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

Refresh generated evidence after extension tracking

Browse Source
This commit is contained in:
yaojingang
2026-06-15 19:09:06 +08:00
parent f0be4dba34
commit ee2130176f
32 changed files with 165 additions and 163 deletions
Download Patch File Download Diff File Expand all files Collapse all files
reports/adoption_drift_report.json
+14 -14
View File
@@ -1,7 +1,7 @@
{
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-15T11:07:11Z",
"generated_at": "2026-06-15T11:08:09Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
@@ -25,14 +25,14 @@
},
"summary": {
"event_count": 1,
"adoption_sample_count": 1,
"activation_count": 1,
"accepted_count": 1,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"edited_count": 0,
"rejected_count": 0,
"missed_count": 0,
"failed_count": 0,
"adoption_rate": 100.0,
"adoption_rate": 0,
"missed_trigger_count": 0,
"wrong_trigger_count": 0,
"bad_output_count": 0,
@@ -41,7 +41,7 @@
"review_overdue_count": 0,
"risk_band": "low",
"event_types": {
"skill_activation": 1
"review_event": 1
},
"failure_types": {},
"source_types": {
@@ -53,31 +53,31 @@
{
"skill": "yao-meta-skill",
"events": 1,
"adoption_events": 1,
"accepted": 1,
"adoption_events": 0,
"accepted": 0,
"edited": 0,
"rejected": 0,
"missed": 0,
"adoption_rate": 100.0
"adoption_rate": 0
}
],
"next_iteration_candidates": [],
"recent_events": [
{
"command": "unknown",
"event": "skill_activation",
"event": "review_event",
"skill": "yao-meta-skill",
"source": "manual",
"version": "1.1.0",
"activation_type": "explicit",
"outcome": "accepted",
"activation_type": "manual",
"outcome": "reviewed",
"failure_type": "none",
"timestamp": "2026-06-13T10:00:00Z"
"timestamp": "2026-06-13T12:00:00Z"
}
],
"failures": [],
"artifacts": {
"events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl",
"events_jsonl": "reports/telemetry_events.jsonl",
"json": "reports/adoption_drift_report.json",
"markdown": "reports/adoption_drift_report.md"
}
reports/adoption_drift_report.md
+5 -5
View File
@@ -5,9 +5,9 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
## Summary
- Events: `1`
- Adoption samples: `1`
- Activation events: `1`
- Adoption rate: `100.0`
- Adoption samples: `0`
- Activation events: `0`
- Adoption rate: `0`
- Missed trigger signals: `0`
- Bad output signals: `0`
- Script error signals: `0`
@@ -25,7 +25,7 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
| Skill | Events | Adoption Samples | Accepted | Edited | Rejected | Missed | Adoption Rate |
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
| `yao-meta-skill` | 1 | 1 | 1 | 0 | 0 | 0 | 100.0 |
| `yao-meta-skill` | 1 | 0 | 0 | 0 | 0 | 0 | 0 |
## Next Iteration Candidates
@@ -33,4 +33,4 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
## Recent Metadata Events
- `2026-06-13T10:00:00Z` `yao-meta-skill` event=`skill_activation` source=`manual` command=`unknown` activation=`explicit` outcome=`accepted` failure=`none`
- `2026-06-13T12:00:00Z` `yao-meta-skill` event=`review_event` source=`manual` command=`unknown` activation=`manual` outcome=`reviewed` failure=`none`
reports/architecture_maintainability.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-15",
"skill_dir": ".",
"summary": {
"python_file_count": 162,
reports/architecture_maintainability.md
+1 -1
View File
@@ -1,6 +1,6 @@
# Architecture Maintainability
Generated at: `2026-06-13`
Generated at: `2026-06-15`
## Summary
reports/benchmark_reproducibility.json
+17 -17
View File
@@ -3,24 +3,24 @@
"ok": true,
"generated_at": "2026-06-15",
"skill_dir": ".",
"commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0",
"commit": "f0be4dba348d6a7cd6534d44d13011cacd5ec566",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 38,
"changed_file_count": 27,
"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/context_budget.json",
" M reports/context_budget.md",
" M reports/context_budget_summary.json",
" M reports/install_simulation.json",
" M reports/install_simulation.md"
" M reports/compiled_targets.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md",
" M reports/python_compatibility.json",
" M reports/python_compatibility.md",
" M reports/review_annotations.json",
" M reports/review_waivers.json",
" M reports/review_waivers.md"
],
"scope": "generation-time status before this report is written"
},
@@ -30,7 +30,7 @@
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56",
"evidence_bundle_sha256": "2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb",
"source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5",
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
"output_case_count": 5,
@@ -52,7 +52,7 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 38
"changed_file_count": 27
},
"public_claim": {
"ready": false,
@@ -68,7 +68,7 @@
},
"release_lock": {
"ready": false,
"commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0",
"commit": "f0be4dba348d6a7cd6534d44d13011cacd5ec566",
"status_scope": "generation-time status before this report is written",
"reason": "working tree was dirty at generation time"
},
@@ -78,7 +78,7 @@
"existing_count": 24,
"missing_count": 0,
"missing_paths": [],
"sha256": "3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56"
"sha256": "2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -151,8 +151,8 @@
"label": "output_execution",
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7967,
"sha256": "712890e85fdd3334e3196b2597555491be047313728c2e2891134da71e1ca7e8"
"bytes": 7965,
"sha256": "e05906fb7e4242e1b4c373285f5bca3283986301f13e08c2d64715efb9f827a4"
},
{
"label": "blind_review",
