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 consistency evidence

Browse Source
This commit is contained in:
yaojingang
2026-06-17 05:00:28 +08:00
parent 9eaa8f6cec
commit 28c48ec248
14 changed files with 245 additions and 260 deletions
Download Patch File Download Diff File Expand all files Collapse all files
reports/adaptation_proposals.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-16T20:58:28Z",
"generated_at": "2026-06-17",
"skill_dir": ".",
"source_patterns": "reports/user_patterns.json",
"pattern_count": 5,
reports/adaptation_proposals.md
+1 -1
View File
@@ -1,6 +1,6 @@
# Adaptation Proposals
- Generated at: `2026-06-16T20:58:28Z`
- Generated at: `2026-06-17`
- Pattern report: `reports/user_patterns.json`
- Proposal only: `true`
- Writes repository files: `false`
reports/benchmark_reproducibility.json
+34 -40
View File
@@ -3,48 +3,43 @@
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "c30882468f45c7e78bef73e0ada161fd1fbaef79",
"commit": "9eaa8f6cec4ba83c07ded0275686252576bee6c3",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 64,
"changed_file_count": 17,
"generated_dirty": true,
"generated_changed_file_count": 60,
"source_dirty": true,
"source_changed_file_count": 4,
"generated_changed_file_count": 17,
"source_dirty": false,
"source_changed_file_count": 0,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/adaptation_proposals.json",
" M reports/adaptation_proposals.md",
" M reports/adoption_drift_report.json",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" M reports/benchmark_reproducibility.json",
" M reports/benchmark_reproducibility.md",
" M reports/compiled_targets.json",
" M reports/context_budget.json",
" M reports/context_budget.md"
],
"source_sample": [
" M scripts/render_evidence_consistency.py",
" M tests/verify_architecture_maintainability.py",
" M tests/verify_evidence_consistency.py",
"?? scripts/evidence_consistency_phase_queue.py"
" M reports/evidence_consistency.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md",
" M reports/review-studio.html",
" M reports/review-studio.json",
" M reports/review-viewer.json",
" M reports/skill-interpretation.json"
],
"source_sample": [],
"generated_sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/adaptation_proposals.json",
" M reports/adaptation_proposals.md",
" M reports/adoption_drift_report.json",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" M reports/benchmark_reproducibility.json",
" M reports/benchmark_reproducibility.md",
" M reports/compiled_targets.json",
" M reports/context_budget.json",
" M reports/context_budget.md"
" M reports/evidence_consistency.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md",
" M reports/review-studio.html",
" M reports/review-studio.json",
" M reports/review-viewer.json",
" M reports/skill-interpretation.json"
],
"generated_dirty_prefixes": [
"dist/",
@@ -58,11 +53,11 @@
},
"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": "0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd",
"evidence_bundle_sha256": "98271c40046d1bf5f6a3ada701b5b1fd88b188bf4122a15424c8b4566cfc8fcf",
"source_contract_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
@@ -82,19 +77,18 @@
"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": 64,
"source_tree_dirty": true,
"source_changed_file_count": 4,
"changed_file_count": 17,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"generated_tree_dirty": true,
"generated_changed_file_count": 60
"generated_changed_file_count": 17
},
"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)",
@@ -103,12 +97,12 @@
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
},
"release_lock": {
"ready": false,
"commit": "c30882468f45c7e78bef73e0ada161fd1fbaef79",
"ready": true,
"commit": "9eaa8f6cec4ba83c07ded0275686252576bee6c3",
"status_scope": "generation-time status before this report is written",
"source_changed_file_count": 4,
"generated_changed_file_count": 60,
"reason": "source files were dirty at generation time"
"source_changed_file_count": 0,
"generated_changed_file_count": 17,
"reason": "only generated evidence artifacts were dirty at generation time"
},
"evidence_bundle": {
"algorithm": "sha256(path,label,exists,artifact_sha256)",
@@ -116,7 +110,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd"
"sha256": "98271c40046d1bf5f6a3ada701b5b1fd88b188bf4122a15424c8b4566cfc8fcf"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -190,7 +184,7 @@
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7967,
"sha256": "615d4b9ec6fb8d487c98e06ffb8cdbe7d34b08b07a2d9ea069eee3cdd4edc0a9"
"sha256": "6edee9440d276bd62d36deee7a5a2c45ce2e7c6817a0e517f0339b266e4055aa"
},
{
"label": "blind_review",
