local-output-eval-runner | 27.55 | 33 | 0.0 | pass |
|
||||
| skill-package-contract | with_skill | command | local-output-eval-runner | 28.21 | 73 | 100.0 | pass |
|
||||
| output-eval-expectation | baseline | command | local-output-eval-runner | 28.18 | 36 | 0.0 | pass |
|
||||
| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.22 | 80 | 100.0 | pass |
|
||||
| ir-before-packaging | baseline | command | local-output-eval-runner | 29.62 | 33 | 0.0 | pass |
|
||||
| ir-before-packaging | with_skill | command | local-output-eval-runner | 28.61 | 80 | 100.0 | pass |
|
||||
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 27.07 | 36 | 0.0 | pass |
|
||||
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.04 | 65 | 100.0 | pass |
|
||||
| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.26 | 37 | 0.0 | pass |
|
||||
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.28 | 98 | 100.0 | pass |
|
||||
|
||||
## Next Fixes
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"archive_sha256": "b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d",
|
||||
"archive_entry_count": 646,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
- Package directory: `dist`
|
||||
- Targets: `4 / 4` adapters present
|
||||
- Archive present: `True`
|
||||
- Archive SHA256: `38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca`
|
||||
- Archive SHA256: `b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d`
|
||||
- Failures: `0`
|
||||
- Warnings: `0`
|
||||
|
||||
|
||||
@@ -21,8 +21,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096"
|
||||
"package_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -53,7 +53,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -78,7 +78,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60"
|
||||
"package_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -6,8 +6,8 @@
|
||||
- Maturity: `governed`
|
||||
- Owner: `Yao Team`
|
||||
- License: `MIT`
|
||||
- Package SHA256: `1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60`
|
||||
- Archive SHA256: `d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096`
|
||||
- Package SHA256: `892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c`
|
||||
- Archive SHA256: `38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca`
|
||||
- Install simulated: `True`
|
||||
|
||||
## Compatibility
|
||||
|
||||
@@ -711,12 +711,12 @@
|
||||
|
||||
<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>121 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>193 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>899 largest lines; 9 watchlist; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock true</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>180 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>646 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>121 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>193 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>899 largest lines; 9 watchlist; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock true</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>180 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>646 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 478929/120000; top deferred scripts 419118; 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; 121 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; 193 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>190 Python files; 0 hotspots; 9 watchlist files; 0 blockers; largest 899 lines; 68 CLI handlers; 18 in entrypoint</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
|
||||
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 990/1000; deferred 480160/120000; top deferred scripts 420349; 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; 121 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; 193 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>190 Python files; 0 hotspots; 9 watchlist files; 0 blockers; largest 899 lines; 68 CLI handlers; 18 in entrypoint</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
|
||||
</section>
|
||||
|
||||
<div class="twocol">
|
||||
@@ -778,12 +778,12 @@
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 478929/120000; top deferred scripts 419118; resource governance governed; quality density 131.3</p></div>
|
||||
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 480160/120000; top deferred scripts 420349; 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>121</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>1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60</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>121</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>892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c</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>
|
||||
|
||||
@@ -848,8 +848,8 @@
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>4</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
|
||||
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>5</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>release lock is not clean or commit is unavailable</span></li><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
@@ -869,12 +869,12 @@
|
||||
|
||||
<section id="registry" class="twocol">
|
||||
<div class="panel"><h2>注册审计</h2><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p></div>
|
||||
<div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible, vscode</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096</code></dd></div></dl></div>
|
||||
<div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible, vscode</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca</code></dd></div></dl></div>
|
||||
</section>
|
||||
|
||||
<section id="release" class="twocol">
|
||||
<div class="panel"><h2>发布路线</h2><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p></div>
|
||||
<div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd>是</dd></div><div><dt>Zip 条目</dt><dd>646</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca</code></dd></div></dl></div>
|
||||
<div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd>是</dd></div><div><dt>Zip 条目</dt><dd>646</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d</code></dd></div></dl></div>
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
|
||||
+87
-73
@@ -43,7 +43,7 @@
|
||||
"key": "context-budget",
|
||||
"label": "上下文",
|
||||
"status": "pass",
|
||||
"detail": "initial load 990/1000; deferred 478929/120000; top deferred scripts 419118; resource governance governed; quality density 131.3",
|
||||
"detail": "initial load 990/1000; deferred 480160/120000; top deferred scripts 420349; resource governance governed; quality density 131.3",
|
||||
"evidence": "reports/context_budget.json",
|
||||
"link": "context_budget.md"
|
||||
},
|
||||
@@ -1812,13 +1812,13 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8a5745cd8b",
|
||||
"source_contract_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"evidence_bundle_sha256": "cb7f095c9e24168f804f6b04a4d30f6be1959f248f693510a57e55eaf842afa0",
|
||||
