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

Refresh phase queue clean-lock evidence

Browse Source
This commit is contained in:
yaojingang
2026-06-17 04:32:58 +08:00
parent 7512dc3309
commit ca23db4296
14 changed files with 417 additions and 528 deletions
Download Patch File Download Diff File Expand all files Collapse all files
reports/benchmark_reproducibility.json
+44 -70
View File
@@ -3,47 +3,22 @@
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "2efe6413f04c9626ba52c554b4dc87baabd0b05b",
"commit": "7512dc3309bfa95d4fc7e1188d1d4a62bd7c460b",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 65,
"changed_file_count": 2,
"generated_dirty": true,
"generated_changed_file_count": 61,
"source_dirty": true,
"source_changed_file_count": 4,
"generated_changed_file_count": 2,
"source_dirty": false,
"source_changed_file_count": 0,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/adoption_drift_report.json",
" M reports/adoption_drift_report.md",
" 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"
],
"source_sample": [
" M scripts/prepare_world_class_submission_kit.py",
" M scripts/world_class_submission_kit_rendering.py",
" M tests/verify_world_class_submission_kit.py",
"?? scripts/world_class_phase_queue.py"
],
"source_sample": [],
"generated_sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/adoption_drift_report.json",
" M reports/adoption_drift_report.md",
" 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"
],
"generated_dirty_prefixes": [
@@ -58,11 +33,11 @@
},
"summary": {
"reproducibility_ready": true,
"release_lock_ready": false,
"release_lock_ready": true,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a",
"evidence_bundle_sha256": "3f56502035ddc8b26c0eca9e3e9d2e84013457336b16f4ce3d338b6b0cd96ef6",
"source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
@@ -79,36 +54,35 @@
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"public_claim_blocker_count": 4,
"working_tree_dirty": true,
"changed_file_count": 65,
"source_tree_dirty": true,
"source_changed_file_count": 4,
"changed_file_count": 2,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"generated_tree_dirty": true,
"generated_changed_file_count": 61
"generated_changed_file_count": 2
},
"public_claim": {
"ready": false,
"scope": "public benchmark or world-class readiness claim",
"blockers": [
"release lock is not clean or commit is unavailable",
"provider-backed model holdout evidence is incomplete",
"human blind-review adjudication is incomplete",
"world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
"world-class source checks are not all accepted (9/19 pass, 10 blocked)"
"world-class source checks are not all accepted (10/19 pass, 9 blocked)"
],
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
},
"release_lock": {
"ready": false,
"commit": "2efe6413f04c9626ba52c554b4dc87baabd0b05b",
"ready": true,
"commit": "7512dc3309bfa95d4fc7e1188d1d4a62bd7c460b",
"status_scope": "generation-time status before this report is written",
"source_changed_file_count": 4,
"generated_changed_file_count": 61,
"reason": "source files were dirty at generation time"
"source_changed_file_count": 0,
"generated_changed_file_count": 2,
"reason": "only generated evidence artifacts were dirty at generation time"
},
"evidence_bundle": {
"algorithm": "sha256(path,label,exists,artifact_sha256)",
@@ -116,7 +90,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a"
"sha256": "3f56502035ddc8b26c0eca9e3e9d2e84013457336b16f4ce3d338b6b0cd96ef6"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -189,8 +163,8 @@
"label": "output_execution",
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7966,
"sha256": "f40063a2ada31c29a3ac9b5965f0887cad6bc19190ec0a3a6b15c92ce5c27b49"
"bytes": 7967,
"sha256": "b7cb8dfb5aeeb71b27ed31f63f260f89343f5f83e5ea307fb0268125fcdf2e87"
},
{
"label": "blind_review",
@@ -232,14 +206,14 @@
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 29715,
"sha256": "8b0d2a84027e0956b11acabc46e5ea5b9d7a311087b792eb57dd544bcd284671"
"sha256": "fbfb0331f8230fe0739214a837639983ed608f880af477c71f8f116df74f5a55"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "0a0ccb00f9f7769c56f109589983562e91f7663f2c96c219d284c3d36eafe58e"
"sha256": "0b9a661b8acc68e19895f05ff4b025f6a16f834a3238cb6e53871aa908e34c34"
},
{