reports/benchmark_reproducibility.md
+12 -13
View File
@@ -1,16 +1,16 @@
# Benchmark Reproducibility
Generated at: `2026-06-17`
Commit: `c30882468f45c7e78bef73e0ada161fd1fbaef79`
Commit: `9eaa8f6cec4ba83c07ded0275686252576bee6c3`
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: `0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd`
Evidence bundle SHA256: `98271c40046d1bf5f6a3ada701b5b1fd88b188bf4122a15424c8b4566cfc8fcf`
## Summary
- reproducibility ready: `true`
- release lock ready: `false`
- release lock ready: `true`
- methodology complete: `true`
- required artifacts: `25`
- missing artifacts: `0`
@@ -24,10 +24,10 @@ Evidence bundle SHA256: `0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e8
- world-class ready: `false`
- world-class source checks: `10` pass / `19` total; `9` blocked
- public claim ready: `false`
- public claim blockers: `5`
- changed files at generation: `64`
- source changed files at generation: `4`
- generated changed files at generation: `60`
- public claim blockers: `4`
- changed files at generation: `17`
- source changed files at generation: `0`
- generated changed files at generation: `17`
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.
@@ -39,7 +39,6 @@ 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) |
@@ -47,15 +46,15 @@ This report proves local benchmark reproducibility only. It keeps external provi
## 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: `0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd`
- sha256: `98271c40046d1bf5f6a3ada701b5b1fd88b188bf4122a15424c8b4566cfc8fcf`
## Methodology Sections
@@ -77,7 +76,7 @@ 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 | `615d4b9ec6fb` |
| output_execution | `reports/output_execution_runs.json` | present | `6edee9440d27` |
| 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` |
reports/evidence_consistency.json
+93 -95
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": 64
"changed_file_count": 14
},
"paths": [
"reports/benchmark_reproducibility.json"
@@ -263,8 +263,8 @@
"key": "overview-benchmark-commit",
"label": "overview embeds the benchmark commit",
"status": "pass",
"expected": "c30882468f45c7e78bef73e0ada161fd1fbaef79",
"actual": "c30882468f45c7e78bef73e0ada161fd1fbaef79",
"expected": "9eaa8f6cec4ba83c07ded0275686252576bee6c3",
"actual": "9eaa8f6cec4ba83c07ded0275686252576bee6c3",
"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": "e1d05a0ec120c6955b331e25941b0ee8a7ffcc0d0d6e22b359367a4312644b37",
"source_contract_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d",
"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": "e1d05a0ec120c6955b331e25941b0ee8a7ffcc0d0d6e22b359367a4312644b37",
"source_contract_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d",
"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": "c30882468f45c7e78bef73e0ada161fd1fbaef79",
"actual": "c30882468f45c7e78bef73e0ada161fd1fbaef79",
"expected": "9eaa8f6cec4ba83c07ded0275686252576bee6c3",
"actual": "9eaa8f6cec4ba83c07ded0275686252576bee6c3",
"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": "e1d05a0ec120c6955b331e25941b0ee8a7ffcc0d0d6e22b359367a4312644b37",
"source_contract_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d",
"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": "e1d05a0ec120c6955b331e25941b0ee8a7ffcc0d0d6e22b359367a4312644b37",
"source_contract_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d",
"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
@@ -2039,7 +2037,7 @@
"summary": {
"phase_queue_count": 2,
"phase_queue_blocked_count": 2,
"phase_queue_row_count": 14,
"phase_queue_row_count": 13,
"phase_queue_next_phase": "unblock-access",
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
@@ -2072,8 +2070,8 @@
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 10,
"row_count": 10,
"blocked_count": 9,
"row_count": 9,
"owners": [
"Browser/Chrome/IDE/provider client integrator",
"human reviewer",
@@ -2215,15 +2213,15 @@
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 2,
"row_count": 2,
"blocked_count": 1,
"row_count": 1,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
"next_action_id": "native-client-telemetry-source-check-external_source_events",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
@@ -2354,15 +2352,15 @@
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 2,
"row_count": 2,
"blocked_count": 1,
"row_count": 1,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
"next_action_id": "native-client-telemetry-source-check-external_source_events",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
@@ -2373,7 +2371,7 @@
"summary": {
"phase_queue_count": 2,
"phase_queue_blocked_count": 2,
