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

chore: refresh source check evidence reports

Browse Source
This commit is contained in:
yaojingang
2026-06-14 13:42:18 +08:00
parent 6ca6f9d609
commit 0936ce727e
24 changed files with 870 additions and 140 deletions
Download Patch File Download Diff File Expand all files Collapse all files
registry/index.json
+1 -1
View File
@@ -16,7 +16,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5"
"package_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a"
}
]
}
registry/packages/yao-meta-skill.json
+3 -3
View File
@@ -16,8 +16,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5",
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc"
"package_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a",
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e"
},
"compatibility": {
"openai": "pass",
@@ -48,7 +48,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc",
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
reports/install_simulation.json
+1 -1
View File
@@ -8,7 +8,7 @@
"installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
"summary": {
"archive_present": true,
"archive_entry_count": 576,
"archive_entry_count": 577,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
reports/output_execution_runs.json
+10 -10
View File
@@ -34,7 +34,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.5,
"duration_ms": 26.18,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -62,7 +62,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.91,
"duration_ms": 26.25,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -85,7 +85,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.88,
"duration_ms": 27.99,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -113,7 +113,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.4,
"duration_ms": 29.37,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -136,7 +136,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.19,
"duration_ms": 29.88,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -164,7 +164,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.57,
"duration_ms": 27.32,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -187,7 +187,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.78,
"duration_ms": 26.55,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -214,7 +214,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 29.9,
"duration_ms": 26.19,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -237,7 +237,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.33,
"duration_ms": 25.85,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -266,7 +266,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.23,
"duration_ms": 26.14,
"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 | 30.5 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 30.91 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 32.88 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 33.4 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 30.19 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 30.57 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 30.78 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 29.9 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 30.33 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 33.23 | 98 | 100.0 | pass |
| skill-package-contract | baseline | command | local-output-eval-runner | 26.18 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 26.25 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 27.99 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.37 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 29.88 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 27.32 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.55 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.19 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 25.85 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.14 | 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": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc",
"archive_entry_count": 576,
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e",
"archive_entry_count": 577,
"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: `11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc`
- Archive SHA256: `36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e`
- Failures: `0`
- Warnings: `0`
reports/registry_audit.json
+4 -4
View File
@@ -21,8 +21,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5",
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc"
"package_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a",
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e"
},
"compatibility": {
"openai": "pass",
@@ -53,7 +53,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc",
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -78,7 +78,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5"
"package_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a"
}
]
},
reports/registry_audit.md
+2 -2
View File
@@ -6,8 +6,8 @@
- Maturity: `governed`
- Owner: `Yao Team`
- License: `MIT`
- Package SHA256: `25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5`
- Archive SHA256: `11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc`
- Package SHA256: `52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a`
- Archive SHA256: `36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e`
- Install simulated: `True`
## Compatibility
reports/review-studio.html
+45 -7
View File
File diff suppressed because one or more lines are too long
reports/review-studio.json
+357 -45
View File
@@ -59,7 +59,7 @@
"key": "trust-report",
"label": "信任报告",
"status": "pass",
"detail": "0 secrets; 97 scripts; 3 network-capable scripts; 0 help smoke failures",
"detail": "0 secrets; 98 scripts; 3 network-capable scripts; 0 help smoke failures",
"evidence": "reports/security_trust_report.json",
"link": "security_trust_report.md"
},
@@ -851,7 +851,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 97
"file_count": 98
},
{
"path": "evals",
@@ -866,7 +866,7 @@
"file_count": 203
}
],
"file_count": 364,
"file_count": 365,
"folder_count": 4,
"distribution": [
{
@@ -891,7 +891,7 @@
},
{
"label": "scripts",
"value": 97
"value": 98
},
{
"label": "evals",
@@ -1020,7 +1020,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 97
"file_count": 98
},
{
"path": "evals",
@@ -1441,9 +1441,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 181,
"script_count": 97,
"internal_module_count": 20,
"scanned_files": 182,
"script_count": 98,
"internal_module_count": 21,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -1461,8 +1461,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 181,
"package_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5"
"package_hash_file_count": 182,
"package_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a"
},
"skill_atlas": {
"skill_count": 12,
@@ -1500,8 +1500,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5",
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc"
"package_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a",
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e"
},
"compatibility": {
"openai": "pass",
@@ -1532,7 +1532,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc",
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1548,8 +1548,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc",
"archive_entry_count": 576,
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e",
"archive_entry_count": 577,
"failure_count": 0,
"warning_count": 0
},
@@ -1560,7 +1560,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 576,