"source_contract_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -1836,11 +1836,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 22
|
||||
},
|
||||
"commit": "30451d41f615562dfd0380414cc8447d4dad5e38",
|
||||
"commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
|
||||
@@ -1945,7 +1945,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 212,
|
||||
"package_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60"
|
||||
"package_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1983,8 +1983,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096"
|
||||
"package_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -2015,7 +2015,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -2031,7 +2031,7 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"archive_sha256": "b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d",
|
||||
"archive_entry_count": 646,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
@@ -2110,12 +2110,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096"
|
||||
"to": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60"
|
||||
"to": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -4488,7 +4488,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.75,
|
||||
"duration_ms": 27.55,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4516,7 +4516,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 25.99,
|
||||
"duration_ms": 28.21,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4539,7 +4539,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.29,
|
||||
"duration_ms": 28.18,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4567,7 +4567,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 29.72,
|
||||
"duration_ms": 29.22,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4590,7 +4590,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 29.38,
|
||||
"duration_ms": 29.62,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4618,7 +4618,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 37.41,
|
||||
"duration_ms": 28.61,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4641,7 +4641,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.96,
|
||||
"duration_ms": 27.07,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4668,7 +4668,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.52,
|
||||
"duration_ms": 26.04,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4691,7 +4691,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 27.23,
|
||||
"duration_ms": 26.26,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4720,7 +4720,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 26.38,
|
||||
"duration_ms": 26.28,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5446,23 +5446,36 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-16",
|
||||
"skill_dir": ".",
|
||||
"commit": "30451d41f615562dfd0380414cc8447d4dad5e38",
|
||||
"commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": false,
|
||||
"changed_file_count": 0,
|
||||
"sample": [],
|
||||
"dirty": true,
|
||||
"changed_file_count": 22,
|
||||
"sample": [
|
||||
" M evidence/world_class/README.md",
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" M reports/architecture_maintainability.json",
|
||||
" M reports/architecture_maintainability.md",
|
||||
" M reports/context_budget.json",
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json",
|
||||
" M reports/output_execution_runs.json",
|
||||
" M reports/output_execution_runs.md",
|
||||
" M reports/package_verification.json",
|
||||
" M reports/package_verification.md"
|
||||
],
|
||||
"scope": "generation-time status before this report is written"
|
||||
},
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8a5745cd8b",
|
||||
"source_contract_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"evidence_bundle_sha256": "cb7f095c9e24168f804f6b04a4d30f6be1959f248f693510a57e55eaf842afa0",
|
||||
"source_contract_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -5480,14 +5493,15 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 22
|
||||
},
|
||||
"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)",
|
||||
@@ -5496,10 +5510,10 @@
|
||||
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
|
||||
},
|
||||
"release_lock": {
|
||||
"ready": true,
|
||||
"commit": "30451d41f615562dfd0380414cc8447d4dad5e38",
|
||||
"ready": false,
|
||||
"commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
|
||||
"status_scope": "generation-time status before this report is written",
|
||||
"reason": "clean generation-time HEAD"
|
||||
"reason": "working tree was dirty at generation time"
|
||||
},
|
||||
"evidence_bundle": {
|
||||
"algorithm": "sha256(path,label,exists,artifact_sha256)",
|
||||
@@ -5507,7 +5521,7 @@
|
||||
"existing_count": 25,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8a5745cd8b"
|
||||
"sha256": "cb7f095c9e24168f804f6b04a4d30f6be1959f248f693510a57e55eaf842afa0"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -5581,7 +5595,7 @@
|
||||
"path": "reports/output_execution_runs.json",
|
||||
"exists": true,
|
||||
"bytes": 7967,
|
||||
"sha256": "dc896e2929e25d8f517ded4024f2bce12030f4be14f885f76255be887117766c"
|
||||
"sha256": "3cacfc88fbb221a0c3e736d2f70683bf45d221b17cfe81ec7be4c8375eab9b14"
|
||||
},
|
||||
{
|
||||
"label": "blind_review",
|
||||
@@ -5616,7 +5630,7 @@
|
||||
"path": "reports/security_trust_report.json",
|
||||
"exists": true,
|
||||
"bytes": 117850,
|
||||
"sha256": "8a6f0eb0c627b1b8a7ffb45fd431b678827a91590028021e145d6b60d2fc4c2e"
|
||||
"sha256": "6273c1b82d09eda9eaed37cd2335e0a9d71b0de130fce5d0692f37021a92ce4b"
|
||||
},
|
||||
{
|
||||
"label": "python_compatibility",
|
||||
@@ -5630,14 +5644,14 @@
|
||||
"path": "reports/registry_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 3183,
|
||||
"sha256": "bd4b1f1cd5b21d0bda736ea14db4e6839e3729f66c787ef3be97619e8d069267"
|
||||
"sha256": "de8f4a0257c67a0b605ecaba30fdb89d9a0c7ba5256dd975c1e66b1df884b6fd"
|
||||
},
|
||||
{
|
||||
"label": "package_verification",
|
||||
"path": "reports/package_verification.json",
|
||||
"exists": true,
|
||||
"bytes": 19338,
|
||||
"sha256": "3fe267c06ebba290d312575d3042fc8a1125ebe7c07c1c555eae2948dbf845d0"
|
||||
"sha256": "5ca9869ad3666cbf6fa0b31ba97717117e240be0c927982808ce8bbeccf68eed"
|
||||
},
|
||||
{
|
||||
"label": "install_simulation",
|
||||
@@ -11891,7 +11905,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 212,
|
||||
"package_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60"
|
||||
"package_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": [],
|
||||
@@ -16063,6 +16077,13 @@
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_world_class_evidence_intake.py",
|
||||
"lines": 867,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_evidence_consistency.py",
|
||||
"lines": 859,
|
||||
@@ -16070,13 +16091,6 @@
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_world_class_evidence_intake.py",
|
||||
"lines": 842,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_review_studio.py",
|
||||
"lines": 816,
|
||||
@@ -16149,6 +16163,13 @@
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_world_class_evidence_intake.py",
|
||||