reports/benchmark_reproducibility.md
+5 -5
View File
@@ -1,9 +1,9 @@
# Benchmark Reproducibility
Generated at: `2026-06-15`
Commit: `7acc6d9cf780e38570c20813186d0efea5ac8ad0`
Commit: `f0be4dba348d6a7cd6534d44d13011cacd5ec566`
Working tree dirty at generation: `true`
Evidence bundle SHA256: `3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56`
Evidence bundle SHA256: `2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb`
## Summary
@@ -23,7 +23,7 @@ Evidence bundle SHA256: `3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70
- world-class source checks: `6` pass / `13` total; `7` blocked
- public claim ready: `false`
- public claim blockers: `5`
- changed files at generation: `38`
- changed files at generation: `27`
This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
@@ -51,7 +51,7 @@ This report proves local benchmark reproducibility only. It keeps external provi
- algorithm: `sha256(path,label,exists,artifact_sha256)`
- artifacts: `24` / `24`
- sha256: `3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56`
- sha256: `2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb`
## Methodology Sections
@@ -73,7 +73,7 @@ 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 | `712890e85fdd` |
| output_execution | `reports/output_execution_runs.json` | present | `e05906fb7e42` |
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
| review_adjudication | `reports/output_review_adjudication.json` | present | `240485a721af` |
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
reports/compiled_targets.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-15",
"skill_dir": ".",
"summary": {
"target_count": 5,
reports/output_execution_runs.json
+10 -10
View File
@@ -34,7 +34,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 38.72,
"duration_ms": 37.08,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -62,7 +62,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 37.27,
"duration_ms": 46.44,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -85,7 +85,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 39.96,
"duration_ms": 36.3,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -113,7 +113,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 39.8,
"duration_ms": 35.96,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -136,7 +136,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 37.28,
"duration_ms": 57.56,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -164,7 +164,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 34.66,
"duration_ms": 43.25,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -187,7 +187,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 36.08,
"duration_ms": 39.31,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -214,7 +214,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 41.08,
"duration_ms": 38.5,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -237,7 +237,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 34.88,
"duration_ms": 38.42,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -266,7 +266,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 34.91,
"duration_ms": 37.66,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
reports/output_execution_runs.md
+10 -10
View File
@@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext
| Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status |
| --- | --- | --- | --- | ---: | ---: | ---: | --- |
| skill-package-contract | baseline | command | local-output-eval-runner | 38.72 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 37.27 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 39.96 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 39.8 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 37.28 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 34.66 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 36.08 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 41.08 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 34.88 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 34.91 | 98 | 100.0 | pass |
| skill-package-contract | baseline | command | local-output-eval-runner | 37.08 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 46.44 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 36.3 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 35.96 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 57.56 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 43.25 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 39.31 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 38.5 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 38.42 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 37.66 | 98 | 100.0 | pass |
## Next Fixes
reports/python_compatibility.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-15",
"root": ".",
"summary": {
"target_python": "3.11",
reports/python_compatibility.md
+1 -1
View File
@@ -1,6 +1,6 @@
# Python Compatibility
Generated at: `2026-06-13`
Generated at: `2026-06-15`
## Summary
reports/review-studio.json
+32 -32
View File
@@ -1676,7 +1676,7 @@
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "6e9d4ffd08e1345536b2b8a017761e75d11d8b4b7a9d86703a081fccaa10ba2d",
"evidence_bundle_sha256": "2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb",
"source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5",
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
"output_case_count": 5,
@@ -1698,9 +1698,9 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 34
"changed_file_count": 27
},
"commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0",