"archive_entry_count": 577,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1627,12 +1627,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc"
"to": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5"
"to": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a"
}
]
},
@@ -3811,7 +3811,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.5,
"duration_ms": 26.18,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3839,7 +3839,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.91,
"duration_ms": 26.25,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3862,7 +3862,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.88,
"duration_ms": 27.99,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3890,7 +3890,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.4,
"duration_ms": 29.37,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3913,7 +3913,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.19,
"duration_ms": 29.88,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3941,7 +3941,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.57,
"duration_ms": 27.32,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3964,7 +3964,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.78,
"duration_ms": 26.55,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3991,7 +3991,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 29.9,
"duration_ms": 26.19,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4014,7 +4014,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.33,
"duration_ms": 25.85,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4043,7 +4043,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.23,
"duration_ms": 26.14,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5272,7 +5272,7 @@
"label": "Trust Security",
"status": "pass",
"objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
"current": "97 scripts; secrets 0; help failures 0",
"current": "98 scripts; secrets 0; help failures 0",
"command": "python3 scripts/yao.py trust .",
"test": "python3 tests/verify_trust_check.py",
"evidence": [
@@ -5346,7 +5346,7 @@
"label": "Registry Distribution",
"status": "pass",
"objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
"current": "archive entries 576; install failures 0",
"current": "archive entries 577; 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": [
@@ -10632,9 +10632,9 @@
"ok": true,
"skill_dir": ".",
"summary": {
"scanned_files": 181,
"script_count": 97,
"internal_module_count": 20,
"scanned_files": 182,
"script_count": 98,
"internal_module_count": 21,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -10652,8 +10652,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 181,
"package_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5"
"package_hash_file_count": 182,
"package_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a"
},
"failures": [],
"warnings": [],
@@ -11936,6 +11936,20 @@
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/world_class_source_checks.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by world-class evidence reports to keep source-evidence readiness checks consistent.",
"has_argparse": false,
"has_main_guard": false,
"uses_input": false,
"uses_network": false,
"uses_file_write": false,
"uses_subprocess": false,
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/yao.py",
"interface": "cli",
@@ -12069,7 +12083,7 @@
"checked_count": 77,
"passed_count": 77,
"failed_count": 0,
"skipped_count": 20,
"skipped_count": 21,
"failed_scripts": [],
"results": [
{
@@ -12900,6 +12914,10 @@
"path": "scripts/world_class_evidence_contract.py",
"reason": "internal module"
},
{
"path": "scripts/world_class_source_checks.py",
"reason": "internal module"
},
{
"path": "scripts/yao_cli_config.py",
"reason": "internal module"
@@ -16935,6 +16953,9 @@
"fix_submission_count": 0,
"unmatched_submission_count": 0,
"invalid_submission_count": 0,
"source_check_count": 13,
"source_pass_count": 6,
"source_blocked_count": 7,
"ready_to_claim_world_class": false,
"review_counts_submission_as_completion": false,
"decision": "awaiting-submissions"
@@ -16966,6 +16987,41 @@
"token_observed_count": 0,
"accepted": false
},
"source_checklist": [
{
"evidence_key": "provider-holdout",
"label": "Provider model run",
"field": "model_executed_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Run provider-backed output-exec with real credentials."
},
{
"evidence_key": "provider-holdout",
"label": "Timing observed",
"field": "timing_observed_count",
"expected": ">0",
"actual": 10,
"status": "pass",
"source_accepted": false,
"next_action": "Provider execution should record timing metadata."
},
{
"evidence_key": "provider-holdout",
"label": "Token usage observed",
"field": "token_observed_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Provider execution should return non-estimated token usage."
}
],
"source_check_count": 3,
"source_pass_count": 1,
"source_blocked_count": 2,
"success_checks": [
"reports/output_execution_runs.json summary.model_executed_count > 0",
"reports/output_execution_runs.json summary.timing_observed_count > 0",
@@ -17002,6 +17058,51 @@
"answer_revealed_count": 0,
"accepted": false
},
"source_checklist": [
{
"evidence_key": "human-adjudication",
"label": "Review pairs exist",
"field": "pair_count",
"expected": ">0",
"actual": 5,
"status": "pass",
"source_accepted": false,
"next_action": "Generate the blind A/B review pack."
},
{
"evidence_key": "human-adjudication",
"label": "No pending decisions",
"field": "pending_count",
"expected": "==0",
"actual": 5,
"status": "blocked",
"source_accepted": false,
"next_action": "Record a reviewer choice for every pair."
},
{
"evidence_key": "human-adjudication",
"label": "Judgments complete",
"field": "judgment_count",
"expected": "==pair_count",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Every pair needs one valid human judgment."
},
{
"evidence_key": "human-adjudication",
"label": "No invalid decisions",
"field": "invalid_decision_count",
"expected": "==0",
"actual": 0,
"status": "pass",
"source_accepted": false,
"next_action": "Fix malformed winner/confidence entries."
}
],
"source_check_count": 4,
"source_pass_count": 2,
"source_blocked_count": 2,
"success_checks": [
"reports/output_review_adjudication.json summary.pending_count == 0",
"reports/output_review_adjudication.json summary.judgment_count == summary.pair_count",
@@ -17040,6 +17141,41 @@
"failure_count": 0,
"accepted": false
},
"source_checklist": [
{
"evidence_key": "native-permission-enforcement",
"label": "Native enforcement",
"field": "native_enforcement_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Collect real target-client or external runtime guard proof."
},
{
"evidence_key": "native-permission-enforcement",
"label": "Probe failures",
"field": "failure_count",
"expected": "==0",
"actual": 0,
"status": "pass",
"source_accepted": false,
"next_action": "Runtime permission probes must stay clean."
},
{
"evidence_key": "native-permission-enforcement",
"label": "Installer support",
"field": "installer_enforcement_ready",
"expected": "true",
"actual": true,
"status": "pass",
"source_accepted": false,
"next_action": "Installer enforcement is supporting evidence, not native proof."
}
],
"source_check_count": 3,
"source_pass_count": 2,
"source_blocked_count": 1,
"success_checks": [
"reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
"reports/runtime_permission_probes.json summary.failure_count == 0",
@@ -17075,6 +17211,41 @@
"risk_band": "low",
"accepted": false
},
"source_checklist": [
{
"evidence_key": "native-client-telemetry",
"label": "External events",
"field": "external_source_events",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Import at least one metadata-only event from a real client."