"label": "package_verification",
@@ -252,78 +226,78 @@
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8604,
"sha256": "34cc602c025c82a478a647d58008414f92c70e72046ca79979d3b038f3d793d2"
"bytes": 8758,
"sha256": "73d46fe333bab7d78e2cb854704e6be0d40ee8eafe2798cfa7b71c2a5a3c9953"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14466,
"sha256": "920bd7f7b3b0fb01c572ed12d9ff788a34a7592d00d9825004d3faba90ebb17b"
"sha256": "4169e5453ba22f0c45e3f8b12eec08ef99ccd3562680d3721ee73c4eef9806c1"
},
{
"label": "world_class_evidence_plan",
"path": "reports/world_class_evidence_plan.json",
"exists": true,
"bytes": 22784,
"sha256": "2beb888d7992fc72073251632a6e85c4075278f9bcea946a46a7e11f8f43e0ca"
"sha256": "4193115d881d4f68e61d2729633f88dd91d55d982af3db70691aafeba852f1ba"
},
{
"label": "world_class_evidence_ledger",
"path": "reports/world_class_evidence_ledger.json",
"exists": true,
"bytes": 26019,
"sha256": "22c85613d7bef62c4d0a4c94b77a8596090dc55c40e1663370d16d903e0b1ffb"
"bytes": 26016,
"sha256": "cb66d3284045b5993d25447f011cc70737dc760765ea3a3b7ae653194f0c4ff4"
},
{
"label": "world_class_evidence_intake",
"path": "reports/world_class_evidence_intake.json",
"exists": true,
"bytes": 20646,
"sha256": "d3f44570e605e6e1b1557889ccca18efbbd8acc1d9a9c638f59961b3dc3e9026"
"sha256": "002fbf07989a804595fdcb51b6d0c8177dc035a1dc8d084b8294a274d21fbc1b"
},
{
"label": "world_class_evidence_preflight",
"path": "reports/world_class_evidence_preflight.json",
"exists": true,
"bytes": 68674,
"sha256": "c9d5fc06305c41f0870f32f30c0440a95e6fbdba402326e339cfd0c771ff960d"
"bytes": 66981,
"sha256": "758807fa5749e0dd46f46d311abfad8af7dd70663e8876569b1a4b8414b42ace"
},
{
"label": "world_class_submission_review",
"path": "reports/world_class_submission_review.json",
"exists": true,
"bytes": 17302,
"sha256": "96624a5b7f79aa0ac43ce60d30486290b9a91f0735254e31329f02e1ee291050"
"bytes": 17299,
"sha256": "f5b1e0e44aeb6e1999182d40fca421ab0a66b91154efc7b518e9ed6f6ac20dd2"
},
{
"label": "world_class_operator_runbook",
"path": "reports/world_class_operator_runbook.json",
"exists": true,
"bytes": 28935,
"sha256": "a7b7809d3b423bf647a528c3b0f6991f2ea3874afdd93a4d6ba74eb189131f2a"
"bytes": 28871,
"sha256": "8da2e2cde3adecec955f7745a4b761edc5af871d1720409cbd4f3b4b4482510e"
},
{
"label": "world_class_operator_runbook_markdown",
"path": "reports/world_class_operator_runbook.md",
"exists": true,
"bytes": 17576,
"sha256": "d72777b421b57f0cf8f31b4d048cf92512e49216d0b0c05cec1686d4aea638ce"
"bytes": 17521,
"sha256": "bfac92bc14f3080b9d723f32a4848aa3cfc10d4c3ee2e3844b65153f34c87c0a"
},
{
"label": "world_class_operator_runbook_html",
"path": "reports/world_class_operator_runbook.html",
"exists": true,
"bytes": 24019,
"sha256": "73d8ef2898f25ae899a618b723f40a6907646c303effa21cbde6156d01a95fc7"
"bytes": 23958,
"sha256": "46b435f98d8a91501580fa1426a8ab0d0f57b3bc92ecd17f42332e655fd2bd85"
},
{
"label": "world_class_claim_guard",
"path": "reports/world_class_claim_guard.json",
"exists": true,
"bytes": 18596,
"sha256": "abe7f7d60c0025e140373fadaefbed4063f285c140c74b9c7cfb464e354bb526"
"sha256": "c846ffc8565a40c270e711a58e968b005afd75be6df1a442b020deebe850386f"
}
],
"missing_artifacts": [],
reports/benchmark_reproducibility.md
+27 -28
View File
@@ -1,16 +1,16 @@
# Benchmark Reproducibility
Generated at: `2026-06-17`
Commit: `2efe6413f04c9626ba52c554b4dc87baabd0b05b`
Commit: `7512dc3309bfa95d4fc7e1188d1d4a62bd7c460b`
Working tree dirty at generation: `true`
Source tree dirty at generation: `true`
Source tree dirty at generation: `false`
Generated evidence dirty at generation: `true`
Evidence bundle SHA256: `7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a`
Evidence bundle SHA256: `3f56502035ddc8b26c0eca9e3e9d2e84013457336b16f4ce3d338b6b0cd96ef6`
## Summary
- reproducibility ready: `true`
- release lock ready: `false`
- release lock ready: `true`
- methodology complete: `true`
- required artifacts: `25`
- missing artifacts: `0`
@@ -22,12 +22,12 @@ Evidence bundle SHA256: `7fbfcb3c47283921ca6bb163600b18448da389c077939157387d807
- provider evidence complete: `false`
- human review complete: `false`
- world-class ready: `false`
- world-class source checks: `9` pass / `19` total; `10` blocked
- world-class source checks: `10` pass / `19` total; `9` blocked