"commit": "f0be4dba348d6a7cd6534d44d13011cacd5ec566",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
@@ -4342,7 +4342,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.2,
"duration_ms": 37.08,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4370,7 +4370,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.82,
"duration_ms": 46.44,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4393,7 +4393,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.01,
"duration_ms": 36.3,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4421,7 +4421,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.83,
"duration_ms": 35.96,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4444,7 +4444,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.81,
"duration_ms": 57.56,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4472,7 +4472,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 35.47,
"duration_ms": 43.25,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4495,7 +4495,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 31.19,
"duration_ms": 39.31,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4522,7 +4522,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 29.94,
"duration_ms": 38.5,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4545,7 +4545,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.34,
"duration_ms": 38.42,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4574,7 +4574,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.94,
"duration_ms": 37.66,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5295,24 +5295,24 @@
"ok": true,
"generated_at": "2026-06-15",
"skill_dir": ".",
"commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0",
"commit": "f0be4dba348d6a7cd6534d44d13011cacd5ec566",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 34,
"changed_file_count": 27,
"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/context_budget.json",
" M reports/context_budget.md",
" M reports/context_budget_summary.json",
" M reports/install_simulation.json",
" M reports/install_simulation.md",
" M reports/compiled_targets.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md"
" M reports/output_execution_runs.md",
" M reports/python_compatibility.json",
" M reports/python_compatibility.md",
" M reports/review_annotations.json",
" M reports/review_waivers.json",
" M reports/review_waivers.md"
],
"scope": "generation-time status before this report is written"
},
@@ -5322,7 +5322,7 @@
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "6e9d4ffd08e1345536b2b8a017761e75d11d8b4b7a9d86703a081fccaa10ba2d",
"evidence_bundle_sha256": "2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb",
"source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5",
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
"output_case_count": 5,
@@ -5344,7 +5344,7 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 34
"changed_file_count": 27
},
"public_claim": {
"ready": false,
@@ -5360,7 +5360,7 @@
},
"release_lock": {
"ready": false,
"commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0",
"commit": "f0be4dba348d6a7cd6534d44d13011cacd5ec566",
"status_scope": "generation-time status before this report is written",
"reason": "working tree was dirty at generation time"
},
@@ -5370,7 +5370,7 @@
"existing_count": 24,
"missing_count": 0,
"missing_paths": [],
"sha256": "6e9d4ffd08e1345536b2b8a017761e75d11d8b4b7a9d86703a081fccaa10ba2d"
"sha256": "2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -5443,8 +5443,8 @@
"label": "output_execution",
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7966,
"sha256": "3d279da7e011bd3ed71c389195c0490f7dbb011dff90ebe99ff3db133f4a9fd6"
"bytes": 7965,
"sha256": "e05906fb7e4242e1b4c373285f5bca3283986301f13e08c2d64715efb9f827a4"
},
{
"label": "blind_review",
@@ -14982,9 +14982,9 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 767,
"other_text_tokens": 1265424,
"other_text_tokens": 1265845,
"estimated_initial_load_tokens": 960,
"estimated_total_text_tokens": 1266191,
"estimated_total_text_tokens": 1266612,
"deferred_resource_tokens": 406347,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
@@ -16898,7 +16898,7 @@
"adoption_drift": {
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-15T11:05:04Z",
"generated_at": "2026-06-15T11:08:09Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
reports/review-viewer.json
+3 -3
View File
@@ -999,7 +999,7 @@
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56",
"evidence_bundle_sha256": "2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb",
"source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5",
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
"output_case_count": 5,
@@ -1021,9 +1021,9 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 38
"changed_file_count": 27
},
"commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0",
"commit": "f0be4dba348d6a7cd6534d44d13011cacd5ec566",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
reports/review_annotations.json
+1 -1
View File
@@ -2,7 +2,7 @@
"schema_version": "1.0",
"ok": true,
"skill_dir": ".",
"source": "tests/tmp_review_studio/empty_review_annotations_input.json",
"source": "reports/review_annotations_input.json",
"summary": {
"annotation_count": 0,
"open_count": 0,
reports/review_waivers.json
+2 -2
View File
@@ -2,7 +2,7 @@
"schema_version": "1.0",
"ok": true,
"skill_dir": ".",
"generated_at": "2026-06-13",
"generated_at": "2026-06-15",
"summary": {
"waiver_count": 0,
"active_count": 0,
@@ -52,7 +52,7 @@
"Reviewer links output_review_adjudication or output_execution evidence."