"phase_queue_row_count": 14,
"phase_queue_row_count": 13,
"phase_queue_next_phase": "unblock-access",
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
@@ -2406,8 +2404,8 @@
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 10,
"row_count": 10,
"blocked_count": 9,
"row_count": 9,
"owners": [
"Browser/Chrome/IDE/provider client integrator",
"human reviewer",
@@ -2549,15 +2547,15 @@
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 2,
"row_count": 2,
"blocked_count": 1,
"row_count": 1,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
"next_action_id": "native-client-telemetry-source-check-external_source_events",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
@@ -2687,15 +2685,15 @@
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 2,
"row_count": 2,
"blocked_count": 1,
"row_count": 1,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
"next_action_id": "native-client-telemetry-source-check-external_source_events",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
@@ -2794,8 +2792,8 @@
"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",
@@ -2943,8 +2941,8 @@
"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
+7 -7
View File
@@ -772,12 +772,12 @@
<section>
<h2>核心指标</h2>
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>5 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>152 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>231 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>696 largest lines; 0 watchlist; 3 early; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock false</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>182 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>689 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>4 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>152 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>231 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>696 largest lines; 0 watchlist; 3 early; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock true</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>182 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>689 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
</section>
<section>
<h2>审查闸门</h2>
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 990/1000; deferred 512782/120000; top deferred scripts 451479; resource governance governed; quality density 131.3</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 152 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 231 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>228 Python files; 0 hotspots; 0 watchlist files; 3 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 10/19 pass; 9 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 990/1000; deferred 512782/120000; top deferred scripts 451479; resource governance governed; quality density 131.3</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 152 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 231 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>228 Python files; 0 hotspots; 0 watchlist files; 3 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 10/19 pass; 9 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
</section>
<section>
@@ -874,14 +874,14 @@
</section>
<section id="telemetry" class="twocol">
<div class="panel"><h2>运营回路</h2><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false</p></div>
<div class="panel"><h2>运营回路</h2><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true</p></div>
<div class="panel"><h2>漂移信号</h2><dl class='kv-grid'><div><dt>事件数</dt><dd>1</dd></div><div><dt>采用率</dt><dd>100</dd></div><div><dt>漏触发</dt><dd>0</dd></div><div><dt>Bad Output Count</dt><dd>0</dd></div><div><dt>风险带</dt><dd>low</dd></div></dl></div>
</section>
<section class="twocol">
<div class="panel"><h2>日常运维</h2><dl class='kv-grid'><div><dt>决策</dt><dd>proposal-review</dd></div><div><dt>提案数</dt><dd>5</dd></div><div><dt>Approval Count</dt><dd>0</dd></div><div><dt>Pending Review Count</dt><dd>0</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>世界级</dt><dd>否</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
<div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>2</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
<div class="panel"><h2>日常运维</h2><dl class='kv-grid'><div><dt>决策</dt><dd>proposal-review</dd></div><div><dt>提案数</dt><dd>5</dd></div><div><dt>Approval Count</dt><dd>0</dd></div><div><dt>Pending Review Count</dt><dd>0</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>世界级</dt><dd>否</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
<div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>2</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>Writes Source Files</dt><dd>否</dd></div><div><dt>Auto Patch Enabled</dt><dd>否</dd></div></dl></div>