},
{
"evidence_key": "native-client-telemetry",
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
{
"evidence_key": "native-client-telemetry",
"label": "Raw content blocked",
"field": "raw_content_allowed",
"expected": "false",
"actual": false,
"status": "pass",
"source_accepted": false,
"next_action": "Telemetry must stay metadata-only."
}
],
"source_check_count": 3,
"source_pass_count": 1,
"source_blocked_count": 2,
"success_checks": [
"reports/adoption_drift_report.json summary.source_types.external > 0",
"reports/adoption_drift_report.json summary.adoption_sample_count > 0",
@@ -17110,6 +17281,9 @@
"ready_for_ledger_review_count": 0,
"valid_packet_source_incomplete_count": 0,
"invalid_submission_count": 0,
"source_check_count": 13,
"source_pass_count": 6,
"source_blocked_count": 7,
"ready_to_claim_world_class": false,
"runbook_counts_as_completion": false,
"decision": "collect-evidence"
@@ -17172,6 +17346,38 @@
"token_observed_count": 0,
"accepted": false
},
"source_checklist": [
{
"evidence_key": "provider-holdout",
"label": "Provider model run",
"field": "model_executed_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Run provider-backed output-exec with real credentials."
},
{
"evidence_key": "provider-holdout",
"label": "Timing observed",
"field": "timing_observed_count",
"expected": ">0",
"actual": 10,
"status": "pass",
"source_accepted": false,
"next_action": "Provider execution should record timing metadata."
},
{
"evidence_key": "provider-holdout",
"label": "Token usage observed",
"field": "token_observed_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Provider execution should return non-estimated token usage."
}
],
"submission_state": {
"status": "missing",
"path": "evidence/world_class/submissions/provider-holdout.json",
@@ -17244,6 +17450,48 @@
"answer_revealed_count": 0,
"accepted": false
},
"source_checklist": [
{
"evidence_key": "human-adjudication",
"label": "Review pairs exist",
"field": "pair_count",
"expected": ">0",
"actual": 5,
"status": "pass",
"source_accepted": false,
"next_action": "Generate the blind A/B review pack."
},
{
"evidence_key": "human-adjudication",
"label": "No pending decisions",
"field": "pending_count",
"expected": "==0",
"actual": 5,
"status": "blocked",
"source_accepted": false,
"next_action": "Record a reviewer choice for every pair."
},
{
"evidence_key": "human-adjudication",
"label": "Judgments complete",
"field": "judgment_count",
"expected": "==pair_count",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Every pair needs one valid human judgment."
},
{
"evidence_key": "human-adjudication",
"label": "No invalid decisions",
"field": "invalid_decision_count",
"expected": "==0",
"actual": 0,
"status": "pass",
"source_accepted": false,
"next_action": "Fix malformed winner/confidence entries."
}
],
"submission_state": {
"status": "missing",
"path": "evidence/world_class/submissions/human-adjudication.json",
@@ -17319,6 +17567,38 @@
"failure_count": 0,
"accepted": false
},
"source_checklist": [
{
"evidence_key": "native-permission-enforcement",
"label": "Native enforcement",
"field": "native_enforcement_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Collect real target-client or external runtime guard proof."
},
{
"evidence_key": "native-permission-enforcement",
"label": "Probe failures",
"field": "failure_count",
"expected": "==0",
"actual": 0,
"status": "pass",
"source_accepted": false,
"next_action": "Runtime permission probes must stay clean."
},
{
"evidence_key": "native-permission-enforcement",
"label": "Installer support",
"field": "installer_enforcement_ready",
"expected": "true",
"actual": true,
"status": "pass",
"source_accepted": false,
"next_action": "Installer enforcement is supporting evidence, not native proof."
}
],
"submission_state": {
"status": "missing",
"path": "evidence/world_class/submissions/native-permission-enforcement.json",
@@ -17388,6 +17668,38 @@
"risk_band": "low",
"accepted": false
},
"source_checklist": [
{
"evidence_key": "native-client-telemetry",
"label": "External events",
"field": "external_source_events",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Import at least one metadata-only event from a real client."
},
{
"evidence_key": "native-client-telemetry",
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
{
"evidence_key": "native-client-telemetry",
"label": "Raw content blocked",
"field": "raw_content_allowed",
"expected": "false",
"actual": false,
"status": "pass",
"source_accepted": false,
"next_action": "Telemetry must stay metadata-only."