- public claim ready: `false`
- public claim blockers: `5`
- changed files at generation: `65`
- source changed files at generation: `4`
- generated changed files at generation: `61`
- public claim blockers: `4`
- changed files at generation: `2`
- source changed files at generation: `0`
- generated changed files at generation: `2`
This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit and dirty samples are generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
@@ -39,23 +39,22 @@ This report proves local benchmark reproducibility only. It keeps external provi
| Blocker |
| --- |
| release lock is not clean or commit is unavailable |
| provider-backed model holdout evidence is incomplete |
| human blind-review adjudication is incomplete |
| world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) |
| world-class source checks are not all accepted (9/19 pass, 10 blocked) |
| world-class source checks are not all accepted (10/19 pass, 9 blocked) |
## Release Lock
- ready: `false`
- reason: source files were dirty at generation time
- ready: `true`
- reason: only generated evidence artifacts were dirty at generation time
- status scope: generation-time status before this report is written
## Evidence Bundle
- algorithm: `sha256(path,label,exists,artifact_sha256)`
- artifacts: `25` / `25`
- sha256: `7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a`
- sha256: `3f56502035ddc8b26c0eca9e3e9d2e84013457336b16f4ce3d338b6b0cd96ef6`
## Methodology Sections
@@ -77,26 +76,26 @@ 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 | `f40063a2ada3` |
| output_execution | `reports/output_execution_runs.json` | present | `b7cb8dfb5aee` |
| 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 | `b1d4729668d1` |
| python_compatibility | `reports/python_compatibility.json` | present | `8b0d2a84027e` |
| registry_audit | `reports/registry_audit.json` | present | `0a0ccb00f9f7` |
| python_compatibility | `reports/python_compatibility.json` | present | `fbfb0331f823` |
| registry_audit | `reports/registry_audit.json` | present | `0b9a661b8acc` |
| package_verification | `reports/package_verification.json` | present | `7aa6c25e8154` |
| install_simulation | `reports/install_simulation.json` | present | `34cc602c025c` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `920bd7f7b3b0` |
| 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 | `c9d5fc06305c` |
| 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` |
| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `73d8ef2898f2` |
| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `abe7f7d60c00` |
| install_simulation | `reports/install_simulation.json` | present | `73d46fe333ba` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `4169e5453ba2` |
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `4193115d881d` |
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `cb66d3284045` |
| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `002fbf07989a` |
| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `758807fa5749` |
| world_class_submission_review | `reports/world_class_submission_review.json` | present | `f5b1e0e44aeb` |
| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `8da2e2cde3ad` |
| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `bfac92bc14f3` |
| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `46b435f98d8a` |
| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `c846ffc8565a` |
## Reproduction Commands
reports/context_budget.json
+2 -2
View File
@@ -6,9 +6,9 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 797,
"other_text_tokens": 1115158,
"other_text_tokens": 1115184,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1115955,
"estimated_total_text_tokens": 1115981,
"deferred_resource_tokens": 509352,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
reports/context_budget_summary.json
+1 -1
View File
@@ -1,5 +1,5 @@
{
"generated_at": "2026-03-31",
"generated_at": "2026-06-17",
"targets": [
{
"label": "root",
reports/evidence_consistency.json
+71 -73
View File
@@ -207,8 +207,8 @@
"key": "benchmark-release-lock-self-consistency",
"label": "Benchmark release lock matches source dirty state",
"status": "pass",
"expected": false,
"actual": false,
"expected": true,
"actual": true,
"paths": [
"reports/benchmark_reproducibility.json"
