frostbyte_neo/yao-meta-skill
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity

Surface preflight repair rows in Review Studio

Browse Source
This commit is contained in:
yaojingang
2026-06-17 04:01:58 +08:00
parent e336777575
commit f2cf8a9e53
64 changed files with 742 additions and 530 deletions
Download Patch File Download Diff File Expand all files Collapse all files
assets/review-studio.css
+8
View File
@@ -290,12 +290,14 @@
}
.action-evidence-checks,
.action-command-list,
.action-repair-list,
.action-runbook-list {
margin: 0;
display: grid;
gap: 8px;
}
.action-evidence-checks,
.action-repair-list,
.action-command-list {
padding: 0;
list-style: none;
@@ -304,6 +306,7 @@
padding-left: 20px;
}
.action-evidence-check,
.action-repair-row,
.action-command-list li {
display: grid;
gap: 3px;
@@ -313,13 +316,18 @@
}
.action-evidence-check.blocked { border-left: 3px solid var(--warn); padding-left: 8px; }
.action-evidence-check.pass { border-left: 3px solid var(--pass); padding-left: 8px; }
.action-repair-row.blocked { border-left: 3px solid var(--warn); padding-left: 8px; }
.action-repair-row.ready { border-left: 3px solid var(--pass); padding-left: 8px; }
.action-evidence-check span,
.action-repair-row span,
.action-command-list span {
color: var(--ink);
font-size: 13px;
}
.action-evidence-check code,
.action-evidence-check small,
.action-repair-row code,
.action-repair-row small,
.action-command-list code,
.action-runbook-list li {
color: var(--muted);
registry/index.json
+2 -2
View File
@@ -1,6 +1,6 @@
{
"schema_version": "2.0",
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"package_count": 1,
"packages": [
{
@@ -16,7 +16,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242"
"package_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12"
}
]
}
registry/packages/yao-meta-skill.json
+4 -4
View File
@@ -16,8 +16,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362"
"package_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806"
},
"compatibility": {
"openai": "pass",
@@ -48,10 +48,10 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
},
"generated_at": "2026-06-17"
"generated_at": "2026-06-13"
}
reports/adoption_drift_report.json
+14 -14
View File
@@ -1,7 +1,7 @@
{
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-17",
"generated_at": "2026-06-16T19:58:53Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
@@ -25,14 +25,14 @@
},
"summary": {
"event_count": 1,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"edited_count": 0,
"rejected_count": 0,
"missed_count": 0,
"failed_count": 0,
"adoption_rate": 0,
"adoption_rate": 100.0,
"missed_trigger_count": 0,
"wrong_trigger_count": 0,
"bad_output_count": 0,
@@ -41,7 +41,7 @@
"review_overdue_count": 0,
"risk_band": "low",
"event_types": {
"review_event": 1
"skill_activation": 1
},
"failure_types": {},
"source_types": {
@@ -53,31 +53,31 @@
{
"skill": "yao-meta-skill",
"events": 1,
"adoption_events": 0,
"accepted": 0,
"adoption_events": 1,
"accepted": 1,
"edited": 0,
"rejected": 0,
"missed": 0,
"adoption_rate": 0
"adoption_rate": 100.0
}
],
"next_iteration_candidates": [],
"recent_events": [
{
"command": "unknown",
"event": "review_event",
"event": "skill_activation",
"skill": "yao-meta-skill",
"source": "manual",
"version": "1.1.0",
"activation_type": "manual",
"outcome": "reviewed",
"activation_type": "explicit",
"outcome": "accepted",
"failure_type": "none",
"timestamp": "2026-06-13T12:00:00Z"
"timestamp": "2026-06-13T10:00:00Z"
}
],
"failures": [],
"artifacts": {
"events_jsonl": "reports/telemetry_events.jsonl",
"events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl",
"json": "reports/adoption_drift_report.json",
"markdown": "reports/adoption_drift_report.md"
}
reports/adoption_drift_report.md
+5 -5
View File
@@ -5,9 +5,9 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
## Summary
- Events: `1`
- Adoption samples: `0`
- Activation events: `0`
- Adoption rate: `0`
- Adoption samples: `1`
- Activation events: `1`
- Adoption rate: `100.0`
- Missed trigger signals: `0`
- Bad output signals: `0`
- Script error signals: `0`
@@ -25,7 +25,7 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
| Skill | Events | Adoption Samples | Accepted | Edited | Rejected | Missed | Adoption Rate |
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
| `yao-meta-skill` | 1 | 0 | 0 | 0 | 0 | 0 | 0 |
| `yao-meta-skill` | 1 | 1 | 1 | 0 | 0 | 0 | 100.0 |
## Next Iteration Candidates
@@ -33,4 +33,4 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
## Recent Metadata Events
- `2026-06-13T12:00:00Z` `yao-meta-skill` event=`review_event` source=`manual` command=`unknown` activation=`manual` outcome=`reviewed` failure=`none`
- `2026-06-13T10:00:00Z` `yao-meta-skill` event=`skill_activation` source=`manual` command=`unknown` activation=`explicit` outcome=`accepted` failure=`none`
reports/architecture_maintainability.json
+11 -11
View File
@@ -1,12 +1,12 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"skill_dir": ".",
"summary": {
"python_file_count": 223,
"python_file_count": 224,
"script_file_count": 148,
"test_file_count": 75,
"test_file_count": 76,
"internal_module_count": 64,
"cli_script_count": 86,
"command_handler_count": 68,
@@ -64,14 +64,6 @@
"early_watch": false,
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "tests/verify_review_studio.py",
"lines": 590,
"kind": "test",
"severity": "pass",
"early_watch": false,
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/render_skill_overview.py",
"lines": 588,
@@ -119,6 +111,14 @@
"severity": "pass",
"early_watch": false,
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/render_review_studio.py",
"lines": 568,
"kind": "cli-script",
"severity": "pass",
"early_watch": false,
"recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
}
],
"watchlist": [],
reports/architecture_maintainability.md
+4 -4
View File
@@ -1,13 +1,13 @@
# Architecture Maintainability
Generated at: `2026-06-17`
Generated at: `2026-06-13`
## Summary
- decision: `pass`
- python files: `223`
- python files: `224`
- scripts: `148`
- tests: `75`
- tests: `76`
- internal modules: `64`
- CLI scripts: `86`
- Yao CLI command handlers: `68`
@@ -47,13 +47,13 @@ No near-threshold files found.
| `tests/verify_output_review_adjudication.py` | `599` | `test` | `pass` |
| `scripts/render_benchmark_reproducibility.py` | `595` | `cli-script` | `pass` |
| `scripts/render_world_class_preflight.py` | `590` | `cli-script` | `pass` |
| `tests/verify_review_studio.py` | `590` | `test` | `pass` |
| `scripts/render_skill_overview.py` | `588` | `cli-script` | `pass` |
| `scripts/build_skill_atlas.py` | `586` | `cli-script` | `pass` |
| `scripts/optimize_description.py` | `585` | `cli-script` | `pass` |
| `scripts/trust_check.py` | `582` | `cli-script` | `pass` |
| `tests/verify_world_class_evidence_ledger.py` | `579` | `test` | `pass` |
| `scripts/render_evidence_consistency.py` | `568` | `cli-script` | `pass` |
| `scripts/render_review_studio.py` | `568` | `cli-script` | `pass` |
## Release Rule
reports/benchmark_reproducibility.json
+22 -22
View File
@@ -3,24 +3,24 @@
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "48a503f8f6ea9ed8b39c5f4c6c07adbc94bca3cb",
"commit": "e3367775750edf6b2f811e7e1f3680c1e2c3e7ab",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 34,
"changed_file_count": 38,
"sample": [
" M assets/review-studio.css",
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" M reports/benchmark_reproducibility.json",
" M reports/benchmark_reproducibility.md",
" M reports/compiled_targets.json",
" M reports/context_budget.json",
" M reports/context_budget.md",
" M reports/context_budget_summary.json",
" M reports/evidence_consistency.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md"
" M reports/evidence_consistency.json"
],
"scope": "generation-time status before this report is written"
},
@@ -30,9 +30,9 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "fa79b95f174e1c2b41a83456e6f6d7d15064dfa388f5c2b79ccc12ccefa2d119",
"source_contract_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"evidence_bundle_sha256": "3f8e332ac63fc5c841400052005674876f29d2f715a48da46424f581dbad8c49",
"source_contract_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -52,7 +52,7 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 34
"changed_file_count": 38
},
"public_claim": {
"ready": false,
@@ -68,7 +68,7 @@
},
"release_lock": {
"ready": false,
"commit": "48a503f8f6ea9ed8b39c5f4c6c07adbc94bca3cb",
"commit": "e3367775750edf6b2f811e7e1f3680c1e2c3e7ab",
"status_scope": "generation-time status before this report is written",
"reason": "working tree was dirty at generation time"
},
@@ -78,7 +78,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "fa79b95f174e1c2b41a83456e6f6d7d15064dfa388f5c2b79ccc12ccefa2d119"
"sha256": "3f8e332ac63fc5c841400052005674876f29d2f715a48da46424f581dbad8c49"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -151,8 +151,8 @@
"label": "output_execution",
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7966,
"sha256": "874d573922462a290776489b7ab760136522b2780339b579e383ab8235af56e8"
"bytes": 7967,
"sha256": "4ea56f4558ee371f71a7908f55a1fbcd2d3f3f18a517a6642a5ed7df6a204b59"
},
{
"label": "blind_review",
@@ -187,42 +187,42 @@
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 134467,
"sha256": "d2e8352cae2c29a009d81bfc78ec4478cc36f045022d0803c7b229d6441fe1e9"
"sha256": "525f9766700afd55e2b5113b5f30a1ca4826ebab0902228a702f7927bffb6019"
},
{
"label": "python_compatibility",
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 29327,
"sha256": "0eeedc1c3ff1fe5e2f9483387e3c56b44dda7eb1b615840afadfb8b55d392787"
"bytes": 29464,
"sha256": "f53cce322cc33af4f7cbc7e22587ac3e0c0359dfa1889a03f38c93472abf319d"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "d0c088f66524fa16c604b88fcd45010303daed7eb9e5273e439451484c09442e"
"sha256": "995ded23370adb49997ef5bdd37e32c59b6aad31ed7813c7520e7e7b40d6e546"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19338,
"sha256": "d18b6336d485f6290b68bf229d491bcd8a08ad872a8e9a53502b996c4f9c1347"
"sha256": "afb99167c57179ff0435c678e7e5638ceaed07042fa9177568ca21d6dc1bef3d"
},
{
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8604,
"sha256": "6d808df453177bf76362f218c41dcd7e41d56283b987f07e1e8fe47c1e9f02f5"
"sha256": "08d96de4662c8e047e351f4241ff3a4f98c521907fc4cd703faadff861bee63a"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14466,
"sha256": "e6f644b1d2f590e76c7f2dd5a4888efad138bd2a2643c0fa60fe2fea81db55e1"
"sha256": "7fc0b099204ca5045de2db9eb19c5cf599f9c87bed1cd7f39c1f5f50704b3fb2"
},
{
"label": "world_class_evidence_plan",
@@ -249,8 +249,8 @@
"label": "world_class_evidence_preflight",
"path": "reports/world_class_evidence_preflight.json",
"exists": true,
"bytes": 57313,
"sha256": "585ec2f93a1dfce5b270af048e3d551676b93231477d7bf4cfe5b08946e82619"
"bytes": 58119,
"sha256": "10671b699295453b130ef8afe6488d2a4ac3220a901df2f86a69ee5eb896c36e"
},
{
"label": "world_class_submission_review",
reports/benchmark_reproducibility.md
+14 -14
View File
@@ -1,9 +1,9 @@
# Benchmark Reproducibility
Generated at: `2026-06-17`
Commit: `48a503f8f6ea9ed8b39c5f4c6c07adbc94bca3cb`
Commit: `e3367775750edf6b2f811e7e1f3680c1e2c3e7ab`
Working tree dirty at generation: `true`
Evidence bundle SHA256: `fa79b95f174e1c2b41a83456e6f6d7d15064dfa388f5c2b79ccc12ccefa2d119`
Evidence bundle SHA256: `3f8e332ac63fc5c841400052005674876f29d2f715a48da46424f581dbad8c49`
## Summary
@@ -12,8 +12,8 @@ Evidence bundle SHA256: `fa79b95f174e1c2b41a83456e6f6d7d15064dfa388f5c2b79ccc12c
- methodology complete: `true`
- required artifacts: `25`
- missing artifacts: `0`
- source contract sha256: `cc61aeda8a4a`
- archive sha256: `b09ad63e1a0c`
- source contract sha256: `f5722de72ecc`
- archive sha256: `52a98e5dd903`
- output cases: `5`
- disclosed failure cases: `3`
- reproduction commands: `23`
@@ -23,7 +23,7 @@ Evidence bundle SHA256: `fa79b95f174e1c2b41a83456e6f6d7d15064dfa388f5c2b79ccc12c
- world-class source checks: `9` pass / `19` total; `10` blocked
- public claim ready: `false`
- public claim blockers: `5`
- changed files at generation: `34`
- changed files at generation: `38`
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.