</section>
@@ -914,8 +914,8 @@
</section>
<section class="twocol">
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>5</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>release lock is not clean or commit is unavailable</span></li><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (10/19 pass, 9 blocked)</span></li></ul></div>
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>4</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (10/19 pass, 9 blocked)</span></li></ul></div>
</section>
<section class="twocol">
reports/review-studio.json
+63 -69
View File
@@ -108,7 +108,7 @@
"key": "operations-loop",
"label": "运营回路",
"status": "pass",
"detail": "1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false",
"detail": "1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true",
"evidence": "reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly",
"link": "adoption_drift_report.md"
},
@@ -2363,11 +2363,11 @@
"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": "0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd",
"evidence_bundle_sha256": "98271c40046d1bf5f6a3ada701b5b1fd88b188bf4122a15424c8b4566cfc8fcf",
"source_contract_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
@@ -2387,15 +2387,15 @@
"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": 64,
"source_tree_dirty": true,
"source_changed_file_count": 4,
"changed_file_count": 17,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"generated_tree_dirty": true,
"generated_changed_file_count": 60
"generated_changed_file_count": 17
},
"commit": "c30882468f45c7e78bef73e0ada161fd1fbaef79",
"commit": "9eaa8f6cec4ba83c07ded0275686252576bee6c3",
"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.",
@@ -5184,7 +5184,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 31.72,
"duration_ms": 37.66,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5212,7 +5212,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 28.31,
"duration_ms": 30.99,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5235,7 +5235,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 28.59,
"duration_ms": 30.31,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5263,7 +5263,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.92,
"duration_ms": 30.12,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5286,7 +5286,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 28.16,
"duration_ms": 30.69,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5314,7 +5314,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 28.43,
"duration_ms": 30.85,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5337,7 +5337,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 28.62,
"duration_ms": 30.37,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5364,7 +5364,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.78,
"duration_ms": 30.98,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5387,7 +5387,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.76,
"duration_ms": 28.23,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5416,7 +5416,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.99,
"duration_ms": 30.43,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -6197,48 +6197,43 @@
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "c30882468f45c7e78bef73e0ada161fd1fbaef79",
"commit": "9eaa8f6cec4ba83c07ded0275686252576bee6c3",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 64,
"changed_file_count": 17,
"generated_dirty": true,
"generated_changed_file_count": 60,
"source_dirty": true,
"source_changed_file_count": 4,
"generated_changed_file_count": 17,
"source_dirty": false,
"source_changed_file_count": 0,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/adaptation_proposals.json",
" M reports/adaptation_proposals.md",
" M reports/adoption_drift_report.json",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" M reports/benchmark_reproducibility.json",
" M reports/benchmark_reproducibility.md",
" M reports/compiled_targets.json",
" M reports/context_budget.json",
" M reports/context_budget.md"
],
"source_sample": [
" M scripts/render_evidence_consistency.py",
" M tests/verify_architecture_maintainability.py",
" M tests/verify_evidence_consistency.py",
"?? scripts/evidence_consistency_phase_queue.py"
" M reports/evidence_consistency.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md",
" M reports/review-studio.html",
" M reports/review-studio.json",
" M reports/review-viewer.json",
" M reports/skill-interpretation.json"
],
"source_sample": [],
"generated_sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/adaptation_proposals.json",