],
@@ -222,7 +222,7 @@
"actual": {
"available": true,
"clean": false,
"changed_file_count": 66
"changed_file_count": 13
},
"paths": [
"reports/benchmark_reproducibility.json"
@@ -263,8 +263,8 @@
"key": "overview-benchmark-commit",
"label": "overview embeds the benchmark commit",
"status": "pass",
"expected": "2efe6413f04c9626ba52c554b4dc87baabd0b05b",
"actual": "2efe6413f04c9626ba52c554b4dc87baabd0b05b",
"expected": "7512dc3309bfa95d4fc7e1188d1d4a62bd7c460b",
"actual": "7512dc3309bfa95d4fc7e1188d1d4a62bd7c460b",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-overview.json"
@@ -276,30 +276,30 @@
"label": "overview embeds benchmark summary fields",
"status": "pass",
"expected": {
"release_lock_ready": false,
"release_lock_ready": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"public_claim_ready": false,
"public_claim_blocker_count": 5
"public_claim_blocker_count": 4
},
"actual": {
"release_lock_ready": false,
"release_lock_ready": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"public_claim_ready": false,
"public_claim_blocker_count": 5
"public_claim_blocker_count": 4
},
"paths": [
"reports/benchmark_reproducibility.json",
@@ -313,13 +313,13 @@
"status": "pass",
"expected": {
"event_count": 1,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_rate": 0,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_rate": 100.0,
"risk_band": "low",
"event_types": {
"review_event": 1
"skill_activation": 1
},
"source_types": {
"manual": 1
@@ -327,13 +327,13 @@
},
"actual": {
"event_count": 1,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_rate": 0,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_rate": 100.0,
"risk_band": "low",
"event_types": {
"review_event": 1
"skill_activation": 1
},
"source_types": {
"manual": 1
@@ -356,8 +356,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"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,
"decision": "evidence-pending"
},
@@ -368,8 +368,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"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,
"decision": "evidence-pending"
},
@@ -389,7 +389,7 @@
"pending_count": 4,
"accepted_count": 0,
"source_check_count": 19,
"source_pass_count": 9
"source_pass_count": 10
},
"actual": {
"ready": false,
@@ -397,7 +397,7 @@
"pending_count": 4,
"accepted_count": 0,
"source_check_count": 19,
"source_pass_count": 9
"source_pass_count": 10
},
"paths": [
"reports/world_class_evidence_ledger.json",
@@ -409,8 +409,8 @@
"key": "interpretation-benchmark-commit",
"label": "interpretation embeds the benchmark commit",
"status": "pass",
"expected": "2efe6413f04c9626ba52c554b4dc87baabd0b05b",
"actual": "2efe6413f04c9626ba52c554b4dc87baabd0b05b",
"expected": "7512dc3309bfa95d4fc7e1188d1d4a62bd7c460b",
"actual": "7512dc3309bfa95d4fc7e1188d1d4a62bd7c460b",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-interpretation.json"
@@ -422,30 +422,30 @@
"label": "interpretation embeds benchmark summary fields",
"status": "pass",
"expected": {
"release_lock_ready": false,
"release_lock_ready": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"public_claim_ready": false,
"public_claim_blocker_count": 5
"public_claim_blocker_count": 4
},
"actual": {
"release_lock_ready": false,
"release_lock_ready": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"public_claim_ready": false,
"public_claim_blocker_count": 5
"public_claim_blocker_count": 4
},
"paths": [
"reports/benchmark_reproducibility.json",
@@ -459,13 +459,13 @@
"status": "pass",
"expected": {
"event_count": 1,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_rate": 0,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_rate": 100.0,
"risk_band": "low",
"event_types": {
"review_event": 1
"skill_activation": 1
},
"source_types": {
"manual": 1
@@ -473,13 +473,13 @@
},
"actual": {
"event_count": 1,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_rate": 0,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_rate": 100.0,
"risk_band": "low",
"event_types": {
"review_event": 1
"skill_activation": 1
},
"source_types": {
"manual": 1
@@ -502,8 +502,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"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,
"decision": "evidence-pending"
},
@@ -514,8 +514,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"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,