"lines": 867,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_evidence_consistency.py",
|
||||
"lines": 859,
|
||||
@@ -16156,13 +16177,6 @@
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_world_class_evidence_intake.py",
|
||||
"lines": 842,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_review_studio.py",
|
||||
"lines": 816,
|
||||
@@ -16214,15 +16228,15 @@
|
||||
"context_budget_tier": "production",
|
||||
"context_budget_limit": 1000,
|
||||
"skill_body_tokens": 797,
|
||||
"other_text_tokens": 1037197,
|
||||
"other_text_tokens": 1039014,
|
||||
"estimated_initial_load_tokens": 990,
|
||||
"estimated_total_text_tokens": 1037994,
|
||||
"deferred_resource_tokens": 478929,
|
||||
"estimated_total_text_tokens": 1039811,
|
||||
"deferred_resource_tokens": 480160,
|
||||
"deferred_resource_warn_threshold": 120000,
|
||||
"deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 419118,
|
||||
"estimated_tokens": 420349,
|
||||
"file_count": 121
|
||||
},
|
||||
{
|
||||
@@ -16244,7 +16258,7 @@
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 419118,
|
||||
"estimated_tokens": 420349,
|
||||
"file_count": 121
|
||||
}
|
||||
],
|
||||
@@ -16267,7 +16281,7 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 419118,
|
||||
"estimated_tokens": 420349,
|
||||
"file_count": 121,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
@@ -22147,8 +22161,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096"
|
||||
"package_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -22179,7 +22193,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -22204,7 +22218,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60"
|
||||
"package_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -22227,7 +22241,7 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"archive_sha256": "b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d",
|
||||
"archive_entry_count": 646,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
@@ -23235,12 +23249,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096"
|
||||
"to": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60"
|
||||
"to": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
+15
-15
@@ -997,13 +997,13 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8a5745cd8b",
|
||||
"source_contract_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"evidence_bundle_sha256": "cb7f095c9e24168f804f6b04a4d30f6be1959f248f693510a57e55eaf842afa0",
|
||||
"source_contract_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -1021,11 +1021,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 22
|
||||
},
|
||||
"commit": "30451d41f615562dfd0380414cc8447d4dad5e38",
|
||||
"commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
|
||||
@@ -1130,7 +1130,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 212,
|
||||
"package_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60"
|
||||
"package_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1168,8 +1168,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096"
|
||||
"package_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -1200,7 +1200,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -1216,7 +1216,7 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"archive_sha256": "b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d",
|
||||
"archive_entry_count": 646,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
@@ -1295,12 +1295,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096"
|
||||
"to": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60"
|
||||
"to": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -23,7 +23,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 212,
|
||||
"package_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60"
|
||||
"package_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": [],
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
- Interactive scripts: `0`
|
||||
- Package hash scope: `source-contract-without-generated-reports`
|
||||
- Package hash files: `212`
|
||||
- Package SHA256: `1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60`
|
||||
- Package SHA256: `892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c`
|
||||
|
||||
## Failures
|
||||
|
||||
|
||||
@@ -1001,13 +1001,13 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8a5745cd8b",
|
||||
"source_contract_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"evidence_bundle_sha256": "cb7f095c9e24168f804f6b04a4d30f6be1959f248f693510a57e55eaf842afa0",
|
||||
"source_contract_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -1025,11 +1025,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 22
|
||||
},
|
||||
"commit": "30451d41f615562dfd0380414cc8447d4dad5e38",
|
||||
"commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
|
||||
@@ -1134,7 +1134,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 212,
|
||||
"package_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60"
|
||||
"package_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1172,8 +1172,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096"
|
||||
"package_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -1204,7 +1204,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -1220,7 +1220,7 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"archive_sha256": "b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d",
|
||||
"archive_entry_count": 646,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
@@ -1299,12 +1299,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096"
|
||||
"to": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60"
|
||||
"to": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -22,6 +22,7 @@ Yao Meta Skill is no longer only a Meta Skill factory. The current working tree
|
||||
- World-Class Evidence Ledger v0 that records current acceptance state, provenance requirements, privacy contracts, and anti-overclaim guards for those remaining gaps.
|
||||
- World-Class Intake Contract Hardening v0 so real evidence submissions must use the ledger's canonical `<evidence-key>.json` filename and are recursively rejected when they include raw prompt, output, transcript, message, credential, secret, token, or API-key fields.
|
||||
- World-Class Submission Matrix v0 so the submission kit exposes a single operator-facing matrix for draft status, artifact readiness, source-check blockers, and the next action without counting matrix rows as completion evidence.
|
||||
- World-Class Submission Artifact Roles v0 so submission kits distinguish `submission-ref` rows that belong in `artifact_refs` from supporting audit assets, reducing operator ambiguity without accepting evidence.
|
||||
- World-Class Submission Kit Rendering v0 so Markdown and HTML kit presentation lives in a dedicated internal renderer, keeping the CLI focused on evidence assembly and file emission.
|
||||
- Benchmark Reproducibility v0 that turns public benchmark methodology, required artifacts, failure disclosure, and reproduction commands into machine-checkable release evidence.
|
||||
- Review Studio 2.0 v0 for one-page blocker, warning, evidence-path, review-action, and release-gate review.