@@ -51,7 +51,7 @@ This report proves local benchmark reproducibility only. It keeps external provi
- algorithm: `sha256(path,label,exists,artifact_sha256)`
- artifacts: `25` / `25`
- sha256: `fa79b95f174e1c2b41a83456e6f6d7d15064dfa388f5c2b79ccc12ccefa2d119`
- sha256: `3f8e332ac63fc5c841400052005674876f29d2f715a48da46424f581dbad8c49`
## Methodology Sections
@@ -73,21 +73,21 @@ 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 | `874d57392246` |
| output_execution | `reports/output_execution_runs.json` | present | `4ea56f4558ee` |
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
| review_adjudication | `reports/output_review_adjudication.json` | present | `91fd88dd9b0f` |
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
| runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` |
| trust_report | `reports/security_trust_report.json` | present | `d2e8352cae2c` |
| python_compatibility | `reports/python_compatibility.json` | present | `0eeedc1c3ff1` |
| registry_audit | `reports/registry_audit.json` | present | `d0c088f66524` |
| package_verification | `reports/package_verification.json` | present | `d18b6336d485` |
| install_simulation | `reports/install_simulation.json` | present | `6d808df45317` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `e6f644b1d2f5` |
| trust_report | `reports/security_trust_report.json` | present | `525f9766700a` |
| python_compatibility | `reports/python_compatibility.json` | present | `f53cce322cc3` |
| registry_audit | `reports/registry_audit.json` | present | `995ded23370a` |
| package_verification | `reports/package_verification.json` | present | `afb99167c571` |
| install_simulation | `reports/install_simulation.json` | present | `08d96de4662c` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `7fc0b099204c` |
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `2beb888d7992` |
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `22c85613d7be` |
| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `d3f44570e605` |
| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `585ec2f93a1d` |
| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `10671b699295` |
| world_class_submission_review | `reports/world_class_submission_review.json` | present | `96624a5b7f79` |
| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `a7b7809d3b42` |
| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `d72777b421b5` |
reports/compiled_targets.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"skill_dir": ".",
"summary": {
"target_count": 5,
reports/context_budget.json
+8 -8
View File
@@ -6,15 +6,15 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 797,
"other_text_tokens": 1107027,
"other_text_tokens": 1107908,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1107824,
"deferred_resource_tokens": 504879,
"estimated_total_text_tokens": 1108705,
"deferred_resource_tokens": 505558,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 443849,
"estimated_tokens": 444443,
"file_count": 148
},
{
@@ -29,14 +29,14 @@
},
{
"path": "assets",
"estimated_tokens": 10903,
"estimated_tokens": 10988,
"file_count": 4
}
],
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 443849,
"estimated_tokens": 444443,
"file_count": 148
}
],
@@ -59,14 +59,14 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 443849,
"estimated_tokens": 444443,
"file_count": 148,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
],
"summary": "Large deferred resources are indexed and backed by evidence."
},
"relevant_file_count": 700,
"relevant_file_count": 702,
"unused_resource_dirs": [],
"quality_signal_points": 130,
"quality_density": 131.3
reports/context_budget.md
+1 -1
View File
@@ -2,7 +2,7 @@
| Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status |
| --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- |
| root | `.` | `production` | 1000 | 990 | 797 | 504879 | `governed` | scripts:443849 | 131.3 | - | ok |
| root | `.` | `production` | 1000 | 990 | 797 | 505558 | `governed` | scripts:444443 | 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 |
reports/context_budget_summary.json
+4 -4
View File
@@ -1,5 +1,5 @@
{
"generated_at": "2026-06-17",
"generated_at": "2026-03-31",
"targets": [
{
"label": "root",
@@ -8,11 +8,11 @@
"budget_limit": 1000,
"initial_tokens": 990,
"skill_body_tokens": 797,
"deferred_resource_tokens": 504879,
"deferred_resource_tokens": 505558,
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 443849,
"estimated_tokens": 444443,
"file_count": 148
}
],
@@ -35,7 +35,7 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 443849,
"estimated_tokens": 444443,
"file_count": 148,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
reports/evidence_consistency.json
+17 -17
View File
@@ -189,12 +189,12 @@
"status": "pass",
"expected": {
"status": "pass",
"detail": "initial load 990/1000; deferred 504879/120000; top deferred scripts 443849; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 505558/120000; top deferred scripts 444443; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json"
},
"actual": {
"status": "pass",
"detail": "initial load 990/1000; deferred 504879/120000; top deferred scripts 443849; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 505558/120000; top deferred scripts 444443; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json"
},
"paths": [
@@ -222,7 +222,7 @@
"actual": {
"available": true,
"clean": false,
"changed_file_count": 34
"changed_file_count": 38
},
"paths": [
"reports/benchmark_reproducibility.json"
@@ -263,8 +263,8 @@
"key": "overview-benchmark-commit",
"label": "overview embeds the benchmark commit",
"status": "pass",
"expected": "48a503f8f6ea9ed8b39c5f4c6c07adbc94bca3cb",
"actual": "48a503f8f6ea9ed8b39c5f4c6c07adbc94bca3cb",
"expected": "e3367775750edf6b2f811e7e1f3680c1e2c3e7ab",
"actual": "e3367775750edf6b2f811e7e1f3680c1e2c3e7ab",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-overview.json"
@@ -279,8 +279,8 @@
"release_lock_ready": false,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"source_contract_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 9,
@@ -292,8 +292,8 @@
"release_lock_ready": false,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"source_contract_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 9,
@@ -409,8 +409,8 @@
"key": "interpretation-benchmark-commit",
"label": "interpretation embeds the benchmark commit",
"status": "pass",
"expected": "48a503f8f6ea9ed8b39c5f4c6c07adbc94bca3cb",
"actual": "48a503f8f6ea9ed8b39c5f4c6c07adbc94bca3cb",
"expected": "e3367775750edf6b2f811e7e1f3680c1e2c3e7ab",
"actual": "e3367775750edf6b2f811e7e1f3680c1e2c3e7ab",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-interpretation.json"
@@ -425,8 +425,8 @@
"release_lock_ready": false,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"source_contract_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 9,
@@ -438,8 +438,8 @@
"release_lock_ready": false,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"source_contract_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 9,
@@ -2423,8 +2423,8 @@
"`3` warnings",
"`62` declared internal modules",
"`86 / 86` CLI help smoke checks passing across `148` scripts",
"`686` zip entries",
"archive with `686` entries",
"`687` zip entries",
"archive with `687` entries",
"`12` installer permission checks enforced",
"`0` permission failures",
"`25` required artifacts",
reports/install_simulation.json
+10 -10
View File
@@ -1,14 +1,14 @@
{
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"skill_dir": ".",
"package_dir": "dist",
"install_root": "dist/install-simulation/simulate-yao-meta-skill",
"installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
"package_dir": "tests/tmp_review_studio/dist",
"install_root": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill",
"installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill",
"summary": {
"archive_present": true,
"archive_entry_count": 686,
"archive_entry_count": 687,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -26,7 +26,7 @@
{
"id": "archive-present",
"status": "pass",
"detail": "Package archive exists: dist/yao-meta-skill.zip"
"detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip"
},
{
"id": "archive-safe-paths",
@@ -272,9 +272,9 @@
"failures": [],
"warnings": [],
"artifacts": {
"archive": "dist/yao-meta-skill.zip",
"package_manifest": "dist/manifest.json",
"json": "reports/install_simulation.json",
"markdown": "reports/install_simulation.md"
"archive": "tests/tmp_review_studio/dist/yao-meta-skill.zip",
"package_manifest": "tests/tmp_review_studio/dist/manifest.json",
"json": "tests/tmp_review_studio/install_simulation.json",
"markdown": "tests/tmp_review_studio/install_simulation.md"
}
}
reports/install_simulation.md
+2 -2
View File
@@ -1,7 +1,7 @@
# Install Simulation
- OK: `True`
- Package directory: `dist`
- Package directory: `tests/tmp_review_studio/dist`
- Archive extracted: `True`
- Entrypoint loaded: `True`
- Manifest loaded: `True`
@@ -16,7 +16,7 @@
| Check | Status | Detail |
| --- | --- | --- |
| `archive-present` | `pass` | Package archive exists: dist/yao-meta-skill.zip |
| `archive-present` | `pass` | Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip |
| `archive-safe-paths` | `pass` | Archive has no absolute or parent-traversal entries |
| `single-top-level` | `pass` | Archive top-level directory is yao-meta-skill |
| `entrypoint-load` | `pass` | Installed SKILL.md frontmatter is readable |
reports/output_execution_runs.json
+10 -10
View File
@@ -34,7 +34,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.73,
"duration_ms": 34.14,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -62,7 +62,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.46,
"duration_ms": 33.01,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -85,7 +85,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.94,
"duration_ms": 36.01,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -113,7 +113,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.74,
"duration_ms": 35.54,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -136,7 +136,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 28.3,
"duration_ms": 33.33,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -164,7 +164,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.82,
"duration_ms": 34.45,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -187,7 +187,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.02,
"duration_ms": 33.48,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -214,7 +214,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.81,
"duration_ms": 35.51,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -237,7 +237,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.75,
"duration_ms": 33.49,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -266,7 +266,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.57,
"duration_ms": 29.48,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
reports/output_execution_runs.md
+10 -10
View File
@@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext
| Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status |
| --- | --- | --- | --- | ---: | ---: | ---: | --- |
| skill-package-contract | baseline | command | local-output-eval-runner | 26.73 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 25.46 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 25.94 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 27.74 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 28.3 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 25.82 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.02 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 25.81 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 25.75 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 25.57 | 98 | 100.0 | pass |
| skill-package-contract | baseline | command | local-output-eval-runner | 34.14 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 33.01 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 36.01 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 35.54 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 33.33 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 34.45 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 33.48 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 35.51 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 33.49 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 29.48 | 98 | 100.0 | pass |
## Next Fixes
reports/package_verification.json
+2 -2
View File
@@ -8,8 +8,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"archive_entry_count": 686,
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"archive_entry_count": 687,
"failure_count": 0,
"warning_count": 0
},
reports/package_verification.md
+1 -1
View File
@@ -4,7 +4,7 @@
- Package directory: `dist`
- Targets: `4 / 4` adapters present
- Archive present: `True`
- Archive SHA256: `b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362`
- Archive SHA256: `52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806`
- Failures: `0`
- Warnings: `0`
reports/python_compatibility.json
+8 -2
View File
@@ -1,11 +1,11 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"root": ".",
"summary": {
"target_python": "3.11",
"file_count": 226,
"file_count": 227,
"issue_count": 0,
"syntax_error_count": 0,
"fstring_311_violation_count": 0,
@@ -934,6 +934,12 @@
"issue_count": 0,
"issues": []
},
{
"path": "tests/review_studio_world_class_assertions.py",
"ok": true,
"issue_count": 0,
"issues": []
},
{
"path": "tests/verify_adaptation_safety.py",
"ok": true,
reports/python_compatibility.md
+2 -2
View File
@@ -1,12 +1,12 @@
# Python Compatibility
Generated at: `2026-06-17`
Generated at: `2026-06-13`
## Summary
- decision: `pass`
- target python: `3.11`
- files scanned: `226`
- files scanned: `227`
- issues: `0`
- syntax errors: `0`
- f-string 3.11 violations: `0`
reports/registry_audit.json
+6 -6
View File
@@ -21,8 +21,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362"
"package_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806"
},
"compatibility": {
"openai": "pass",
@@ -53,16 +53,16 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
},
"generated_at": "2026-06-17"
"generated_at": "2026-06-13"
},
"index": {
"schema_version": "2.0",
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"package_count": 1,
"packages": [
{
@@ -78,7 +78,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242"
"package_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12"
}
]
},
reports/registry_audit.md
+2 -2
View File
@@ -6,8 +6,8 @@
- Maturity: `governed`
- Owner: `Yao Team`
- License: `MIT`
- Package SHA256: `cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242`
- Archive SHA256: `b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362`
- Package SHA256: `f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12`
- Archive SHA256: `52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806`
- Install simulated: `True`
## Compatibility
reports/review-studio.html
+16 -8
View File
File diff suppressed because one or more lines are too long
reports/review-studio.json
+234 -80
View File
@@ -44,7 +44,7 @@
"key": "context-budget",
"label": "上下文",
"status": "pass",
"detail": "initial load 990/1000; deferred 504879/120000; top deferred scripts 443849; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 505558/120000; top deferred scripts 444443; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json",
"link": "context_budget.md"
},
@@ -68,7 +68,7 @@
"key": "python-compat",
"label": "Python 兼容",
"status": "pass",
"detail": "Python 3.11; 226 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards",
"detail": "Python 3.11; 227 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards",
"evidence": "reports/python_compatibility.json",
"link": "python_compatibility.md"
},
@@ -76,7 +76,7 @@
"key": "architecture-maintainability",
"label": "架构维护",
"status": "pass",
"detail": "223 Python files; 0 hotspots; 0 watchlist files; 2 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint",
"detail": "224 Python files; 0 hotspots; 0 watchlist files; 2 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint",
"evidence": "reports/architecture_maintainability.json",
"link": "architecture_maintainability.md"
},
@@ -367,6 +367,26 @@
"exists": true,
"link": "world_class_evidence_intake.md"
},
{
"path": "reports/world_class_evidence_preflight.md",
"label": "world-class evidence preflight",
"kind": "report",
"line": 1,
"matched_pattern": "# World-Class Evidence Preflight",
"excerpt": "# World-Class Evidence Preflight",
"exists": true,
"link": "world_class_evidence_preflight.md"
},
{
"path": "reports/world_class_evidence_preflight.html",
"label": "world-class preflight HTML",
"kind": "report",
"line": 6,
"matched_pattern": "World-Class Evidence Preflight",
"excerpt": "<title>World-Class Evidence Preflight</title>",
"exists": true,
"link": "world_class_evidence_preflight.html"
},
{
"path": "reports/world_class_submission_review.md",
"label": "world-class submission review",
@@ -512,6 +532,34 @@
"next_action": "Provider execution should return non-estimated token usage."