}
],
"submission_state": {
"status": "missing",
"path": "evidence/world_class/submissions/native-client-telemetry.json",
@@ -17783,8 +18095,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5",
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc"
"package_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a",
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e"
},
"compatibility": {
"openai": "pass",
@@ -17815,7 +18127,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc",
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -17840,7 +18152,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5"
"package_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a"
}
]
},
@@ -17863,8 +18175,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc",
"archive_entry_count": 576,
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e",
"archive_entry_count": 577,
"failure_count": 0,
"warning_count": 0
},
@@ -18529,7 +18841,7 @@
"installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
"summary": {
"archive_present": true,
"archive_entry_count": 576,
"archive_entry_count": 577,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -18871,12 +19183,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc"
"to": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5"
"to": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a"
}
]
},
reports/review-viewer.json
+17 -17
View File
@@ -438,7 +438,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 97
"file_count": 98
},
{
"path": "evals",
@@ -453,7 +453,7 @@
"file_count": 203
}
],
"file_count": 364,
"file_count": 365,
"folder_count": 4,
"distribution": [
{
@@ -478,7 +478,7 @@
},
{
"label": "scripts",
"value": 97
"value": 98
},
{
"label": "evals",
@@ -607,7 +607,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 97
"file_count": 98
},
{
"path": "evals",
@@ -1028,9 +1028,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 181,
"script_count": 97,
"internal_module_count": 20,
"scanned_files": 182,
"script_count": 98,
"internal_module_count": 21,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -1048,8 +1048,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 181,
"package_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5"
"package_hash_file_count": 182,
"package_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a"
},
"skill_atlas": {
"skill_count": 12,
@@ -1087,8 +1087,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5",
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc"
"package_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a",
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e"
},
"compatibility": {
"openai": "pass",
@@ -1119,7 +1119,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc",
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1135,8 +1135,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc",
"archive_entry_count": 576,
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e",
"archive_entry_count": 577,
"failure_count": 0,
"warning_count": 0
},
@@ -1147,7 +1147,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 576,
"archive_entry_count": 577,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1214,12 +1214,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc"
"to": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5"
"to": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a"
}
]
},
reports/security_trust_report.json
+24 -6
View File
@@ -2,9 +2,9 @@
"ok": true,
"skill_dir": ".",
"summary": {
"scanned_files": 181,
"script_count": 97,
"internal_module_count": 20,
"scanned_files": 182,
"script_count": 98,
"internal_module_count": 21,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -22,8 +22,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 181,
"package_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5"
"package_hash_file_count": 182,
"package_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a"
},
"failures": [],
"warnings": [],
@@ -1306,6 +1306,20 @@
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/world_class_source_checks.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by world-class evidence reports to keep source-evidence readiness checks consistent.",
"has_argparse": false,
"has_main_guard": false,
"uses_input": false,
"uses_network": false,
"uses_file_write": false,
"uses_subprocess": false,
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/yao.py",
"interface": "cli",
@@ -1439,7 +1453,7 @@
"checked_count": 77,
"passed_count": 77,
"failed_count": 0,
"skipped_count": 20,
"skipped_count": 21,
"failed_scripts": [],
"results": [
{
@@ -2270,6 +2284,10 @@
"path": "scripts/world_class_evidence_contract.py",
"reason": "internal module"
},
{
"path": "scripts/world_class_source_checks.py",
"reason": "internal module"
},
{
"path": "scripts/yao_cli_config.py",
"reason": "internal module"
reports/security_trust_report.md
+6 -5
View File
@@ -1,9 +1,9 @@
# Security Trust Report
- OK: `True`
- Scanned files: `181`
- Scripts: `97`
- Internal script modules: `20`
- Scanned files: `182`
- Scripts: `98`
- Internal script modules: `21`
- Secret findings: `0`
- Network-capable scripts: `3`
- Network policy covered scripts: `3`
@@ -15,8 +15,8 @@
- CLI help smoke failures: `0`
- Interactive scripts: `0`
- Package hash scope: `source-contract-without-generated-reports`
- Package hash files: `181`
- Package SHA256: `25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5`
- Package hash files: `182`
- Package SHA256: `52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a`
## Failures
@@ -152,6 +152,7 @@
| scripts/validate_skill.py | cli | False | True | True | False | False | False | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/verify_package.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/world_class_evidence_contract.py | internal-module | True | False | False | False | False | False | False | Imported by world-class evidence reports to share intake validation and artifact integrity checks. |
| scripts/world_class_source_checks.py | internal-module | True | False | False | False | False | False | False | Imported by world-class evidence reports to keep source-evidence readiness checks consistent. |
| scripts/yao.py | cli | False | True | True | False | False | False | True | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/yao_cli_config.py | internal-module | True | False | False | False | False | False | False | Imported by yao.py for CLI target maps and side-effect-free shaping helpers. |
| scripts/yao_cli_create_commands.py | internal-module | True | True | False | False | False | False | False | Imported by yao.py to keep skill creation and quickstart command handlers out of the CLI orchestrator. |
reports/skill-overview.html
+1 -1
View File
@@ -771,7 +771,7 @@
<p><span data-lang="zh-CN">让 reviewer 快速确认关键文件、目录和资产分布。</span><span data-lang="en">Lets reviewers confirm key files, directories, and asset distribution quickly.</span></p>
</div>
<div class="two-col">