"decision": "evidence-pending"
},
@@ -535,7 +535,7 @@
"pending_count": 4,
"accepted_count": 0,
"source_check_count": 19,
"source_pass_count": 9
"source_pass_count": 10
},
"actual": {
"ready": false,
@@ -543,7 +543,7 @@
"pending_count": 4,
"accepted_count": 0,
"source_check_count": 19,
"source_pass_count": 9
"source_pass_count": 10
},
"paths": [
"reports/world_class_evidence_ledger.json",
@@ -1342,7 +1342,7 @@
"external_pending_count": 3,
"human_pending_count": 1,
"source_check_count": 19,
"source_pass_count": 9,
"source_pass_count": 10,
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
"entries": [
@@ -1402,8 +1402,7 @@
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
"summary_en": "Real external-client metadata-only events have not been imported yet.",
"blocked_checks": [
"External events",
"Adoption sample"
"External events"
]
}
]
@@ -1417,7 +1416,7 @@
"external_pending_count": 3,
"human_pending_count": 1,
"source_check_count": 19,
"source_pass_count": 9,
"source_pass_count": 10,
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
"entries": [
@@ -1477,8 +1476,7 @@
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
"summary_en": "Real external-client metadata-only events have not been imported yet.",
"blocked_checks": [
"External events",
"Adoption sample"
"External events"
]
}
]
@@ -1828,15 +1826,15 @@
"expected": {
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"public_claim_ready": false
},
"actual": {
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"public_claim_ready": false
},
"paths": [
@@ -1852,8 +1850,8 @@
"expected": {
"pending_count": 4,
"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,
"preflight_counts_as_evidence": false,
"credential_value_exposed": false
@@ -1861,8 +1859,8 @@
"actual": {
"pending_count": 4,
"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,
"preflight_counts_as_evidence": false,
"credential_value_exposed": false
@@ -2116,8 +2114,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 19,
"source_pass_count": 9,
"source_blocked_count": 10,
"source_pass_count": 10,
"source_blocked_count": 9,
"plan_keys": [
"human-adjudication",
"native-client-telemetry",
@@ -2265,8 +2263,8 @@
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 19,
"source_pass_count": 9,
"source_blocked_count": 10,
"source_pass_count": 10,
"source_blocked_count": 9,
"plan_keys": [
"human-adjudication",
"native-client-telemetry",
reports/review-studio.html
+11 -11
View File
File diff suppressed because one or more lines are too long
reports/review-studio.json
+176 -255
View File
File diff suppressed because it is too large Load Diff
reports/review-viewer.json
+27 -28
View File
@@ -412,7 +412,7 @@
"external_pending_count": 3,
"human_pending_count": 1,
"source_check_count": 19,
"source_pass_count": 9,
"source_pass_count": 10,
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
"entries": [
@@ -472,8 +472,7 @@
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
"summary_en": "Real external-client metadata-only events have not been imported yet.",
"blocked_checks": [
"External events",
"Adoption sample"
"External events"
]
}
]
@@ -1006,11 +1005,11 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": false,
"release_lock_ready": true,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a",
"evidence_bundle_sha256": "3f56502035ddc8b26c0eca9e3e9d2e84013457336b16f4ce3d338b6b0cd96ef6",
"source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
@@ -1027,18 +1026,18 @@
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"public_claim_blocker_count": 4,
"working_tree_dirty": true,
"changed_file_count": 65,
"source_tree_dirty": true,
"source_changed_file_count": 4,
"changed_file_count": 2,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"generated_tree_dirty": true,
"generated_changed_file_count": 61
"generated_changed_file_count": 2
},
"commit": "2efe6413f04c9626ba52c554b4dc87baabd0b05b",
"commit": "7512dc3309bfa95d4fc7e1188d1d4a62bd7c460b",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
@@ -1218,7 +1217,7 @@
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
},
"generated_at": "2026-06-17"
"generated_at": "2026-06-13"
},
"failures": [],
"warnings": []
@@ -1330,14 +1329,14 @@
"ok": true,