}
],
"repair_rows": [
{
"repair_type": "precheck",
"target": "openai-api-key",
"status": "blocked",
"blocking_reason": "Required env precheck is missing.",
"next_action": "Set OPENAI_API_KEY in the operator shell; never commit or print the value.",
"counts_as_completion": false
},
{
"repair_type": "source-check",
"target": "model_executed_count",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '>0'.",
"next_action": "Run provider-backed output-exec with real credentials.",
"counts_as_completion": false
},
{
"repair_type": "source-check",
"target": "token_observed_count",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '>0'.",
"next_action": "Provider execution should return non-estimated token usage.",
"counts_as_completion": false
}
],
"repair_blocked_count": 3,
"repair_counts_as_completion": false,
"commands": [
{
"key": "prepare_submission",
@@ -648,6 +696,58 @@
"next_action": "Complete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints."
}
],
"repair_rows": [
{
"repair_type": "precheck",
"target": "human-reviewer",
"status": "blocked",
"blocking_reason": "Required human precheck is human-required.",
"next_action": "Assign a real reviewer identity before claiming human adjudication.",
"counts_as_completion": false
},
{
"repair_type": "source-check",
"target": "pending_count",
"status": "blocked",
"blocking_reason": "Current value 5 does not satisfy '==0'.",
"next_action": "Record a reviewer choice and reason for every pair.",
"counts_as_completion": false
},
{
"repair_type": "source-check",
"target": "judgment_count",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '==pair_count'.",
"next_action": "Every pair needs one valid human judgment.",
"counts_as_completion": false
},
{
"repair_type": "source-check",
"target": "reviewer_metadata_present",
"status": "blocked",
"blocking_reason": "Current value False does not satisfy 'true'.",
"next_action": "Record reviewer and reviewed_at before adjudication can count.",
"counts_as_completion": false
},
{
"repair_type": "source-check",
"target": "blind_review_attested",
"status": "blocked",
"blocking_reason": "Current value False does not satisfy 'true'.",
"next_action": "Set reviewer_attestation only after choices are completed before opening the answer key.",
"counts_as_completion": false
},
{
"repair_type": "source-check",
"target": "ready_for_human_evidence",
"status": "blocked",
"blocking_reason": "Current value False does not satisfy 'true'.",
"next_action": "Complete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints.",
"counts_as_completion": false
}
],
"repair_blocked_count": 6,
"repair_counts_as_completion": false,
"commands": [
{
"key": "prepare_submission",
@@ -759,6 +859,26 @@
"next_action": "Collect real target-client or external runtime guard proof."
}
],
"repair_rows": [
{
"repair_type": "precheck",
"target": "native-guard",
"status": "blocked",
"blocking_reason": "Required external precheck is external-required.",
"next_action": "Attach a real target-client or external installer runtime guard; metadata fallback is not enough.",
"counts_as_completion": false
},
{
"repair_type": "source-check",
"target": "native_enforcement_count",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '>0'.",
"next_action": "Collect real target-client or external runtime guard proof.",
"counts_as_completion": false
}
],
"repair_blocked_count": 2,
"repair_counts_as_completion": false,
"commands": [
{
"key": "prepare_submission",
@@ -871,6 +991,34 @@
"next_action": "Telemetry must include adoption outcome evidence."
}
],
"repair_rows": [
{
"repair_type": "precheck",
"target": "external-client",
"status": "blocked",
"blocking_reason": "Required external precheck is external-required.",
"next_action": "Install a real Browser, Chrome, IDE, or provider client that emits metadata-only events.",
"counts_as_completion": false
},
{
"repair_type": "source-check",
"target": "external_source_events",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '>0'.",
"next_action": "Import at least one metadata-only event from a real client.",
"counts_as_completion": false
},
{
"repair_type": "source-check",
"target": "adoption_sample_count",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '>0'.",
"next_action": "Telemetry must include adoption outcome evidence.",
"counts_as_completion": false
}
],
"repair_blocked_count": 3,
"repair_counts_as_completion": false,
"commands": [
{
"key": "prepare_submission",
@@ -2011,9 +2159,9 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "fa79b95f174e1c2b41a83456e6f6d7d15064dfa388f5c2b79ccc12ccefa2d119",
"source_contract_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"evidence_bundle_sha256": "3f8e332ac63fc5c841400052005674876f29d2f715a48da46424f581dbad8c49",
"source_contract_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -2033,9 +2181,9 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 34
"changed_file_count": 38
},
"commit": "48a503f8f6ea9ed8b39c5f4c6c07adbc94bca3cb",
"commit": "e3367775750edf6b2f811e7e1f3680c1e2c3e7ab",
"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.",
@@ -2140,7 +2288,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 240,
"package_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242"
"package_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12"
},
"skill_atlas": {
"skill_count": 12,
@@ -2178,8 +2326,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362"
"package_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806"
},
"compatibility": {
"openai": "pass",
@@ -2210,7 +2358,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -2226,8 +2374,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"archive_entry_count": 686,
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"archive_entry_count": 687,
"failure_count": 0,
"warning_count": 0
},
@@ -2238,7 +2386,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 686,
"archive_entry_count": 687,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -2305,12 +2453,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362"
"to": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242"
"to": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12"
}
]
},
@@ -4824,7 +4972,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.73,
"duration_ms": 34.14,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4852,7 +5000,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.46,
"duration_ms": 33.01,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4875,7 +5023,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.94,
"duration_ms": 36.01,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4903,7 +5051,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.74,
"duration_ms": 35.54,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4926,7 +5074,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 28.3,
"duration_ms": 33.33,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4954,7 +5102,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.82,
"duration_ms": 34.45,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4977,7 +5125,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.02,
"duration_ms": 33.48,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5004,7 +5152,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.81,
"duration_ms": 35.51,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5027,7 +5175,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.75,
"duration_ms": 33.49,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5056,7 +5204,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.57,
"duration_ms": 29.48,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5837,24 +5985,24 @@
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "48a503f8f6ea9ed8b39c5f4c6c07adbc94bca3cb",
"commit": "e3367775750edf6b2f811e7e1f3680c1e2c3e7ab",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 34,
"changed_file_count": 38,
"sample": [
" M assets/review-studio.css",
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" M reports/benchmark_reproducibility.json",
" M reports/benchmark_reproducibility.md",
" M reports/compiled_targets.json",
" M reports/context_budget.json",
" M reports/context_budget.md",
" M reports/context_budget_summary.json",
" M reports/evidence_consistency.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md"
" M reports/evidence_consistency.json"
],
"scope": "generation-time status before this report is written"
},
@@ -5864,9 +6012,9 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "fa79b95f174e1c2b41a83456e6f6d7d15064dfa388f5c2b79ccc12ccefa2d119",
"source_contract_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"evidence_bundle_sha256": "3f8e332ac63fc5c841400052005674876f29d2f715a48da46424f581dbad8c49",
"source_contract_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -5886,7 +6034,7 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 34
"changed_file_count": 38
},
"public_claim": {
"ready": false,
@@ -5902,7 +6050,7 @@
},
"release_lock": {
"ready": false,
"commit": "48a503f8f6ea9ed8b39c5f4c6c07adbc94bca3cb",
"commit": "e3367775750edf6b2f811e7e1f3680c1e2c3e7ab",
"status_scope": "generation-time status before this report is written",
"reason": "working tree was dirty at generation time"
},
@@ -5912,7 +6060,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "fa79b95f174e1c2b41a83456e6f6d7d15064dfa388f5c2b79ccc12ccefa2d119"
"sha256": "3f8e332ac63fc5c841400052005674876f29d2f715a48da46424f581dbad8c49"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -5985,8 +6133,8 @@
"label": "output_execution",
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7966,
"sha256": "874d573922462a290776489b7ab760136522b2780339b579e383ab8235af56e8"
"bytes": 7967,
"sha256": "4ea56f4558ee371f71a7908f55a1fbcd2d3f3f18a517a6642a5ed7df6a204b59"
},
{
"label": "blind_review",
@@ -6021,42 +6169,42 @@
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 134467,
"sha256": "d2e8352cae2c29a009d81bfc78ec4478cc36f045022d0803c7b229d6441fe1e9"
"sha256": "525f9766700afd55e2b5113b5f30a1ca4826ebab0902228a702f7927bffb6019"
},
{
"label": "python_compatibility",
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 29327,
"sha256": "0eeedc1c3ff1fe5e2f9483387e3c56b44dda7eb1b615840afadfb8b55d392787"
"bytes": 29464,
"sha256": "f53cce322cc33af4f7cbc7e22587ac3e0c0359dfa1889a03f38c93472abf319d"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "d0c088f66524fa16c604b88fcd45010303daed7eb9e5273e439451484c09442e"
"sha256": "995ded23370adb49997ef5bdd37e32c59b6aad31ed7813c7520e7e7b40d6e546"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19338,
"sha256": "d18b6336d485f6290b68bf229d491bcd8a08ad872a8e9a53502b996c4f9c1347"
"sha256": "afb99167c57179ff0435c678e7e5638ceaed07042fa9177568ca21d6dc1bef3d"
},
{
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8604,
"sha256": "6d808df453177bf76362f218c41dcd7e41d56283b987f07e1e8fe47c1e9f02f5"
"sha256": "08d96de4662c8e047e351f4241ff3a4f98c521907fc4cd703faadff861bee63a"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14466,
"sha256": "e6f644b1d2f590e76c7f2dd5a4888efad138bd2a2643c0fa60fe2fea81db55e1"
"sha256": "7fc0b099204ca5045de2db9eb19c5cf599f9c87bed1cd7f39c1f5f50704b3fb2"
},
{
"label": "world_class_evidence_plan",
@@ -6083,8 +6231,8 @@
"label": "world_class_evidence_preflight",
"path": "reports/world_class_evidence_preflight.json",
"exists": true,
"bytes": 57313,
"sha256": "585ec2f93a1dfce5b270af048e3d551676b93231477d7bf4cfe5b08946e82619"
"bytes": 58119,
"sha256": "10671b699295453b130ef8afe6488d2a4ac3220a901df2f86a69ee5eb896c36e"
},
{
"label": "world_class_submission_review",
@@ -6462,7 +6610,7 @@
"label": "Registry Distribution",
"status": "pass",
"objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
"current": "archive entries 686; install failures 0",
"current": "archive entries 687; install failures 0",
"command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .",
"test": "python3 tests/verify_registry_audit.py",
"evidence": [
@@ -7070,7 +7218,7 @@
"compiled_targets": {
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"skill_dir": ".",
"summary": {
"target_count": 5,
@@ -12441,7 +12589,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 240,
"package_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242"
"package_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12"
},
"failures": [],
"warnings": [],
@@ -15880,7 +16028,7 @@
"root": ".",
"summary": {
"target_python": "3.11",
"file_count": 226,
"file_count": 227,
"issue_count": 0,
"syntax_error_count": 0,
"fstring_311_violation_count": 0,
@@ -16809,6 +16957,12 @@
"issue_count": 0,
"issues": []
},
{
"path": "tests/review_studio_world_class_assertions.py",
"ok": true,
"issue_count": 0,
"issues": []
},
{
"path": "tests/verify_adaptation_safety.py",
"ok": true,
@@ -17266,9 +17420,9 @@
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"python_file_count": 223,
"python_file_count": 224,
"script_file_count": 148,
"test_file_count": 75,
"test_file_count": 76,
"internal_module_count": 64,
"cli_script_count": 86,
"command_handler_count": 68,
@@ -17326,14 +17480,6 @@
"early_watch": false,
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "tests/verify_review_studio.py",
"lines": 590,
"kind": "test",
"severity": "pass",
"early_watch": false,
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/render_skill_overview.py",
"lines": 588,
@@ -17381,6 +17527,14 @@
"severity": "pass",
"early_watch": false,
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/render_review_studio.py",
"lines": 568,
"kind": "cli-script",
"severity": "pass",
"early_watch": false,
"recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
}
],
"watchlist": [],
@@ -17417,15 +17571,15 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 797,
"other_text_tokens": 1107027,
"other_text_tokens": 1107857,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1107824,
"deferred_resource_tokens": 504879,
"estimated_total_text_tokens": 1108654,
"deferred_resource_tokens": 505558,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 443849,
"estimated_tokens": 444443,
"file_count": 148
},
{
@@ -17440,14 +17594,14 @@
},
{
"path": "assets",
"estimated_tokens": 10903,
"estimated_tokens": 10988,
"file_count": 4
}
],
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 443849,
"estimated_tokens": 444443,
"file_count": 148
}
],
@@ -17470,14 +17624,14 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 443849,
"estimated_tokens": 444443,
"file_count": 148,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
],
"summary": "Large deferred resources are indexed and backed by evidence."