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text x="20" y="30" class="chart-title">资产分布</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-0.8" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-1.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-2.3" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="24.1 75.9" stroke-dashoffset="-3.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="72.9 27.1" stroke-dashoffset="-27.1" pathLength="100" transform="rotate(-90 130 130)"/><text x="130" y="136" text-anchor="middle">364项</text><text x="235" y="78">SKILL.md</text><text x="235" y="100">README.md</text><text x="235" y="122">agents/interface.yaml</text><text x="235" y="144">manifest.json</text><text x="235" y="166">references</text><text x="235" y="188">scripts</text></svg><figcaption>资产分布图展示当前包体的文件和目录重心。</figcaption></figure>
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text x="20" y="30" class="chart-title">资产分布</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-0.7" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-1.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.7 99.3" stroke-dashoffset="-2.2" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="23.9 76.1" stroke-dashoffset="-3.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="73.1 26.9" stroke-dashoffset="-26.9" pathLength="100" transform="rotate(-90 130 130)"/><text x="130" y="136" text-anchor="middle">365项</text><text x="235" y="78">SKILL.md</text><text x="235" y="100">README.md</text><text x="235" y="122">agents/interface.yaml</text><text x="235" y="144">manifest.json</text><text x="235" y="166">references</text><text x="235" y="188">scripts</text></svg><figcaption>资产分布图展示当前包体的文件和目录重心。</figcaption></figure>
<table>
<thead><tr><th><span data-lang="zh-CN">路径</span><span data-lang="en">Path</span></th><th><span data-lang="zh-CN">作用</span><span data-lang="en">Role</span></th><th><span data-lang="zh-CN">类型</span><span data-lang="en">Type</span></th></tr></thead>
<tbody><tr><td>SKILL.md</td><td><span data-lang="zh-CN">Skill 入口文件</span><span data-lang="en">Skill entrypoint</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>README.md</td><td><span data-lang="zh-CN">人类可读使用说明</span><span data-lang="en">Human-readable usage guide</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>agents/interface.yaml</td><td><span data-lang="zh-CN">跨平台接口元数据</span><span data-lang="en">Neutral interface metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>manifest.json</td><td><span data-lang="zh-CN">生命周期与打包元数据</span><span data-lang="en">Lifecycle and portability metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>references</td><td><span data-lang="zh-CN">扩展指导与复用资料</span><span data-lang="en">Extended guidance and reusable notes</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>scripts</td><td><span data-lang="zh-CN">确定性脚本或本地工具</span><span data-lang="en">Deterministic helpers or local tooling</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>evals</td><td><span data-lang="zh-CN">触发与质量检查</span><span data-lang="en">Trigger and quality checks</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>reports</td><td><span data-lang="zh-CN">生成的证据与总结报告</span><span data-lang="en">Generated evidence and overview artifacts</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr></tbody>
reports/skill-overview.json
+17 -17
View File
@@ -437,7 +437,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 97
"file_count": 98
},
{
"path": "evals",
@@ -452,7 +452,7 @@
"file_count": 203
}
],
"file_count": 364,
"file_count": 365,
"folder_count": 4,
"distribution": [
{
@@ -477,7 +477,7 @@
},
{
"label": "scripts",
"value": 97
"value": 98
},
{
"label": "evals",
@@ -606,7 +606,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 97
"file_count": 98
},
{
"path": "evals",
@@ -1027,9 +1027,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 181,
"script_count": 97,
"internal_module_count": 20,
"scanned_files": 182,
"script_count": 98,
"internal_module_count": 21,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -1047,8 +1047,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 181,
"package_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5"
"package_hash_file_count": 182,
"package_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a"
},
"skill_atlas": {
"skill_count": 12,
@@ -1086,8 +1086,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5",
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc"
"package_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a",
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e"
},
"compatibility": {
"openai": "pass",
@@ -1118,7 +1118,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc",
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1134,8 +1134,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc",
"archive_entry_count": 576,
"archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e",
"archive_entry_count": 577,
"failure_count": 0,
"warning_count": 0
},
@@ -1146,7 +1146,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 576,
"archive_entry_count": 577,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1213,12 +1213,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc"
"to": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5"
"to": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a"
}
]
},
reports/skill_os2_coverage.json
+2 -2
View File
@@ -122,7 +122,7 @@
"label": "Trust Security",
"status": "pass",
"objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
"current": "97 scripts; secrets 0; help failures 0",
"current": "98 scripts; secrets 0; help failures 0",
"command": "python3 scripts/yao.py trust .",
"test": "python3 tests/verify_trust_check.py",
"evidence": [
@@ -196,7 +196,7 @@
"label": "Registry Distribution",
"status": "pass",
"objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
"current": "archive entries 576; install failures 0",
"current": "archive entries 577; 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
@@ -21,9 +21,9 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
| Skill IR | `pass` | schema 2.0.0; targets 5 | `python3 scripts/yao.py skill-ir .` | `python3 tests/verify_skill_ir.py` |
| Output Eval Lab | `pass` | 5 cases; delta 100.0; execution 10 | `python3 scripts/yao.py output-exec . && python3 scripts/yao.py output-review .` | `python3 tests/verify_output_eval_lab.py` |
| Runtime Conformance | `pass` | 5/5 targets pass | `python3 scripts/yao.py conformance .` | `python3 tests/verify_conformance_suite.py` |
| Trust Security | `pass` | 97 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
| Trust Security | `pass` | 98 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 576; 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 577; 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
+2 -2
View File
@@ -70,12 +70,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc"
"to": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5"
"to": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a"
}
]
},
reports/world_class_operator_runbook.html
+11 -2
View File
@@ -22,7 +22,7 @@
h3 { margin:4px 0 10px; font-size:22px; }
h4 { margin:0 0 8px; font-size:16px; }
.lede { max-width:800px; color:var(--muted); font-size:20px; }
.stats { display:grid; grid-template-columns:repeat(4, minmax(0,1fr)); gap:12px; margin-top:26px; }