" M reports/adaptation_proposals.md",
" M reports/adoption_drift_report.json",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" M reports/benchmark_reproducibility.json",
" M reports/benchmark_reproducibility.md",
" M reports/compiled_targets.json",
" M reports/context_budget.json",
" M reports/context_budget.md"
" M reports/evidence_consistency.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md",
" M reports/review-studio.html",
" M reports/review-studio.json",
" M reports/review-viewer.json",
" M reports/skill-interpretation.json"
],
"generated_dirty_prefixes": [
"dist/",
@@ -6252,11 +6247,11 @@
},
"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": "0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd",
"evidence_bundle_sha256": "98271c40046d1bf5f6a3ada701b5b1fd88b188bf4122a15424c8b4566cfc8fcf",
"source_contract_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
@@ -6276,19 +6271,18 @@
"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": 64,
"source_tree_dirty": true,
"source_changed_file_count": 4,
"changed_file_count": 17,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"generated_tree_dirty": true,
"generated_changed_file_count": 60
"generated_changed_file_count": 17
},
"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)",
@@ -6297,12 +6291,12 @@
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
},
"release_lock": {
"ready": false,
"commit": "c30882468f45c7e78bef73e0ada161fd1fbaef79",
"ready": true,
"commit": "9eaa8f6cec4ba83c07ded0275686252576bee6c3",
"status_scope": "generation-time status before this report is written",
"source_changed_file_count": 4,
"generated_changed_file_count": 60,
"reason": "source files were dirty at generation time"
"source_changed_file_count": 0,
"generated_changed_file_count": 17,
"reason": "only generated evidence artifacts were dirty at generation time"
},
"evidence_bundle": {
"algorithm": "sha256(path,label,exists,artifact_sha256)",
@@ -6310,7 +6304,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd"
"sha256": "98271c40046d1bf5f6a3ada701b5b1fd88b188bf4122a15424c8b4566cfc8fcf"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -6384,7 +6378,7 @@
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7967,
"sha256": "615d4b9ec6fb8d487c98e06ffb8cdbe7d34b08b07a2d9ea069eee3cdd4edc0a9"
"sha256": "6edee9440d276bd62d36deee7a5a2c45ce2e7c6817a0e517f0339b266e4055aa"
},
{
"label": "blind_review",
@@ -17961,9 +17955,9 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 797,
"other_text_tokens": 1121236,
"other_text_tokens": 1121225,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1122033,
"estimated_total_text_tokens": 1122022,
"deferred_resource_tokens": 512782,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
@@ -20036,7 +20030,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": false,
"release_lock_ready": true,
"evidence_consistency_ok": true,
"writes_source_files": false,
"auto_patch_enabled": false,
@@ -20053,7 +20047,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": false,
"release_lock_ready": true,
"evidence_consistency_ok": true,
"writes_source_files": false,
"auto_patch_enabled": false,
@@ -20502,7 +20496,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": false,
"release_lock_ready": true,
"evidence_consistency_ok": true
},
"actions": [
@@ -20537,7 +20531,7 @@
"weekly_curator": {
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-16T20:58:28Z",
"generated_at": "2026-06-17",
"skill_dir": ".",
"decision": "curator-review",
"week_id": "2026-W25",
@@ -20551,7 +20545,7 @@
"top_score": 88,
"skill_count": 12,
"actionable_portfolio_issue_count": 0,
"release_lock_ready": false,
"release_lock_ready": true,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
@@ -20571,7 +20565,7 @@
"top_score": 88,
"skill_count": 12,
"actionable_portfolio_issue_count": 0,
"release_lock_ready": false,
"release_lock_ready": true,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
@@ -20824,7 +20818,7 @@
"no_route_opportunity_count": 0
},
"release_state": {
"release_lock_ready": false,
"release_lock_ready": true,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4
@@ -21002,7 +20996,7 @@
"adaptation_proposals": {
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-16T20:58:28Z",
"generated_at": "2026-06-17",
"skill_dir": ".",
"source_patterns": "reports/user_patterns.json",
"pattern_count": 5,
reports/review-viewer.json
+8 -8
View File
@@ -1005,11 +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": "0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd",
"evidence_bundle_sha256": "98271c40046d1bf5f6a3ada701b5b1fd88b188bf4122a15424c8b4566cfc8fcf",