],
"suggested_evidence": "reports/output_review_adjudication.md",
"suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md",
"suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-15 --evidence reports/output_review_adjudication.md",
"world_class_boundary": "Does not count as provider, human, or public world-class completion evidence."
},
{
reports/review_waivers.md
+1 -1
View File
@@ -35,7 +35,7 @@
- waiver allowed: `true`
- risk: review pending 5; model-executed 0; output failures 0
- evidence: `reports/output_review_adjudication.md`
- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md`
- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-15 --evidence reports/output_review_adjudication.md`
- world-class boundary: Does not count as provider, human, or public world-class completion evidence.
#### Required Review
reports/skill-overview.json
+3 -3
View File
@@ -998,7 +998,7 @@
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56",
"evidence_bundle_sha256": "2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb",
"source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5",
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
"output_case_count": 5,
@@ -1020,9 +1020,9 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 38
"changed_file_count": 27
},
"commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0",
"commit": "f0be4dba348d6a7cd6534d44d13011cacd5ec566",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
reports/skill_os2_coverage.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-15",
"skill_dir": ".",
"summary": {
"item_count": 20,
reports/skill_os2_coverage.md
+1 -1
View File
@@ -1,6 +1,6 @@
# Skill OS 2.0 Blueprint Coverage
Generated at: `2026-06-13`
Generated at: `2026-06-15`
## Summary
reports/world_class_claim_guard.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-15",
"skill_dir": ".",
"summary": {
"ledger_ready_to_claim_world_class": false,
reports/world_class_claim_guard.md
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Claim Guard
Generated at: `2026-06-13`
Generated at: `2026-06-15`
## Summary
reports/world_class_evidence_intake.json
+2 -2
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-15",
"skill_dir": ".",
"summary": {
"schema_present": true,
@@ -307,7 +307,7 @@
"source_accepted": false,
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 1,
"adoption_sample_count": 0,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
reports/world_class_evidence_intake.md
+1 -1
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Intake
Generated at: `2026-06-13`
Generated at: `2026-06-15`
## Summary
reports/world_class_evidence_ledger.json
+9 -9
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-15",
"skill_dir": ".",
"summary": {
"ledger_entry_count": 4,
@@ -14,8 +14,8 @@
"missing_submission_count": 4,
"invalid_submission_count": 0,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"submitted_but_pending_count": 0,
"source_accepted_without_valid_submission_count": 0,
"overclaim_guard_active": true,
@@ -351,7 +351,7 @@
"status": "pending",
"source_status": "external_required",
"source_accepted": false,
"current": "external source events 0; adoption samples 1",
"current": "external source events 0; adoption samples 0",
"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>/",
@@ -388,7 +388,7 @@
],
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 1,
"adoption_sample_count": 0,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
@@ -409,8 +409,8 @@
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 1,
"status": "pass",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
@@ -426,8 +426,8 @@
}
],
"source_check_count": 3,
"source_pass_count": 2,
"source_blocked_count": 1,
"source_pass_count": 1,
"source_blocked_count": 2,
"submission_state": {
"status": "missing",
"path": "evidence/world_class/submissions/native-client-telemetry.json",
reports/world_class_evidence_ledger.md
+7 -7
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Ledger
Generated at: `2026-06-13`
Generated at: `2026-06-15`
## Summary
@@ -8,8 +8,8 @@ Generated at: `2026-06-13`
- ready to claim world-class: `false`
- entries: `4`
- source accepted: `0`
- source checks: `7` pass / `13` total
- source blocked: `6`
- source checks: `6` pass / `13` total
- source blocked: `7`
- accepted: `0`
- pending: `4`
- human pending: `1`
@@ -29,7 +29,7 @@ This ledger records the current evidence state. It requires both passing source
| `provider-holdout` | `pending` | `missing` | `external` | model-executed 0; token-observed 0 | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. |
| `human-adjudication` | `pending` | `missing` | `human` | 0/5 decisions; pending 5 | Record real A/B choices in the decision template, then regenerate adjudication. |
| `native-permission-enforcement` | `pending` | `missing` | `external` | native-enforced targets 0; installer-enforced targets 4 | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. |
| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 1 | Install a real client against the native host and import production metadata-only events. |
| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 0 | Install a real client against the native host and import production metadata-only events. |
## Provider Holdout
@@ -167,8 +167,8 @@ This ledger records the current evidence state. It requires both passing source
- objective: Import production metadata-only events from a real external client into the local drift loop.