|
||||
|
||||
+15
-15
@@ -996,13 +996,13 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "f7b6c8fac83208f863f1e110b175eac345a7da3dc76240fd4a027a8a5745cd8b",
|
||||
"source_contract_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"evidence_bundle_sha256": "cb7f095c9e24168f804f6b04a4d30f6be1959f248f693510a57e55eaf842afa0",
|
||||
"source_contract_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -1020,11 +1020,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 22
|
||||
},
|
||||
"commit": "30451d41f615562dfd0380414cc8447d4dad5e38",
|
||||
"commit": "e0a19e9b24a28e57e04aa8254013402eb93bf86b",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
|
||||
@@ -1129,7 +1129,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 212,
|
||||
"package_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60"
|
||||
"package_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1167,8 +1167,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60",
|
||||
"archive_sha256": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096"
|
||||
"package_sha256": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -1199,7 +1199,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096",
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -1215,7 +1215,7 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca",
|
||||
"archive_sha256": "b90b116cb657d9fa1ba2f3f0620a05965890b996917626dcdc7f974a05aaeb0d",
|
||||
"archive_entry_count": 646,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
@@ -1294,12 +1294,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096"
|
||||
"to": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60"
|
||||
"to": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -70,12 +70,12 @@
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "d543b93ac3b301b4abfb6f749509fac8234e501b2a5e2af93361a7250f8e5096"
|
||||
"to": "38e8e607c1ed5bd016ea242f8fac3e8dfdfe16b165876bc4e19f587481e7c5ca"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "1b03b1e4bab90eac18aa1ee7f0ddd1d7293c3bdfb32620531c4fc231e33e2b60"
|
||||
"to": "892708619b13ff1af2f189a9a4526123c509bb8b3899dc721af6e66a80ba492c"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -69,6 +69,25 @@ def artifact_rows_by_key_and_path(rows: list[dict[str, Any]]) -> dict[tuple[str,
|
||||
return ready
|
||||
|
||||
|
||||
def template_artifact_ref_paths(skill_dir: Path, item: dict[str, Any]) -> set[str]:
|
||||
template_path = skill_dir / str(item.get("template_path", ""))
|
||||
errors: list[str] = []
|
||||
payload = load_template_payload(template_path, errors)
|
||||
if payload is None:
|
||||
return set()
|
||||
refs = payload.get("artifact_refs", [])
|
||||
if not isinstance(refs, list):
|
||||
return set()
|
||||
paths: set[str] = set()
|
||||
for ref in refs:
|
||||
if not isinstance(ref, dict):
|
||||
continue
|
||||
path = str(ref.get("path", "")).strip()
|
||||
if path:
|
||||
paths.add(path)
|
||||
return paths
|
||||
|
||||
|
||||
def load_template_payload(path: Path, errors: list[str]) -> dict[str, Any] | None:
|
||||
try:
|
||||
payload = json.loads(path.read_text(encoding="utf-8"))
|
||||
@@ -201,12 +220,22 @@ def artifact_row(skill_dir: Path, evidence_key: str, pattern: str, path: Path, s
|
||||
}
|
||||
|
||||
|
||||
def with_artifact_role(row: dict[str, Any], submission_ref_paths: set[str]) -> dict[str, Any]:
|
||||
is_submission_ref = str(row.get("path", "")) in submission_ref_paths
|
||||
return {
|
||||
**row,
|
||||
"artifact_role": "submission-ref" if is_submission_ref else "supporting-evidence",
|
||||
"submission_ref_required": is_submission_ref,
|
||||
}
|
||||
|
||||
|
||||
def artifact_checklist_for_item(skill_dir: Path, item: dict[str, Any]) -> list[dict[str, Any]]:
|
||||
key = str(item.get("evidence_key", ""))
|
||||
must_collect = item.get("must_collect", {}) if isinstance(item.get("must_collect", {}), dict) else {}
|
||||
artifacts = must_collect.get("evidence_artifacts", [])
|
||||
if not isinstance(artifacts, list):
|
||||
return []
|
||||
submission_ref_paths = template_artifact_ref_paths(skill_dir, item)
|
||||
rows: list[dict[str, Any]] = []
|
||||
for artifact in artifacts:
|
||||
pattern = str(artifact or "").strip()
|
||||
@@ -214,31 +243,12 @@ def artifact_checklist_for_item(skill_dir: Path, item: dict[str, Any]) -> list[d
|
||||
continue
|
||||
if Path(pattern).is_absolute() or ".." in Path(pattern).parts:
|
||||
rows.append(
|
||||
{
|
||||
"evidence_key": key,
|
||||
"source_pattern": pattern,
|
||||
"path": pattern,
|
||||
"status": "unsafe-path",
|
||||
"exists": False,
|
||||
"is_file": False,
|
||||
"sha256": "",
|
||||
"artifact_ref_ready": False,
|
||||
"copy_path": "",
|
||||
"copy_sha256": "",
|
||||
"contains_raw_content": False,
|
||||
"concrete_reference_required": True,
|
||||
}
|
||||
)
|
||||
continue
|
||||
if has_glob_pattern(pattern):
|
||||
matches = sorted(path for path in skill_dir.glob(pattern) if path.is_file())
|
||||
if not matches:
|
||||
rows.append(
|
||||
with_artifact_role(
|
||||
{
|
||||
"evidence_key": key,
|
||||