.stats { display:grid; grid-template-columns:repeat(5, minmax(0,1fr)); gap:12px; margin-top:26px; }
.stats article, .panel, .item-card { border:1px solid var(--line); border-radius:8px; background:#fff; }
.stats article { padding:16px; }
.stats span, .item-card span, .muted { color:var(--muted); }
@@ -42,6 +42,11 @@
.mini-grid { display:grid; grid-template-columns:repeat(3, minmax(0,1fr)); gap:12px; margin-top:14px; }
.mini-grid section, .panel { background:var(--soft); border-radius:8px; padding:14px; min-width:0; }
.mini-grid li, .panel li { overflow-wrap:anywhere; }
.source-panel { background:var(--soft); border-radius:8px; padding:14px; min-width:0; }
.source-checks { list-style:none; padding:0; margin:0; display:grid; gap:8px; }
.source-check { border-top:1px solid var(--line); padding-top:8px; display:grid; gap:3px; }
.source-check span { color:var(--ink); }
.source-check code, .source-check small { overflow-wrap:anywhere; }
@media (max-width:820px) { .stats, .mini-grid { grid-template-columns:1fr; } h1 { font-size:38px; } .topbar-inner { align-items:flex-start; flex-direction:column; } }
</style>
</head>
@@ -52,7 +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></strong></article><article><span>Invalid</span><strong></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></strong></article><article><span>Source</span><strong>6/13</strong></article><article><span>Invalid</span><strong></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">
@@ -69,6 +74,7 @@
<section><h4>Success Checks</h4><ul><li>reports/output_execution_runs.json summary.model_executed_count &gt; 0</li><li>reports/output_execution_runs.json summary.timing_observed_count &gt; 0</li><li>reports/output_execution_runs.json summary.token_observed_count &gt; 0</li><li>reports/skill_os2_audit.json item provider-holdout status becomes pass</li></ul></section>
<section><h4>Privacy</h4><ul><li>Do not commit provider credentials or environment dumps.</li><li>The output execution report records output hashes and aggregate run metadata, not raw provider prompts.</li></ul></section>
</div>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>Provider model run</span><code>model_executed_count: / &gt;0</code><small>Run provider-backed output-exec with real credentials.</small></li><li class='source-check pass'><span>Timing observed</span><code>timing_observed_count: 10 / &gt;0</code><small>Provider execution should record timing metadata.</small></li><li class='source-check blocked'><span>Token usage observed</span><code>token_observed_count: / &gt;0</code><small>Provider execution should return non-estimated token usage.</small></li></ul></section>
</article><article class="item-card awaiting-submission">
<header><span>human · awaiting-submission</span><h3>Human Adjudication</h3></header>
<p>No evidence packet has been submitted for review.</p>
@@ -83,6 +89,7 @@
<section><h4>Success Checks</h4><ul><li>reports/output_review_adjudication.json summary.pending_count == 0</li><li>reports/output_review_adjudication.json summary.judgment_count == summary.pair_count</li><li>reports/output_review_adjudication.json summary.invalid_decision_count == 0</li><li>reports/skill_os2_audit.json item human-adjudication status becomes pass</li></ul></section>
<section><h4>Privacy</h4><ul><li>Reviewer decisions should not include raw user data or private customer detail.</li><li>Keep the answer key separate until after decisions are recorded.</li></ul></section>
</div>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check pass'><span>Review pairs exist</span><code>pair_count: 5 / &gt;0</code><small>Generate the blind A/B review pack.</small></li><li class='source-check blocked'><span>No pending decisions</span><code>pending_count: 5 / ==0</code><small>Record a reviewer choice for every pair.</small></li><li class='source-check blocked'><span>Judgments complete</span><code>judgment_count: / ==pair_count</code><small>Every pair needs one valid human judgment.</small></li><li class='source-check pass'><span>No invalid decisions</span><code>invalid_decision_count: / ==0</code><small>Fix malformed winner/confidence entries.</small></li></ul></section>
</article><article class="item-card awaiting-submission">
<header><span>external · awaiting-submission</span><h3>Native Permission Enforcement</h3></header>
<p>No evidence packet has been submitted for review.</p>
@@ -97,6 +104,7 @@
<section><h4>Success Checks</h4><ul><li>reports/runtime_permission_probes.json summary.native_enforcement_count &gt; 0</li><li>reports/runtime_permission_probes.json summary.failure_count == 0</li><li>reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence</li><li>reports/skill_os2_audit.json item native-permission-enforcement status becomes pass</li></ul></section>
<section><h4>Privacy</h4><ul><li>Do not mark native_enforcement true for metadata-only fallbacks.</li><li>Keep residual risks visible for targets that still rely on operator enforcement.</li></ul></section>
</div>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>Native enforcement</span><code>native_enforcement_count: / &gt;0</code><small>Collect real target-client or external runtime guard proof.</small></li><li class='source-check pass'><span>Probe failures</span><code>failure_count: / ==0</code><small>Runtime permission probes must stay clean.</small></li><li class='source-check pass'><span>Installer support</span><code>installer_enforcement_ready: True / true</code><small>Installer enforcement is supporting evidence, not native proof.</small></li></ul></section>
</article><article class="item-card awaiting-submission">
<header><span>external · awaiting-submission</span><h3>Native Client Telemetry</h3></header>
<p>No evidence packet has been submitted for review.</p>
@@ -111,6 +119,7 @@
<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>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>External events</span><code>external_source_events: / &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: / &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</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
+141
View File
@@ -11,6 +11,9 @@
"ready_for_ledger_review_count": 0,
"valid_packet_source_incomplete_count": 0,
"invalid_submission_count": 0,
"source_check_count": 13,
"source_pass_count": 6,
"source_blocked_count": 7,
"ready_to_claim_world_class": false,
"runbook_counts_as_completion": false,
"decision": "collect-evidence"
@@ -73,6 +76,38 @@
"token_observed_count": 0,
"accepted": false
},
"source_checklist": [
{
"evidence_key": "provider-holdout",
"label": "Provider model run",
"field": "model_executed_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Run provider-backed output-exec with real credentials."
},
{
"evidence_key": "provider-holdout",
"label": "Timing observed",
"field": "timing_observed_count",
"expected": ">0",
"actual": 10,
"status": "pass",
"source_accepted": false,
"next_action": "Provider execution should record timing metadata."
},
{
"evidence_key": "provider-holdout",
"label": "Token usage observed",
"field": "token_observed_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Provider execution should return non-estimated token usage."