- source status: `external_required`
- observed state: `{"external_source_events": 0, "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false}`
- source checks: `2` pass / `3` total
- observed state: `{"external_source_events": 0, "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false}`
- source checks: `1` pass / `3` total
- submission state: `{"status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", "artifact_ref_count": 0, "attested_real_evidence": false, "privacy_contract_satisfied": false, "ledger_counts_as_completion": false}`
### Provenance Requirements
@@ -192,7 +192,7 @@ This ledger records the current evidence state. It requires both passing source
| Check | Current | Expected | Status |
| --- | --- | --- | --- |
| External events | `0` | `>0` | `blocked` |
| Adoption sample | `1` | `>0` | `pass` |
| Adoption sample | `0` | `>0` | `blocked` |
| Raw content blocked | `False` | `false` | `pass` |
### Completion Assertions
reports/world_class_evidence_plan.json
+3 -3
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-15",
"skill_dir": ".",
"summary": {
"audit_decision": "continue-iteration",
@@ -141,7 +141,7 @@
"status": "external_required",
"category": "external",
"owner": "Browser/Chrome/IDE/provider client integrator",
"current": "external source events 0; adoption samples 1",
"current": "external source events 0; adoption samples 0",
"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>/",
@@ -299,7 +299,7 @@
"status": "external_required",
"category": "external",
"owner": "Browser/Chrome/IDE/provider client integrator",
"current": "external source events 0; adoption samples 1",
"current": "external source events 0; adoption samples 0",
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"runbook": [
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
reports/world_class_evidence_plan.md
+2 -2
View File
@@ -1,6 +1,6 @@
# World-Class Evidence Plan
Generated at: `2026-06-13`
Generated at: `2026-06-15`
## Summary
@@ -22,7 +22,7 @@ This report is an execution plan for the remaining world-class evidence gaps. It
| `provider-holdout` | `external_required` | `external` | operator with provider credentials | model-executed 0; token-observed 0 |
| `human-adjudication` | `human_required` | `human` | human reviewer | 0/5 decisions; pending 5 |
| `native-permission-enforcement` | `external_required` | `external` | target client or installer integrator | native-enforced targets 0; installer-enforced targets 4 |
| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 1 |
| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 0 |
## Provider Holdout
reports/world_class_operator_runbook.html
+4 -4
View File
@@ -57,7 +57,7 @@
<span class="eyebrow">Evidence Operations</span>
<h1>World-Class Operator Runbook</h1>
<p class="lede">A single operating page for collecting the remaining human and external evidence. It coordinates action, but does not accept evidence or change the ledger.</p>
<div class="stats"><article><span>Pending</span><strong>4</strong></article><article><span>Awaiting</span><strong>4</strong></article><article><span>Ready</span><strong>0</strong></article><article><span>Source</span><strong>7/13</strong></article><article><span>Blocked</span><strong>6</strong></article><article><span>Invalid</span><strong>0</strong></article></div>
<div class="stats"><article><span>Pending</span><strong>4</strong></article><article><span>Awaiting</span><strong>4</strong></article><article><span>Ready</span><strong>0</strong></article><article><span>Source</span><strong>6/13</strong></article><article><span>Blocked</span><strong>7</strong></article><article><span>Invalid</span><strong>0</strong></article></div>
</section>
<section class="section panel" id="fast-path"><h2>Fast Path</h2><ol><li>Run the real external or human work for one evidence item.</li><li>Generate and fill the matching submission draft.</li><li>Validate intake and inspect the submission review queue.</li><li>Refresh the ledger and run the claim guard before making any completion claim.</li></ol></section>
<section class="section" id="items"><h2>Evidence Items</h2><div class="item-grid"><article class="item-card awaiting-submission">
@@ -120,7 +120,7 @@
<dl>
<dt>Owner</dt><dd>Browser/Chrome/IDE/provider client integrator</dd>