},
"relevant_file_count": 700,
"relevant_file_count": 702,
"unused_resource_dirs": [],
"quality_signal_points": 130,
"quality_density": 131.3
@@ -25082,8 +25236,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362"
"package_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806"
},
"compatibility": {
"openai": "pass",
@@ -25114,7 +25268,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -25139,7 +25293,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242"
"package_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12"
}
]
},
@@ -25162,8 +25316,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"archive_entry_count": 686,
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"archive_entry_count": 687,
"failure_count": 0,
"warning_count": 0
},
@@ -25828,7 +25982,7 @@
"installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
"summary": {
"archive_present": true,
"archive_entry_count": 686,
"archive_entry_count": 687,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -26170,12 +26324,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362"
"to": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242"
"to": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12"
}
]
},
reports/review-viewer.json
+14 -14
View File
@@ -1010,9 +1010,9 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "fa79b95f174e1c2b41a83456e6f6d7d15064dfa388f5c2b79ccc12ccefa2d119",
"source_contract_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"evidence_bundle_sha256": "3f8e332ac63fc5c841400052005674876f29d2f715a48da46424f581dbad8c49",
"source_contract_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -1032,9 +1032,9 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 34
"changed_file_count": 38
},
"commit": "48a503f8f6ea9ed8b39c5f4c6c07adbc94bca3cb",
"commit": "e3367775750edf6b2f811e7e1f3680c1e2c3e7ab",
"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.",
@@ -1139,7 +1139,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 240,
"package_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242"
"package_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12"
},
"skill_atlas": {
"skill_count": 12,
@@ -1177,8 +1177,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362"
"package_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806"
},
"compatibility": {
"openai": "pass",
@@ -1209,7 +1209,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1225,8 +1225,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"archive_entry_count": 686,
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"archive_entry_count": 687,
"failure_count": 0,
"warning_count": 0
},
@@ -1237,7 +1237,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 686,
"archive_entry_count": 687,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1304,12 +1304,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362"
"to": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242"
"to": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12"
}
]
},
reports/review_annotations.json
+1 -1
View File
@@ -2,7 +2,7 @@
"schema_version": "1.0",
"ok": true,
"skill_dir": ".",
"source": "reports/review_annotations_input.json",
"source": "tests/tmp_review_studio/empty_review_annotations_input.json",
"summary": {
"annotation_count": 0,
"open_count": 0,
reports/review_waivers.json
+2 -2
View File
@@ -2,7 +2,7 @@
"schema_version": "1.0",
"ok": true,
"skill_dir": ".",
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"summary": {
"waiver_count": 0,
"active_count": 0,
@@ -92,7 +92,7 @@
"Reviewer links output_review_adjudication or output_execution evidence."
],
"suggested_evidence": "reports/output_review_adjudication.md",
"suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-17 --evidence reports/output_review_adjudication.md",
"suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md",
"world_class_boundary": "Does not count as provider, human, or public world-class completion evidence."
},
{
reports/review_waivers.md
+1 -1
View File
@@ -38,7 +38,7 @@
- waiver allowed: `true`
- risk: review pending 5; model-executed 0; output failures 0
- evidence: `reports/output_review_adjudication.md`
- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-17 --evidence reports/output_review_adjudication.md`
- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md`
- world-class boundary: Does not count as provider, human, or public world-class completion evidence.
#### Required Review
reports/runtime_permission_probes.json
+5 -5
View File
@@ -2,7 +2,7 @@
"schema_version": "1.0",
"ok": true,
"skill_dir": ".",
"package_dir": "dist",
"package_dir": "tests/tmp_review_studio/dist",
"expected_capabilities": [
"file_write",
"network",
@@ -42,7 +42,7 @@
{
"target": "openai",
"status": "pass",
"adapter": "dist/targets/openai/adapter.json",
"adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json",
"permission_model": "metadata-only",
"native_enforcement": false,
"metadata_fallback_explicit": true,
@@ -139,7 +139,7 @@
{
"target": "claude",
"status": "pass",
"adapter": "dist/targets/claude/adapter.json",
"adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json",
"permission_model": "neutral-source-plus-adapter",
"native_enforcement": false,
"metadata_fallback_explicit": true,
@@ -221,7 +221,7 @@
{
"target": "generic",
"status": "pass",
"adapter": "dist/targets/generic/adapter.json",
"adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json",
"permission_model": "agent-skills-compatible-metadata",
"native_enforcement": false,
"metadata_fallback_explicit": true,
@@ -303,7 +303,7 @@
{
"target": "vscode",
"status": "pass",
"adapter": "dist/targets/vscode/adapter.json",
"adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json",
"permission_model": "vscode-workspace-trust-plus-metadata",
"native_enforcement": false,
"metadata_fallback_explicit": true,
reports/security_trust_report.json
+1 -1
View File
@@ -23,7 +23,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 240,
"package_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242"
"package_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12"
},
"failures": [],
"warnings": [],
reports/security_trust_report.md
+1 -1
View File
@@ -16,7 +16,7 @@
- Interactive scripts: `0`
- Package hash scope: `source-contract-without-generated-reports`
- Package hash files: `240`
- Package SHA256: `cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242`
- Package SHA256: `f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12`
## Failures
reports/skill-interpretation.json
+14 -14
View File
@@ -1014,9 +1014,9 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "fa79b95f174e1c2b41a83456e6f6d7d15064dfa388f5c2b79ccc12ccefa2d119",
"source_contract_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"evidence_bundle_sha256": "3f8e332ac63fc5c841400052005674876f29d2f715a48da46424f581dbad8c49",
"source_contract_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -1036,9 +1036,9 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 34
"changed_file_count": 38
},
"commit": "48a503f8f6ea9ed8b39c5f4c6c07adbc94bca3cb",
"commit": "e3367775750edf6b2f811e7e1f3680c1e2c3e7ab",
"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.",
@@ -1143,7 +1143,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 240,
"package_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242"
"package_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12"
},
"skill_atlas": {
"skill_count": 12,
@@ -1181,8 +1181,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362"
"package_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806"
},
"compatibility": {
"openai": "pass",
@@ -1213,7 +1213,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1229,8 +1229,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"archive_entry_count": 686,
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"archive_entry_count": 687,
"failure_count": 0,
"warning_count": 0
},
@@ -1241,7 +1241,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 686,
"archive_entry_count": 687,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1308,12 +1308,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362"
"to": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242"
"to": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12"
}
]
},
reports/skill-os-2-review.md
+2 -2
View File
@@ -140,8 +140,8 @@ Next move: add real client or installer permission enforcement integration.
| Runtime Permission Probes | `4 / 4` target adapters probed, `0` native-enforcement adapters, `4` explicit metadata fallbacks, `4` residual risks retained for reviewer visibility |
| Skill Atlas | `12` scanned skills, `1` actionable root skill, `1` telemetry report, `0` actionable route collisions, `0` actionable owner gaps, `0` actionable stale skills, `0` actionable drift signals, `24` scoped non-actionable issue signals retained for visibility |
| Registry Audit | package metadata generated with version, owner, license, source checksum, archive checksum, Skill IR provenance, and compatibility matrix |
| Package Verification | `4 / 4` target adapters present, archive verified, `686` zip entries, `0` failures, `0` warnings |
| Install Simulation | archive with `686` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings |
| Package Verification | `4 / 4` target adapters present, archive verified, `687` zip entries, `0` failures, `0` warnings |
| Install Simulation | archive with `687` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings |
| Local Install Sync Preflight | `make sync-local-install` and `make sync-active-install` rebuild the package first, then sync only after install simulation passes with `12` enforced installer permission checks and `0` permission failures |
| Upgrade Check | current package declares `minor` over the 1.0.0 baseline, recommended bump is `minor`, and release notes include added targets plus checksum changes |
| Adoption Drift | `1` metadata-only review event, `1` adoption sample, adoption `100`, risk band `low`; optional `yao.py` CLI capture, external client `telemetry-emit`, `5` `telemetry-hooks` recipes, Browser/Chrome native messaging host, and validated external JSONL import are available but off by default for reproducible release evidence; raw `reports/telemetry_events.jsonl` is gitignored and blocked from zip packages |
reports/skill-overview.json
+14 -14
View File
@@ -1009,9 +1009,9 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "fa79b95f174e1c2b41a83456e6f6d7d15064dfa388f5c2b79ccc12ccefa2d119",
"source_contract_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"evidence_bundle_sha256": "3f8e332ac63fc5c841400052005674876f29d2f715a48da46424f581dbad8c49",
"source_contract_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -1031,9 +1031,9 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 34
"changed_file_count": 38
},
"commit": "48a503f8f6ea9ed8b39c5f4c6c07adbc94bca3cb",
"commit": "e3367775750edf6b2f811e7e1f3680c1e2c3e7ab",
"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.",
@@ -1138,7 +1138,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 240,
"package_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242"
"package_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12"
},
"skill_atlas": {
"skill_count": 12,
@@ -1176,8 +1176,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242",
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362"
"package_sha256": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806"
},
"compatibility": {
"openai": "pass",
@@ -1208,7 +1208,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1224,8 +1224,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362",
"archive_entry_count": 686,
"archive_sha256": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806",
"archive_entry_count": 687,
"failure_count": 0,
"warning_count": 0
},
@@ -1236,7 +1236,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 686,
"archive_entry_count": 687,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1303,12 +1303,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362"
"to": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242"
"to": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12"
}
]
},
reports/skill_atlas.json
+4 -4
View File
@@ -44,7 +44,7 @@
},
"catalog": {
"workspace_root": ".",
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"skills": [
{
"name": "yao-meta-skill",
@@ -282,8 +282,8 @@
"report": "reports/adoption_drift_report.json",
"risk_band": "low",
"event_count": 1,
"adoption_sample_count": 0,
"adoption_rate": 0,
"adoption_sample_count": 1,
"adoption_rate": 100.0,
"candidate_count": 0
}
},
@@ -946,7 +946,7 @@
"name": "incident-command-governor",
"path": "examples/governed-incident-command/generated-skill",
"reason": "review overdue by cadence monthly",
"age_days": 78,
"age_days": 74,
"allowed_days": 31,
"actionable": false,
"scope": "example"
reports/skill_os2_audit.json
+4 -4
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"skill_dir": ".",
"summary": {
"item_count": 15,
@@ -285,7 +285,7 @@
"key": "registry-distribution",
"label": "Registry Distribution",
"status": "pass",
"current": "zip entries 686; install failures 0; permission failures 0",
"current": "zip entries 687; install failures 0; permission failures 0",
"target": "Package metadata, archive checksum, package verification, and install simulation pass",
"evidence": [
{
@@ -351,7 +351,7 @@
"key": "native-client-telemetry",
"label": "Native Client Telemetry",
"status": "external_required",
"current": "external source events 0; adoption samples 0",
"current": "external source events 0; adoption samples 1",
"target": "A real Browser/Chrome/provider client sends production metadata events",
"evidence": [
{
@@ -433,7 +433,7 @@
"key": "native-client-telemetry",
"label": "Native Client Telemetry",
"status": "external_required",
"current": "external source events 0; adoption samples 0",
"current": "external source events 0; adoption samples 1",
"target": "A real Browser/Chrome/provider client sends production metadata events",
"evidence": [
{
reports/skill_os2_audit.md
+3 -3
View File
@@ -1,6 +1,6 @@
# Skill OS 2.0 Audit
Generated at: `2026-06-17`
Generated at: `2026-06-13`
## Summary
@@ -27,10 +27,10 @@ Generated at: `2026-06-17`
| Permission Metadata | pass | 4/4 target probes pass; metadata fallback 4; installer enforcement 4 | Packaged adapters expose explicit permission metadata, residual risks, and installer enforcement evidence when available | Preserve residual-risk notes until real native enforcement exists. |
| Native Permission Enforcement | external-required | native-enforced targets 0; installer-enforced targets 4 | At least one target/client enforces approved permissions at runtime | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. |
| Skill Atlas | pass | 12 skills; actionable collisions 0 | Workspace catalog, route overlap, stale/owner gaps, drift, and no-route opportunities | Feed real drift data into Atlas once client telemetry is installed. |
| Registry Distribution | pass | zip entries 686; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. |
| Registry Distribution | pass | zip entries 687; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. |