"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,
@@ -1346,7 +1345,7 @@
"review_overdue_count": 0,
"risk_band": "low",
"event_types": {
"review_event": 1
"skill_activation": 1
},
"failure_types": {},
"source_types": {
@@ -1621,7 +1620,7 @@
"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>/",
@@ -1674,8 +1673,8 @@
"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,
@@ -2101,7 +2100,7 @@
"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>/",
@@ -2138,7 +2137,7 @@
],
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 0,
"adoption_sample_count": 1,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
@@ -2159,8 +2158,8 @@
"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."
},
@@ -2176,8 +2175,8 @@
}
],
"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/skill-interpretation.html
+1 -1
View File
@@ -929,7 +929,7 @@
</table>
</div>
</div>
<article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>9 / 19</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">提供商实跑</span><span data-lang="en">Provider model run</span></li><li><span data-lang="zh-CN">Token 用量</span><span data-lang="en">Token usage observed</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li><li><span data-lang="zh-CN">Reviewer metadata</span><span data-lang="en">Reviewer metadata</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li><li><span data-lang="zh-CN">采用样本</span><span data-lang="en">Adoption sample</span></li></ul></article></div></article>
<article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>10 / 19</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">提供商实跑</span><span data-lang="en">Provider model run</span></li><li><span data-lang="zh-CN">Token 用量</span><span data-lang="en">Token usage observed</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li><li><span data-lang="zh-CN">Reviewer metadata</span><span data-lang="en">Reviewer metadata</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li></ul></article></div></article>
</div>
</section>
reports/skill-interpretation.json
+27 -28
View File
@@ -412,7 +412,7 @@
"external_pending_count": 3,
"human_pending_count": 1,
"source_check_count": 19,
"source_pass_count": 9,
"source_pass_count": 10,
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
"entries": [
@@ -472,8 +472,7 @@
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
"summary_en": "Real external-client metadata-only events have not been imported yet.",
"blocked_checks": [
"External events",
"Adoption sample"
"External events"
]
}
]
@@ -1010,11 +1009,11 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": false,
"release_lock_ready": true,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a",
"evidence_bundle_sha256": "3f56502035ddc8b26c0eca9e3e9d2e84013457336b16f4ce3d338b6b0cd96ef6",
"source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
@@ -1031,18 +1030,18 @@
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"public_claim_blocker_count": 4,
"working_tree_dirty": true,
"changed_file_count": 65,
"source_tree_dirty": true,
"source_changed_file_count": 4,
"changed_file_count": 2,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"generated_tree_dirty": true,
"generated_changed_file_count": 61
"generated_changed_file_count": 2
},
"commit": "2efe6413f04c9626ba52c554b4dc87baabd0b05b",
"commit": "7512dc3309bfa95d4fc7e1188d1d4a62bd7c460b",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
@@ -1222,7 +1221,7 @@
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
},
"generated_at": "2026-06-17"
"generated_at": "2026-06-13"
},
"failures": [],
"warnings": []
@@ -1334,14 +1333,14 @@
"ok": true,
"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,
@@ -1350,7 +1349,7 @@
"review_overdue_count": 0,
"risk_band": "low",
"event_types": {
"review_event": 1
"skill_activation": 1
},
"failure_types": {},
"source_types": {
@@ -1625,7 +1624,7 @@
"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>/",
@@ -1678,8 +1677,8 @@
"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,
@@ -2105,7 +2104,7 @@
"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>/",
@@ -2142,7 +2141,7 @@
],
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 0,
"adoption_sample_count": 1,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
@@ -2163,8 +2162,8 @@
"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."