<dt>Ledger</dt><dd><code>pending</code></dd>
<dt>Blocked</dt><dd><code>1</code></dd>
<dt>Blocked</dt><dd><code>2</code></dd>
<dt>Submission</dt><dd><code>evidence/world_class/submissions/native-client-telemetry.json</code></dd>
</dl>
<section class="source-panel"><h4>Source Runbook</h4><ul><li>python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://&lt;extension-id&gt;/</li><li>Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.</li><li>python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl</li><li>python3 scripts/yao.py skill-atlas --workspace-root .</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at &lt;YYYY-MM-DD&gt;</li><li>Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></section>
@@ -130,8 +130,8 @@
<section><h4>Success Checks</h4><ul><li>reports/adoption_drift_report.json summary.source_types.external &gt; 0</li><li>reports/adoption_drift_report.json summary.adoption_sample_count &gt; 0</li><li>reports/skill_os2_audit.json item native-client-telemetry status becomes pass</li></ul></section>
<section><h4>Privacy</h4><ul><li>Telemetry must remain metadata-only and local-first.</li><li>Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.</li></ul></section>
</div>
<section class="source-panel"><h4>Next Source Actions</h4><ul><li>Import at least one metadata-only event from a real client.</li></ul></section>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>External events</span><code>external_source_events: 0 / &gt;0</code><small>Import at least one metadata-only event from a real client.</small></li><li class='source-check pass'><span>Adoption sample</span><code>adoption_sample_count: 1 / &gt;0</code><small>Telemetry must include adoption outcome evidence.</small></li><li class='source-check pass'><span>Raw content blocked</span><code>raw_content_allowed: False / false</code><small>Telemetry must stay metadata-only.</small></li></ul></section>
<section class="source-panel"><h4>Next Source Actions</h4><ul><li>Import at least one metadata-only event from a real client.</li><li>Telemetry must include adoption outcome evidence.</li></ul></section>
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>External events</span><code>external_source_events: 0 / &gt;0</code><small>Import at least one metadata-only event from a real client.</small></li><li class='source-check blocked'><span>Adoption sample</span><code>adoption_sample_count: 0 / &gt;0</code><small>Telemetry must include adoption outcome evidence.</small></li><li class='source-check pass'><span>Raw content blocked</span><code>raw_content_allowed: False / false</code><small>Telemetry must stay metadata-only.</small></li></ul></section>
</article></div></section>
<section class="section panel" id="boundary"><h2>Boundary</h2><ul><li>Planned work, draft packets, metadata fallback, pending human decisions, and local command runners do not count as completion.</li><li>Valid intake means ready for submission review; ledger review still requires passing source evidence.</li><li>The world-class ledger and claim guard remain the source of truth.</li></ul></section>
</main>
reports/world_class_operator_runbook.json
+10 -9
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-15",
"skill_dir": ".",
"summary": {
"evidence_item_count": 4,
@@ -12,8 +12,8 @@
"valid_packet_source_incomplete_count": 0,
"invalid_submission_count": 0,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"ready_to_claim_world_class": false,
"runbook_counts_as_completion": false,
"decision": "collect-evidence"
@@ -394,7 +394,7 @@
"review_state": "awaiting-submission",
"source_accepted": false,
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
"current": "external source events 0; adoption samples 1",
"current": "external source events 0; adoption samples 0",
"execution_runbook": [
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
"Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
@@ -442,7 +442,7 @@
],
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 1,
"adoption_sample_count": 0,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
@@ -463,8 +463,8 @@
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 1,
"status": "pass",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
@@ -479,9 +479,10 @@
"next_action": "Telemetry must stay metadata-only."