| Review Studio | pass | decision review; warnings 3; score 91 | One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations | Resolve human/external warning gates before claiming full release readiness. |
| Telemetry Drift | pass | events 1; risk low; recipes 5 | Local-first metadata-only event contract, aggregate drift report, hook recipes, and import path | Keep raw JSONL out of distributed packages and use aggregate reports for Atlas. |
| Native Client Telemetry | external-required | external source events 0; adoption samples 0 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. |
| Native Client Telemetry | external-required | external source events 0; adoption samples 1 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. |
## Open Highest-Leverage Gaps
reports/skill_os2_coverage.json
+2 -2
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"skill_dir": ".",
"summary": {
"item_count": 21,
@@ -204,7 +204,7 @@
"label": "Registry Distribution",
"status": "pass",
"objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
"current": "archive entries 686; install failures 0",
"current": "archive entries 687; install failures 0",
"command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .",
"test": "python3 tests/verify_registry_audit.py",
"evidence": [
reports/skill_os2_coverage.md
+2 -2
View File
@@ -1,6 +1,6 @@
# Skill OS 2.0 Blueprint Coverage
Generated at: `2026-06-17`
Generated at: `2026-06-13`
## Summary
@@ -28,7 +28,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
| Runtime Conformance | `pass` | 5/5 targets pass | `python3 scripts/yao.py conformance .` | `python3 tests/verify_conformance_suite.py` |
| Trust Security | `pass` | 148 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
| Skill Atlas | `pass` | 12 scanned skills; actionable collisions 0 | `python3 scripts/yao.py skill-atlas --workspace-root .` | `python3 tests/verify_skill_atlas.py` |
| Registry Distribution | `pass` | archive entries 686; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` |
| Registry Distribution | `pass` | archive entries 687; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` |
| Review Studio | `pass` | 16 gates; decision review; warnings 3 | `python3 scripts/yao.py review-studio .` | `python3 tests/verify_review_studio.py` |
| Telemetry Drift | `pass` | events 1; recipes 5; risk low | `python3 scripts/yao.py telemetry-hooks . && python3 scripts/yao.py adoption-drift .` | `python3 tests/verify_telemetry_hooks.py` |
reports/upgrade_check.json
+5 -5
View File
@@ -1,7 +1,7 @@
{
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"previous": {
"name": "yao-meta-skill",
"version": "1.0.0",
@@ -70,12 +70,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "b09ad63e1a0cb59beba3ba7f71e285e981b84b3de6d4f9f7404618c25d96c362"
"to": "52a98e5dd903b6896643f3c0a725cd5dddc0b38dc6ec20b8c3ab8b88ffb85806"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "cc61aeda8a4a7567aca6432c73fc8faf0ed3ed753c8254245d92675edeec5242"
"to": "f5722de72ecc9012625622740af45a982c120984a0c8189eb91742b152745a12"
}
]
},
@@ -90,7 +90,7 @@
"artifacts": {
"previous_package": "registry/examples/yao-meta-skill-1.0.0.json",
"current_package": "reports/registry_audit.json",
"json": "reports/upgrade_check.json",
"markdown": "reports/upgrade_check.md"
"json": "tests/tmp_review_studio/upgrade_check.json",
"markdown": "tests/tmp_review_studio/upgrade_check.md"
}
}
reports/world_class_claim_guard.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"skill_dir": ".",
"summary": {
"ledger_ready_to_claim_world_class": false,
reports/world_class_claim_guard.md
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Claim Guard
Generated at: `2026-06-17`
Generated at: `2026-06-13`
## Summary
reports/world_class_evidence_intake.json
+2 -2
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"skill_dir": ".",
"summary": {
"schema_present": true,
@@ -328,7 +328,7 @@
"source_accepted": false,
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 0,
"adoption_sample_count": 1,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
reports/world_class_evidence_intake.md
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Intake
Generated at: `2026-06-17`
Generated at: `2026-06-13`
## Summary
reports/world_class_evidence_ledger.json
+11 -11
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"skill_dir": ".",
"decision": "evidence-pending",
"ready_to_claim_world_class": false,
@@ -16,8 +16,8 @@
"missing_submission_count": 4,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 9,
"source_blocked_count": 10,
"source_pass_count": 10,
"source_blocked_count": 9,
"submitted_but_pending_count": 0,
"source_accepted_without_valid_submission_count": 0,
"overclaim_guard_active": true,
@@ -33,8 +33,8 @@
"missing_submission_count": 4,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 9,
"source_blocked_count": 10,
"source_pass_count": 10,
"source_blocked_count": 9,
"submitted_but_pending_count": 0,
"source_accepted_without_valid_submission_count": 0,
"overclaim_guard_active": true,
@@ -486,7 +486,7 @@
"status": "pending",
"source_status": "external_required",
"source_accepted": false,
"current": "external source events 0; adoption samples 0",
"current": "external source events 0; adoption samples 1",
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"runbook": [
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -523,7 +523,7 @@
],
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 0,
"adoption_sample_count": 1,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
@@ -544,8 +544,8 @@
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"actual": 1,
"status": "pass",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
@@ -561,8 +561,8 @@
}
],
"source_check_count": 3,
"source_pass_count": 1,
"source_blocked_count": 2,
"source_pass_count": 2,
"source_blocked_count": 1,
"submission_state": {
"status": "missing",
"path": "evidence/world_class/submissions/native-client-telemetry.json",
reports/world_class_evidence_ledger.md
+7 -7
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Ledger
Generated at: `2026-06-17`
Generated at: `2026-06-13`
## Summary
@@ -8,8 +8,8 @@ Generated at: `2026-06-17`
- ready to claim world-class: `false`
- entries: `4`
- source accepted: `0`
- source checks: `9` pass / `19` total
- source blocked: `10`
- source checks: `10` pass / `19` total
- source blocked: `9`
- accepted: `0`
- pending: `4`
- human pending: `1`
@@ -30,7 +30,7 @@ This ledger records the current evidence state. It requires both passing source
| `provider-holdout` | `pending` | `missing` | `external` | model-executed 0; token-observed 0 | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. |
| `human-adjudication` | `pending` | `missing` | `human` | 0/5 decisions; pending 5 | Record real A/B choices, reviewer metadata, and blind-review attestation, then regenerate adjudication. |
| `native-permission-enforcement` | `pending` | `missing` | `external` | native-enforced targets 0; installer-enforced targets 4 | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. |
| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 0 | Install a real client against the native host and import production metadata-only events. |
| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 1 | Install a real client against the native host and import production metadata-only events. |
## Provider Holdout
@@ -186,8 +186,8 @@ This ledger records the current evidence state. It requires both passing source
- objective: Import production metadata-only events from a real external client into the local drift loop.
- source status: `external_required`
- observed state: `{"external_source_events": 0, "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false}`
- source checks: `1` pass / `3` total
- observed state: `{"external_source_events": 0, "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false}`
- source checks: `2` pass / `3` total
- submission state: `{"status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", "artifact_ref_count": 0, "attested_real_evidence": false, "privacy_contract_satisfied": false, "ledger_reviewer_approved": false, "ledger_reviewer": "", "ledger_reviewed_at": "", "ledger_counts_as_completion": false}`
### Provenance Requirements
@@ -211,7 +211,7 @@ This ledger records the current evidence state. It requires both passing source
| Check | Current | Expected | Status |
| --- | --- | --- | --- |
| External events | `0` | `>0` | `blocked` |
| Adoption sample | `0` | `>0` | `blocked` |
| Adoption sample | `1` | `>0` | `pass` |
| Raw content blocked | `False` | `false` | `pass` |
### Completion Assertions
reports/world_class_evidence_plan.json
+3 -3
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"skill_dir": ".",
"summary": {
"audit_decision": "continue-iteration",
@@ -154,7 +154,7 @@
"status": "external_required",
"category": "external",
"owner": "Browser/Chrome/IDE/provider client integrator",
"current": "external source events 0; adoption samples 0",
"current": "external source events 0; adoption samples 1",
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"runbook": [
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
@@ -325,7 +325,7 @@
"status": "external_required",
"category": "external",
"owner": "Browser/Chrome/IDE/provider client integrator",
"current": "external source events 0; adoption samples 0",
"current": "external source events 0; adoption samples 1",
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"runbook": [
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
reports/world_class_evidence_plan.md
+2 -2
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Plan
Generated at: `2026-06-17`
Generated at: `2026-06-13`
## Summary
@@ -22,7 +22,7 @@ This report is an execution plan for the remaining world-class evidence gaps. It
| `provider-holdout` | `external_required` | `external` | operator with provider credentials | model-executed 0; token-observed 0 |
| `human-adjudication` | `human_required` | `human` | human reviewer | 0/5 decisions; pending 5 |
| `native-permission-enforcement` | `external_required` | `external` | target client or installer integrator | native-enforced targets 0; installer-enforced targets 4 |
| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 0 |
| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 1 |
## Provider Holdout
reports/world_class_evidence_preflight.html
+4 -17
View File
@@ -66,7 +66,7 @@
<span class="eyebrow">Evidence Collection</span>
<h1>World-Class Evidence Preflight</h1>
<p class="lede">This operator view shows which external and human evidence is still blocked, which commands prepare editable submission drafts, and why preflight never counts as accepted evidence.</p>
<div class="stats"><article><span>Decision</span><strong>collection-preflight-blocked</strong></article><article><span>Pending</span><strong>4</strong></article><article><span>Ready</span><strong>1</strong></article><article><span>Blocked</span><strong>3</strong></article><article><span>Source</span><strong>9/19</strong></article><article><span>Repairs</span><strong>14/14</strong></article></div>
<div class="stats"><article><span>Decision</span><strong>collection-preflight-blocked</strong></article><article><span>Pending</span><strong>4</strong></article><article><span>Ready</span><strong>1</strong></article><article><span>Blocked</span><strong>3</strong></article><article><span>Source</span><strong>10/19</strong></article><article><span>Repairs</span><strong>13/13</strong></article></div>
</section>
<section class="section two-col" id="handoff">
<article class="panel">
@@ -845,15 +845,15 @@
</dl>
</article>
<article class="check-row blocked">
<article class="check-row pass">
<div>
<span>adoption_sample_count</span>
<strong>Adoption sample</strong>
</div>
<dl>
<dt>Current</dt><dd><code>0</code></dd>
<dt>Current</dt><dd><code>1</code></dd>
<dt>Expected</dt><dd><code>&gt;0</code></dd>
<dt>Status</dt><dd>blocked</dd>
<dt>Status</dt><dd>pass</dd>
<dt>Action</dt><dd>Telemetry must include adoption outcome evidence.</dd>
</dl>
</article>
@@ -900,19 +900,6 @@
<dt>Evidence</dt><dd>does not count as completion</dd>
</dl>
</article>
<article class="repair-row blocked">
<div>
<span>source-check</span>
<strong>adoption_sample_count</strong>
</div>
<dl>
<dt>Status</dt><dd>blocked</dd>
<dt>Reason</dt><dd>Current value 0 does not satisfy &#x27;&gt;0&#x27;.</dd>
<dt>Action</dt><dd>Telemetry must include adoption outcome evidence.</dd>
<dt>Evidence</dt><dd>does not count as completion</dd>
</dl>
</article>
</div>
</section>
<section class="runbook">
reports/world_class_evidence_preflight.json
+9 -29
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"skill_dir": ".",
"summary": {
"evidence_item_count": 4,
@@ -14,10 +14,10 @@
"collection_ready_count": 1,
"collection_blocked_count": 3,
"source_check_count": 19,
"source_pass_count": 9,
"source_blocked_count": 10,
"repair_checklist_count": 14,
"repair_blocked_count": 14,
"source_pass_count": 10,
"source_blocked_count": 9,
"repair_checklist_count": 13,
"repair_blocked_count": 13,
"repair_ready_count": 0,
"repair_counts_as_completion": false,
"pending_count": 4,
@@ -715,8 +715,8 @@
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"actual": 1,
"status": "pass",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
@@ -804,16 +804,6 @@
"next_action": "Import at least one metadata-only event from a real client.",
"source": "source_checklist",
"counts_as_completion": false
},
{
"evidence_key": "native-client-telemetry",
"repair_type": "source-check",
"target": "adoption_sample_count",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '>0'.",
"next_action": "Telemetry must include adoption outcome evidence.",
"source": "source_checklist",
"counts_as_completion": false
}
]
}
@@ -1163,8 +1153,8 @@
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"actual": 1,
"status": "pass",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
@@ -1309,16 +1299,6 @@
"next_action": "Import at least one metadata-only event from a real client.",
"source": "source_checklist",
"counts_as_completion": false
},
{
"evidence_key": "native-client-telemetry",
"repair_type": "source-check",
"target": "adoption_sample_count",
"status": "blocked",
"blocking_reason": "Current value 0 does not satisfy '>0'.",
"next_action": "Telemetry must include adoption outcome evidence.",
"source": "source_checklist",
"counts_as_completion": false
}
],
"submissions": {
reports/world_class_evidence_preflight.md
+4 -5
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Preflight
Generated at: `2026-06-17`
Generated at: `2026-06-13`
## Summary
@@ -10,8 +10,8 @@ Generated at: `2026-06-17`
- credential value exposed: `false`
- collection ready: `1`
- collection blocked: `3`
- source checks: `9` pass / `19` total
- repair rows: `14` blocked / `14` total
- source checks: `10` pass / `19` total
- repair rows: `13` blocked / `13` total
This preflight report checks whether an operator can start collecting the remaining external or human evidence. It never accepts evidence, prints secret values, or changes the world-class ledger.