"source_pattern": pattern,
|
||||
"path": pattern,
|
||||
"status": "glob-no-match",
|
||||
"status": "unsafe-path",
|
||||
"exists": False,
|
||||
"is_file": False,
|
||||
"sha256": "",
|
||||
@@ -247,13 +257,38 @@ def artifact_checklist_for_item(skill_dir: Path, item: dict[str, Any]) -> list[d
|
||||
"copy_sha256": "",
|
||||
"contains_raw_content": False,
|
||||
"concrete_reference_required": True,
|
||||
}
|
||||
},
|
||||
submission_ref_paths,
|
||||
)
|
||||
)
|
||||
continue
|
||||
if has_glob_pattern(pattern):
|
||||
matches = sorted(path for path in skill_dir.glob(pattern) if path.is_file())
|
||||
if not matches:
|
||||
rows.append(
|
||||
with_artifact_role(
|
||||
{
|
||||
"evidence_key": key,
|
||||
"source_pattern": pattern,
|
||||
"path": pattern,
|
||||
"status": "glob-no-match",
|
||||
"exists": False,
|
||||
"is_file": False,
|
||||
"sha256": "",
|
||||
"artifact_ref_ready": False,
|
||||
"copy_path": "",
|
||||
"copy_sha256": "",
|
||||
"contains_raw_content": False,
|
||||
"concrete_reference_required": True,
|
||||
},
|
||||
submission_ref_paths,
|
||||
)
|
||||
)
|
||||
continue
|
||||
for match in matches:
|
||||
rows.append(artifact_row(skill_dir, key, pattern, match, "ready"))
|
||||
rows.append(with_artifact_role(artifact_row(skill_dir, key, pattern, match, "ready"), submission_ref_paths))
|
||||
continue
|
||||
rows.append(artifact_row(skill_dir, key, pattern, skill_dir / pattern, ""))
|
||||
rows.append(with_artifact_role(artifact_row(skill_dir, key, pattern, skill_dir / pattern, ""), submission_ref_paths))
|
||||
return rows
|
||||
|
||||
|
||||
@@ -305,6 +340,10 @@ def build_submission_kit(
|
||||
artifact_ready_count = sum(1 for item in artifact_checklist if item.get("artifact_ref_ready"))
|
||||
artifact_missing_count = sum(1 for item in artifact_checklist if not item.get("artifact_ref_ready"))
|
||||
artifact_glob_count = sum(1 for item in artifact_checklist if item.get("concrete_reference_required"))
|
||||
submission_ref_rows = [item for item in artifact_checklist if item.get("submission_ref_required")]
|
||||
supporting_rows = [item for item in artifact_checklist if not item.get("submission_ref_required")]
|
||||
submission_ref_ready_count = sum(1 for item in submission_ref_rows if item.get("artifact_ref_ready"))
|
||||
supporting_artifact_ready_count = sum(1 for item in supporting_rows if item.get("artifact_ref_ready"))
|
||||
source_summary = summarize_source_checklist(source_checklist)
|
||||
matrix_summary = summarize_evidence_matrix(evidence_matrix)
|
||||
ok = not unknown_keys and skipped_count == 0
|
||||
@@ -325,6 +364,12 @@ def build_submission_kit(
|
||||
"artifact_ready_count": artifact_ready_count,
|
||||
"artifact_missing_count": artifact_missing_count,
|
||||
"artifact_glob_expansion_count": artifact_glob_count,
|
||||
"submission_ref_count": len(submission_ref_rows),
|
||||
"submission_ref_ready_count": submission_ref_ready_count,
|
||||
"submission_ref_missing_count": len(submission_ref_rows) - submission_ref_ready_count,
|
||||
"supporting_artifact_count": len(supporting_rows),
|
||||
"supporting_artifact_ready_count": supporting_artifact_ready_count,
|
||||
"supporting_artifact_missing_count": len(supporting_rows) - supporting_artifact_ready_count,
|
||||
"artifact_prefill_enabled": prefill_artifacts,
|
||||
"artifact_ref_prefill_count": prefilled_artifact_ref_count,
|
||||
"artifact_ref_unfilled_count": unfilled_artifact_ref_count,
|
||||
|
||||
@@ -50,14 +50,15 @@ def render_readme(report: dict[str, Any]) -> str:
|
||||
"",
|
||||
"This matrix combines draft, artifact, and source-check readiness into one operator action list. Matrix rows are guidance only; they do not count as completion evidence.",
|
||||
"",
|
||||
"| Evidence | Stage | Draft | Artifacts | Source checks | Next action |",
|
||||
"| --- | --- | --- | ---: | ---: | --- |",
|
||||
"| Evidence | Stage | Draft | Submission refs | Supporting assets | Source checks | Next action |",
|
||||
"| --- | --- | --- | ---: | ---: | ---: | --- |",
|
||||
]
|
||||
)
|
||||
for item in report.get("evidence_matrix", []):
|
||||
lines.append(
|
||||
f"| `{item['evidence_key']}` | `{item['stage']}` | `{item['draft_status']}` | "
|
||||
f"`{item['artifact_ready_count']}/{item['artifact_total_count']}` | "
|
||||
f"`{item.get('submission_ref_ready_count', 0)}/{item.get('submission_ref_total_count', 0)}` | "
|
||||
f"`{item.get('supporting_artifact_ready_count', 0)}/{item.get('supporting_artifact_total_count', 0)}` | "
|
||||
f"`{item['source_pass_count']}/{item['source_check_count']}` | {item['next_action']} |"
|
||||
)
|
||||
lines.extend(["", "## Execution Runbook", ""])
|
||||
@@ -77,13 +78,16 @@ def render_readme(report: dict[str, Any]) -> str:
|
||||
"",
|
||||
"Use these paths and SHA-256 digests when filling `artifact_refs`. Glob patterns are expanded into concrete files; submissions must reference concrete paths, not globs.",
|
||||
"",
|
||||
"| Evidence | Path | Status | SHA-256 |",
|
||||
"| --- | --- | --- | --- |",
|
||||
"| Evidence | Role | Path | Status | SHA-256 |",