}
],
"submission_state": {
"status": "missing",
"path": "evidence/world_class/submissions/provider-holdout.json",
@@ -145,6 +180,48 @@
"answer_revealed_count": 0,
"accepted": false
},
"source_checklist": [
{
"evidence_key": "human-adjudication",
"label": "Review pairs exist",
"field": "pair_count",
"expected": ">0",
"actual": 5,
"status": "pass",
"source_accepted": false,
"next_action": "Generate the blind A/B review pack."
},
{
"evidence_key": "human-adjudication",
"label": "No pending decisions",
"field": "pending_count",
"expected": "==0",
"actual": 5,
"status": "blocked",
"source_accepted": false,
"next_action": "Record a reviewer choice for every pair."
},
{
"evidence_key": "human-adjudication",
"label": "Judgments complete",
"field": "judgment_count",
"expected": "==pair_count",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Every pair needs one valid human judgment."
},
{
"evidence_key": "human-adjudication",
"label": "No invalid decisions",
"field": "invalid_decision_count",
"expected": "==0",
"actual": 0,
"status": "pass",
"source_accepted": false,
"next_action": "Fix malformed winner/confidence entries."
}
],
"submission_state": {
"status": "missing",
"path": "evidence/world_class/submissions/human-adjudication.json",
@@ -220,6 +297,38 @@
"failure_count": 0,
"accepted": false
},
"source_checklist": [
{
"evidence_key": "native-permission-enforcement",
"label": "Native enforcement",
"field": "native_enforcement_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Collect real target-client or external runtime guard proof."
},
{
"evidence_key": "native-permission-enforcement",
"label": "Probe failures",
"field": "failure_count",
"expected": "==0",
"actual": 0,
"status": "pass",
"source_accepted": false,
"next_action": "Runtime permission probes must stay clean."
},
{
"evidence_key": "native-permission-enforcement",
"label": "Installer support",
"field": "installer_enforcement_ready",
"expected": "true",
"actual": true,
"status": "pass",
"source_accepted": false,
"next_action": "Installer enforcement is supporting evidence, not native proof."
}
],
"submission_state": {
"status": "missing",
"path": "evidence/world_class/submissions/native-permission-enforcement.json",
@@ -289,6 +398,38 @@
"risk_band": "low",
"accepted": false
},
"source_checklist": [
{
"evidence_key": "native-client-telemetry",
"label": "External events",
"field": "external_source_events",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Import at least one metadata-only event from a real client."
},
{
"evidence_key": "native-client-telemetry",
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
{
"evidence_key": "native-client-telemetry",
"label": "Raw content blocked",
"field": "raw_content_allowed",
"expected": "false",
"actual": false,
"status": "pass",
"source_accepted": false,
"next_action": "Telemetry must stay metadata-only."
}
],
"submission_state": {
"status": "missing",
"path": "evidence/world_class/submissions/native-client-telemetry.json",
reports/world_class_operator_runbook.md
+33
View File
@@ -73,6 +73,14 @@ This runbook coordinates evidence collection only. It does not accept submission
- reports/world_class_evidence_intake.json
- reports/world_class_evidence_intake.md
### Source Evidence Snapshot
| Check | Current | Expected | Status |
| --- | --- | --- | --- |
| Provider model run | `0` | `>0` | `blocked` |
| Timing observed | `10` | `>0` | `pass` |
| Token usage observed | `0` | `>0` | `blocked` |
## Human Adjudication
- objective: Record real blind A/B reviewer decisions before claiming human output review completion.
@@ -118,6 +126,15 @@ This runbook coordinates evidence collection only. It does not accept submission
- reports/world_class_evidence_intake.json
- reports/world_class_evidence_intake.md
### Source Evidence Snapshot
| Check | Current | Expected | Status |
| --- | --- | --- | --- |
| Review pairs exist | `5` | `>0` | `pass` |
| No pending decisions | `5` | `==0` | `blocked` |
| Judgments complete | `0` | `==pair_count` | `blocked` |
| No invalid decisions | `0` | `==0` | `pass` |
## Native Permission Enforcement
- objective: Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.
@@ -164,6 +181,14 @@ This runbook coordinates evidence collection only. It does not accept submission
- reports/world_class_evidence_intake.json
- reports/world_class_evidence_intake.md
### Source Evidence Snapshot
| Check | Current | Expected | Status |
| --- | --- | --- | --- |
| Native enforcement | `0` | `>0` | `blocked` |
| Probe failures | `0` | `==0` | `pass` |
| Installer support | `True` | `true` | `pass` |
## Native Client Telemetry
- objective: Import production metadata-only events from a real external client into the local drift loop.
@@ -207,6 +232,14 @@ This runbook coordinates evidence collection only. It does not accept submission
- reports/world_class_evidence_intake.json
- reports/world_class_evidence_intake.md
### Source Evidence Snapshot
| Check | Current | Expected | Status |
| --- | --- | --- | --- |
| External events | `0` | `>0` | `blocked` |
| Adoption sample | `0` | `>0` | `blocked` |
| Raw content blocked | `False` | `false` | `pass` |
## Boundary
- Planned work, draft packets, metadata fallback, pending human decisions, and local command runners do not count as completion.
reports/world_class_submission_review.json
+153
View File
@@ -12,6 +12,9 @@
"fix_submission_count": 0,
"unmatched_submission_count": 0,
"invalid_submission_count": 0,
"source_check_count": 13,
"source_pass_count": 6,
"source_blocked_count": 7,
"ready_to_claim_world_class": false,
"review_counts_submission_as_completion": false,
"decision": "awaiting-submissions"
@@ -43,6 +46,41 @@
"token_observed_count": 0,
"accepted": false
},
"source_checklist": [
{
"evidence_key": "provider-holdout",
"label": "Provider model run",
"field": "model_executed_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Run provider-backed output-exec with real credentials."