@@ -66,7 +66,6 @@ Repair rows convert preflight and source blockers into concrete operator actions
| `native-permission-enforcement` | `source-check` | `native_enforcement_count` | `blocked` | Collect real target-client or external runtime guard proof. |
| `native-client-telemetry` | `precheck` | `external-client` | `blocked` | Install a real Browser, Chrome, IDE, or provider client that emits metadata-only events. |
| `native-client-telemetry` | `source-check` | `external_source_events` | `blocked` | Import at least one metadata-only event from a real client. |
| `native-client-telemetry` | `source-check` | `adoption_sample_count` | `blocked` | Telemetry must include adoption outcome evidence. |
## Provider Holdout
@@ -178,7 +177,7 @@ Repair rows convert preflight and source blockers into concrete operator actions
| Check | Current | Expected | Status | Next action |
| --- | --- | --- | --- | --- |
| External events | `0` | `>0` | `blocked` | Import at least one metadata-only event from a real client. |
| Adoption sample | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. |
| Adoption sample | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. |
| Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. |
## Boundary
reports/world_class_operator_runbook.html
+4 -4
View File
@@ -57,7 +57,7 @@
<span class="eyebrow">Evidence Operations</span>
<h1>World-Class Operator Runbook</h1>
<p class="lede">A single operating page for collecting the remaining human and external evidence. It coordinates action, but does not accept evidence or change the ledger.</p>
<div class="stats"><article><span>Pending</span><strong>4</strong></article><article><span>Awaiting</span><strong>4</strong></article><article><span>Ready</span><strong>0</strong></article><article><span>Source</span><strong>9/19</strong></article><article><span>Blocked</span><strong>10</strong></article><article><span>Invalid</span><strong>0</strong></article></div>
<div class="stats"><article><span>Pending</span><strong>4</strong></article><article><span>Awaiting</span><strong>4</strong></article><article><span>Ready</span><strong>0</strong></article><article><span>Source</span><strong>10/19</strong></article><article><span>Blocked</span><strong>9</strong></article><article><span>Invalid</span><strong>0</strong></article></div>
</section>
<section class="section panel" id="fast-path"><h2>Fast Path</h2><ol><li>Run the real external or human work for one evidence item.</li><li>Generate and fill the matching submission draft.</li><li>Validate intake and inspect the submission review queue.</li><li>Refresh the ledger and run the claim guard before making any completion claim.</li></ol></section>
<section class="section" id="items"><h2>Evidence Items</h2><div class="item-grid"><article class="item-card awaiting-submission">
@@ -120,7 +120,7 @@
<dl>
<dt>Owner</dt><dd>Browser/Chrome/IDE/provider client integrator</dd>
<dt>Ledger</dt><dd><code>pending</code></dd>
<dt>Blocked</dt><dd><code>2</code></dd>
<dt>Blocked</dt><dd><code>1</code></dd>
<dt>Submission</dt><dd><code>evidence/world_class/submissions/native-client-telemetry.json</code></dd>
</dl>
<section class="source-panel"><h4>Source Runbook</h4><ul><li>python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://&lt;extension-id&gt;/</li><li>Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.</li><li>python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl</li><li>python3 scripts/yao.py skill-atlas --workspace-root .</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></section>
@@ -130,8 +130,8 @@
<section><h4>Success Checks</h4><ul><li>reports/adoption_drift_report.json summary.source_types.external &gt; 0</li><li>reports/adoption_drift_report.json summary.adoption_sample_count &gt; 0</li><li>reports/skill_os2_audit.json item native-client-telemetry status becomes pass</li></ul></section>
<section><h4>Privacy</h4><ul><li>Telemetry must remain metadata-only and local-first.</li><li>Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.</li></ul></section>
</div>
<section class="source-panel"><h4>Next Source Actions</h4><ul><li>Import at least one metadata-only event from a real client.</li><li>Telemetry must include adoption outcome evidence.</li></ul></section>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>External events</span><code>external_source_events: 0 / &gt;0</code><small>Import at least one metadata-only event from a real client.</small></li><li class='source-check blocked'><span>Adoption sample</span><code>adoption_sample_count: 0 / &gt;0</code><small>Telemetry must include adoption outcome evidence.</small></li><li class='source-check pass'><span>Raw content blocked</span><code>raw_content_allowed: False / false</code><small>Telemetry must stay metadata-only.</small></li></ul></section>
<section class="source-panel"><h4>Next Source Actions</h4><ul><li>Import at least one metadata-only event from a real client.</li></ul></section>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>External events</span><code>external_source_events: 0 / &gt;0</code><small>Import at least one metadata-only event from a real client.</small></li><li class='source-check pass'><span>Adoption sample</span><code>adoption_sample_count: 1 / &gt;0</code><small>Telemetry must include adoption outcome evidence.</small></li><li class='source-check pass'><span>Raw content blocked</span><code>raw_content_allowed: False / false</code><small>Telemetry must stay metadata-only.</small></li></ul></section>
</article></div></section>
<section class="section panel" id="boundary"><h2>Boundary</h2><ul><li>Planned work, draft packets, metadata fallback, pending human decisions, and local command runners do not count as completion.</li><li>Valid intake means ready for submission review; ledger review still requires passing source evidence.</li><li>The world-class ledger and claim guard remain the source of truth.</li></ul></section>
</main>
reports/world_class_operator_runbook.json
+9 -10
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"skill_dir": ".",
"summary": {
"evidence_item_count": 4,
@@ -12,8 +12,8 @@
"valid_packet_source_incomplete_count": 0,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 9,
"source_blocked_count": 10,
"source_pass_count": 10,
"source_blocked_count": 9,
"ready_to_claim_world_class": false,
"runbook_counts_as_completion": false,
"decision": "collect-evidence"
@@ -487,7 +487,7 @@
"review_state": "awaiting-submission",
"source_accepted": false,
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"current": "external source events 0; adoption samples 0",
"current": "external source events 0; adoption samples 1",
"execution_runbook": [
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
"Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
@@ -535,7 +535,7 @@
],
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 0,
"adoption_sample_count": 1,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
@@ -556,8 +556,8 @@
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"actual": 1,
"status": "pass",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
@@ -572,10 +572,9 @@
"next_action": "Telemetry must stay metadata-only."
}
],
"blocked_source_check_count": 2,
"blocked_source_check_count": 1,
"next_source_actions": [
"Import at least one metadata-only event from a real client.",
"Telemetry must include adoption outcome evidence."
"Import at least one metadata-only event from a real client."
],
"submission_state": {
"status": "missing",
reports/world_class_operator_runbook.md
+4 -5
View File
@@ -1,6 +1,6 @@
# World-Class Operator Runbook
Generated at: `2026-06-17`
Generated at: `2026-06-13`
## Summary
@@ -28,7 +28,7 @@ This runbook coordinates evidence collection only. It does not accept submission
| `provider-holdout` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Run provider-backed output-exec with real credentials. | operator with provider credentials |
| `human-adjudication` | `pending` | `awaiting-submission` | `awaiting-submission` | `5` | Record a reviewer choice and reason for every pair. | human reviewer |
| `native-permission-enforcement` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Collect real target-client or external runtime guard proof. | target client or installer integrator |
| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator |
| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator |
## Provider Holdout
@@ -261,7 +261,7 @@ This runbook coordinates evidence collection only. It does not accept submission
- objective: Import production metadata-only events from a real external client into the local drift loop.
- blocking reason: No evidence packet has been submitted for review.
- blocked source checks: `2`
- blocked source checks: `1`
- submission: `evidence/world_class/submissions/native-client-telemetry.json`
- template: `evidence/world_class/templates/native-client-telemetry.intake.json`
@@ -314,14 +314,13 @@ This runbook coordinates evidence collection only. It does not accept submission
### Next Source Actions
- Import at least one metadata-only event from a real client.
- Telemetry must include adoption outcome evidence.