|
||||
"| --- | --- | --- | --- | --- |",
|
||||
]
|
||||
)
|
||||
for item in report.get("artifact_checklist", []):
|
||||
digest = item.get("sha256") or "n/a"
|
||||
lines.append(f"| `{item['evidence_key']}` | `{item['path']}` | `{item['status']}` | `{digest}` |")
|
||||
lines.append(
|
||||
f"| `{item['evidence_key']}` | `{item.get('artifact_role', 'supporting-evidence')}` | "
|
||||
f"`{item['path']}` | `{item['status']}` | `{digest}` |"
|
||||
)
|
||||
lines.extend(
|
||||
[
|
||||
"",
|
||||
@@ -172,6 +176,7 @@ def render_html_artifact_checklist(items: list[dict[str, Any]]) -> str:
|
||||
</div>
|
||||
<dl>
|
||||
<dt>Pattern</dt><dd><code>{pattern}</code></dd>
|
||||
<dt>Role</dt><dd>{role}</dd>
|
||||
<dt>Status</dt><dd>{status}</dd>
|
||||
<dt>SHA-256</dt><dd><code>{sha}</code></dd>
|
||||
</dl>
|
||||
@@ -181,6 +186,7 @@ def render_html_artifact_checklist(items: list[dict[str, Any]]) -> str:
|
||||
key=html_text(item.get("evidence_key", "")),
|
||||
path=html_text(item.get("path", "")),
|
||||
pattern=html_text(item.get("source_pattern", "")),
|
||||
role=html_text(item.get("artifact_role", "supporting-evidence")),
|
||||
sha=html_text(item.get("sha256") or "n/a"),
|
||||
)
|
||||
for item in items
|
||||
@@ -229,7 +235,8 @@ def render_html_matrix(items: list[dict[str, Any]]) -> str:
|
||||
</header>
|
||||
<dl>
|
||||
<dt>Draft</dt><dd>{draft}</dd>
|
||||
<dt>Artifacts</dt><dd>{artifact_ready}/{artifact_total} ready</dd>
|
||||
<dt>Submission refs</dt><dd>{submission_ref_ready}/{submission_ref_total} ready</dd>
|
||||
<dt>Supporting assets</dt><dd>{supporting_ready}/{supporting_total} ready</dd>
|
||||
<dt>Source</dt><dd>{source_pass}/{source_total} pass</dd>
|
||||
<dt>Owner</dt><dd>{owner}</dd>
|
||||
</dl>
|
||||
@@ -239,8 +246,10 @@ def render_html_matrix(items: list[dict[str, Any]]) -> str:
|
||||
stage=html_text(item.get("stage", "")),
|
||||
key=html_text(item.get("evidence_key", "")),
|
||||
draft=html_text(item.get("draft_status", "")),
|
||||
artifact_ready=html_text(item.get("artifact_ready_count", 0)),
|
||||
artifact_total=html_text(item.get("artifact_total_count", 0)),
|
||||
submission_ref_ready=html_text(item.get("submission_ref_ready_count", 0)),
|
||||
submission_ref_total=html_text(item.get("submission_ref_total_count", 0)),
|
||||
supporting_ready=html_text(item.get("supporting_artifact_ready_count", 0)),
|
||||
supporting_total=html_text(item.get("supporting_artifact_total_count", 0)),
|
||||
source_pass=html_text(item.get("source_pass_count", 0)),
|
||||
source_total=html_text(item.get("source_check_count", 0)),
|
||||
owner=html_text(item.get("owner", "")),
|
||||
@@ -291,12 +300,15 @@ def render_html(report: dict[str, Any]) -> str:
|
||||
summary = report["summary"]
|
||||
artifact_ready = summary.get("artifact_ready_count", 0)
|
||||
artifact_total = summary.get("artifact_checklist_count", 0)
|
||||
submission_ref_ready = summary.get("submission_ref_ready_count", 0)
|
||||
submission_ref_total = summary.get("submission_ref_count", 0)
|
||||
stats = [
|
||||
("Requested", summary["requested_count"]),
|
||||
("Written", summary["written_count"]),
|
||||
("Existing", summary["existing_count"]),
|
||||
("Skipped", summary["skipped_count"]),
|
||||
("Artifacts", f"{artifact_ready}/{artifact_total}"),
|
||||
("Submit refs", f"{submission_ref_ready}/{submission_ref_total}"),
|
||||
("Support", f"{artifact_ready - submission_ref_ready}/{artifact_total - submission_ref_total}"),
|
||||
("Prefilled", summary.get("artifact_ref_prefill_count", 0)),
|
||||
]
|
||||
stat_html = "".join(
|
||||
@@ -378,9 +390,9 @@ def render_html(report: dict[str, Any]) -> str:
|
||||
<article class="panel"><h2>Workflow</h2><ol><li>Run the real provider, human review, native permission, or native client telemetry work first.</li><li>Edit the matching JSON draft with aggregate artifact references and provenance metadata.</li><li>Set template_only to false only after real evidence exists.</li><li>Use prefilled SHA-256 values as convenience data, not evidence acceptance.</li><li>Validate intake, refresh the ledger, then guard public claims.</li></ol></article>
|
||||
<aside class="panel"><h2>Commands</h2><ul class="commands">{render_html_commands(report['commands'])}</ul></aside>
|
||||
</section>
|
||||
<section class="section" id="matrix"><h2>Evidence Matrix</h2><p class="muted">The matrix combines draft status, artifact readiness, source checks, and the next operator action. It is guidance only and never counts as accepted evidence.</p><div class="matrix-grid">{matrix_html}</div></section>
|
||||
<section class="section" id="matrix"><h2>Evidence Matrix</h2><p class="muted">The matrix separates submission artifact_refs from supporting assets, then combines draft status, source checks, and the next operator action. It is guidance only and never counts as accepted evidence.</p><div class="matrix-grid">{matrix_html}</div></section>
|
||||
<section class="section" id="drafts"><h2>Drafts</h2><div class="draft-grid">{render_html_files(report['files'])}</div></section>