},
@@ -2180,8 +2179,8 @@
}
],
"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/skill-overview.html
+1 -1
View File
@@ -929,7 +929,7 @@
</table>
</div>
</div>
<article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>9 / 19</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">提供商实跑</span><span data-lang="en">Provider model run</span></li><li><span data-lang="zh-CN">Token 用量</span><span data-lang="en">Token usage observed</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li><li><span data-lang="zh-CN">Reviewer metadata</span><span data-lang="en">Reviewer metadata</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li><li><span data-lang="zh-CN">采用样本</span><span data-lang="en">Adoption sample</span></li></ul></article></div></article>
<article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>10 / 19</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">提供商实跑</span><span data-lang="en">Provider model run</span></li><li><span data-lang="zh-CN">Token 用量</span><span data-lang="en">Token usage observed</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li><li><span data-lang="zh-CN">Reviewer metadata</span><span data-lang="en">Reviewer metadata</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li></ul></article></div></article>
</div>
</section>
reports/skill-overview.json
+27 -28
View File
@@ -411,7 +411,7 @@
"external_pending_count": 3,
"human_pending_count": 1,
"source_check_count": 19,
"source_pass_count": 9,
"source_pass_count": 10,
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
"entries": [
@@ -471,8 +471,7 @@
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
"summary_en": "Real external-client metadata-only events have not been imported yet.",
"blocked_checks": [
"External events",
"Adoption sample"
"External events"
]
}
]
@@ -1005,11 +1004,11 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": false,
"release_lock_ready": true,
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "7fbfcb3c47283921ca6bb163600b18448da389c077939157387d8075e9c3867a",
"evidence_bundle_sha256": "3f56502035ddc8b26c0eca9e3e9d2e84013457336b16f4ce3d338b6b0cd96ef6",
"source_contract_sha256": "7fa19df8aebad9a73567ce9519f2d391d3c8f8b9b5a248ee9bc75d5066e219e4",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
@@ -1026,18 +1025,18 @@
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 9,
"world_class_source_blocked_count": 10,
"world_class_source_pass_count": 10,
"world_class_source_blocked_count": 9,
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"public_claim_blocker_count": 4,
"working_tree_dirty": true,
"changed_file_count": 65,
"source_tree_dirty": true,
"source_changed_file_count": 4,
"changed_file_count": 2,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"generated_tree_dirty": true,
"generated_changed_file_count": 61
"generated_changed_file_count": 2
},
"commit": "2efe6413f04c9626ba52c554b4dc87baabd0b05b",
"commit": "7512dc3309bfa95d4fc7e1188d1d4a62bd7c460b",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
@@ -1217,7 +1216,7 @@
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
},
"generated_at": "2026-06-17"
"generated_at": "2026-06-13"
},
"failures": [],
"warnings": []
@@ -1329,14 +1328,14 @@
"ok": true,
"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,
@@ -1345,7 +1344,7 @@
"review_overdue_count": 0,
"risk_band": "low",
"event_types": {
"review_event": 1
"skill_activation": 1
},
"failure_types": {},
"source_types": {
@@ -1620,7 +1619,7 @@
"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>/",
@@ -1673,8 +1672,8 @@
"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,
@@ -2100,7 +2099,7 @@
"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>/",
@@ -2137,7 +2136,7 @@
],
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 0,
"adoption_sample_count": 1,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
@@ -2158,8 +2157,8 @@
"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."
},
@@ -2175,8 +2174,8 @@
}
],
"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_preflight.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"evidence_item_count": 4,
reports/world_class_evidence_preflight.md
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Preflight
Generated at: `2026-06-13`
Generated at: `2026-06-17`
## Summary