### Source Evidence Snapshot
| Check | Current | Expected | Status | Next action |
| --- | --- | --- | --- | --- |
| External events | `0` | `>0` | `blocked` | Import at least one metadata-only event from a real client. |
| Adoption sample | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. |
| Adoption sample | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. |
| Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. |
## Boundary
reports/world_class_submission_review.json
+10 -10
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"skill_dir": ".",
"decision": "awaiting-submissions",
"ready_to_claim_world_class": false,
@@ -14,8 +14,8 @@
"unmatched_submission_count": 0,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 9,
"source_blocked_count": 10,
"source_pass_count": 10,
"source_blocked_count": 9,
"review_counts_submission_as_completion": false,
"summary": {
"review_item_count": 4,
@@ -27,8 +27,8 @@
"unmatched_submission_count": 0,
"invalid_submission_count": 0,
"source_check_count": 19,
"source_pass_count": 9,
"source_blocked_count": 10,
"source_pass_count": 10,
"source_blocked_count": 9,
"ready_to_claim_world_class": false,
"review_counts_submission_as_completion": false,
"decision": "awaiting-submissions"
@@ -378,7 +378,7 @@
"intake_errors": [],
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 0,
"adoption_sample_count": 1,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
@@ -399,8 +399,8 @@
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"actual": 1,
"status": "pass",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
@@ -416,8 +416,8 @@
}
],
"source_check_count": 3,
"source_pass_count": 1,
"source_blocked_count": 2,
"source_pass_count": 2,
"source_blocked_count": 1,
"success_checks": [
"reports/adoption_drift_report.json summary.source_types.external > 0",
"reports/adoption_drift_report.json summary.adoption_sample_count > 0",
reports/world_class_submission_review.md
+2 -2
View File
@@ -1,6 +1,6 @@
# World-Class Submission Review
Generated at: `2026-06-17`
Generated at: `2026-06-13`
## Summary
@@ -153,7 +153,7 @@ This report is a read-only reviewer queue. It does not accept evidence or make w
#### Source Checks
- External events: 0 / >0 => blocked
- Adoption sample: 0 / >0 => blocked
- Adoption sample: 1 / >0 => pass
- Raw content blocked: False / false => pass
#### Completion Assertions
scripts/review_studio_action_evidence.py
+37 -1
View File
@@ -98,6 +98,7 @@ def world_class_action_steps(data: dict[str, Any]) -> list[dict[str, Any]]:
if not key:
continue
checklist = intake_by_key.get(key, {})
preflight_item = preflight_by_key.get(key, {})
submission = entry.get("submission_state", {}) if isinstance(entry.get("submission_state", {}), dict) else {}
source_checks = entry.get("source_checklist", []) if isinstance(entry.get("source_checklist", []), list) else []
blocked_checks = [
@@ -112,12 +113,25 @@ def world_class_action_steps(data: dict[str, Any]) -> list[dict[str, Any]]:
for row in source_checks
if isinstance(row, dict) and str(row.get("status", "")) != "pass"
]
repair_rows = []
for row in preflight_item.get("repair_checklist", []) if isinstance(preflight_item, dict) else []:
if not isinstance(row, dict):
continue
repair_rows.append(
{
"repair_type": str(row.get("repair_type", "")),
"target": str(row.get("target", "")),
"status": str(row.get("status", "blocked")),
"blocking_reason": str(row.get("blocking_reason", "")),
"next_action": str(row.get("next_action", "")),
"counts_as_completion": row.get("counts_as_completion") is True,
}
)
derived_pass_count = sum(1 for row in source_checks if isinstance(row, dict) and str(row.get("status", "")) == "pass")
runbook = entry.get("runbook", [])
if not runbook and isinstance(checklist.get("must_collect", {}), dict):
runbook = checklist["must_collect"].get("runbook", [])
must_collect = checklist.get("must_collect", {}) if isinstance(checklist.get("must_collect", {}), dict) else {}
preflight_item = preflight_by_key.get(key, {})
submission_kit = (
preflight_item.get("submission_kit", {})
if isinstance(preflight_item.get("submission_kit", {}), dict)
@@ -137,6 +151,9 @@ def world_class_action_steps(data: dict[str, Any]) -> list[dict[str, Any]]:
"source_pass_count": int(entry.get("source_pass_count", 0) or derived_pass_count),
"source_blocked_count": int(entry.get("source_blocked_count", 0) or len(blocked_checks)),
"blocked_checks": blocked_checks,
"repair_rows": repair_rows,
"repair_blocked_count": sum(1 for row in repair_rows if row.get("status") != "ready"),
"repair_counts_as_completion": any(row.get("counts_as_completion") for row in repair_rows),
"commands": action_command_rows(checklist.get("commands", {}) if isinstance(checklist.get("commands", {}), dict) else {}),
"runbook": [str(item) for item in runbook[:3]],
"provenance_requirements": first_text_items(
@@ -228,6 +245,17 @@ def render_action_evidence_steps(steps: list[dict[str, Any]]) -> str:
"</li>"
)
runbook_rows = [f"<li>{html.escape(str(item))}</li>" for item in step.get("runbook", [])]
repair_rows = []
for row in step.get("repair_rows", []):
repair_rows.append(
"<li class='action-repair-row "
+ html.escape(str(row.get("status", "blocked")))
+ "'>"
f"<span>{html.escape(str(row.get('repair_type', '')))} · {html.escape(str(row.get('target', '')))}</span>"
f"<code>{html.escape(str(row.get('blocking_reason', '')))}</code>"
f"<small>{html.escape(str(row.get('next_action', '')))}</small>"
"</li>"
)
cards.append(
"<article class='action-evidence-item "
+ html.escape(str(step.get("status", "pending")))
@@ -238,6 +266,7 @@ def render_action_evidence_steps(steps: list[dict[str, Any]]) -> str:
f"<dl><dt>提交</dt><dd><code>{html.escape(str(step.get('submission_path', '')))}</code></dd>"
f"<dt>模板</dt><dd><code>{html.escape(str(step.get('template_path', '')))}</code></dd>"
f"<dt>阻断</dt><dd>{html.escape(str(step.get('source_blocked_count', 0)))} blocked / {html.escape(str(step.get('source_pass_count', 0)))} pass</dd>"
f"<dt>修复</dt><dd>{html.escape(str(step.get('repair_blocked_count', 0)))} repair rows; counts as completion: {html.escape(str(step.get('repair_counts_as_completion') is True).lower())}</dd>"
f"<dt>下一步</dt><dd>{html.escape(str(step.get('next_action', '')))}</dd></dl>"
"<section><h5>阻断检查</h5>"
+ (
@@ -246,6 +275,13 @@ def render_action_evidence_steps(steps: list[dict[str, Any]]) -> str:
else "<p class='muted'>暂无阻断检查。</p>"
)
+ "</section>"
"<details class='action-repair-details'><summary>修复清单</summary>"
+ (
"<ul class='action-repair-list'>" + "".join(repair_rows) + "</ul>"
if repair_rows
else "<p class='muted'>暂无修复项。</p>"
)
+ "</details>"
"<details class='action-command-details'><summary>操作命令</summary>"
+ (
"<ul class='action-command-list'>" + "".join(command_rows) + "</ul>"
scripts/review_studio_actions.py
+2
View File
@@ -229,6 +229,8 @@ ACTION_GUIDANCE: dict[str, dict[str, Any]] = {
{"path": "reports/world_class_evidence_ledger.md", "label": "world-class evidence ledger", "kind": "report", "patterns": ["# World-Class Evidence Ledger"]},
{"path": "reports/world_class_evidence_plan.md", "label": "world-class evidence plan", "kind": "report", "patterns": ["# World-Class Evidence Plan"]},
{"path": "reports/world_class_evidence_intake.md", "label": "world-class evidence intake", "kind": "report", "patterns": ["# World-Class Evidence Intake"]},
{"path": "reports/world_class_evidence_preflight.md", "label": "world-class evidence preflight", "kind": "report", "patterns": ["# World-Class Evidence Preflight"]},
{"path": "reports/world_class_evidence_preflight.html", "label": "world-class preflight HTML", "kind": "report", "patterns": ["World-Class Evidence Preflight"]},
{"path": "reports/world_class_submission_review.md", "label": "world-class submission review", "kind": "report", "patterns": ["# World-Class Submission Review"]},
{"path": "reports/world_class_claim_guard.md", "label": "world-class claim guard", "kind": "report", "patterns": ["# World-Class Claim Guard"]},
{"path": "evidence/world_class/intake.schema.json", "label": "evidence intake schema", "kind": "schema", "patterns": ["Yao World-Class Evidence Intake"]},
skill_atlas/catalog.json
+3 -3
View File
@@ -1,6 +1,6 @@
{
"workspace_root": ".",
"generated_at": "2026-06-17",
"generated_at": "2026-06-13",
"skills": [
{
"name": "yao-meta-skill",
@@ -238,8 +238,8 @@
"report": "reports/adoption_drift_report.json",
"risk_band": "low",
"event_count": 1,
"adoption_sample_count": 0,
"adoption_rate": 0,
"adoption_sample_count": 1,
"adoption_rate": 100.0,
"candidate_count": 0
}
},
skill_atlas/stale_skills.json
+1 -1
View File
@@ -24,7 +24,7 @@
"name": "incident-command-governor",
"path": "examples/governed-incident-command/generated-skill",
"reason": "review overdue by cadence monthly",
"age_days": 78,
"age_days": 74,
"allowed_days": 31,
"actionable": false,
"scope": "example"
tests/review_studio_world_class_assertions.py
+126
View File
@@ -0,0 +1,126 @@
#!/usr/bin/env python3
"""Focused assertions for Review Studio world-class evidence actions."""
def assert_world_class_action(full_payload: dict) -> None:
world_class_action = next(
item for item in full_payload["review_actions"] if item["gate_key"] == "world-class-evidence"
)
assert {item["path"] for item in world_class_action["source_refs"]} >= {
"reports/world_class_evidence_ledger.md",
"reports/world_class_evidence_plan.md",
"reports/world_class_evidence_intake.md",
"reports/world_class_evidence_preflight.md",
"reports/world_class_evidence_preflight.html",
"reports/world_class_submission_review.md",
"reports/world_class_claim_guard.md",
"evidence/world_class/intake.schema.json",
"evidence/world_class/templates/provider-holdout.intake.json",
"evidence/world_class/templates/human-adjudication.intake.json",
"evidence/world_class/templates/native-permission-enforcement.intake.json",
"evidence/world_class/templates/native-client-telemetry.intake.json",
"reports/skill_os2_audit.md",
}, world_class_action
assert all(item["exists"] for item in world_class_action["source_refs"]), world_class_action
assert all("matched_pattern" in item for item in world_class_action["source_refs"]), world_class_action
assert all("excerpt" in item for item in world_class_action["source_refs"]), world_class_action
assert all(isinstance(item["line"], int) and item["line"] >= 1 for item in world_class_action["source_refs"]), world_class_action
assert any(
item["path"] == "reports/world_class_evidence_ledger.md"
and item["matched_pattern"] == "# World-Class Evidence Ledger"
and "World-Class Evidence Ledger" in item["excerpt"]
for item in world_class_action["source_refs"]
), world_class_action
assert "world-class-runbook" in world_class_action["verification_command"], world_class_action
assert "--submissions-dir evidence/world_class/submissions" in world_class_action["verification_command"], world_class_action
assert "reports/world_class_operator_runbook.html" in world_class_action["source_fix"], world_class_action
assert {item["key"] for item in world_class_action["evidence_steps"]} == {
"provider-holdout",
"human-adjudication",
"native-permission-enforcement",
"native-client-telemetry",
}, world_class_action
provider_action_step = next(
item for item in world_class_action["evidence_steps"] if item["key"] == "provider-holdout"
)
assert provider_action_step["status"] == "pending", provider_action_step
assert provider_action_step["readiness"] == "awaiting-submission", provider_action_step
assert provider_action_step["submission_path"] == "evidence/world_class/submissions/provider-holdout.json", provider_action_step
assert provider_action_step["template_path"] == "evidence/world_class/templates/provider-holdout.intake.json", provider_action_step
assert provider_action_step["source_blocked_count"] == 2, provider_action_step
assert provider_action_step["repair_blocked_count"] == 3, provider_action_step
assert provider_action_step["repair_counts_as_completion"] is False, provider_action_step
assert {item["label"] for item in provider_action_step["blocked_checks"]} == {
"Provider model run",
"Token usage observed",
}, provider_action_step
provider_repair_rows = {item["target"]: item for item in provider_action_step["repair_rows"]}
assert set(provider_repair_rows) == {"openai-api-key", "model_executed_count", "token_observed_count"}, provider_repair_rows
assert provider_repair_rows["openai-api-key"]["repair_type"] == "precheck", provider_repair_rows
assert provider_repair_rows["model_executed_count"]["repair_type"] == "source-check", provider_repair_rows
assert all(item["counts_as_completion"] is False for item in provider_action_step["repair_rows"]), provider_action_step
assert any("world-class-intake" in item["command"] for item in provider_action_step["commands"]), provider_action_step
assert any("world-class-ledger" in item["command"] for item in provider_action_step["commands"]), provider_action_step
assert any("output-exec --provider-runner openai" in item for item in provider_action_step["runbook"]), provider_action_step
assert not any("<redacted>" in item or "OPENAI_API_KEY=" in item for item in provider_action_step["runbook"]), provider_action_step
assert "provider-backed model run" in provider_action_step["provenance_requirements"], provider_action_step
assert "reports/output_execution_runs.json summary.model_executed_count > 0" in provider_action_step["success_checks"], provider_action_step
assert "reports/output_execution_runs.json" in provider_action_step["evidence_artifacts"], provider_action_step
provider_role_contract = provider_action_step["artifact_role_contract"]
assert provider_role_contract["role_source"] == "world-class-submission-kit", provider_role_contract
assert provider_role_contract["counts_as_evidence"] is False, provider_role_contract
assert provider_role_contract["artifact_prefill_counts_as_evidence"] is False, provider_role_contract
assert provider_role_contract["submission_ref_total_count"] == 1, provider_role_contract
assert provider_role_contract["submission_ref_ready_count"] == 1, provider_role_contract
provider_role_rows = {item["role"]: item for item in provider_role_contract["roles"]}
assert provider_role_rows["submission-ref"]["copy_to_artifact_refs"] is True, provider_role_rows
assert provider_role_rows["supporting-evidence"]["copy_to_artifact_refs"] is False, provider_role_rows
assert any("provider credentials" in item for item in provider_action_step["privacy_contract"]), provider_action_step
human_action_step = next(