|
||||
<section class="section" id="artifacts"><h2>Artifact Checklist</h2><p class="muted">Copy concrete paths and SHA-256 digests from here into artifact_refs after real evidence exists. Glob patterns are expanded for operator convenience only.</p><div class="artifact-grid">{artifact_html}</div></section>
|
||||
<section class="section" id="artifacts"><h2>Artifact Checklist</h2><p class="muted">Rows marked submission-ref are the paths expected in artifact_refs. Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into the submission. Glob patterns are expanded for operator convenience only.</p><div class="artifact-grid">{artifact_html}</div></section>
|
||||
<section class="section" id="source"><h2>Source Evidence Snapshot</h2><p class="muted">This section shows current aggregate source checks. It explains remaining blockers without changing the ledger.</p><div class="source-grid">{source_html}</div></section>
|
||||
<section class="section" id="evidence"><h2>Evidence Requirements</h2><div class="evidence-grid">{evidence_html}</div></section>
|
||||
<section class="section" id="safety"><h2>Safety Boundary</h2><div class="notice"><ul><li>Drafts never count as accepted ledger evidence.</li><li>Valid intake means ready for ledger review, not world-class completion.</li><li>Do not include credentials, raw prompts, raw outputs, transcripts, notes, or private user content.</li></ul></div></section>
|
||||
|
||||
@@ -93,6 +93,10 @@ def build_evidence_matrix(
|
||||
draft_status, draft_path = _draft_status(files_by_key, key)
|
||||
artifact_ready_count = sum(1 for row in artifact_rows if row.get("artifact_ref_ready"))
|
||||
artifact_missing_count = len(artifact_rows) - artifact_ready_count
|
||||
submission_ref_rows = [row for row in artifact_rows if row.get("submission_ref_required")]
|
||||
supporting_rows = [row for row in artifact_rows if not row.get("submission_ref_required")]
|
||||
submission_ref_ready_count = sum(1 for row in submission_ref_rows if row.get("artifact_ref_ready"))
|
||||
supporting_artifact_ready_count = sum(1 for row in supporting_rows if row.get("artifact_ref_ready"))
|
||||
source_pass_count = sum(1 for row in source_rows if row.get("status") == "pass")
|
||||
source_blocked_count = len(source_rows) - source_pass_count
|
||||
invalid_draft = draft_status not in {"written", "exists"}
|
||||
@@ -115,6 +119,12 @@ def build_evidence_matrix(
|
||||
"artifact_ready_count": artifact_ready_count,
|
||||
"artifact_total_count": len(artifact_rows),
|
||||
"artifact_missing_count": artifact_missing_count,
|
||||
"submission_ref_ready_count": submission_ref_ready_count,
|
||||
"submission_ref_total_count": len(submission_ref_rows),
|
||||
"submission_ref_missing_count": len(submission_ref_rows) - submission_ref_ready_count,
|
||||
"supporting_artifact_ready_count": supporting_artifact_ready_count,
|
||||
"supporting_artifact_total_count": len(supporting_rows),
|
||||
"supporting_artifact_missing_count": len(supporting_rows) - supporting_artifact_ready_count,
|
||||
"source_pass_count": source_pass_count,
|
||||
"source_check_count": len(source_rows),
|
||||
"source_blocked_count": source_blocked_count,
|
||||
@@ -137,5 +147,15 @@ def summarize_evidence_matrix(matrix: list[dict[str, Any]]) -> dict[str, int]:
|
||||
"evidence_matrix_prepare_draft_count": sum(1 for item in matrix if item.get("stage") == "prepare-draft"),
|
||||
"evidence_matrix_fix_artifacts_count": sum(1 for item in matrix if item.get("stage") == "fix-artifacts"),
|
||||
"evidence_matrix_validate_packet_count": sum(1 for item in matrix if item.get("stage") == "validate-packet"),
|
||||
"evidence_matrix_submission_ref_count": sum(int(item.get("submission_ref_total_count", 0)) for item in matrix),
|
||||
"evidence_matrix_submission_ref_ready_count": sum(
|
||||
int(item.get("submission_ref_ready_count", 0)) for item in matrix
|
||||
),
|
||||
"evidence_matrix_supporting_artifact_count": sum(
|
||||
int(item.get("supporting_artifact_total_count", 0)) for item in matrix
|
||||
),
|
||||
"evidence_matrix_supporting_artifact_ready_count": sum(
|
||||
int(item.get("supporting_artifact_ready_count", 0)) for item in matrix
|
||||
),
|
||||
"evidence_matrix_counts_as_completion": 0,
|
||||
}
|
||||
|
||||
@@ -617,11 +617,19 @@ def main() -> None:
|
||||