}
],
"blocked_source_check_count": 1,
"blocked_source_check_count": 2,
"next_source_actions": [
"Import at least one metadata-only event from a real client."
"Import at least one metadata-only event from a real client.",
"Telemetry must include adoption outcome evidence."
],
"submission_state": {
"status": "missing",
reports/world_class_operator_runbook.md
+5 -4
View File
@@ -1,6 +1,6 @@
# World-Class Operator Runbook
Generated at: `2026-06-13`
Generated at: `2026-06-15`
## Summary
@@ -28,7 +28,7 @@ This runbook coordinates evidence collection only. It does not accept submission
| `provider-holdout` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Run provider-backed output-exec with real credentials. | operator with provider credentials |
| `human-adjudication` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Record a reviewer choice for every pair. | human reviewer |
| `native-permission-enforcement` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Collect real target-client or external runtime guard proof. | target client or installer integrator |
| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator |
| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator |
## Provider Holdout
@@ -239,7 +239,7 @@ This runbook coordinates evidence collection only. It does not accept submission
- objective: Import production metadata-only events from a real external client into the local drift loop.
- blocking reason: No evidence packet has been submitted for review.
- blocked source checks: `1`
- blocked source checks: `2`
- submission: `evidence/world_class/submissions/native-client-telemetry.json`
- template: `evidence/world_class/templates/native-client-telemetry.intake.json`
@@ -292,13 +292,14 @@ This runbook coordinates evidence collection only. It does not accept submission
### Next Source Actions
- Import at least one metadata-only event from a real client.
- Telemetry must include adoption outcome evidence.
### Source Evidence Snapshot
| Check | Current | Expected | Status | Next action |
| --- | --- | --- | --- | --- |
| External events | `0` | `>0` | `blocked` | Import at least one metadata-only event from a real client. |
| Adoption sample | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. |
| Adoption sample | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. |
| Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. |
## Boundary
reports/world_class_submission_review.json
+8 -8
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-13",
"generated_at": "2026-06-15",
"skill_dir": ".",
"summary": {
"review_item_count": 4,
@@ -13,8 +13,8 @@
"unmatched_submission_count": 0,
"invalid_submission_count": 0,
"source_check_count": 13,
"source_pass_count": 7,
"source_blocked_count": 6,
"source_pass_count": 6,
"source_blocked_count": 7,
"ready_to_claim_world_class": false,
"review_counts_submission_as_completion": false,
"decision": "awaiting-submissions"
@@ -265,7 +265,7 @@
"intake_errors": [],
"observed_state": {
"external_source_events": 0,
"adoption_sample_count": 1,
"adoption_sample_count": 0,
"raw_content_allowed": false,
"risk_band": "low",
"accepted": false
@@ -286,8 +286,8 @@
"label": "Adoption sample",
"field": "adoption_sample_count",
"expected": ">0",
"actual": 1,
"status": "pass",
"actual": 0,
"status": "blocked",
"source_accepted": false,
"next_action": "Telemetry must include adoption outcome evidence."
},
@@ -303,8 +303,8 @@
}
],
"source_check_count": 3,
"source_pass_count": 2,
"source_blocked_count": 1,
"source_pass_count": 1,
"source_blocked_count": 2,
"success_checks": [
"reports/adoption_drift_report.json summary.source_types.external > 0",
"reports/adoption_drift_report.json summary.adoption_sample_count > 0",
reports/world_class_submission_review.md
+2 -2
View File
@@ -1,6 +1,6 @@
# World-Class Submission Review
Generated at: `2026-06-13`
Generated at: `2026-06-15`
## Summary
@@ -138,7 +138,7 @@ This report is a read-only reviewer queue. It does not accept evidence or make w
#### Source Checks
- External events: 0 / >0 => blocked
- Adoption sample: 1 / >0 => pass
- Adoption sample: 0 / >0 => blocked
- Raw content blocked: False / false => pass
#### Completion Assertions