item for item in world_class_action["evidence_steps"] if item["key"] == "human-adjudication"
)
assert human_action_step["repair_blocked_count"] >= 2, human_action_step
human_repair_rows = {item["target"]: item for item in human_action_step["repair_rows"]}
assert human_repair_rows["human-reviewer"]["repair_type"] == "precheck", human_repair_rows
assert human_repair_rows["pending_count"]["repair_type"] == "source-check", human_repair_rows
assert "prompt_sha256" in " ".join(human_action_step["success_checks"]), human_action_step
assert "prompt_sha256" in " ".join(human_action_step["privacy_contract"]), human_action_step
assert full_payload["data"]["world_class_evidence_ledger"]["summary"]["pending_count"] == 4
assert full_payload["data"]["world_class_evidence_intake"]["summary"]["decision"] == "awaiting-submissions"
submission_review = full_payload["data"]["world_class_submission_review"]
assert submission_review["summary"]["decision"] == "awaiting-submissions", submission_review
assert submission_review["summary"]["review_counts_submission_as_completion"] is False, submission_review
assert submission_review["summary"]["awaiting_submission_count"] == 4, submission_review
assert submission_review["summary"]["source_check_count"] >= 13, submission_review
assert submission_review["summary"]["source_blocked_count"] >= 6, submission_review
human_review_item = next(item for item in submission_review["items"] if item["evidence_key"] == "human-adjudication")
human_review_source = {item["field"]: item for item in human_review_item["source_checklist"]}
assert human_review_item["observed_state"]["raw_content_allowed"] is False, human_review_item
assert human_review_item["observed_state"]["raw_content_path_count"] == 0, human_review_item
assert human_review_source["raw_content_allowed"]["status"] == "pass", human_review_source
runbook = full_payload["data"]["world_class_operator_runbook"]
assert runbook["summary"]["decision"] == "collect-evidence", runbook
assert runbook["summary"]["runbook_counts_as_completion"] is False, runbook
assert runbook["summary"]["awaiting_submission_count"] == 4, runbook
intake = full_payload["data"]["world_class_evidence_intake"]
assert intake["summary"]["template_pass_count"] == 4, intake
assert intake["summary"]["operator_checklist_count"] == 4, intake
assert intake["summary"]["operator_checklist_ready_count"] == 0, intake
assert intake["summary"]["ready_to_claim_world_class"] is False, intake
provider_checklist = next(item for item in intake["operator_checklist"] if item["evidence_key"] == "provider-holdout")
assert provider_checklist["readiness"] == "awaiting-submission", provider_checklist
assert provider_checklist["submission_path"] == "evidence/world_class/submissions/provider-holdout.json", provider_checklist
assert provider_checklist["commands"]["validate_intake"] == "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions", provider_checklist
assert provider_checklist["commands"]["submission_review"] == "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions", provider_checklist
assert provider_checklist["commands"]["refresh_ledger"] == "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions", provider_checklist
assert "provider-backed model run" in provider_checklist["must_collect"]["provenance_requirements"], provider_checklist
assert any(
"output-exec --provider-runner openai" in step for step in provider_checklist["must_collect"]["runbook"]
), provider_checklist
assert full_payload["data"]["world_class_claim_guard"]["summary"]["decision"] == "claim-guard-pass-evidence-pending"
assert full_payload["data"]["world_class_claim_guard"]["summary"]["violation_count"] == 0
assert full_payload["data"]["world_class_claim_guard"]["summary"]["ledger_pending_count"] == 4
tests/verify_review_studio.py
+6 -98
View File
@@ -5,6 +5,7 @@ import sys
from review_studio_helpers import ROOT, prepare_tmp_root, render_review_studio_fixture
from review_studio_world_class_assertions import assert_world_class_action
sys.path.insert(0, str(ROOT / "scripts"))
import render_review_studio as review_studio # noqa: E402
@@ -244,104 +245,7 @@ def main() -> None:
assert "scripts/cross_packager.py" not in early_watch_paths, full_payload["data"]["architecture_maintainability"]
action_keys = {item["gate_key"] for item in full_payload["review_actions"]}
assert action_keys == {"output-lab", "review-waivers", "world-class-evidence"}, full_payload["review_actions"]
world_class_action = next(item for item in full_payload["review_actions"] if item["gate_key"] == "world-class-evidence")
assert {item["path"] for item in world_class_action["source_refs"]} >= {
"reports/world_class_evidence_ledger.md",
"reports/world_class_evidence_plan.md",
"reports/world_class_evidence_intake.md",
"reports/world_class_submission_review.md",
"reports/world_class_claim_guard.md",
"evidence/world_class/intake.schema.json",
"evidence/world_class/templates/provider-holdout.intake.json",
"evidence/world_class/templates/human-adjudication.intake.json",
"evidence/world_class/templates/native-permission-enforcement.intake.json",
"evidence/world_class/templates/native-client-telemetry.intake.json",
"reports/skill_os2_audit.md",
}, world_class_action
assert all(item["exists"] for item in world_class_action["source_refs"]), world_class_action
assert all("matched_pattern" in item for item in world_class_action["source_refs"]), world_class_action
assert all("excerpt" in item for item in world_class_action["source_refs"]), world_class_action
assert all(isinstance(item["line"], int) and item["line"] >= 1 for item in world_class_action["source_refs"]), world_class_action
assert any(
item["path"] == "reports/world_class_evidence_ledger.md"
and item["matched_pattern"] == "# World-Class Evidence Ledger"
and "World-Class Evidence Ledger" in item["excerpt"]
for item in world_class_action["source_refs"]
), world_class_action
assert "world-class-runbook" in world_class_action["verification_command"], world_class_action
assert "--submissions-dir evidence/world_class/submissions" in world_class_action["verification_command"], world_class_action
assert "reports/world_class_operator_runbook.html" in world_class_action["source_fix"], world_class_action
assert {item["key"] for item in world_class_action["evidence_steps"]} == {
"provider-holdout",
"human-adjudication",
"native-permission-enforcement",
"native-client-telemetry",
}, world_class_action
provider_action_step = next(item for item in world_class_action["evidence_steps"] if item["key"] == "provider-holdout")
assert provider_action_step["status"] == "pending", provider_action_step
assert provider_action_step["readiness"] == "awaiting-submission", provider_action_step
assert provider_action_step["submission_path"] == "evidence/world_class/submissions/provider-holdout.json", provider_action_step
assert provider_action_step["template_path"] == "evidence/world_class/templates/provider-holdout.intake.json", provider_action_step
assert provider_action_step["source_blocked_count"] == 2, provider_action_step
assert {item["label"] for item in provider_action_step["blocked_checks"]} == {
"Provider model run",
"Token usage observed",
}, provider_action_step
assert any("world-class-intake" in item["command"] for item in provider_action_step["commands"]), provider_action_step
assert any("world-class-ledger" in item["command"] for item in provider_action_step["commands"]), provider_action_step
assert any("output-exec --provider-runner openai" in item for item in provider_action_step["runbook"]), provider_action_step
assert not any("<redacted>" in item or "OPENAI_API_KEY=" in item for item in provider_action_step["runbook"]), provider_action_step
assert "provider-backed model run" in provider_action_step["provenance_requirements"], provider_action_step
assert "reports/output_execution_runs.json summary.model_executed_count > 0" in provider_action_step["success_checks"], provider_action_step
assert "reports/output_execution_runs.json" in provider_action_step["evidence_artifacts"], provider_action_step
provider_role_contract = provider_action_step["artifact_role_contract"]
assert provider_role_contract["role_source"] == "world-class-submission-kit", provider_role_contract
assert provider_role_contract["counts_as_evidence"] is False, provider_role_contract
assert provider_role_contract["artifact_prefill_counts_as_evidence"] is False, provider_role_contract
assert provider_role_contract["submission_ref_total_count"] == 1, provider_role_contract
assert provider_role_contract["submission_ref_ready_count"] == 1, provider_role_contract
provider_role_rows = {item["role"]: item for item in provider_role_contract["roles"]}
assert provider_role_rows["submission-ref"]["copy_to_artifact_refs"] is True, provider_role_rows
assert provider_role_rows["supporting-evidence"]["copy_to_artifact_refs"] is False, provider_role_rows
assert any("provider credentials" in item for item in provider_action_step["privacy_contract"]), provider_action_step
human_action_step = next(item for item in world_class_action["evidence_steps"] if item["key"] == "human-adjudication")
assert "prompt_sha256" in " ".join(human_action_step["success_checks"]), human_action_step
assert "prompt_sha256" in " ".join(human_action_step["privacy_contract"]), human_action_step
assert full_payload["data"]["world_class_evidence_ledger"]["summary"]["pending_count"] == 4, full_payload["data"]["world_class_evidence_ledger"]
assert full_payload["data"]["world_class_evidence_intake"]["summary"]["decision"] == "awaiting-submissions", full_payload["data"]["world_class_evidence_intake"]
assert full_payload["data"]["world_class_submission_review"]["summary"]["decision"] == "awaiting-submissions", full_payload["data"]["world_class_submission_review"]
assert full_payload["data"]["world_class_submission_review"]["summary"]["review_counts_submission_as_completion"] is False, full_payload["data"]["world_class_submission_review"]
assert full_payload["data"]["world_class_submission_review"]["summary"]["awaiting_submission_count"] == 4, full_payload["data"]["world_class_submission_review"]
assert full_payload["data"]["world_class_submission_review"]["summary"]["source_check_count"] >= 13, full_payload["data"]["world_class_submission_review"]
assert full_payload["data"]["world_class_submission_review"]["summary"]["source_blocked_count"] >= 6, full_payload["data"]["world_class_submission_review"]
human_review_items = full_payload["data"]["world_class_submission_review"]["items"]
human_review_item = next(item for item in human_review_items if item["evidence_key"] == "human-adjudication")
human_review_source = {item["field"]: item for item in human_review_item["source_checklist"]}
assert human_review_item["observed_state"]["raw_content_allowed"] is False, human_review_item
assert human_review_item["observed_state"]["raw_content_path_count"] == 0, human_review_item
assert human_review_source["raw_content_allowed"]["status"] == "pass", human_review_source
assert full_payload["data"]["world_class_operator_runbook"]["summary"]["decision"] == "collect-evidence", full_payload["data"]["world_class_operator_runbook"]
assert full_payload["data"]["world_class_operator_runbook"]["summary"]["runbook_counts_as_completion"] is False, full_payload["data"]["world_class_operator_runbook"]
assert full_payload["data"]["world_class_operator_runbook"]["summary"]["awaiting_submission_count"] == 4, full_payload["data"]["world_class_operator_runbook"]
assert full_payload["data"]["world_class_evidence_intake"]["summary"]["template_pass_count"] == 4, full_payload["data"]["world_class_evidence_intake"]
assert full_payload["data"]["world_class_evidence_intake"]["summary"]["operator_checklist_count"] == 4, full_payload["data"]["world_class_evidence_intake"]
assert full_payload["data"]["world_class_evidence_intake"]["summary"]["operator_checklist_ready_count"] == 0, full_payload["data"]["world_class_evidence_intake"]
assert full_payload["data"]["world_class_evidence_intake"]["summary"]["ready_to_claim_world_class"] is False, full_payload["data"]["world_class_evidence_intake"]
intake_checklist = full_payload["data"]["world_class_evidence_intake"]["operator_checklist"]
assert len(intake_checklist) == 4, intake_checklist
provider_checklist = next(item for item in intake_checklist if item["evidence_key"] == "provider-holdout")
assert provider_checklist["readiness"] == "awaiting-submission", provider_checklist
assert provider_checklist["submission_path"] == "evidence/world_class/submissions/provider-holdout.json", provider_checklist
assert provider_checklist["commands"]["validate_intake"] == "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions", provider_checklist
assert provider_checklist["commands"]["submission_review"] == "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions", provider_checklist
assert provider_checklist["commands"]["refresh_ledger"] == "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions", provider_checklist
assert "provider-backed model run" in provider_checklist["must_collect"]["provenance_requirements"], provider_checklist
assert any(
"output-exec --provider-runner openai" in step for step in provider_checklist["must_collect"]["runbook"]
), provider_checklist
assert full_payload["data"]["world_class_claim_guard"]["summary"]["decision"] == "claim-guard-pass-evidence-pending", full_payload["data"]["world_class_claim_guard"]
assert full_payload["data"]["world_class_claim_guard"]["summary"]["violation_count"] == 0, full_payload["data"]["world_class_claim_guard"]
assert full_payload["data"]["world_class_claim_guard"]["summary"]["ledger_pending_count"] == 4, full_payload["data"]["world_class_claim_guard"]
assert_world_class_action(full_payload)
if full_payload["data"]["skill_os2_coverage"]:
assert full_payload["data"]["skill_os2_coverage"]["summary"]["local_blueprint_ready"] is True, full_payload["data"]["skill_os2_coverage"]
assert full_payload["data"]["skill_os2_coverage"]["summary"]["public_world_class_ready"] is False, full_payload["data"]["skill_os2_coverage"]
@@ -429,6 +333,10 @@ def main() -> None:
assert "证据采集" in html, html
assert "action-evidence-grid" in html, html
assert "action-evidence-checks" in html, html
assert "action-repair-list" in html, html
assert "action-repair-row blocked" in html, html
assert "openai-api-key" in html, html
assert "model_executed_count" in html, html
assert "action-command-list" in html, html
assert "action-runbook-list" in html, html
assert "采集契约" in html, html