},
{
"evidence_key": "provider-holdout",
"label": "Timing observed",
"field": "timing_observed_count",
"expected": ">0",
"actual": 10,
"status": "pass",
"source_accepted": false,
"next_action": "Provider execution should record timing metadata."
},
{
"evidence_key": "provider-holdout",
"label": "Token usage observed",
"field": "token_observed_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Provider execution should return non-estimated token usage."
}
],
"source_check_count": 3,
"source_pass_count": 1,
"source_blocked_count": 2,
"success_checks": [
"reports/output_execution_runs.json summary.model_executed_count > 0",
"reports/output_execution_runs.json summary.timing_observed_count > 0",
@@ -79,6 +117,51 @@
"answer_revealed_count": 0,
"accepted": false
},
"source_checklist": [
{
"evidence_key": "human-adjudication",
"label": "Review pairs exist",
"field": "pair_count",
"expected": ">0",
"actual": 5,
"status": "pass",
"source_accepted": false,
"next_action": "Generate the blind A/B review pack."
},
{
"evidence_key": "human-adjudication",
"label": "No pending decisions",
"field": "pending_count",
"expected": "==0",
"actual": 5,
"status": "blocked",
"source_accepted": false,
"next_action": "Record a reviewer choice for every pair."
},
{
"evidence_key": "human-adjudication",
"label": "Judgments complete",
"field": "judgment_count",
"expected": "==pair_count",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Every pair needs one valid human judgment."
},
{
"evidence_key": "human-adjudication",
"label": "No invalid decisions",
"field": "invalid_decision_count",
"expected": "==0",
"actual": 0,
"status": "pass",
"source_accepted": false,
"next_action": "Fix malformed winner/confidence entries."
}
],
"source_check_count": 4,
"source_pass_count": 2,
"source_blocked_count": 2,
"success_checks": [
"reports/output_review_adjudication.json summary.pending_count == 0",
"reports/output_review_adjudication.json summary.judgment_count == summary.pair_count",
@@ -117,6 +200,41 @@
"failure_count": 0,
"accepted": false
},
"source_checklist": [
{
"evidence_key": "native-permission-enforcement",
"label": "Native enforcement",
"field": "native_enforcement_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Collect real target-client or external runtime guard proof."
},
{
"evidence_key": "native-permission-enforcement",
"label": "Probe failures",
"field": "failure_count",
"expected": "==0",
"actual": 0,
"status": "pass",
"source_accepted": false,
"next_action": "Runtime permission probes must stay clean."
},
{
"evidence_key": "native-permission-enforcement",
"label": "Installer support",
"field": "installer_enforcement_ready",
"expected": "true",
"actual": true,
"status": "pass",
"source_accepted": false,
"next_action": "Installer enforcement is supporting evidence, not native proof."
}
],
"source_check_count": 3,
"source_pass_count": 2,
"source_blocked_count": 1,
"success_checks": [
"reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
"reports/runtime_permission_probes.json summary.failure_count == 0",
@@ -152,6 +270,41 @@
"risk_band": "low",
"accepted": false
},
"source_checklist": [
{
"evidence_key": "native-client-telemetry",
"label": "External events",
"field": "external_source_events",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Import at least one metadata-only event from a real client."
},
{
"evidence_key": "native-client-telemetry",
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
{
"evidence_key": "native-client-telemetry",
"label": "Raw content blocked",
"field": "raw_content_allowed",
"expected": "false",
"actual": false,
"status": "pass",
"source_accepted": false,
"next_action": "Telemetry must stay metadata-only."
}
],
"source_check_count": 3,
"source_pass_count": 1,
"source_blocked_count": 2,
"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
+25
View File
@@ -40,6 +40,12 @@ This report is a read-only reviewer queue. It does not accept evidence or make w
#### Source Checks
- Provider model run: 0 / >0 => blocked
- Timing observed: 10 / >0 => pass
- Token usage observed: 0 / >0 => blocked
#### Completion Assertions
- reports/output_execution_runs.json summary.model_executed_count > 0
- reports/output_execution_runs.json summary.timing_observed_count > 0
- reports/output_execution_runs.json summary.token_observed_count > 0
@@ -66,6 +72,13 @@ This report is a read-only reviewer queue. It does not accept evidence or make w
#### Source Checks
- Review pairs exist: 5 / >0 => pass
- No pending decisions: 5 / ==0 => blocked
- Judgments complete: 0 / ==pair_count => blocked
- No invalid decisions: 0 / ==0 => pass
#### Completion Assertions
- reports/output_review_adjudication.json summary.pending_count == 0
- reports/output_review_adjudication.json summary.judgment_count == summary.pair_count
- reports/output_review_adjudication.json summary.invalid_decision_count == 0
@@ -92,6 +105,12 @@ This report is a read-only reviewer queue. It does not accept evidence or make w
#### Source Checks
- Native enforcement: 0 / >0 => blocked
- Probe failures: 0 / ==0 => pass
- Installer support: True / true => pass
#### Completion Assertions
- reports/runtime_permission_probes.json summary.native_enforcement_count > 0
- reports/runtime_permission_probes.json summary.failure_count == 0
- reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence
@@ -118,6 +137,12 @@ 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
- Raw content blocked: False / false => pass
#### Completion Assertions
- reports/adoption_drift_report.json summary.source_types.external > 0
- reports/adoption_drift_report.json summary.adoption_sample_count > 0
- reports/skill_os2_audit.json item native-client-telemetry status becomes pass