assert kit_payload["summary"]["written_count"] == 1, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["artifact_checklist_count"] >= 1, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["artifact_ready_count"] >= 1, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["submission_ref_count"] == 1, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["submission_ref_ready_count"] == 1, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["supporting_artifact_count"] >= 1, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["supporting_artifact_ready_count"] >= 1, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["source_check_count"] == 3, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["source_pass_count"] == 1, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["source_blocked_count"] == 2, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["evidence_matrix_count"] == 1, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["evidence_matrix_collect_source_count"] == 1, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["evidence_matrix_submission_ref_count"] == 1, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["evidence_matrix_submission_ref_ready_count"] == 1, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["evidence_matrix_supporting_artifact_count"] >= 1, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["evidence_matrix_supporting_artifact_ready_count"] >= 1, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["evidence_matrix_counts_as_completion"] == 0, kit_payload["summary"]
|
||||
assert kit_payload["summary"]["drafts_count_as_evidence"] is False, kit_payload["summary"]
|
||||
assert kit_payload["safety"]["template_only_drafts"] is True, kit_payload["safety"]
|
||||
@@ -634,6 +642,10 @@ def main() -> None:
|
||||
assert matrix_row["draft_status"] == "written", matrix_row
|
||||
assert matrix_row["artifact_ready_count"] >= 1, matrix_row
|
||||
assert matrix_row["artifact_total_count"] >= matrix_row["artifact_ready_count"], matrix_row
|
||||
assert matrix_row["submission_ref_ready_count"] == 1, matrix_row
|
||||
assert matrix_row["submission_ref_total_count"] == 1, matrix_row
|
||||
assert matrix_row["supporting_artifact_ready_count"] >= 1, matrix_row
|
||||
assert matrix_row["supporting_artifact_total_count"] >= matrix_row["supporting_artifact_ready_count"], matrix_row
|
||||
assert matrix_row["source_pass_count"] == 1, matrix_row
|
||||
assert matrix_row["source_check_count"] == 3, matrix_row
|
||||
assert matrix_row["source_blocked_count"] == 2, matrix_row
|
||||
@@ -642,8 +654,12 @@ def main() -> None:
|
||||
artifact_rows = {item["path"]: item for item in kit_payload["artifact_checklist"]}
|
||||
assert "reports/output_execution_runs.json" in artifact_rows, artifact_rows
|
||||
assert artifact_rows["reports/output_execution_runs.json"]["artifact_ref_ready"] is True, artifact_rows
|
||||
assert artifact_rows["reports/output_execution_runs.json"]["artifact_role"] == "submission-ref", artifact_rows
|
||||
assert artifact_rows["reports/output_execution_runs.json"]["submission_ref_required"] is True, artifact_rows
|
||||
assert len(artifact_rows["reports/output_execution_runs.json"]["sha256"]) == 64, artifact_rows
|
||||
assert artifact_rows["reports/output_execution_runs.json"]["contains_raw_content"] is False, artifact_rows
|
||||
assert artifact_rows["reports/output_execution_runs.md"]["artifact_role"] == "supporting-evidence", artifact_rows
|
||||
assert artifact_rows["reports/output_execution_runs.md"]["submission_ref_required"] is False, artifact_rows
|
||||
source_rows = {item["field"]: item for item in kit_payload["source_checklist"]}
|
||||
assert source_rows["model_executed_count"]["status"] == "blocked", source_rows
|
||||
assert source_rows["model_executed_count"]["actual"] == 0, source_rows
|
||||
@@ -667,6 +683,10 @@ def main() -> None:
|
||||
assert "validate intake" in kit_readme, kit_readme
|
||||
assert "Artifact Checklist" in kit_readme, kit_readme
|
||||
assert "Evidence Matrix" in kit_readme, kit_readme
|
||||
assert "Submission refs" in kit_readme, kit_readme
|
||||
assert "Supporting assets" in kit_readme, kit_readme
|
||||
assert "`submission-ref`" in kit_readme, kit_readme
|
||||
assert "`supporting-evidence`" in kit_readme, kit_readme
|
||||
assert "`collect-source`" in kit_readme, kit_readme
|
||||
assert "Matrix rows are guidance only" in kit_readme, kit_readme
|
||||
assert "Source Evidence Snapshot" in kit_readme, kit_readme
|
||||
@@ -680,7 +700,11 @@ def main() -> None:
|
||||
assert "Evidence Matrix" in kit_html, kit_html
|
||||
assert "matrix-card collect-source" in kit_html, kit_html
|
||||
assert (
|
||||
f"<dt>Artifacts</dt><dd>{matrix_row['artifact_ready_count']}/{matrix_row['artifact_total_count']} ready</dd>"
|
||||
f"<dt>Submission refs</dt><dd>{matrix_row['submission_ref_ready_count']}/{matrix_row['submission_ref_total_count']} ready</dd>"
|
||||
in kit_html
|
||||
), kit_html
|
||||
assert (
|
||||
f"<dt>Supporting assets</dt><dd>{matrix_row['supporting_artifact_ready_count']}/{matrix_row['supporting_artifact_total_count']} ready</dd>"
|
||||
in kit_html
|
||||
), kit_html
|
||||
assert "<dt>Source</dt><dd>1/3 pass</dd>" in kit_html, kit_html
|
||||
@@ -692,6 +716,7 @@ def main() -> None:
|
||||
assert "Execution Runbook" in kit_html, kit_html
|
||||
assert "output-exec --provider-runner openai" in kit_html, kit_html
|
||||
assert "Do not include credentials, raw prompts, raw outputs, transcripts, notes, or private user content." in kit_html, kit_html
|
||||
assert "Rows marked submission-ref are the paths expected in artifact_refs" in kit_html, kit_html
|
||||
|
||||
prefilled_kit_dir = TMP / "prefilled_submission_kit"
|
||||
prefilled_proc = run_kit(
|
||||
|
||||
Reference in New Issue
Block a user