"source_contract_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
@@ -1029,15 +1029,15 @@
"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": 64,
"source_tree_dirty": true,
"source_changed_file_count": 4,
"changed_file_count": 17,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"generated_tree_dirty": true,
"generated_changed_file_count": 60
"generated_changed_file_count": 17
},
"commit": "c30882468f45c7e78bef73e0ada161fd1fbaef79",
"commit": "9eaa8f6cec4ba83c07ded0275686252576bee6c3",
"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.",
reports/skill-interpretation.json
+8 -8
View File
@@ -1009,11 +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": "0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd",
"evidence_bundle_sha256": "98271c40046d1bf5f6a3ada701b5b1fd88b188bf4122a15424c8b4566cfc8fcf",
"source_contract_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
@@ -1033,15 +1033,15 @@
"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": 64,
"source_tree_dirty": true,
"source_changed_file_count": 4,
"changed_file_count": 17,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"generated_tree_dirty": true,
"generated_changed_file_count": 60
"generated_changed_file_count": 17
},
"commit": "c30882468f45c7e78bef73e0ada161fd1fbaef79",
"commit": "9eaa8f6cec4ba83c07ded0275686252576bee6c3",
"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.",
reports/skill-overview.json
+8 -8
View File
@@ -1004,11 +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": "0cb0e7e0eea477ba17f31508bcac41bd049cfeda2fc9fe16a46e7e89f6c024cd",
"evidence_bundle_sha256": "98271c40046d1bf5f6a3ada701b5b1fd88b188bf4122a15424c8b4566cfc8fcf",
"source_contract_sha256": "5533575c144fb56486ab7320bfbd9f6655a6360cc1c2fbab837c40a7bc57ca6d",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"output_case_count": 5,
@@ -1028,15 +1028,15 @@
"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": 64,
"source_tree_dirty": true,
"source_changed_file_count": 4,
"changed_file_count": 17,
"source_tree_dirty": false,
"source_changed_file_count": 0,
"generated_tree_dirty": true,
"generated_changed_file_count": 60
"generated_changed_file_count": 17
},
"commit": "c30882468f45c7e78bef73e0ada161fd1fbaef79",
"commit": "9eaa8f6cec4ba83c07ded0275686252576bee6c3",
"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.",
reports/skillops/daily/2026-06-17.json
+3 -3
View File
@@ -14,7 +14,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": false,
"release_lock_ready": true,
"evidence_consistency_ok": true,
"writes_source_files": false,
"auto_patch_enabled": false,
@@ -31,7 +31,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": false,
"release_lock_ready": true,
"evidence_consistency_ok": true,
"writes_source_files": false,
"auto_patch_enabled": false,
@@ -480,7 +480,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": false,
"release_lock_ready": true,
"evidence_consistency_ok": true
},
"actions": [
reports/skillops/daily/2026-06-17.md
+1 -1
View File
@@ -14,7 +14,7 @@ Generated at: `2026-06-17`
- local blueprint ready: `true`
- public world-class ready: `false`
- world-class pending: `4`
- release lock ready: `false`
- release lock ready: `true`
- evidence consistency ok: `true`
This report is an operations cockpit for explicit-source SkillOps. It does not scan private logs, write source files, apply patches, or count as world-class external or human evidence.
reports/skillops/weekly/2026-W25.json
+4 -4
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-16T20:58:28Z",
"generated_at": "2026-06-17",
"skill_dir": ".",
"decision": "curator-review",
"week_id": "2026-W25",
@@ -15,7 +15,7 @@
"top_score": 88,
"skill_count": 12,
"actionable_portfolio_issue_count": 0,
"release_lock_ready": false,
"release_lock_ready": true,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
@@ -35,7 +35,7 @@
"top_score": 88,
"skill_count": 12,
"actionable_portfolio_issue_count": 0,
"release_lock_ready": false,
"release_lock_ready": true,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
@@ -288,7 +288,7 @@
"no_route_opportunity_count": 0
},
"release_state": {
"release_lock_ready": false,
"release_lock_ready": true,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4
reports/skillops/weekly/2026-W25.md
+2 -2
View File
@@ -1,6 +1,6 @@
# Weekly SkillOps Curator Report
Generated at: `2026-06-16T20:58:28Z`
Generated at: `2026-06-17`
Week: `2026-W25`
## Summary
@@ -13,7 +13,7 @@ Week: `2026-W25`
- top_score: `88`
- skill_count: `12`
- actionable_portfolio_issue_count: `0`
- release_lock_ready: `False`
- release_lock_ready: `True`
- evidence_consistency_ok: `True`
- public_world_class_ready: `False`
- world_class_pending_count: `4`